A method of monitoring an electrical machine, wherein the method includes: a) obtaining temperature measurement values of the temperature at a plurality of locations of the electrical machine, b) obtaining estimated temperatures at the plurality of locations given by a thermal model of the electrical machine, the thermal model including initial weight parameter values, c) minimizing a difference between the temperature measurement values and the estimated temperatures by finding optimal weight parameter values, d) storing the initial weight parameter values to thereby obtain a storage of used weight parameter values, and updating the optimal weight parameter values as new initial weight parameter values, and repeating steps a)-d) over and over during operation of the electrical machine.

The invention relates to a method for automatically setting at least one parameter of an actuator control system which is designed to control a control variable of an actuator to a predefinable setpoint. The actuator control system is designed to generate a control variable depending on the at least one parameter, the setpoint and the control variable and to actuate the actuator depending on this control variable. A new value of the at least one parameter is determined depending on a stationary probability distribution of the control variable, and the parameter is then set to this new value.

The invention relates to a method for predicting benchmark value of unit equipment based on XGBoost algorithm and a system thereof, wherein the method comprises the following steps: the historical operation data of unit equipment is obtained, the data is preprocessed, and a data set containing a plurality of samples is constructed, and each sample includes the benchmark value of a plurality of parameters of the equipment corresponding to a plurality of features; RF out-of-bag estimation is used for feature importance calculation to eliminate the features with low importance; the data is standardized to eliminate the dimensional effects among features; the data set is input to construct an XGBoost model, and Bayesian super parameter optimization is conducted to obtain the prediction model of benchmark values; and the real-time data of equipment operation is input, and the benchmark values of various equipment parameters are predicted by the prediction model of benchmark values. Compared with the prior art, the invention mines the correlation among data based on the XGBoost algorithm to predict a reasonable equipment benchmark value, and has the advantages of high generalization ability, high prediction accuracy and operation speed and great improvement of the automation ability of the unit.

A system may include virtual sensors representative of operation of different portions of a tangible system. The virtual sensors may receive measured characteristics of the tangible system and may separately output values representative of operation of a common component of the tangible system based on the one or more measured characteristics input into each virtual sensor. A controller may receive the output values from the virtual sensors and determine a state of the common component by comparing the first output value with the second output value.

A method of behavior monitoring includes receiving, from a first sensor of a mobile sensor platform, first sensor data indicative of operation of a monitored device, wherein the monitored device is distinct from the mobile sensor platform; providing, as input to a trained behavior model associated with the monitored device, input data based at least in part on the first sensor data to generate behavior model output data; generating, based on the behavior model output data, a control command; and sending the control command to the mobile sensor platform or the monitored device.

The present invention discloses a hoisting container pose control method of a double-rope winding type ultra-deep vertical shaft hoisting system. The method comprises the following steps of step 1, building a mathematical model of a double-rope winding type ultra-deep vertical shaft hoisting subsystem; step 2, building a position closed-loop mathematical model of an electrohydraulic servo subsystem; step 3, outputting a flatness characteristics of a nonlinear system; step 4, designing a pose leveling flatness controller of a double-rope winding type ultra-deep vertical shaft hoisting subsystem; and step 5, designing a position closed-loop flatness controller of the electrohydraulic servo subsystem.

Systems and methods may use a low speed controller in addition to an economic optimizer to achieve long-term objectives without significantly disrupting or destabilizing an electrical system. Specific long-term objectives include maximizing a capacity factor incentive and regulating battery degradation, but the methods and systems herein can be extended to more long-term objectives. A low speed controller can adjust one or more parameters of a cost function based on the relation between the projected state of the electrical system and the one or more parameters to effectuate a change to the electrical system to attempt to comply with the long-term objective.

A method for recording data relating to the performance of an oil and gas flow network uses statistical data to represent raw data in a compact form. Categories are assigned to time intervals in the data. The method comprises: (1) gathering data covering a period of time, wherein the data relates to the status of one or more control point(s) within the flow network and to one or more flow parameter(s) of interest in one or more flow path(s) of the flow network; (2) identifying multiple time intervals in the data during which the control points and the flow parameter(s) can be designated as being in a category selected from multiple categories; (3) assigning a selected category of the multiple categories to each one of the multiple datasets that are framed by the multiple time intervals; and (4) extracting statistical data representative of some or all of the datasets identified in step (2) to thereby represent the original data from step (1) in a compact form including details of the category assigned to each time interval in step (3).

A method of controlling a real production process, wherein the method includes: a) receiving initial condition data from an on-line simulator system simulating the real production process, and b) performing an optimization based on the initial condition data and on an objective function to obtain set points for controlling the real production process.

In general, techniques are described by which a computing system detects low-impact collisions. A computing system includes at least one processor and memory. The memory includes instructions that, when executed, cause the at least one processor to determine whether an object collided with a vehicle based on a comparison of data received from at least one motion sensor configured to measure at least an acceleration of the vehicle and data received from a plurality of level sensors, wherein each level sensor is configured to measure a relative position between a body of the vehicle and a respective wheel of a plurality of wheels of the vehicle. Execution of the instructions further causes the at least one processor to perform one or more actions in response to determining that the object collided with the vehicle.