OPTIMIZING ENERGY EFFICIENCY FOR ORE SMELTING IN BLAST FURNACES BY SURFACE SCANNING

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for optimizing energy efficiency for ore smelting in blast furnaces. One of the methods is a pelletization process control method that includes obtaining images of pelletized particles; determining one or more characteristics of the pelletized particles; in response to determining that at least one or more of the characteristics is outside of a pelletization parameter, determining an adjustment to a control parameter of the pelletization system; and sending one or more signals to adjust the control parameter of the pelletization system. Another method is an iron ore smelting method that includes determining quantities of reactants to be added to the blast furnace with the pelletized particles in the stream of pelletized particles; and sending one or more signals that cause the controller to add the reactants of to the blast furnace according to the determined quantities.

Claims

1. A pelletization process control method comprising: obtaining, from first sensors positioned along a stream of pelletized particles downstream from an exit of a pelletization system, images of pelletized particles within the stream of pelletized particles; determining, from the images, a shape-irregularities factor that represents a deviation of a surface area of the pelletized particle from a surface area of a regular sphere having the same volume; in response to determining that the shape-irregularities factor is outside of a pelletization parameter, determining an adjustment to a control parameter of the pelletization system; and sending, to a controller of the pelletization system, one or more signals that cause the controller to adjust the control parameter of the pelletization system.

2. The method of claim 1, wherein the shape-irregularities factor further represents a volume of the pelletized particle based on the images of the pelletized particles.

3. The method of claim 2, further comprising: calculating a surface area measurement of each of the pelletized particles based on the volume and the images of the pelletized particles.

4. The method of claim 1, wherein the pelletized particles are iron ore pellets.

5. The method of claim 1, wherein the sensors are optical sensors.

6. The method of claim 1, wherein determining an adjustment to a control parameter of the pelletization system further comprises: calculating an adjustment of an amount of additives, an adjustment to a spin speed, an adjustment to a feed rate, or a combination thereof.

7. The method of claim 6, wherein determining the shape-irregularities factor comprises: determining a three-dimensional reconstruction of each pelletized particle from multiple images; determining a surface-area measurement and a volume measurement of the reconstructed pelletized particle; and calculating the shape-irregularities factor as a function of a ratio of surface area to a theoretical surface area of a regular sphere having the same volume.

8. An iron ore smelting method comprising: obtaining, from first sensors positioned along a stream of pelletized particles downstream from an exit of a pelletization system, images of pelletized particles within the stream of pelletized particles; determining, from the images, a shape-irregularities factor that represents a deviation of a surface area of the pelletized particle from a surface area of a regular sphere having the same volume; determining, based on the shape-irregularities factor, quantities of one or more reactants to be added to a blast furnace with the pelletized particles in the stream of pelletized particles; and sending, to an ingredient metering system of the blast furnace, one or more signals that cause a controller to add at least one of the reactants to the blast furnace according to the determined quantities.

9. The method of claim 8, wherein the reactants are one or more of limestone, coke, and the pelletized particles.

10. The method of claim 8, further comprising: determining an adjustment to a flow rate of blast air to the blast furnace, a temperature of the blast air to the blast furnace, or both based at least in part on the adjustment to quantities of at least one of the reactants; and sending, to the controller, one or more signals that cause the controller to adjust the flow rate, the blast air temperature, or both.

11. The method of claim 10, wherein the shape-irregularities factor is based on a size, shape, and surface area of each pelletized particle.

12. The method of claim 11, wherein determining the shape-irregularities factor comprises: determining a three-dimensional reconstruction of each pelletized particle from multiple images; determining a surface-area measurement and a volume measurement of the reconstructed pelletized particle; and calculating the shape-irregularities factor as a function of a ratio of surface area to a theoretical surface area of a regular sphere having the same volume.

13. The method of claim 12, further comprising: applying one or more image-processing operations including edge detection, segmentation, voxelization, or point-cloud fitting to determine the particle surface-area measurement.

14. The method of claim 10, wherein determining an adjustment to quantities of one or more reactants further comprises: determining the adjustment to quantities of one or more reactants based on a homogeneity of the pelletized particles indicated by the shape-irregularities factor.

15. The method of claim 14, wherein the homogeneity of the pelletized particles indicates a packing efficiency of the pelletized particles.

16. The method of claim 14, wherein determining the reactant quantities further comprises: computing a population-level distribution of shape-irregularities factor values across multiple pelletized particles; and determining a homogeneity index indicative of packing efficiency in the blast furnace.

17. The method of claim 16, wherein determining the adjustment to the control parameter or the furnace-operation parameter further comprises: computing a distribution of shape-irregularities factor values across the stream of pelletized particles; and weighting control responses according to a variance of the distribution.

18. A pelletization system comprising: at least one processor; and a data store coupled to the at least one processor having instructions stored thereon which, when executed by the at least one processor, causes the at least one processor to perform operations comprising: obtaining, from first sensors positioned along a stream of pelletized particles downstream from an exit of the pelletization system, images of pelletized particles within the stream of pelletized particles; determining, from the images, a shape-irregularities factor that represents a deviation of a surface area of the pelletized particle from a surface area of a regular sphere having the same volume; in response to determining that at least one or more of the characteristics is outside of a pelletization parameter, determining an adjustment to a control parameter of the pelletization system; and sending, to a controller of the pelletization system, one or more signals that cause the controller to adjust the control parameter of the pelletization system.

19. The system of claim 18, wherein the shape-irregularities factor further represents a volume of the pelletized particle based on the images of the pelletized particles.

20. An iron ore smelting system comprising: a pelletization system; a blast furnace; and at least one processor, and a data store coupled to the at least one processor having instructions stored thereon which, when executed by the at least one processor, causes the at least one processor to perform operations comprising: obtaining, from first sensors positioned along a stream of pelletized particles downstream from an exit of the pelletization system, images of pelletized particles within the stream of pelletized particles; determining, from the images, one or more characteristics of the pelletized particles; determining, based on the one or one or more characteristics of the pelletized particles, quantities of one or more reactants to be added to the blast furnace with the pelletized particles in the stream of pelletized particles; and sending, to an ingredient metering system of the blast furnace, one or more signals that cause a controller to add at least one of the reactants to the blast furnace according to the determined quantities.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0019] FIG. 1 depicts an exemplary pelletization system.

[0020] FIG. 2 depicts a block diagram of an exemplary control system for the pelletization system of FIG. 1.

[0021] FIG. 3 depicts a flow diagram that illustrates an example process for operating the pelletization system of FIG. 1.

[0022] FIG. 4 depicts an exemplary iron ore smelting blast furnace system.

[0023] FIG. 5 depicts a block diagram of an exemplary control system for the iron ore smelting blast furnace system of FIG. 4.

[0024] FIG. 6 depicts a flow diagram that illustrates an example process for operating the iron ore smelting blast furnace system of FIG. 4.

[0025] FIG. 7 depicts a schematic diagram of a computer system that may be applied to any of the computer-implemented methods and other techniques described herein.

[0026] Like reference numbers and designations in the various drawings indicate like elements.

DETAILED DESCRIPTION

[0027] FIG. 1 depicts an exemplary pelletization system 100. In operation, the pelletization system 100 pelletizes iron ores 101 in a pelletizing drum 112. The pelletizing drum 112 can crush the iron ores 101 to particular sizes and/or geometries. Operations of the pelletizing drum 112 can be controlled by control signals 124 from a control system 102. For example, control signals 124 from the control system 102 can cause the pelletizing drum 112 to increase or decrease sizes of particles 105 or to adjust control parameters of the pelletizing drum 112. Sensors 104 can capture characteristics of the particles 105 at an output of the pelletizing drum 115. The pelletization system 100 can generate the particles and achieve desired structural properties by adaptively adjusting control parameters of the pelletizing drum 112, such as adjusting the proportion of additives 114. Additives 114 can include solids, such as clay, and liquids, based on the captured characteristics. The operation of the system 100 is described in more detail below in reference to FIGS. 2 and 3.

[0028] The pelletization system 100 includes the control system 102. The control system 102 receives input from sensors 104. The control system 102 can control the operations of one or more metering systems based on analyses of data obtained from the sensors 104.

[0029] Particles 105 can be conveyed from the pelletizing drum 112 to an output of the pelletizing drum 115. For example, the particles 105 can be conveyed by a series of conveyors and augers. The particles 105 are then passed through the sensors 104 at the output of the pelletizing drum 115. In some examples, the particles 105 might pass through one or more other systems after passing through the output of the pelletizing drum, such as an iron ore smelting blast furnace system, as described in more detail below with reference to FIGS. 4-6.

[0030] The sensors 104 are arranged to obtain sensor data 122 of the particles 105. For example, in some implementations, sensors can be arranged in an array along a conveyor or a chute of the output of the pelletizing drum 115. The sensors can transmit images of the particles to the control system 102, which (as explained in more detail below) can use image processing algorithms to identify particle shapes and sizes and to determine particle surface area.

[0031] Some implementations can include a series of sieves to separate particles by size. In such implementations, the sensors 104 can be positioned proximate to each sieve to capture images of the particles passing through the sieve. The images can then be used, for example, to determine an approximate count of each size range of particles exiting each sieve.

[0032] The sensors 104 can include various different sensors configured to capture various characteristics of concrete particles. For example, the sensors used by the sensors 104 can include, but are not limited to, optical sensors (e.g., visible light cameras, infra-red cameras, near IR (NIR) sensors, dynamic optical microscopy sensors) and mechanical sensors (e.g., sieves, sedigraphs, impact hammer, electrodynamic vibrator), and spectrometers. In some examples, diffuse reflectance spectroscopy can be used across the visible, near- and shortwave-infrared spectral regions (400 to 2500 nm) as a tool to assess the strength of particles.

[0033] In some examples, the sensors 104 can use laser diffraction and dynamic light scattering in combination with empirical rheological measurements to capture measurements of the particles, such as a volume of the particles.

[0034] The sensor data 122 can include images of each of the particles 105 at the output of the pelletizing drum 115, volumes of each of the particles 105 at the output of the pelletizing drum 115, or both. The images are used by the control system 102 to determine characteristics of the particles 105. For example, particle characteristics can include, but are not limited to, particle sizes, shapes, surface areas, sphericity, porosity, density, strength, and particle size distribution.

[0035] In particular, the control system 102 can use the sensor data 122 to calculate a shape-irregularity factor (SIF) based on measurements from images of each particle, including size, shape, volume, and specific surface area. For each particle, the SIF represents a specific excess surface area of an irregular shape of the particle compared to regular spheres of the same size or volume as the particle.

[0036] For example, a particle within a certain size range (e.g., 2 mm-3 mm) can have an irregular shape. The sensors 104 can capture images of the particle and provide the images to the control system 102 as part of the sensor data 122. The control system 102 can measure a size, shape, and specific surface area of the particle, and the control system 102 can determine a SIF of the particle based on comparing the irregularities of the particles with other particles within the same size range.

[0037] As such, the control system 102 can analyze the particles 105 using sensor data 122 from the sensors 104 by determining a SIF for each of the particles 105, as described in further detail with reference to FIG. 2. The particle analysis can be used to optimize the pelletization process. For example, the control system 102 can send control signals 124 to control an amount of additives 114, such as clay and H.sub.2O, provided to the particles 105 at the pelletizing drum 112.

[0038] In some examples, the control system 102 can use control signals 124 to adjust control parameters of the pelletizing drum 112. The control parameters include one or more of a crush size of particles 105 generated by the pelletizing drum 112, a spin speed of the pelletizing drum 112, or a feed rate of the pelletizing drum 112 to improve the characteristics of the particles 105 based on the SIF of each particle. For example, the control system 102 can determine, for a certain number of particles, that the SIF is outside of a specified range, and the control system 102 can send one or more control signals 124 to the pelletizing drum 112 to adjust the spin speed.

[0039] FIG. 2 is a block diagram of an exemplary control system 102 for the pelletization system 100. In some implementations, control system 102 can control a combined system that iteratively adjusts control parameters of the pelletizing drum 112 based on the measurements (e.g., the surface area measurements) of the particles 105 from images and measurements captured at the output of the pelletizing drum 115.

[0040] The system 102 includes a computing system 202 in communication with the sensors 104 and a metering control system 212 which can control the control signals 124 for additives. Computing system 202 is configured to control various aspects of the pelletization process. For example, computing system 202 can store and execute one or more computer instruction sets to control the execution of aspects of the pelletization processes described herein. Computing system 202 can include a system of one or more computing devices. The computing devices can be, e.g., a system of one more servers. For example, a first server can be configured to receive and process data from the sensors 104. Another server can be configured to interface with the pelletizing drum control system 206 and issue control commands based on analysis results from the first server. Another server can be configured to interface with the additive metering control system 208 and issue control commands based on surface area measurements from the first server.

[0041] In some implementations, the computing system 202 can be operated or controlled from a user computing device 204. User computing device 204 can be a computing device, e.g., desktop computer, laptop computer, tablet computer, or other portable or stationary computing device.

[0042] Briefly, computing system 202 can control the overall pelletization system 100 to generate pelletized particles within desired parameters. The computing system 202 can use the sensors 104 to capture and measure particles as they are outputted by the pelletizing drum. The measurements can be used as control process feedback to adjust parameters of the pelletization process to maintain the output pellets within desired parameters.

[0043] In some implementations, the computing system 202 obtains surface area measurements from the sensors, and the computing system 202 can interface with the pelletizing drum control system 206 to determine adjustments to the pelletization system. The system calculates the SIF for each particle to determine, e.g., whether the particles meet desired properties or whether the computing system 202 should send control signals to adjust the pelletization system (e.g., by adjusting an amount of additives, adjusting a spin speed of the pelletizing drum, or adjusting a feed rate of the pelletizing drum).

[0044] In some implementations, computing system 202 can include a set of operations modules for controlling different aspects of the pelletization process. The operation modules can be provided as one or more computer executable software modules, hardware modules, or a combination thereof. For example, one or more of the operation modules can be implemented as blocks of software code with instructions that cause one or more processors of the computing system 202 to execute operations described herein. In addition or alternatively, one or more of the operations modules can be implemented in electronic circuitry such as, e.g., programmable logic circuits, field programmable logic arrays (FPGA), or application specific integrated circuits (ASIC). The operation modules can include the pelletizing drum control system 206 and the additive metering control system 208.

[0045] The pelletizing drum control system 206 can include surface area measurement algorithms. For example, in some implementations, the pelletizing drum control system 206 interfaces with the sensors 104 and receive sensor data 122. The pelletizing drum control system 206 can process the sensor data 122 to determine particle characteristics of each analyzed particle. The sensor data 122 can include measurements of the particles, such as the volume of the particles, and images of the particles.

[0046] For example, as discussed in more detail below, the pelletizing drum control system 206 can execute data analysis algorithms to interpret the sensor data 122 and determine particle characteristics including, but not limited to, particle size distributions, particle shape distributions, and particle surface area distributions, in order to calculate the SIF of each particle.

[0047] In some implementations, the data analysis algorithms include a packing efficiency model to determine a packing efficiency of the mixture based on the particle characteristics. The model can be a theoretical and analytical particle packing model-based Bayesian optimization algorithmor other machine learning modelto determine a packing efficiency of the particles and estimate control parameters of the mixture.

[0048] In some implementations, the data analysis algorithms can include a machine learning model to estimate particle packing efficiency and/or rheometry parameters from measured particle characteristics. For example, the machine learning model can include a model that has been trained on experimental data to receive particle characteristics of particles as input, and to generate a predicted output, e.g., an estimate of the particle packing efficiency.

[0049] In some implementations, the pelletizing drum control system 206 can use a lookup table of SIFs to correlate measured particle characteristics (e.g., size/shape distributions) to experimentally determined control parameters. For example, the pelletizing drum control system 206 can compare the measured particle characteristics to entries in the lookup table and estimate the control parameters based on correlating entries of experimentally determined control parameters in the lookup table. In some examples, the pelletizing drum control system 206 may interpolate between entries in the lookup table or extrapolate the table data when the measured particle characteristics do not precisely match with a table entry.

[0050] For example, the pelletizing drum control system 206 can determine which control parameters to adjust and a degree of adjustment based on the measured particle characteristics. For instance, if a particle shape is outside of desired shape (e.g., measured pellets have an irregular or rough surface area) in comparison to a table entry, the pelletizing drum control system 206 can cause the pelletizing drum to adjust the spin speed, an amount of clay added to the pelletizing drum, an amount of H.sub.2O added to the pelletizing drum, a feed rate, a retention time, and angle of the pelletizing drum, or a combination thereof.

[0051] In some implementations, the pelletizing drum control system 206 can include a machine learning model to estimate an adjustment to a control parameter of the pelletizing drum. In particular, the machine learning model can include a model that has been trained on experimental data to receive particle characteristics, such as the SIF, as input, and to generate a predicted adjustment to a control parameter.

[0052] For example, the adjustment to the control parameter can be an adjustment to an amount of additives from measured particle characteristics., e.g., an adjustment to an amount of clay and/or H.sub.2O to use in the pelletization system 100. In another example, the predicted adjustment to a control parameter can include, but is not limited to, adjusting the crush size of the particles, adjusting the spin speed of the pelletizing drum, adjusting the feed rate of the pelletizing drum, or a combination thereof.

[0053] In some implementations, the machine learning model is a deep learning model that employs multiple layers of models to generate an output for a received input. A deep neural network is a deep machine learning model that includes an output layer and one or more hidden layers that each applies a non-linear transformation to a received input to generate an output. In some cases, the neural network may be a recurrent neural network. A recurrent neural network is a neural network that receives an input sequence and generates an output sequence from the input sequence. In particular, a recurrent neural network uses some or all of the internal state of the network after processing a previous input in the input sequence to generate an output from the current input in the input sequence. In some other implementations, the machine learning model is a convolutional neural network. In some implementations, the machine learning model is an ensemble of models that may include all or a subset of the architectures described above.

[0054] A machine learning model can be trained to estimate control parameters for pelletization particles based on measured characteristics of the particles. In some examples, the machine learning model can be trained on experimentally determined data relating known characteristics of particles to experimentally determined control parameters.

[0055] The computing system 202 can send control signals to the pelletizing drum based on the determined adjustments to the control parameters. For example, the pelletizing drum control system 206 can interface with the additive metering control system 208 directly or via the computing system 202 to control the addition of additives to the pelletizing drum. For example, the pelletizing drum control system 206 can issue commands from the computing system 202 to the additive metering control system 208 to control the addition of additives to the particles 105, such as CO.sub.2 and/or H.sub.2O. In particular, the computing system 202 can then interface with the additive metering control system 208 to operate valves from clay and/or H.sub.2O supply tanks of additives 114 in order to apply appropriate amounts of clay and/or H.sub.2O to the pelletizing drum.

[0056] In some other examples the pelletizing drum control system 206 can interface with the pelletizing drum 112 to adjust the crush size of the particles, adjust the spin speed of the pelletizing drum, the feed rate of the pelletizing drum, or a combination thereof.

[0057] FIG. 3 is a flow diagram that illustrates a process 300 for controlling operation of a pelletization system 100. The process 300 can be performed by one or more computing devices. For example, as discussed above, the process 300 may be performed by computing system 202 of FIG. 2. For convenience, operations of process 300 are described as being performed by a control system.

[0058] The control system obtains images of the pelletized particles (302). For example, as discussed above, the control system can receive data from various sensors of the pelletization system.

[0059] The control system determines characteristics of the pelletized particles (304). The control system can analyze the sensor data to characterize the particles. For example, the control system can use image analysis algorithms and volume measurements to detect general shapes and sizes of particles as they are conveyed to the output of the pelletizing drum, and the control system can determine a SIF factor for each of the particles.

[0060] In some examples, the control system can characterize particles by developing a histogram of the particle size distribution within the aggregate and a histogram of particle shape distribution within the aggregate. The control system can employ the image analysis algorithm to obtain a rough count of aggregate particles within each of a series of size ranges (e.g., >2 mm, 2 mm-3 mm, 3 mm-4 mm, 4 mm-5 mm, etc.). In some implementations, the control system can similarly employ the image analysis algorithm to obtain a rough count of aggregate particles with various shapes or degrees of sphericity based on the SIF.

[0061] The control system determines an adjustment to a control parameter of the pelletization system (306). For example, the control system can compare characteristics of the particles with target characteristics using the SIF for each particle. If the estimated characteristics differ by a threshold amount from the target characteristics (e.g., the SIF for a certain number of particles is higher than a threshold), the control system can determine to adjust control parameters of the pelletization system.

[0062] The control system sends one or more signals to adjust one or more control parameters of the pelletization system (308). For example, the control system can send control signals to the metering system to adjust the additives or the pelletizing drum to adjust control parameters of the pelletizing drum.

[0063] For example, the control system can control the addition of additives to the pelletizing drum by issuing commands to a metering control system of the pelletization system. In particular, the control system can interface with the metering control system to operate valves from clay and/or H.sub.2O supply tanks of additives in order to apply appropriate amounts of clay and/or H.sub.2O to the pelletizing drum.

[0064] In some other examples the control system can interface with the pelletizing drum to adjust the spin speed of the pelletizing drum, the feed rate of the pelletizing drum, or a combination thereof.

[0065] The computing system can iteratively send the one or more signals in order to iteratively adjust the control parameters based on the determined characteristics of the particles (310).

[0066] FIG. 4 depicts an exemplary iron ore smelting blast furnace system 400. In operation, the iron ore smelting blast furnace system 400 processes particles 105 in a blast furnace 408. The blast furnace 408 can generate smelted iron by processing the particles 105. Operations of the blast furnace 408 can be controlled by control signals 412 from a control system 402.

[0067] The iron ore smelting system 400 includes the control system 402. The control system 402 receives input from sensors 104. The control system 402 can control the operations of one or more metering systems based on analyses of data obtained from the sensors 104. In some examples, the control system 402 can be used to control the operations of one or more metering system for other liquid solid or solid gas-reaction like catalytic reactors, or charges for electric arc furnaces and oxygen furnaces.

[0068] Additionally, the iron ore smelting system 400 includes a blast furnace 408. The blast furnace includes a first section 404 and a second section 406. The inputs of the blast furnace 408 enter from the top of the blast furnace. Generally, the inputs include iron ore pelletized particles (e.g., particles 105) and reactants 418, such as coke and limestone.

[0069] The blast furnace 408 passes the input to the first section 404 to generate a reduction of iron ore at high temperatures (e.g., 250 C.-750 C.). The blast furnace 408 then passes the products of the reduction reaction to the second section 406, which is at relatively higher temperatures (750 C.-1500 C.) than the first section 404. At the second section 406, the inputs reacts with CO.sub.2. In particular, the coke reacts with the CO.sub.2. Additionally, the limestone decomposes and produces slag 420. The iron ore smelting system 400 then adds blast air 416 at a certain flow rate and blast air temperature, which reacts with the coke to expel waste gases 409. Thus, at the bottom of the blast furnace 408, smelted molted iron 422 remains as an output of the blast furnace 408.

[0070] The blast furnace 408 takes as input particles 105 and reactants 418. The reactants 418 can include a certain amount of limestone and a certain amount of coke. The particles 105 can be from the output of a pelletization system 100.

[0071] The particles 105 are passed through the sensors 104 as the particles 105 are conveyed to the blast furnace 408. The sensors 104 are arranged to measure characteristics of the particles. For example, in some implementations, sensors can be arranged in an array along a conveyor or a chute from the pelletization system 100 to the blast furnace 408. The sensors can transmit images of the particles to the control system 402, which (as explained in more detail below) can use image processing algorithms to identify particle shapes and sizes and to determine particle surface area. In some implementations, the sensors 104 are the same as those discussed in reference to FIG. 1. That is, a pelletization system may be co-located with the ore smelting system such that the pellets are transported directly from the pelletization system to the blast furnace 408.

[0072] The sensors 104 can include various different sensors configured to measure various characteristics of concrete particles. For example, the sensors used by the sensors 104 can include, but are not limited to, optical sensors (e.g., visible light cameras, infra-red cameras, near IR (NIR) sensors, dynamic optical microscopy sensors) and mechanical sensors (e.g., sieves, sedigraphs, impact hammer, electrodynamic vibrator), and spectrometers. In some examples, diffuse reflectance spectroscopy can be used across the visible, near- and shortwave-infrared spectral regions (400 to 2500 nm) as a tool to assess the strength of particles.

[0073] The sensor data 410 is used by the control system 102 to determine characteristics of the particles 105. For example, particle characteristics can include, but are not limited to, particle sizes, shapes, surface areas, sphericity, porosity, density, strength, and particle size distribution.

[0074] In some examples, the sensors 104 can use laser diffraction and dynamic light scattering in combination with empirical rheological measurements to capture measurements of the particles, such as a volume of the particles.

[0075] The sensor data 410 can include images of each of the particles 105 at the output of the pelletizing drum 115, volumes of each of the particles 105 at the output of the pelletizing drum 115, or both. The images are used by the control system 102 to determine characteristics of the particles 105. For example, particle characteristics can include, but are not limited to, particle sizes, shapes, surface areas, sphericity, porosity, density, strength, and particle size distribution.

[0076] Generally, the surface reaction rate of the blast furnace 408 depends on the mixability of the different reactants 418 and the particles 105, especially the particles 105. In particular, the homogeneity of the particles has a direct relationship with the surface reaction rates at the second section 406 of the blast furnace 408. The homogeneity of the particles depends on the similarity of particle size for each of the particles. For example, particles of the same size tend to aggregate, which can lead to higher surface reaction rates, and particles of different sizes tend to segregate, which can lead to inefficient reactions and relatively lower surface reaction rates.

[0077] On the other hand, the homogeneity of the particles has an inverse relationship with the packing density of the particles. Particles of similar sizes can create voids in the flow of particles 105 that can be too large, resulting in under packing, or too small, which can decrease blast furnace efficiency and result in incomplete combustion of the coke. Thus, there is a tradeoff between mixability and packing density based on the homogeneity of the particles. Higher packing density can be achieved by exponential size distribution (heterogeneity), whereas higher mixability is achieved by greater size homogeneity.

[0078] Additionally, the shape of the particles 105 can affect the efficiency of the blast furnace 408. Different particle shapes can also create voids in the flow of particles 105 that are too large or too small, which can affect the way that gas (e.g., CO2) flows through the blast furnace 408, which impacts the quality of the smelted molten iron 422. The particle shape also affects the surface area of the particles, which has a direct impact on the surface reaction rates of the blast furnace 408 and the way the particles 105 move through the blast furnace 408.

[0079] In order to optimize the mixability and the packing efficiency of the particles 105, the control system 402 can use the sensor data 410 to calculate a shape-irregularity factor (SIF) based on measurements from images of each particle, including size, shape, volume, and specific surface area. For each particle, the SIF represents a specific excess surface area of an irregular shape of the particle compared to regular spheres of the same size or volume as the particle.

[0080] For example, a particle within a certain size range (e.g., 2 mm-3 mm) can have an irregular shape. The sensors 104 can capture images of the particle and provide the images to the control system 402 as part of the sensor data 410. The control system 102 can measure a size, shape, and specific surface area of the particle, and the control system 402 can determine a SIF of the particle based on comparing the irregularities of the particles with other particles within the same size range.

[0081] As such, the control system 402 can analyze the particles 105 using sensor data 410 from the sensors 104 by determining a SIF for each of the particles 105, as described in further detail with reference to FIG. 5. The particle analysis can be used to optimize the iron ore smelting process. For example, the control system 402 can send control signals 412 to control an amount of reactants 418 and particles 105 added to the blast furnace, and the control system 402 can send control signals 414 to control parameters of the blast air 416, such as a flow rate of the blast air, a temperature of the blast air, or both.

[0082] The control system 402 can send control signals 414 to ensure a uniform air pathway and an even pressure drop throughout the blast furnace.

[0083] In particular, the control system 402 can send control signals 414 to resolve uneven pressure drops of the blast furnace caused by inadequate packing efficiency of the particles 105, such as too many voids between the particles 105 (e.g., cold spots) or too few voids between the particles 105 (e.g., hot spots). Uneven pressure drops can result in inefficient reactions. As such, the control system 402 can send control signals 414 to increase the flow rate of the blast air in order to allow for more efficient reactions.

[0084] FIG. 5 is a block diagram of an exemplary control system 402 for the iron ore smelting blast furnace system 400. In some implementations, control system 402 can control a combined system that iteratively adjusts reactants of a blast furnace and parameters of blast air based on the measurements (e.g., the surface area measurements) of the particles 105 from a pelletization system 100.

[0085] The control system 402 includes a computing system 502 in communication with the sensors 104, a blast furnace control system 504, and a reactant metering control system 506. The blast furnace control system 504 can control the control signals 414 for parameters of the blast air. The reactant metering control system 506 can control the control signals 124 for adding certain quantities of reactants 418.

[0086] Computing system 502 is configured to control various aspects of the pelletization process. For example, computing system 502 can store and execute one or more computer instruction sets to control the execution of aspects of the iron ore smelting processes described herein. Computing system 502 can include a system of one or more computing devices. The computing devices can be, e.g., a system of one more servers. For example, a first server can be configured to receive and process data from the sensors 104. Another server can be configured to interface with the reactant metering control system 506 and issue control commands based on analysis results from the first server. Another server can be configured to interface with the blast furnace control 504 and issue control commands based on surface area measurements from the first server.

[0087] In some implementations, the computing system 502 can be operated or controlled from a user computing device 204. User computing device 204 can be a computing device, e.g., desktop computer, laptop computer, tablet computer, or other portable or stationary computing device.

[0088] Briefly, computing system 502 can control the overall iron ore smelting system 400 to generate smelted iron. The computing system 202 can use the sensors 104 to capture and measure particles as they are outputted by the pelletization system 100.

[0089] In some implementations, the computing system 502 obtains surface area measurements from the sensors, and the computing system 502 can interface with the blast furnace control system 504 or the reactant metering control system 506 to determine adjustments to the blast furnace 408. The system calculates the SIF for each particle to determine, e.g., whether the particles meet desired properties or whether the computing system should send control signals to adjust the blast furnace 408 (e.g., by adjusting an amount of reactions, adjusting the flow rate of the blast air, adjusting the feed rate of the particles, adjusting the feed position of the particles, or adjusting a temperature of the blast air).

[0090] In some implementations, computing system 202 can include a set of operations modules for controlling different aspects of the pelletization process. The operation modules can be provided as one or more computer executable software modules, hardware modules, or a combination thereof. For example, one or more of the operation modules can be implemented as blocks of software code with instructions that cause one or more processors of the computing system 202 to execute operations described herein. In addition or alternatively, one or more of the operations modules can be implemented in electronic circuitry such as, e.g., programmable logic circuits, field programmable logic arrays (FPGA), or application specific integrated circuits (ASIC). The operation modules can include the blast furnace control system 504 and the reactant metering control system 506.

[0091] The blast furnace control system 504 can include surface area measurement algorithms and one or more lookup tables. For example, in some implementations, the blast furnace control system 504 interfaces with the sensors 104 and receives sensor data 410. The blast furnace control system 504 can process the sensor data 410 to determine particle characteristics of each analyzed particle. The sensor data 410 can include measurements of the particles, such as the volume of the particles, and images of the particles. Additionally, the sensor data 410 can include measurements of the reactants, such as the volume of the coke and the volume of the limestone. In particular, the coke is sieved, such that the blast furnace control system 504 can send control signals to adjust the particle size distribution.

[0092] For example, as discussed in more detail below, the blast furnace control system 504 can execute data analysis algorithms to interpret the sensor data 410 and determine particle characteristics including, but not limited to, particle size distributions, particle shape distributions, and particle surface area distributions, in order to calculate the SIF of each particle.

[0093] In some implementations, the data analysis algorithms include a mixability model to determine a mixability of the particles based on the particle characteristics. The model can be a theoretical and analytical particle packing model-based Bayesian optimization algorithmor other machine learning modelto determine a mixability of the particles and estimate quantities of the reactants to add to the blast furnace and control parameters of the blast air.

[0094] In some implementations, the data analysis algorithms include a packing efficiency model to determine a mixability or a packing efficiency of the particles based on the particle characteristics. The model can be a theoretical and analytical particle packing model-based Bayesian optimization algorithmor other machine learning modelto determine a packing efficiency of the particles and estimate quantities of the reactants to add to the blast furnace and control parameters of the blast air.

[0095] In some implementations, the data analysis algorithms can include a machine learning model to estimate particle mixability or packing efficiency and/or rheometry parameters from measured particle characteristics. For example, the machine learning model can include a model that has been trained on experimental data to receive particle characteristics of particles as input, and to generate a predicted output, e.g., an estimate of the particle packing efficiency.

[0096] The blast furnace control system 504 can compare measured particle characteristics (e.g., size/shape distributions) to experimentally determined control parameters. For example, the blast furnace control system 504 can compare the measured particle characteristics to entries in a lookup table and estimate the control parameters based on correlating entries of experimentally determined control parameters in the lookup table. In some examples, the blast furnace control system 504 may interpolate between entries in the lookup table or extrapolate the table data when the measured particle characteristics do not precisely match with a table entry.

[0097] In some implementations, the blast furnace control system 504 can include a machine learning model to estimate an adjustment to a control parameter of the pelletizing drum. In particular, the machine learning model can include a model that has been trained on experimental data to receive particle characteristics, such as the SIF, as input, and to generate a predicted adjustment to quantities of the reactants to add to the blast furnace, control parameters of the blast air, or both.

[0098] For example, the adjustment to an amount of reactants from measured particle characteristics can be adjusted to an amount of coke to add to the blast furnace. In another example, the predicted adjustment can include, but is not limited to, adjusting the flow rate of the blast air, the temperature of the blast air, or a combination thereof.

[0099] In some implementations, the machine learning model is a deep learning model that employs multiple layers of models to generate an output for a received input. A deep neural network is a deep machine learning model that includes an output layer and one or more hidden layers that each applies a non-linear transformation to a received input to generate an output. In some cases, the neural network may be a recurrent neural network. A recurrent neural network is a neural network that receives an input sequence and generates an output sequence from the input sequence. In particular, a recurrent neural network uses some or all of the internal state of the network after processing a previous input in the input sequence to generate an output from the current input in the input sequence. In some other implementations, the machine learning model is a convolutional neural network. In some implementations, the machine learning model is an ensemble of models that may include all or a subset of the architectures described above.

[0100] A machine learning model can be trained to estimate control parameters for pelletization particles based on measured characteristics of the particles. In some examples, the machine learning model can be trained on experimentally determined data relating known characteristics of particles to experimentally determined control parameters.

[0101] The computing system 502 can send control signals to the blast furnace based on the determined adjustments to the reactants, the blast air, or both.

[0102] For example, the blast furnace control 504 can interface with the reactant metering control system 506 directly or via the computing system 202 to control the addition of certain quantities of reactants, such as coke or limestone, to the blast furnace. For example, the blast furnace control system 504 can issue commands from the computing system 202 to the reactant metering control system 506 to control an amount of coke to add to the blast furnace based on the SIFs of the particles, which has a direct impact on the reaction rates of coke and the particles. In particular, the computing system 502 can interface with the reactant metering control system 506 to operate valves from coke and/or limestone supply tanks in order to apply appropriate quantities of coke and/or limestone to the blast furnace.

[0103] In some other examples, the blast furnace control system 504 can interface with the blast furnace to adjust parameters of the blast air. For example, the blast furnace control system 504 can issue commands from the computing system 202 to the blast furnace to control a temperature of the blast air or a flow rate of the blast air based on the SIFs of the particles, which has a direct impact on the way that gas moves through the blast furnace. In particular, the computing system 502 can interface with the blast furnace to operate valves from a blast air supply tank.

[0104] FIG. 6 is a flow diagram that illustrates a process 600 for controlling operation of the iron ore smelting blast furnace system 400. The process 600 can be performed by one or more computing devices. For example, as discussed above, the process 600 may be performed by computing system 402 of FIG. 5. For convenience, operations of process 600 are described as being performed by a control system.

[0105] The computing system obtains images of the pelletized particles (602). For example, as discussed above, the control system can receive data from various sensors of the pelletization system.

[0106] The computing system can determine characteristics of the particles (604). The control system can analyze the sensor data to characterize the particles. For example, the control system can use image analysis algorithms and volume measurements to detect general shapes and sizes of particles as they are conveyed to the output of the pelletizing drum, and the control system can determine a SIF factor for each of the particles.

[0107] In some examples, the control system can characterize particles (e.g., an by developing a histogram of the particle size distribution within the aggregate and a histogram of particle shape distribution within the aggregate. The control system can employ the image analysis algorithm to obtain a rough count of aggregate particles within each of a series of size ranges (e.g., >2 mm, 2 mm-3 mm, 3 mm-4 mm, 4 mm-5 mm, etc.). In some implementations, the control system can similarly employ the image analysis algorithm to obtain a rough count of aggregate particles with various shapes or degrees of sphericity based on the SIF.

[0108] The computing system can determine quantities of reactants to add to the blast furnace (606). In some implementations, characteristics of the particles can be compared with target characteristics using the SIF for each particle. If the estimated characteristics differ by a threshold amount from the target characteristics (e.g., the SIF for a certain number of particles is higher than a threshold), the control system can determine to adjust an amount of reactants, such as coke, limestone, or particles, to add to the blast furnace.

[0109] In some other examples, the computing system can also determine to adjust parameters of the blast air. For example, if the particles are measured to have a relatively high SIF (e.g., a relatively high amount of irregularities in shape, size, or both), the particles can be associated with a slower surface reaction rate. As such, the computing system can determine whether to increase the flow of blast air, increase the temperature of the blast air, or both, in order to increase the rate of the reaction.

[0110] The computing system can send one or more signals to add one or more reactants (608). For example, the control system can send control signals to the metering system to adjust the additives or the blast furnace to adjust control parameters of the pelletizing drum. For example, the control system can control the addition of additives to the blast furnace by issuing commands to a reactant metering control system of the blast furnace. In particular, the control system can interface with the reactant metering control system to operate valves from coke and/or limestone supply tanks in order to apply appropriate quantities of coke and/or limestone to the blast furnace.

[0111] In some other examples the control system can interface with the blast furnace to adjust parameters of the blast air, such as the flow rate of the blast air, a temperature of the blast air, or both.

[0112] The computing system can iteratively send the one or more signals in order to iteratively adjust the quantities of the reactants based on the determined characteristics of the particles (610).

[0113] FIG. 7 is a schematic diagram of a computer system 700. The system 700 can be used to carry out the operations described in association with any of the computer-implemented methods described previously, according to some implementations. In some implementations, computing systems and devices and the functional operations described in this specification can be implemented in digital electronic circuitry, in tangibly-embodied computer software or firmware, in computer hardware, including the structures disclosed in this specification (e.g., system 700) and their structural equivalents, or in combinations of one or more of them. The system 700 is intended to include various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers, including vehicles installed on base units or pod units of modular vehicles. The system 700 can also include mobile devices, such as personal digital assistants, cellular telephones, smartphones, and other similar computing devices. Additionally, the system can include portable storage media, such as, Universal Serial Bus (USB) flash drives. For example, the USB flash drives may store operating systems and other applications. The USB flash drives can include input/output components, such as a wireless transducer or USB connector that may be inserted into a USB port of another computing device.

[0114] The system 700 includes a processor 710, a memory 720, a storage device 730, and an input/output device 740. Each of the components 710, 720, 730, and 740 are interconnected using a system bus 750. The processor 710 is capable of processing instructions for execution within the system 700. The processor may be designed using any of a number of architectures. For example, the processor 710 may be a CISC (Complex Instruction Set Computers) processor, a RISC (Reduced Instruction Set Computer) processor, or a MISC (Minimal Instruction Set Computer) processor.

[0115] In one implementation, the processor 710 is a single-threaded processor. In another implementation, the processor 710 is a multi-threaded processor. The processor 710 is capable of processing instructions stored in the memory 720 or on the storage device 730 to display graphical information for a user interface on the input/output device 740.

[0116] The memory 720 stores information within the system 700. In one implementation, the memory 720 is a computer-readable medium. In one implementation, the memory 720 is a volatile memory unit. In another implementation, the memory 720 is a non-volatile memory unit.

[0117] The storage device 730 is capable of providing mass storage for the system 700. In one implementation, the storage device 730 is a computer-readable medium. In various different implementations, the storage device 730 may be a floppy disk device, a hard disk device, an optical disk device, or a tape device.

[0118] The input/output device 740 provides input/output operations for the system 700. In one implementation, the input/output device 740 includes a keyboard and/or pointing device. In another implementation, the input/output device 740 includes a display unit for displaying graphical user interfaces.

[0119] The features described can be implemented in digital electronic circuitry, or in computer hardware, firmware, software, or in combinations of them. The apparatus can be implemented in a computer program product tangibly embodied in an information carrier, e.g., in a machine-readable storage device for execution by a programmable processor; and method steps can be performed by a programmable processor executing a program of instructions to perform functions of the described implementations by operating on input data and generating output. The described features can be implemented advantageously in one or more computer programs that are executable on a programmable system including at least one programmable processor coupled to receive data and instructions from, and to transmit data and instructions to, a data storage system, at least one input device, and at least one output device. A computer program is a set of instructions that can be used, directly or indirectly, in a computer to perform a certain activity or bring about a certain result. A computer program can be written in any form of programming language, including compiled or interpreted languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0120] Suitable processors for the execution of a program of instructions include, by way of example, both general and special purpose microprocessors, and the sole processor or one of multiple processors of any kind of computer. Generally, a processor will receive instructions and data from a read-only memory or a random access memory or both. The essential elements of a computer are a processor for executing instructions and one or more memories for storing instructions and data. Generally, a computer will also include, or be operatively coupled to communicate with, one or more mass storage devices for storing data files; such devices include magnetic disks, such as internal hard disks and removable disks; magneto-optical disks; and optical disks. Storage devices suitable for tangibly embodying computer program instructions and data include all forms of non-volatile memory, including by way of example semiconductor memory devices, such as EPROM, EEPROM, and flash memory devices; magnetic disks such as internal hard disks and removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks. The processor and the memory can be supplemented by, or incorporated in, ASICs (application-specific integrated circuits).

[0121] To provide for interaction with a user, the features can be implemented on a computer having a display device such as a CRT (cathode ray tube) or LCD (liquid crystal display) monitor for displaying information to the user and a keyboard and a pointing device such as a mouse or a trackball by which the user can provide input to the computer. Additionally, such activities can be implemented via touchscreen flat-panel displays and other appropriate mechanisms.

[0122] The features can be implemented in a computer system that includes a back-end component, such as a data server, or that includes a middleware component, such as an application server or an Internet server, or that includes a front-end component, such as a client computer having a graphical user interface or an Internet browser, or any combination of them. The components of the system can be connected by any form or medium of digital data communication such as a communication network. Examples of communication networks include a local area network (LAN), a wide area network (WAN), peer-to-peer networks (having ad-hoc or static members), grid computing infrastructures, and the Internet.

[0123] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a network, such as the described one. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

[0124] While this specification contains many specific implementation details, these should not be construed as limitations on the scope of any inventions or of what may be claimed, but rather as descriptions of features specific to particular implementations of particular inventions. Certain features that are described in this specification in the context of separate implementations can also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple implementations separately or in any suitable subcombination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.

[0125] Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Moreover, the separation of various system components in the implementations described above should not be understood as requiring such separation in all implementations, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0126] Thus, particular implementations of the subject matter have been described. Other implementations are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In certain implementations, multitasking and parallel processing may be advantageous.

[0127] As used herein, the term ready mix refers to concrete that is batched for delivery from a central plant instead of being mixed on a job site. Typically, a batch of ready mix is tailor-made according to the specifics of a particular construction project and delivered in a plastic condition, usually in cylindrical trucks often referred to as concrete mixers.

[0128] As used herein, the term real-time refers to transmitting or processing data without intentional delay given the processing limitations of a system, the time required to accurately obtain data, and the rate of change of the data. Although there may be some actual delays, the delays are generally imperceptible to a user.

[0129] While this specification contains many specific implementation details, these should not be construed as limitations on the scope of what is being claimed, which is defined by the claims themselves, but rather as descriptions of features that may be specific to particular embodiments of particular inventions. Certain features that are described in this specification in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination. Moreover, although features may be described above as acting in certain combinations and even initially be claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claim may be directed to a subcombination or variation of a subcombination.

[0130] Particular embodiments of the subject matter have been described. Other embodiments are within the scope of the following claims. For example, the actions recited in the claims can be performed in a different order and still achieve desirable results. As one example, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some cases, multitasking and parallel processing may be advantageous.