METHOD FOR CONTROLLING A CRUSHER

Abstract

A method for controlling a crusher having a crushing tool and a vibratory conveyor (1) having a drive (5), includes capturing bulk material (2) in a capture region (4) using a sensor (3). So that, in the case of grains with an inhomogeneous grain size distribution, even large grains can be crushed with a constant crushing result without a risk of the crusher being damaged, an effective diameter d.sub.eff, which results from the largest diameter d.sub.max and the direction (9) thereof, transverse to the conveying direction (8) of a grain of the bulk material (2) is determined as the controlled variable in the capture region (4). If the effective diameter d.sub.eff exceeds a predefined power threshold value, the power of the crushing tool is increased and/or, if the effective diameter d.sub.eff exceeds a predefined switch-off limit value, the drive (5) is switched off.

Claims

1. A method for controlling a crusher having a crushing tool and a vibratory conveyor having a drive, said method comprising: capturing bulk material in a capturing region using a sensor; determining an effective diameter d.sub.eff, which is derived from a largest diameter d.sub.max and a direction thereof, that is transverse to a conveying direction of a grain of the bulk material as a controlled variable in the capturing region; and increasing power of the crushing tool when the effective diameter d.sub.eff exceeds a predetermined power threshold value or switching off the drive when the effective diameter d.sub.eff exceeds a predetermined shutdown threshold value.

2. The method according to claim 1, wherein at least two actuators of the drive are controlled so that the effective diameter d.sub.eff is reduced transversely to the conveying direction.

3. The method according to claim 1, wherein, when the effective diameter d.sub.eff transverse to the conveying direction of a grain in the capturing region exceeds a predetermined alignment threshold value, at least two actuators of the drive are controlled so as to reduce the effective diameter d.sub.eff of the grains.

4. The method according to claim 1, wherein the drive is controlled so that a volume, captured at predetermined intervals by a volume sensor, of the bulk material lying in the capturing region corresponds as a controlled variable to a preset value.

5. The method according to claim 4, wherein the sensor comprises a depth sensor that generates a two-dimensional depth image of the bulk material conveyed past the depth sensor, and the two-dimensional depth image is fed to a previously trained convolutional neural network that has at least three successive convolution layers and a downstream classifier, wherein an output value of the neural network is output as a parameter of the bulk material present in the capturing region.

6. A training method for training the neural network for a method according to claim 5, said training method comprising first acquiring example depth images each of a respective example grain with a known individual parameter and storing said example depth images together with the individual parameters thereof; combining a plurality of said example depth images randomly so as to form a training depth image to which a sum of the individual parameters, a maximum value of the individual parameters, or a mean value of the individual parameters of the combined example depth images is assigned as a common parameters; and feeding the training depth image to the neural network on an input side thereof, and feeding the common parameter assigned to said training depth image to the neural network on an output side thereof; and adapting weights of the individual network nodes in a learning step.

7. The method according to claim 2, wherein, when the effective diameter d.sub.eff transverse to the conveying direction of a grain in the capturing region exceeds a predetermined alignment threshold value, the at least two actuators of the drive are controlled so as to reduce the effective diameter d.sub.eff of the grains.

8. The method according to claim 2, wherein the drive is controlled so that a volume, captured at predetermined intervals by a volume sensor, of the bulk material lying in the capturing region corresponds as a controlled variable to a preset value.

9. The method according to claim 3, wherein the drive is controlled so that a volume, captured at predetermined intervals by a volume sensor, of the bulk material lying in the capturing region corresponds as a controlled variable to a preset value.

10. The method according to claim 7, wherein the drive is controlled so that a volume, captured at predetermined intervals by a volume sensor, of the bulk material lying in the capturing region corresponds as a controlled variable to a preset value.

11. The method according to claim 8, wherein the sensor comprises a depth sensor that generates a two-dimensional depth image of the bulk material conveyed past the depth sensor, and the two-dimensional depth image is fed to a previously trained convolutional neural network that has at least three successive convolution layers and a downstream classifier, wherein an output value of the neural network is output as a parameter of the bulk material present in the capturing region.

12. The method according to claim 9, wherein the sensor comprises a depth sensor that generates a two-dimensional depth image of the bulk material conveyed past the depth sensor, and the two-dimensional depth image is fed to a previously trained convolutional neural network that has at least three successive convolution layers and a downstream classifier, wherein an output value of the neural network is output as a parameter of the bulk material present in the capturing region.

13. The method according to claim 10, wherein the sensor comprises a depth sensor that generates a two-dimensional depth image of the bulk material conveyed past the depth sensor, and the two-dimensional depth image is fed to a previously trained convolutional neural network that has at least three successive convolution layers and a downstream classifier, wherein an output value of the neural network is output as a parameter of the bulk material present in the capturing region.

Description

BRIEF DESCRIPTION OF THE INVENTION

[0014] In the drawing, the subject matter of the invention is shown by way of example, wherein:

[0015] FIG. 1 shows a schematic side view of a vibratory conveyor for carrying out the method according to the invention, and

[0016] FIG. 2 shows a top view of such a vibratory conveyor on a larger scale.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] A method according to the invention can be used for the control of a vibratory conveyor 1 shown in FIG. 1. Vibratory conveyors 1 are used, for example, for feeding crushers with bulk material 2. In order to enable effective crushing even in the case of inhomogeneous bulk material 2, i.e. bulk material 2 with strongly varying grain size distribution, and at the same time to increase the service life of the crusher, an effective diameter d.sub.eff transverse to the conveying direction 8 of a grain of the bulk material 2 resulting from the largest diameter d.sub.max and its direction 9 is used as a controlled variable (FIG. 2). If the effective diameter d.sub.eff exceeds a predetermined power threshold value, the power of a crushing tool of a crusher not shown is increased. When the effective diameter d.sub.eff exceeds a predetermined shutdown threshold, the drive 5 of the vibratory conveyor 1 is switched off. To determine the effective diameter d.sub.eff or the largest diameter d.sub.max of the bulk material 2, a sensor 3 is provided which picks up the bulk material 2 lying in its capturing region 4 and transfers the recorded data to a control unit 6. The control unit 6 can determine the diameters by means of common image processing methods or with the aid of a pre-trained neural network and control the drive 5, as well as a drive of the crusher (not shown), depending on the specified limit or threshold values.

[0018] In addition, the drive 5 can be controlled in such a way that the volume of the bulk material 2 lying in the capturing region 4, which is detected by the sensor 3 at predetermined intervals, corresponds to a preset value as a controlled variable. In this context, the drive 5 is controlled by adjusting the vibration amplitude and/or the vibration frequency in such a way that the controlled variable corresponds to a preset value. Such a preset value can, for example, be a range of a nominal volume input flow to which a crusher to be fed is designed.

[0019] As can be seen from FIG. 2, the grains of the bulk material 2 can be aligned by selective control of the drive 5. For this purpose, the drive 5 can comprise several unbalance motors 7 as drives, which can be controlled independently of each other via actuators with regard to their vibration amplitude and vibration frequency. In this way, an asymmetrical vibration input can be generated, whereby, for example, particularly long bulk material grains can be aligned in such a way that their largest diameter d.sub.max is displaced in the conveying direction 8 and thus their effective diameter d.sub.eff, resulting from the largest diameter d.sub.max and its direction 9 is reduced. This can prevent blocking of the crusher by particularly long bulk material 2.

[0020] To ensure that only bulk material 2 which can actually cause a blockage of the crusher is displaced, the effective diameter d.sub.eff resulting from the largest diameter d.sub.max and direction 9 thereof can be compared with an alignment threshold value. Only if the alignment threshold value is exceeded is a displacement of the bulk material 2 initiated by a corresponding control of the actuators of the unbalance motors 7.

[0021] FIG. 2 also shows a bulk material grain 9 which, due to its formation, would lead to a blocking of the crusher even after an appropriate alignment of the largest diameter d.sub.max. In order to prevent damage to the crusher caused by a particularly coarse bulk material grain 10, it is proposed that the control device 6 switches off the drive 5 when the effective diameter d.sub.eff resulting from the largest diameter d.sub.max and its direction 9 is exceeded via a shutdown threshold value.

[0022] If the effective diameter d.sub.eff is just below the shutdown threshold value, an increase in the crushing tool power can be sufficient. For this purpose, the crushing tool can be controlled by the control device 6 if the effective diameter d.sub.eff exceeds a power threshold value.