CN117097227B - Speed regulation control method and related device for motor - Google Patents
Speed regulation control method and related device for motor Download PDFInfo
- Publication number
- CN117097227B CN117097227B CN202311341548.8A CN202311341548A CN117097227B CN 117097227 B CN117097227 B CN 117097227B CN 202311341548 A CN202311341548 A CN 202311341548A CN 117097227 B CN117097227 B CN 117097227B
- Authority
- CN
- China
- Prior art keywords
- speed regulation
- target
- parameter
- data
- regulation control
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000004458 analytical method Methods 0.000 claims abstract description 110
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 48
- 238000011156 evaluation Methods 0.000 claims abstract description 48
- 238000005457 optimization Methods 0.000 claims abstract description 36
- 238000000605 extraction Methods 0.000 claims abstract description 21
- 238000013499 data model Methods 0.000 claims description 20
- 230000007246 mechanism Effects 0.000 claims description 15
- 238000003860 storage Methods 0.000 claims description 15
- 239000013598 vector Substances 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 11
- 238000013507 mapping Methods 0.000 claims description 9
- 230000002457 bidirectional effect Effects 0.000 claims description 4
- 238000009827 uniform distribution Methods 0.000 claims description 4
- 125000004122 cyclic group Chemical group 0.000 claims description 3
- 230000001276 controlling effect Effects 0.000 claims 1
- 230000001105 regulatory effect Effects 0.000 claims 1
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 18
- 230000004044 response Effects 0.000 description 10
- 230000008859 change Effects 0.000 description 7
- 238000012544 monitoring process Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000011217 control strategy Methods 0.000 description 5
- 239000000284 extract Substances 0.000 description 5
- 238000013459 approach Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 241000254158 Lampyridae Species 0.000 description 3
- 238000005299 abrasion Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 230000008646 thermal stress Effects 0.000 description 3
- 238000013506 data mapping Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000010355 oscillation Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
- H02P29/00—Arrangements for regulating or controlling electric motors, appropriate for both AC and DC motors
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Abstract
The invention relates to the field of artificial intelligence, and discloses a speed regulation control method and a related device for a motor, which are used for improving the speed regulation control accuracy of the motor. The method comprises the following steps: calculating an initial speed regulation control parameter according to the target rotating speed data and the actual rotating speed data; performing parameter classification to obtain current data and temperature data, and performing feature extraction to obtain a target current feature and a target temperature feature; initializing through a fly algorithm to generate a plurality of first candidate control parameters; updating the group to generate a plurality of second candidate control parameters; inputting a plurality of second candidate control parameters into a speed regulation control analysis model for parameter performance analysis to obtain speed regulation performance evaluation indexes and selecting optimal speed regulation control parameters; and carrying out speed regulation control on the target motor according to the optimal speed regulation control parameters, acquiring the real-time running state of the target motor, and carrying out model parameter optimization on the speed regulation control analysis model according to the real-time running state to obtain an optimized speed regulation control analysis model.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a speed regulation control method and a related device of a motor.
Background
Motors are widely used in various industrial applications and household appliances. Performance optimization and stability control of the motor are critical to improving efficiency, reducing energy consumption, and extending motor life. Therefore, research and development of efficient motor speed regulation control methods has been an important topic in the field of motor engineering.
The traditional controller is widely applied to motor speed regulation control. While PID controllers are effective in many situations, they typically require manual adjustment of parameters and are difficult to handle with complex nonlinear systems, and the error in the manual experience is large, resulting in low accuracy in the governor control of the motor.
Disclosure of Invention
The invention provides a speed regulation control method and a related device for a motor, which are used for improving the speed regulation control accuracy of the motor.
The first aspect of the invention provides a speed regulation control method of a motor, which comprises the following steps:
acquiring state parameter data and actual rotation speed data of a target motor, acquiring target rotation speed data set by a user, and calculating initial speed regulation control parameters of the target motor according to the target rotation speed data and the actual rotation speed data;
performing parameter classification on the state parameter data to obtain current data and temperature data, and performing feature extraction on the current data and the temperature data to obtain target current features and target temperature features;
Initializing the initial speed regulation control parameters, the target current characteristics and the target temperature characteristics through a preset fly algorithm to generate an initialized speed regulation control parameter group, wherein the initialized speed regulation control parameter group comprises a plurality of first candidate control parameters;
calculating the fitness value of each first candidate control parameter in the initialized speed regulation control parameter group, and carrying out group updating on the initialized speed regulation control parameter group according to the fitness value to generate a plurality of second candidate control parameters;
inputting the plurality of second candidate control parameters into a preset speed regulation control analysis model for parameter performance analysis to obtain speed regulation performance evaluation indexes of each second candidate control parameter, and selecting the optimal speed regulation control parameters of the target motor according to the speed regulation performance evaluation indexes;
and carrying out speed regulation control on the target motor according to the optimal speed regulation control parameters, acquiring the real-time running state of the target motor, and carrying out model parameter optimization on the speed regulation control analysis model according to the real-time running state to obtain an optimized speed regulation control analysis model.
With reference to the first aspect, in a first implementation manner of the first aspect of the present invention, the obtaining state parameter data and actual rotation speed data of the target motor, obtaining target rotation speed data set by a user, and calculating an initial speed regulation control parameter of the target motor according to the target rotation speed data and the actual rotation speed data includes:
Acquiring state parameter data and actual rotating speed data of a target motor, and acquiring target rotating speed data set by a user;
calculating target difference data between the target rotation speed data and the actual rotation speed data;
calculating a proportional coefficient, an integral coefficient and a differential coefficient of the target motor through a preset PID control algorithm;
according to the proportionality coefficient, calculating a proportionality term corresponding to the target difference data, calculating an integral term corresponding to the target difference data according to the integral coefficient, and calculating a differential term corresponding to the target difference data according to the differential coefficient;
and generating initial speed regulation control parameters of the target motor according to the proportional term, the integral term and the differential term.
With reference to the first aspect, in a second implementation manner of the first aspect of the present invention, the performing parameter classification on the state parameter data to obtain current data and temperature data, and performing feature extraction on the current data and the temperature data to obtain a target current feature and a target temperature feature, includes:
a data space preset by the state parameter data mapping value is used for generating a state parameter data model, and a first current data point and a first temperature data point are determined according to the state parameter data;
Performing current parameter traversal on the state parameter data model according to the first current data points to obtain a plurality of second current data points, and performing traversal analysis on the plurality of second current data points to obtain current associated data points of each second current data point;
generating current data from the first current data point, the plurality of second current data points, and the current-related data point;
performing temperature parameter traversal on the state parameter data model according to the first temperature data points to obtain a plurality of second temperature data points, and performing traversal analysis on the plurality of second temperature data points to obtain temperature associated data points of each second temperature data point;
generating temperature data from the first temperature data point, the plurality of second temperature data points, and the temperature-related data point;
performing curve fitting on the current data to generate a current state curve, and performing curve fitting on the temperature data to generate a temperature state curve;
and extracting the characteristics of the current state curve to obtain a target current characteristic, and extracting the characteristics of the temperature state curve to obtain a target temperature characteristic.
With reference to the first aspect, in a third implementation manner of the first aspect of the present invention, the initializing, by using a preset fire fly algorithm, the initial speed regulation control parameter, the target current feature and the target temperature feature to generate an initialized speed regulation control parameter group, where the initialized speed regulation control parameter group includes a plurality of first candidate control parameters, and includes:
inputting the initial speed regulation control parameters, the target current characteristics and the target temperature characteristics into a preset fly algorithm, and determining the corresponding parameter space range and parameter quantity through the fly algorithm;
generating uniformly distributed positions according to the parameter space range and the parameter quantity by adopting a random number generator;
and generating an initialized speed regulation control parameter group according to the uniform distribution positions, wherein the initialized speed regulation control parameter group comprises a plurality of first candidate control parameters.
With reference to the first aspect, in a fourth implementation manner of the first aspect of the present invention, the calculating an fitness value of each first candidate control parameter in the initialized speed regulation control parameter group, and performing group update according to the initialized speed regulation control parameter group according to the fitness value, to generate a plurality of second candidate control parameters includes:
Calculating the fitness value of each first candidate control parameter in the initialized speed regulation control parameter group;
calculating parameter space distances of a plurality of first candidate control parameters in the initialized speed regulation control parameter group by adopting an attraction mechanism;
according to the parameter space distance, performing parameter space position movement on the plurality of first candidate control parameters to obtain updated parameter space positions;
and carrying out iterative optimization on the initialized speed regulation control parameter group according to the updated parameter space position to generate a plurality of second candidate control parameters.
With reference to the first aspect, in a fifth implementation manner of the first aspect of the present invention, inputting the plurality of second candidate control parameters into a preset speed regulation control analysis model to perform parameter performance analysis, to obtain a speed regulation performance evaluation index of each second candidate control parameter, and selecting an optimal speed regulation control parameter of the target motor according to the speed regulation performance evaluation index, where the method includes:
inputting the plurality of second candidate control parameters into a preset speed regulation control analysis model, wherein the speed regulation control analysis model comprises a plurality of sub analysis models;
Respectively carrying out high-dimensional space mapping on the plurality of second candidate control parameters through the objective kernel function in each sub-analysis model to obtain a plurality of high-dimensional space features;
extracting the characteristics of the plurality of high-dimensional space characteristics through a bidirectional threshold cyclic network in each sub-analysis model to obtain a plurality of target characteristic vectors;
calculating performance speed regulation performance evaluation indexes of the target feature vectors through the fully connected network in each sub-analysis model to obtain speed regulation performance evaluation indexes of each second candidate control parameter;
and comparing the speed regulation performance evaluation indexes to obtain a target comparison result, and selecting the optimal speed regulation control parameters of the target motor from the plurality of second candidate control parameters according to the target comparison result.
With reference to the first aspect, in a sixth implementation manner of the first aspect of the present invention, the performing speed regulation control on the target motor according to the optimal speed regulation control parameter, obtaining a real-time running state of the target motor, and performing model parameter optimization on the speed regulation control analysis model according to the real-time running state to obtain an optimized speed regulation control analysis model, where the method includes:
Generating a corresponding speed regulation control signal according to the optimal speed regulation control parameter, and transmitting the speed regulation control signal to the target motor;
responding to the speed regulation control signal through the target motor, and acquiring the real-time running state of the target motor;
extracting state characteristics of the real-time running state to obtain target running state characteristics, and calculating a loss value of the target running state characteristics and a speed regulation performance evaluation index of the optimal speed regulation control parameter to obtain a target loss value;
and according to the target loss value, carrying out model parameter optimization on the speed regulation control analysis model to obtain an optimized speed regulation control analysis model.
The second aspect of the present invention provides a speed regulation control device for a motor, the speed regulation control device for a motor comprising:
the acquisition module is used for acquiring state parameter data and actual rotating speed data of a target motor, acquiring target rotating speed data set by a user and calculating initial speed regulation control parameters of the target motor according to the target rotating speed data and the actual rotating speed data;
the classification module is used for carrying out parameter classification on the state parameter data to obtain current data and temperature data, and carrying out feature extraction on the current data and the temperature data to obtain a target current feature and a target temperature feature;
The initialization module is used for initializing the initial speed regulation control parameters, the target current characteristics and the target temperature characteristics through a preset fly algorithm to generate an initialization speed regulation control parameter group, wherein the initialization speed regulation control parameter group comprises a plurality of first candidate control parameters;
the updating module is used for calculating the fitness value of each first candidate control parameter in the initialized speed regulation control parameter group, and carrying out group updating on the initialized speed regulation control parameter group according to the fitness value to generate a plurality of second candidate control parameters;
the analysis module is used for inputting the plurality of second candidate control parameters into a preset speed regulation control analysis model to perform parameter performance analysis, obtaining speed regulation performance evaluation indexes of each second candidate control parameter, and selecting the optimal speed regulation control parameters of the target motor according to the speed regulation performance evaluation indexes;
and the optimization module is used for carrying out speed regulation control on the target motor according to the optimal speed regulation control parameters, acquiring the real-time running state of the target motor, and carrying out model parameter optimization on the speed regulation control analysis model according to the real-time running state to obtain an optimized speed regulation control analysis model.
A third aspect of the present invention provides a speed regulation control apparatus for an electric motor, comprising: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the motor governor control apparatus to perform the motor governor control method described above.
A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored therein that, when run on a computer, cause the computer to perform the above-described speed regulation control method of a motor.
According to the technical scheme provided by the invention, an initial speed regulation control parameter is calculated according to target speed data and actual speed data; performing parameter classification to obtain current data and temperature data, and performing feature extraction to obtain a target current feature and a target temperature feature; initializing through a fly algorithm to generate a plurality of first candidate control parameters; updating the group to generate a plurality of second candidate control parameters; inputting a plurality of second candidate control parameters into a speed regulation control analysis model for parameter performance analysis to obtain speed regulation performance evaluation indexes and selecting optimal speed regulation control parameters; according to the optimal speed regulation control parameters, speed regulation control is carried out on the target motor, the real-time running state of the target motor is obtained, the model parameter optimization is carried out on the speed regulation control analysis model according to the real-time running state, and the optimized speed regulation control analysis model is obtained. The optimal control parameters enable the motor to more accurately reach the target rotating speed set by a user, speed errors are reduced, and response speed and accuracy of the motor are improved. The motor can run more effectively by continuously optimizing the speed regulation control parameters, and the optimized speed regulation control ensures that the motor is more stable in running, thereby reducing mechanical abrasion and thermal stress. The running state of the motor is monitored in real time, and the control parameters are dynamically adjusted, so that the motor can be ensured to keep running stably under different working conditions. Allowing the motor to adaptively adjust the control parameters under different operating environment and load requirements without manual intervention. This increases the flexibility and adaptability of the system. By real-time performance monitoring and parameter optimization, the motor is able to continually seek optimal performance at run-time rather than relying on static parameter settings. The motor can adapt to the changing working condition and load requirement, and the speed regulation control accuracy of the motor is further improved.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a method for controlling speed regulation of a motor according to an embodiment of the present invention;
FIG. 2 is a flow chart of a group update in an embodiment of the invention;
FIG. 3 is a flow chart of parameter performance analysis in an embodiment of the invention;
FIG. 4 is a flow chart of model parameter optimization in an embodiment of the invention;
FIG. 5 is a schematic diagram of an embodiment of a speed control device for an electric motor according to an embodiment of the present invention;
fig. 6 is a schematic view of an embodiment of a speed regulation control device for a motor according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a speed regulation control method and a related device for a motor, which are used for improving the speed regulation control accuracy of the motor. The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
For ease of understanding, a specific flow of an embodiment of the present invention is described below with reference to fig. 1, and an embodiment of a speed regulation control method for a motor in an embodiment of the present invention includes:
s101, acquiring state parameter data and actual rotation speed data of a target motor, acquiring target rotation speed data set by a user, and calculating initial speed regulation control parameters of the target motor according to the target rotation speed data and the actual rotation speed data;
it is to be understood that the execution body of the present invention may be a speed regulation control device of a motor, and may also be a terminal or a server, which is not limited herein. The embodiment of the invention is described by taking a server as an execution main body as an example.
Specifically, the server obtains data, which is the basis of control. The server obtains state parameter data (e.g., current, voltage, power, etc.) of the target motor as well as actual rotational speed data, which is typically collected by a sensor or encoder. In addition, the user will typically set the desired target rotational speed data to inform the system of the desired motor speed. The server performs calculation of initial governor control parameters. The key to this step is to calculate the proportional, integral and derivative coefficients of the target motor, which will affect the response of the control system. The server calculates an error between the target rotational speed data and the actual rotational speed data, which error reflects a difference between the actual speed and the desired speed of the motor. The server calculates a proportional term, an integral term, and a differential term from the error using a PID (proportional-integral-derivative) control algorithm. The calculation of these terms is done according to the PID coefficients set in advance. The proportional term is used to handle the current error and the integral term is used to handle the case where the error accumulates over time, while the derivative term helps to dampen oscillations and rapid changes in the system. According to the calculated proportional term, integral term and derivative term, the server generates initial speed regulation control parameters of the target motor. These parameters will be used to adjust the control input to the motor to gradually approach the user-set target speed. For example, assume that the user expects the motor to run at 1000RPM, but the actual speed is only 950RPM, which means that there is a 50RPM error. The server calculates a proportional term, an integral term and a derivative term according to the set PID coefficient through a PID control algorithm, and then uses the proportional term, the integral term and the derivative term to adjust the input of the motor, gradually reduce the error and enable the motor speed to approach the target value.
S102, carrying out parameter classification on state parameter data to obtain current data and temperature data, and carrying out feature extraction on the current data and the temperature data to obtain target current features and target temperature features;
specifically, the server maps the state parameter data into a preset data space to generate a state parameter data model and determines a first current data point and a first temperature data point. Then, a plurality of second current data points are obtained through current parameter traversal, and traversal analysis is carried out on the data points so as to obtain current correlation data points of each second current data point. And similarly, obtaining a plurality of second temperature data points through temperature parameter traversal, and carrying out traversal analysis on the data points to obtain temperature associated data points of each second temperature data point. The server then integrates the first current data point, the plurality of second current data points, and the current-related data point, generating current data. Similarly, by integrating the first temperature data point, the plurality of second temperature data points, and the temperature-related data point, temperature data is generated. These data reflect the change in the state parameters of the motor over time. The server uses curve fitting technology to fit the current data to generate a current state curve, and fits the temperature data to generate a temperature state curve. These curves clearly show the trend of the current and temperature of the motor over time. And the server obtains the target current characteristic and the target temperature characteristic by extracting the characteristics of the current state curve and the temperature state curve. These features include information about peaks, averages, waveform shapes, speed of change, etc. of the curve, which helps to better understand the performance and status of the motor. These features are key parameters for motor speed regulation control, which can be used to adjust the control strategy to meet the user's requirements for motor performance. For example, assume that the server has a motor for industrial production, responsible for driving mechanical devices on a production line. The server ensures that the motor can run at a precise speed during the production process to maintain production stability. The server is equipped with sensors to collect state parameter data of the motor, including current and temperature. The server also sets a desired target speed, say the server motor is running at 1000 revolutions per minute. The server maps the state parameter data into a data space, generating a state parameter data model. In the model, the server selects a first current data point and a first temperature data point and determines their initial values. Through the current parameter traversal, the server obtains a plurality of second current data points representing changes in motor current at different points in time. By analyzing these data points, the server obtains current-related data points that characterize the current change, such as an upward trend or a downward trend of the current. Similarly, through temperature parameter traversal, the server obtains a plurality of second temperature data points describing changes in motor temperature over time. After analyzing these data points, the server obtains temperature-related data points reflecting the fluctuation of temperature. The server integrates the first current data point, the plurality of second current data points, and the current-related data points, generating a state curve for the current data. The curve can display the change trend of the motor current along with time, and help the server to know the current state of the motor. At the same time, by integrating the first temperature data point, the plurality of second temperature data points, and the temperature-related data points, a state curve of the temperature data is generated. This curve reflects the change in motor temperature over time, helping the server to know the temperature state of the motor. The server performs feature extraction on the current state curve, for example, features such as peak value, average value and frequency analysis of the current are extracted. Meanwhile, the characteristic extraction is also carried out on the temperature state curve, including the highest temperature, the temperature change speed and the like.
S103, initializing the initial speed regulation control parameters, the target current characteristics and the target temperature characteristics through a preset fire fly algorithm to generate an initialized speed regulation control parameter group, wherein the initialized speed regulation control parameter group comprises a plurality of first candidate control parameters;
it should be noted that the fire fly algorithm is a meta-heuristic algorithm, which is generally used to optimize the problem, and may be used to search the parameter space to find the optimal solution. In motor governor control, the server will use a fly algorithm to initialize a population of governor control parameters. The server prepares the input parameters. These parameters include an initial governor control parameter, a target current characteristic, and a target temperature characteristic. The initial governor control parameter is typically a parameter that is estimated or set based on the initial state and control requirements of the motor. The target current signature and the target temperature signature describe the current and temperature conditions reached by the server motor. The server uses a fly algorithm to determine the parameter space range and the number of parameters. The parameter space range refers to a range of parameter values, which are generally determined according to the performance and operating conditions of the motor. The parameter number indicates how many parameters are included in the server-generated initialized throttle control parameter population. These two factors will affect the size and diversity of the search space. Using a random number generator, the server generates evenly distributed locations from the determined parameter space ranges and parameter numbers. These positions will be candidates for initializing the governor control parameters. The uniform distribution helps to ensure that the generated parameters are uniformly distributed in the parameter space, increasing the breadth of the search. The generated uniformly distributed positions are used as candidate values of the initialized speed regulation control parameters, so that an initialized speed regulation control parameter group is formed. The population includes a plurality of first candidate control parameters, each representing a throttle control strategy. For example, assume that the server has a motor that needs to be throttled to meet a particular production demand. The server first determines initial governor control parameters such as a proportional coefficient, an integral coefficient, and a derivative coefficient, as well as a target current characteristic and a target temperature characteristic. The server uses a fly algorithm to initialize a population of throttle control parameters. The server determines the parameter space range of the search as follows: the proportional coefficient is between 0 and 1, the integral coefficient is between 0 and 0.5, and the differential coefficient is between 0 and 0.2. The server generates 10 initialized throttle control parameters. By means of the random number generator, the server generates evenly distributed positions as follows: first parameter: the proportional coefficient is 0.6, the integral coefficient is 0.3, and the differential coefficient is 0.1; the second parameter: a proportionality coefficient of 0.2, an integral coefficient of 0.1, a differential coefficient of 0.05..tenth parameter: the proportional coefficient is 0.8, the integral coefficient is 0.4, and the differential coefficient is 0.15. These parameters represent the first candidate control parameters in the initialized population of throttle control parameters. The server now has a number of different governor control parameters that can be used for motor control. The server selects the optimal parameters by evaluating their performance to ensure that the motor can run at the desired speed.
S104, calculating the fitness value of each first candidate control parameter in the initialized speed regulation control parameter group, initializing the speed regulation control parameter group according to the fitness value, and updating the group to generate a plurality of second candidate control parameters;
specifically, the server defines a fitness function to evaluate the performance of each first candidate control parameter. The fitness function is typically based on the actual operating conditions and the desired performance metrics of the motor. For example, the fitness function may include indicators of motor speed error, current ripple, etc. For each first candidate control parameter, it is applied to the motor control system, run for a period of time, and record the performance of the motor. An fitness value is calculated using a defined fitness function, which value reflects the behavior of the parameter in actual operation. The higher the fitness value, the better the performance of the parameter. In the parameter space, a distance between each first candidate control parameter and the other parameters is calculated. This may be done by euclidean distance or other distance metric. The distance metric may help the server learn the interrelationship between the parameters to determine the role of the attraction mechanism. From the calculated parameter spatial distance, a new position of the parameter is determined using an attraction mechanism. Parameters that are closer in distance will attract each other, resulting in them being closer together in parameter space. This mechanism may take different forms, such as introducing random perturbations or using mathematical models to model interactions between parameters. The location of the first candidate control parameter in the parameter space is updated according to the result of the attraction force mechanism. This will cause the parameters to move in the parameter space and affect their performance. The updated position reflects the interplay and adjustment between the parameters. The steps of calculating fitness values, attraction mechanisms and parameter space position movements described above are repeated by iteration until a stop condition is met. In each iteration, the position of the first candidate control parameter is gradually adjusted to find a more optimal combination of parameters. At the end of each round of iterations, one or more second candidate control parameters are generated. These parameters represent an updated throttle control strategy whose performance should be closer to the desired value. For example, assume that the server has a motor, the goal being to run it at 1000 revolutions per minute. The server has three initial governor control parameters: proportional coefficient (Kp), integral coefficient (Ki), differential coefficient (Kd). The server first calculates an fitness value for each first candidate control parameter. Let the fitness value of the first parameter (kp=0.5, ki=0.2, kd=0.1) be 0.05, the fitness value of the second parameter be 0.04, and so on. The server calculates a parameter space distance, for example, a distance between the first parameter and the second parameter of 0.3. The server uses an attraction mechanism to determine the new location of the parameter based on the distance. In this embodiment, the server assumes that the closer parameters will attract each other and move them closer together. After the parameter spatial position has been moved, the server gets updated first candidate control parameters, such as (kp=0.52, ki=0.18, kd=0.12). The server continues iterating, calculating fitness values, applying attraction mechanisms, and parameter space position movements until a stop condition is reached. The server generates a plurality of second candidate control parameters that represent different throttle control strategies. By evaluating their performance, the server selects the optimal combination of parameters to ensure that the motor is operating at the desired speed. This approach allows the server to dynamically adjust the control parameters to accommodate different operating conditions and performance requirements.
S105, inputting a plurality of second candidate control parameters into a preset speed regulation control analysis model for parameter performance analysis to obtain speed regulation performance evaluation indexes of each second candidate control parameter, and selecting the optimal speed regulation control parameters of the target motor according to the speed regulation performance evaluation indexes;
specifically, a plurality of second candidate control parameters are input into a preset throttle control analysis model. This model is a complex computing system that includes multiple sub-analytical models, each model focusing on a different performance assessment. These parameters represent different motor speed regulation strategies, whose performance needs to be evaluated to select the best combination of parameters. In the throttle control analysis model, each second candidate control parameter is mapped to a high-dimensional space by an objective kernel function, and this mapping process helps to better understand the relationship between the parameters. The bi-directional threshold cycle network is used to perform feature extraction on high-dimensional spatial features, which helps capture key characteristics of parameters. Each sub-analysis model comprises a fully-connected network, and the task of the sub-analysis model is to calculate performance evaluation indexes, wherein the indexes can reflect the performance of each second candidate control parameter in motor speed regulation. These performance metrics may include speed error, stability, response time, etc., depending on the particular application and requirements. Through this performance evaluation process, the server obtains performance evaluation indexes for each of the second candidate control parameters, which are presented in the form of multidimensional data. The server compares these multidimensional data to determine which parameters are optimal. In comparing performance evaluation metrics, the server considers the importance of different metrics, e.g., speed error is more critical for some applications than others. Thus, these metrics may be weighted to comprehensively account for different aspects of performance. By comparing the performance evaluation index, the server can determine which second candidate control parameter performs best as a whole and select it as the optimal governor control parameter for the target motor. This process allows the server to dynamically select the applicable control strategy to ensure that the motor can operate at the desired speed, depending on different operating conditions and performance requirements.
S106, performing speed regulation control on the target motor according to the optimal speed regulation control parameters, acquiring the real-time running state of the target motor, and performing model parameter optimization on the speed regulation control analysis model according to the real-time running state to obtain the optimized speed regulation control analysis model.
Specifically, according to the optimal speed regulation control parameters estimated previously, corresponding speed regulation control signals are generated. These signals will be transmitted to the target motor for controlling its rotational speed. This is an actual control operation based on the previous optimization results. The target motor responds to the speed regulation control signal and starts to operate. At this time, the operation data of the motor, including key parameters such as rotation speed, current, temperature, etc., can be collected in real time through the sensor or the monitoring device. These data will be used for monitoring and analysis of real-time operating conditions. And extracting state characteristics from the real-time running state data. The method comprises the steps of analyzing the actual running condition of the motor and extracting key running state characteristics. For example, characteristics of actual rotational speed fluctuation, current peak, temperature rise rate, etc. of the motor may be calculated. And calculating a target loss value by using the data extracted from the state characteristics and combining the optimized speed regulation control parameter and the performance evaluation index. This loss value reflects the difference between the actual operating state of the motor and the expected performance. This can be achieved by comparing the actual operating state characteristics with the target values of the performance evaluation index of the optimal speed control parameters. The calculation result of the target loss value is used for guiding the optimization of the model parameters. By minimizing the target loss value, the parameters of the throttle control analysis model can be updated and optimized. This process involves machine learning algorithms, optimization algorithms, or other mathematical methods to continually improve the accuracy and performance of the model. For example, assume that the server has determined optimal throttle control parameters, such as a proportional coefficient, an integral coefficient, and a derivative coefficient, which are used to generate the throttle control signal. The server transmits these signals to the target motor and monitors its actual operating state. When the motor is running, the server collects data such as actual rotation speed, current, temperature and the like. The server extracts from these data the state characteristics such as the actual speed fluctuation of the motor and the current peaks. At the same time, the server calculates a target loss value reflecting the difference between the actual performance and the expected performance of the motor. It is assumed that the target performance of the server is to minimize motor speed fluctuations and current peaks. The calculation result of the target loss value of the server shows that there is some gap between the actual performance of the motor and the target performance, which is caused by external disturbance or imperfect model parameters. The server uses the target loss value to optimize parameters of the throttle control analysis model. By continuously adjusting the model parameters, the server enables the model to better match the actual behavior of the motor, thereby further improving the performance and stability of the motor.
In the embodiment of the invention, an initial speed regulation control parameter is calculated according to target speed data and actual speed data; performing parameter classification to obtain current data and temperature data, and performing feature extraction to obtain a target current feature and a target temperature feature; initializing through a fly algorithm to generate a plurality of first candidate control parameters; updating the group to generate a plurality of second candidate control parameters; inputting a plurality of second candidate control parameters into a speed regulation control analysis model for parameter performance analysis to obtain speed regulation performance evaluation indexes and selecting optimal speed regulation control parameters; according to the optimal speed regulation control parameters, speed regulation control is carried out on the target motor, the real-time running state of the target motor is obtained, the model parameter optimization is carried out on the speed regulation control analysis model according to the real-time running state, and the optimized speed regulation control analysis model is obtained. The optimal control parameters enable the motor to more accurately reach the target rotating speed set by a user, speed errors are reduced, and response speed and accuracy of the motor are improved. The motor can run more effectively by continuously optimizing the speed regulation control parameters, and the optimized speed regulation control ensures that the motor is more stable in running, thereby reducing mechanical abrasion and thermal stress. The running state of the motor is monitored in real time, and the control parameters are dynamically adjusted, so that the motor can be ensured to keep running stably under different working conditions. Allowing the motor to adaptively adjust the control parameters under different operating environment and load requirements without manual intervention. This increases the flexibility and adaptability of the system. By real-time performance monitoring and parameter optimization, the motor is able to continually seek optimal performance at run-time rather than relying on static parameter settings. The motor can adapt to the changing working condition and load requirement, and the speed regulation control accuracy of the motor is further improved.
In a specific embodiment, the process of executing step S101 may specifically include the following steps:
(1) Acquiring state parameter data and actual rotating speed data of a target motor, and acquiring target rotating speed data set by a user;
(2) Calculating target difference data between the target rotating speed data and the actual rotating speed data;
(3) Calculating a proportional coefficient, an integral coefficient and a differential coefficient of the target motor through a preset PID control algorithm;
(4) According to the proportion coefficient, calculating a proportion term corresponding to the target difference data, calculating an integral term corresponding to the target difference data according to the integral coefficient, and calculating a differential term corresponding to the target difference data according to the differential coefficient;
(5) And generating initial speed regulation control parameters of the target motor according to the proportional term, the integral term and the differential term.
Specifically, the server obtains three types of key data: status parameter data (e.g., current, voltage, power, etc.) of the target motor, actual rotational speed data (typically measured in real time by a sensor or encoder), and user-set target rotational speed data, which is the rotational speed value reached by the motor desired by the user. The server calculates target difference data between the target rotational speed data and the actual rotational speed data. This difference reflects the difference between the current rotational speed of the motor and the rotational speed desired by the user. The server incorporates a PID (proportional-integral-derivative) control algorithm, a classical algorithm widely used in control systems. The PID algorithm requires three parameters: a proportional coefficient (P), an integral coefficient (I) and a differential coefficient (D). The server calculates a proportional term, an integral term, and a differential term according to the PID algorithm. The proportional term is proportional to the target difference data for processing the current error. The integral term is used to handle the case where the error accumulates over time in order to eliminate steady state error. The differentiation term helps to dampen oscillations and rapid changes in the system. By combining the proportional, integral and derivative terms together, the server generates the initial governor control parameters for the motor. These parameters will be used to dynamically adjust the control input of the motor to gradually adjust its rotational speed to a target value set by the user. For example, assume that the server has a motor that the user wishes to speed to 1000RPM, but the actual measured speed is only 950RPM. This means that the target difference data is 50RPM. The server selects the following PID parameter values: proportional coefficient (P) =0.1, integral coefficient (I) =0.01, differential coefficient (D) =0.05. By applying the PID algorithm, the server calculates the initial governor control parameters: proportional term=p=50 rpm=0.1×50 rpm=5, integral term=i=50 rpm=0.01×50 rpm=0.5, differential term=d=50 rpm=2.5. Thus, the initial governor control parameters are: proportional term = 5, integral term = 0.5, differential term = 2.5. These parameters will be used for the actual control of the motor to gradually approach the 1000RPM target speed set by the user. This method allows parameter adjustment to be made according to the needs of different motors and applications to ensure that the motors are operating in an accurate manner.
In a specific embodiment, the process of executing step S102 may specifically include the following steps:
(1) A state parameter data mapping value is preset in a data space, a state parameter data model is generated, and a first current data point and a first temperature data point are determined according to the state parameter data;
(2) Performing current parameter traversal on the state parameter data model according to the first current data points to obtain a plurality of second current data points, and performing traversal analysis on the plurality of second current data points to obtain current associated data points of each second current data point;
(3) Generating current data from the first current data point, the plurality of second current data points, and the current-related data point;
(4) Performing temperature parameter traversal on the state parameter data model according to the first temperature data points to obtain a plurality of second temperature data points, and performing traversal analysis on the plurality of second temperature data points to obtain temperature associated data points of each second temperature data point;
(5) Generating temperature data according to the first temperature data point, the plurality of second temperature data points and the temperature-related data points;
(6) Performing curve fitting on the current data to generate a current state curve, and performing curve fitting on the temperature data to generate a temperature state curve;
(7) And extracting the characteristics of the current state curve to obtain a target current characteristic, and extracting the characteristics of the temperature state curve to obtain a target temperature characteristic.
Specifically, the server creates a state parameter data model to map state parameter data to a preset data space. This data model is a mathematical representation for converting actual state parameter data into a processable form. In this process, the server also determines a first current data point and a first temperature data point, which are the starting points for the initial data analysis. The server performs a current parameter traversal of the state parameter data model using the first current data point. This means that the server generates a plurality of second current data points within the range of current data and analyzes them in detail to obtain current-related data points for each second current data point. These associated data points may reflect the trend of the current parameter in different situations. Similarly, the server also performs a temperature parameter traversal of the state parameter data model using the first temperature data point. This includes generating a plurality of second temperature data points and analyzing them in detail to obtain temperature-related data points for each second temperature data point. These data points assist the server in understanding the change in temperature parameters. The server generates current and temperature data from the first and second data points and the associated data points of current and temperature. The data are calculated according to the state parameter data model and the traversal analysis result. The server performs curve fitting on the current data to generate a current state curve, and performs curve fitting on the temperature data to generate a temperature state curve. Curve fitting is a mathematical technique used to find the best fit curve to best describe the trend of the data. And the server performs characteristic extraction on the current state curve and the temperature state curve. This includes extracting key features from the curve, such as peaks, valleys, means, standard deviations, etc. These features provide important information about the current and temperature conditions that can be used for further analysis and control. For example, assume that the server is monitoring a state parameter of a motor, including current and temperature. The server first creates a state parameter data model and determines a first current data point and a first temperature data point. The server generates a plurality of second current data points through current parameter traversal, and analyzes the second current data points to obtain current associated data points. Similarly, the server generates a plurality of second temperature data points using the temperature parameter traversal and obtains temperature-related data points. From these data points, the server calculates the current and temperature data and performs curve fitting to generate a current state curve and a temperature state curve. The server extracts from these curves the target current characteristics and the target temperature characteristics, which can be used for further speed regulation control and performance analysis of the motor. This process allows the server to better understand the operating state of the motor in order to more precisely control and monitor its performance.
In a specific embodiment, the process of executing step S103 may specifically include the following steps:
(1) Inputting the initial speed regulation control parameters, the target current characteristics and the target temperature characteristics into a preset fly algorithm, and determining the corresponding parameter space range and parameter quantity through the fly algorithm;
(2) A random number generator is adopted, and uniformly distributed positions are generated according to the parameter space range and the parameter quantity;
(3) And generating an initialized speed regulation control parameter group according to the uniformly distributed positions, wherein the initialized speed regulation control parameter group comprises a plurality of first candidate control parameters.
Specifically, the server inputs the initial speed regulation control parameter, the target current characteristic and the target temperature characteristic into a preset fly algorithm. The fly algorithm is a heuristic algorithm based on the behavior of fireflies in the nature, and simulates the mutual attraction and chase among fireflies. In this algorithm, fireflies represent candidate solutions, i.e., server-generated initialization governor control parameters. Through the fly algorithm, the server determines the range of the parameter space and the number of parameters to be generated. The parameter space range determines the range in which the parameters can take values, and the number of parameters indicates how many initial throttle control parameters the server generates. This step is the key to the algorithm, as it determines the size and diversity of the search space. The server uses a random number generator to generate evenly distributed locations. These locations represent the locations of potential candidate solutions in the parameter space. The key idea of the fly algorithm is to move the fly (i.e. the parameter) towards a higher brightness according to the attractive force mechanism. Here, the brightness may be regarded as a value of an optimization target, i.e., a performance index that the server optimizes in motor control. According to the generated uniform distribution positions, the server forms an initialized speed regulation control parameter group. This population comprises a plurality of first candidate control parameters, which are distributed at different locations in the parameter space. In this way, the server gets a diverse initial set of parameters for further motor control optimization. For example, assume that the server has a motor whose speed control parameters need to be adjusted. The server inputs the initial speed regulation control parameter, the target current characteristic and the target temperature characteristic into a fire fly algorithm. The server determines the range of parameter space, e.g., a proportional coefficient between 0 and 1, an integral coefficient between 0 and 2, and a differential coefficient between 0 and 0.5, and decides to generate 10 initial governor control parameters. Using a random number generator, the server generates 10 evenly distributed positions within this parameter space representing 10 different first candidate control parameters. These parameters are distributed over various regions of the parameter space. The server obtains an initialized population of throttle control parameters comprising 10 first candidate control parameters. These parameters can be used as the starting point of an optimization algorithm for further motor speed control performance optimization. Through continuous iteration and optimization, the server finds the optimal control parameters so as to realize stable and efficient operation of the motor.
In a specific embodiment, as shown in fig. 2, the process of executing step S104 may specifically include the following steps:
s201, calculating the fitness value of each first candidate control parameter in the initialized speed regulation control parameter group;
s202, calculating parameter space distances of a plurality of first candidate control parameters in an initialized speed regulation control parameter group by adopting an attractive force mechanism;
s203, moving the parameter space positions of the plurality of first candidate control parameters according to the parameter space distance to obtain updated parameter space positions;
s204, carrying out iterative optimization on the initialized speed regulation control parameter group according to the updated parameter space position, and generating a plurality of second candidate control parameters.
Specifically, the server calculates an fitness value of each first candidate control parameter in the initialized speed regulation control parameter group. The fitness value is a measure reflecting the performance of the parameter and is typically calculated based on the actual operation and desired performance of the motor. The higher the fitness value, the better the performance of the parameter in actual operation. The server uses an attraction mechanism to calculate a parameter spatial distance between a plurality of first candidate control parameters in the initialized population of throttle control parameters. The attraction mechanism simulates the mutual attraction force between objects in nature, wherein the objects are candidate control parameters of the server. The parameter space distance can be calculated based on the difference in the values of the parameters, typically using Euclidean distance or Manhattan distance, etc. And according to the parameter space distance, the server performs parameter space position movement on the plurality of first candidate control parameters. In the parameter space, parameters with higher fitness values will appeal to parameters with lower fitness values, moving them towards more favorable performance optimizations. And according to the updated parameter space position, the server carries out iterative optimization on the initialized speed regulation control parameter group to generate a plurality of second candidate control parameters. This iterative process may be accomplished using various optimization algorithms, such as genetic algorithms, simulated annealing algorithms, and the like. In each iteration, the server calculates a new fitness value and updates the parameter locations continuously until an optimal combination of parameters is found or a stopping condition is reached. For example, assume that the server has a motor whose speed control parameters need to be adjusted. The server has generated an initialization parameter set comprising 10 first candidate control parameters. The server calculates an fitness value for each first candidate control parameter, wherein a higher fitness value indicates a better performance. The server calculates the parameter spatial distance between these parameters using an attraction mechanism. For example, if the distance between two parameters is closer, the attractive force between them will be stronger, thus more interactive and adjusting. The server moves the individual parameter positions in the parameter space in a direction that is more favorable for performance optimization based on the calculation results of the attraction mechanism. In multiple iterations, the server continues to calculate fitness values, updating the parameter locations until an optimal combination of parameters is found or a stop condition is reached. Through this process, the server finds the optimal governor control parameters to achieve high performance operation of the motor.
In a specific embodiment, as shown in fig. 3, the process of executing step S105 may specifically include the following steps:
s301, inputting a plurality of second candidate control parameters into a preset speed regulation control analysis model, wherein the speed regulation control analysis model comprises a plurality of sub analysis models;
s302, respectively carrying out high-dimensional space mapping on a plurality of second candidate control parameters through target kernel functions in each sub-analysis model to obtain a plurality of high-dimensional space features;
s303, extracting features of a plurality of high-dimensional space features through a bidirectional threshold circulation network in each sub-analysis model to obtain a plurality of target feature vectors;
s304, calculating performance speed regulation performance evaluation indexes of a plurality of target feature vectors through a fully connected network in each sub-analysis model to obtain speed regulation performance evaluation indexes of each second candidate control parameter;
s305, comparing the speed regulation performance evaluation indexes to obtain a target comparison result, and selecting the optimal speed regulation control parameters of the target motor from the plurality of second candidate control parameters according to the target comparison result.
Specifically, the server has a plurality of second candidate control parameters, which need to be evaluated for performance. The server inputs these parameters into a preset throttle control analytical model, which typically includes a plurality of sub-analytical models. Each sub-analytical model has its own tasks such as high-dimensional spatial mapping, feature extraction, and performance evaluation. In each sub-analytical model, the server uses a target kernel function to spatially map a plurality of second candidate control parameters in high dimensions. High-dimensional spatial mapping is a technique that maps parameters from an original space to a higher-dimensional space, which helps extract complex relationships between parameters. Each second candidate control parameter will be represented in high-dimensional space as a high-dimensional spatial feature. The server uses a bi-directional threshold-cycling network to perform feature extraction on these high-dimensional spatial features. The purpose of feature extraction is to extract features from the high-dimensional data that are meaningful for performance evaluation. These features include various statistics, frequency domain analysis results, time domain features, and the like. And the server calculates performance evaluation indexes of the extracted features through a fully connected network. These performance evaluation indicators are typically calculated from real-time operation and desired performance of the motor. For example, the performance evaluation index includes response time, stability, overshoot, and the like. The performance evaluation index calculated in each sub-analysis model will be used to compare the performance of the respective second candidate control parameter. The result of the comparison will yield a target comparison result, which includes the performance of each parameter. And according to the target comparison result, the server selects the second candidate control parameter with optimal performance as the final speed regulation control parameter so as to realize the optimal performance of the motor. For example, assuming the server has one motor, the optimal control parameters need to be selected to achieve the desired speed regulation performance. The server has three second candidate control parameters: parameter a, parameter B and parameter C. The server inputs these parameters into a throttle control analytical model that includes three sub-analytical models. In the first sub-analytical model, the server maps parameter A to a high-dimensional space using an objective kernel function and extracts feature vectors. Also, in the second sub-analysis model, the server performs the same operation on the parameter B, and obtains the feature vector of the parameter B. In the third sub-analysis model, the server processes parameter C. Each sub-analysis model uses a bi-directional threshold cycle network to perform feature extraction on the feature vectors. This includes extracting key statistics in the feature vectors and frequency domain analysis results. In a fully connected network, the server calculates performance evaluation metrics for each parameter, such as response time, stability, etc. After comparing these metrics, the server determines which parameters perform best in terms of performance. For example, if parameter a performs best in terms of performance, the server will select parameter a as the final governor control parameter to optimize the governor performance of the motor. This process may select the optimal parameters through multiple iterations and comparisons.
In a specific embodiment, as shown in fig. 4, the process of executing step S106 may specifically include the following steps:
s401, generating a corresponding speed regulation control signal according to the optimal speed regulation control parameter, and transmitting the speed regulation control signal to a target motor;
s402, responding to a speed regulation control signal through a target motor, and acquiring a real-time running state of the target motor;
s403, extracting state characteristics of the real-time running state to obtain target running state characteristics, and calculating a loss value of the target running state characteristics and a speed regulation performance evaluation index of the optimal speed regulation control parameter to obtain a target loss value;
and S404, optimizing model parameters of the speed regulation control analysis model according to the target loss value to obtain an optimized speed regulation control analysis model.
Specifically, the server generates corresponding speed regulation control signals according to the optimal speed regulation control parameters. These signals are typically waveforms of voltage or current that will be used to adjust the input to the motor to achieve the desired rotational speed. These signals may be calculated from the motor model and the optimal parameters. The generated governor control signal is transmitted to the target motor. The motor will respond to these signals and will operate accordingly based on its input. Real-time operating state data of the motor will be collected and monitored. At this stage, the server performs state feature extraction on the real-time running state of the motor. This involves data acquired from the sensors, such as current, rotational speed, temperature, etc. The purpose of feature extraction is to convert complex real-time state data into meaningful features for further analysis. The server calculates a loss value between the target running state characteristic and the speed regulation performance evaluation index of the optimal speed regulation control parameter. This loss value reflects the difference between the actual operating state and the desired state of the motor. Different performance evaluation indicators may be used to quantify such differences, such as sum of squares error, absolute error, response time, etc. And according to the calculated target loss value, the server optimizes the model parameters of the speed regulation control analysis model. The server attempts different parameter combinations to reduce the target loss value, thereby improving the performance of the motor. This process requires multiple iterations to find the optimal combination of model parameters. For example, assuming the server has one motor, the server achieves faster start-up times by adjusting its control parameters. The server improves the response speed of the motor by optimizing the control parameters. The server generates an optimized control signal to ensure that the motor starts at the desired speed. The server transmits these signals to the motor and begins monitoring the real-time operating state of the motor. The server measures the rotational speed and current of the motor and extracts features therefrom, such as start-up time, response time, etc. The server calculates the difference between the actual start-up time and the expected start-up time, resulting in a loss value. This loss value reflects the difference in motor starting performance. The server uses this loss value to optimize model parameters of the motor. The server adjusts the parameters of the control algorithm to reduce the loss value of the start-up time. This can be done by trying different parameter values multiple times until the best performance is obtained. By way of this example, the server sees how optimal performance tuning of the motor is achieved using a throttle control analysis model.
The above describes a method for controlling speed of a motor in an embodiment of the present invention, and the following describes a device for controlling speed of a motor in an embodiment of the present invention, referring to fig. 5, one embodiment of the device for controlling speed of a motor in an embodiment of the present invention includes:
the acquisition module 501 is configured to acquire state parameter data and actual rotation speed data of a target motor, acquire target rotation speed data set by a user, and calculate an initial speed regulation control parameter of the target motor according to the target rotation speed data and the actual rotation speed data;
the classification module 502 is configured to perform parameter classification on the state parameter data to obtain current data and temperature data, and perform feature extraction on the current data and the temperature data to obtain a target current feature and a target temperature feature;
an initialization module 503, configured to perform an initialization process on the initial speed regulation control parameter, the target current feature, and the target temperature feature through a preset fire fly algorithm, to generate an initialized speed regulation control parameter group, where the initialized speed regulation control parameter group includes a plurality of first candidate control parameters;
the updating module 504 is configured to calculate an fitness value of each first candidate control parameter in the initialized speed-regulating control parameter group, and perform group updating on the initialized speed-regulating control parameter group according to the fitness value, so as to generate a plurality of second candidate control parameters;
The analysis module 505 is configured to input the plurality of second candidate control parameters into a preset speed regulation control analysis model to perform parameter performance analysis, obtain a speed regulation performance evaluation index of each second candidate control parameter, and select an optimal speed regulation control parameter of the target motor according to the speed regulation performance evaluation index;
and the optimizing module 506 is configured to perform speed regulation control on the target motor according to the optimal speed regulation control parameter, obtain a real-time running state of the target motor, and perform model parameter optimization on the speed regulation control analysis model according to the real-time running state to obtain an optimized speed regulation control analysis model.
Calculating an initial speed regulation control parameter according to the target rotating speed data and the actual rotating speed data through the cooperative cooperation of the components; performing parameter classification to obtain current data and temperature data, and performing feature extraction to obtain a target current feature and a target temperature feature; initializing through a fly algorithm to generate a plurality of first candidate control parameters; updating the group to generate a plurality of second candidate control parameters; inputting a plurality of second candidate control parameters into a speed regulation control analysis model for parameter performance analysis to obtain speed regulation performance evaluation indexes and selecting optimal speed regulation control parameters; according to the optimal speed regulation control parameters, speed regulation control is carried out on the target motor, the real-time running state of the target motor is obtained, the model parameter optimization is carried out on the speed regulation control analysis model according to the real-time running state, and the optimized speed regulation control analysis model is obtained. The optimal control parameters enable the motor to more accurately reach the target rotating speed set by a user, speed errors are reduced, and response speed and accuracy of the motor are improved. The motor can run more effectively by continuously optimizing the speed regulation control parameters, and the optimized speed regulation control ensures that the motor is more stable in running, thereby reducing mechanical abrasion and thermal stress. The running state of the motor is monitored in real time, and the control parameters are dynamically adjusted, so that the motor can be ensured to keep running stably under different working conditions. Allowing the motor to adaptively adjust the control parameters under different operating environment and load requirements without manual intervention. This increases the flexibility and adaptability of the system. By real-time performance monitoring and parameter optimization, the motor is able to continually seek optimal performance at run-time rather than relying on static parameter settings. The motor can adapt to the changing working condition and load requirement, and the speed regulation control accuracy of the motor is further improved.
The above fig. 5 describes the speed regulation control device of the motor in the embodiment of the present invention in detail from the point of view of modularized functional entities, and the following describes the speed regulation control apparatus of the motor in the embodiment of the present invention in detail from the point of view of hardware processing.
Fig. 6 is a schematic structural diagram of a motor speed regulation control device according to an embodiment of the present invention, where the motor speed regulation control device 600 may have a relatively large difference due to different configurations or performances, and may include one or more processors (central processing units, CPU) 610 (e.g., one or more processors) and a memory 620, and one or more storage media 630 (e.g., one or more mass storage devices) storing application programs 633 or data 632. Wherein the memory 620 and the storage medium 630 may be transitory or persistent storage. The program stored in the storage medium 630 may include one or more modules (not shown), each of which may include a series of instruction operations in the throttle control apparatus 600 of the motor. Still further, the processor 610 may be configured to communicate with the storage medium 630 and execute a series of instruction operations in the storage medium 630 on the throttle control apparatus 600 of the motor.
The motor throttle control apparatus 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input/output interfaces 660, and/or one or more operating systems 631, such as Windows Server, mac OS X, unix, linux, freeBSD, and the like. It will be appreciated by those skilled in the art that the configuration of the throttle control apparatus of the motor shown in fig. 6 is not limiting and may include more or fewer components than shown, or may be combined with certain components, or may be arranged with different components.
The invention also provides a speed regulation control device of the motor, which comprises a memory and a processor, wherein the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the speed regulation control method of the motor in the above embodiments.
The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, or may be a volatile computer readable storage medium, in which instructions are stored which, when executed on a computer, cause the computer to perform the steps of the speed regulation control method of the motor.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. The speed regulation control method of the motor is characterized by comprising the following steps of:
acquiring state parameter data and actual rotation speed data of a target motor, acquiring target rotation speed data set by a user, and calculating initial speed regulation control parameters of the target motor according to the target rotation speed data and the actual rotation speed data;
performing parameter classification on the state parameter data to obtain current data and temperature data, and performing feature extraction on the current data and the temperature data to obtain target current features and target temperature features; the method specifically comprises the following steps: mapping the state parameter data to a preset data space, generating a state parameter data model, and determining a first current data point and a first temperature data point according to the state parameter data; performing current parameter traversal on the state parameter data model according to the first current data points to obtain a plurality of second current data points, and performing traversal analysis on the plurality of second current data points to obtain current associated data points of each second current data point; generating current data from the first current data point, the plurality of second current data points, and the current-related data point; performing temperature parameter traversal on the state parameter data model according to the first temperature data points to obtain a plurality of second temperature data points, and performing traversal analysis on the plurality of second temperature data points to obtain temperature associated data points of each second temperature data point; generating temperature data from the first temperature data point, the plurality of second temperature data points, and the temperature-related data point; performing curve fitting on the current data to generate a current state curve, and performing curve fitting on the temperature data to generate a temperature state curve; extracting features of the current state curve to obtain target current features, and extracting features of the temperature state curve to obtain target temperature features;
Initializing the initial speed regulation control parameters, the target current characteristics and the target temperature characteristics through a preset fly algorithm to generate an initialized speed regulation control parameter group, wherein the initialized speed regulation control parameter group comprises a plurality of first candidate control parameters;
calculating the fitness value of each first candidate control parameter in the initialized speed regulation control parameter group, and carrying out group updating on the initialized speed regulation control parameter group according to the fitness value to generate a plurality of second candidate control parameters;
inputting the plurality of second candidate control parameters into a preset speed regulation control analysis model for parameter performance analysis to obtain speed regulation performance evaluation indexes of each second candidate control parameter, and selecting the optimal speed regulation control parameters of the target motor according to the speed regulation performance evaluation indexes; the method specifically comprises the following steps: inputting the plurality of second candidate control parameters into a preset speed regulation control analysis model, wherein the speed regulation control analysis model comprises a plurality of sub analysis models; respectively carrying out high-dimensional space mapping on the plurality of second candidate control parameters through the objective kernel function in each sub-analysis model to obtain a plurality of high-dimensional space features; extracting the characteristics of the plurality of high-dimensional space characteristics through a bidirectional threshold cyclic network in each sub-analysis model to obtain a plurality of target characteristic vectors; calculating performance speed regulation performance evaluation indexes of the target feature vectors through the fully connected network in each sub-analysis model to obtain speed regulation performance evaluation indexes of each second candidate control parameter; comparing the speed regulation performance evaluation indexes to obtain a target comparison result, and selecting an optimal speed regulation control parameter of the target motor from the plurality of second candidate control parameters according to the target comparison result;
And carrying out speed regulation control on the target motor according to the optimal speed regulation control parameters, acquiring the real-time running state of the target motor, and carrying out model parameter optimization on the speed regulation control analysis model according to the real-time running state to obtain an optimized speed regulation control analysis model.
2. The method according to claim 1, wherein the step of obtaining state parameter data and actual rotational speed data of a target motor, obtaining target rotational speed data set by a user, and calculating initial speed regulation control parameters of the target motor according to the target rotational speed data and the actual rotational speed data, comprises:
acquiring state parameter data and actual rotating speed data of a target motor, and acquiring target rotating speed data set by a user;
calculating target difference data between the target rotation speed data and the actual rotation speed data;
calculating a proportional coefficient, an integral coefficient and a differential coefficient of the target motor through a preset PID control algorithm;
according to the proportionality coefficient, calculating a proportionality term corresponding to the target difference data, calculating an integral term corresponding to the target difference data according to the integral coefficient, and calculating a differential term corresponding to the target difference data according to the differential coefficient;
And generating initial speed regulation control parameters of the target motor according to the proportional term, the integral term and the differential term.
3. The method according to claim 1, wherein the initializing the initial speed control parameter, the target current characteristic, and the target temperature characteristic by a preset fire fly algorithm generates an initialized speed control parameter group, wherein the initialized speed control parameter group includes a plurality of first candidate control parameters, including:
inputting the initial speed regulation control parameters, the target current characteristics and the target temperature characteristics into a preset fly algorithm, and determining the corresponding parameter space range and parameter quantity through the fly algorithm;
generating uniformly distributed positions according to the parameter space range and the parameter quantity by adopting a random number generator;
and generating an initialized speed regulation control parameter group according to the uniform distribution positions, wherein the initialized speed regulation control parameter group comprises a plurality of first candidate control parameters.
4. The method of claim 1, wherein calculating the fitness value of each first candidate control parameter in the initialized speed control parameter group, and performing group update according to the initialized speed control parameter group according to the fitness value, and generating a plurality of second candidate control parameters comprises:
Calculating the fitness value of each first candidate control parameter in the initialized speed regulation control parameter group;
calculating parameter space distances of a plurality of first candidate control parameters in the initialized speed regulation control parameter group by adopting an attraction mechanism;
according to the parameter space distance, performing parameter space position movement on the plurality of first candidate control parameters to obtain updated parameter space positions;
and carrying out iterative optimization on the initialized speed regulation control parameter group according to the updated parameter space position to generate a plurality of second candidate control parameters.
5. The method for controlling speed regulation of a motor according to claim 1, wherein the step of performing speed regulation control on the target motor according to the optimal speed regulation control parameter, obtaining a real-time running state of the target motor, and performing model parameter optimization on the speed regulation control analysis model according to the real-time running state to obtain an optimized speed regulation control analysis model comprises:
generating a corresponding speed regulation control signal according to the optimal speed regulation control parameter, and transmitting the speed regulation control signal to the target motor;
responding to the speed regulation control signal through the target motor, and acquiring the real-time running state of the target motor;
Extracting state characteristics of the real-time running state to obtain target running state characteristics, and calculating a loss value of the target running state characteristics and a speed regulation performance evaluation index of the optimal speed regulation control parameter to obtain a target loss value;
and according to the target loss value, carrying out model parameter optimization on the speed regulation control analysis model to obtain an optimized speed regulation control analysis model.
6. A speed regulation control device of an electric motor, characterized in that the speed regulation control device of an electric motor comprises:
the acquisition module is used for acquiring state parameter data and actual rotating speed data of a target motor, acquiring target rotating speed data set by a user and calculating initial speed regulation control parameters of the target motor according to the target rotating speed data and the actual rotating speed data;
the classification module is used for carrying out parameter classification on the state parameter data to obtain current data and temperature data, and carrying out feature extraction on the current data and the temperature data to obtain a target current feature and a target temperature feature; the method specifically comprises the following steps: mapping the state parameter data to a preset data space, generating a state parameter data model, and determining a first current data point and a first temperature data point according to the state parameter data; performing current parameter traversal on the state parameter data model according to the first current data points to obtain a plurality of second current data points, and performing traversal analysis on the plurality of second current data points to obtain current associated data points of each second current data point; generating current data from the first current data point, the plurality of second current data points, and the current-related data point; performing temperature parameter traversal on the state parameter data model according to the first temperature data points to obtain a plurality of second temperature data points, and performing traversal analysis on the plurality of second temperature data points to obtain temperature associated data points of each second temperature data point; generating temperature data from the first temperature data point, the plurality of second temperature data points, and the temperature-related data point; performing curve fitting on the current data to generate a current state curve, and performing curve fitting on the temperature data to generate a temperature state curve; extracting features of the current state curve to obtain target current features, and extracting features of the temperature state curve to obtain target temperature features;
The initialization module is used for initializing the initial speed regulation control parameters, the target current characteristics and the target temperature characteristics through a preset fly algorithm to generate an initialization speed regulation control parameter group, wherein the initialization speed regulation control parameter group comprises a plurality of first candidate control parameters;
the updating module is used for calculating the fitness value of each first candidate control parameter in the initialized speed regulation control parameter group, and carrying out group updating on the initialized speed regulation control parameter group according to the fitness value to generate a plurality of second candidate control parameters;
the analysis module is used for inputting the plurality of second candidate control parameters into a preset speed regulation control analysis model to perform parameter performance analysis, obtaining speed regulation performance evaluation indexes of each second candidate control parameter, and selecting the optimal speed regulation control parameters of the target motor according to the speed regulation performance evaluation indexes; the method specifically comprises the following steps: inputting the plurality of second candidate control parameters into a preset speed regulation control analysis model, wherein the speed regulation control analysis model comprises a plurality of sub analysis models; respectively carrying out high-dimensional space mapping on the plurality of second candidate control parameters through the objective kernel function in each sub-analysis model to obtain a plurality of high-dimensional space features; extracting the characteristics of the plurality of high-dimensional space characteristics through a bidirectional threshold cyclic network in each sub-analysis model to obtain a plurality of target characteristic vectors; calculating performance speed regulation performance evaluation indexes of the target feature vectors through the fully connected network in each sub-analysis model to obtain speed regulation performance evaluation indexes of each second candidate control parameter; comparing the speed regulation performance evaluation indexes to obtain a target comparison result, and selecting an optimal speed regulation control parameter of the target motor from the plurality of second candidate control parameters according to the target comparison result;
And the optimization module is used for carrying out speed regulation control on the target motor according to the optimal speed regulation control parameters, acquiring the real-time running state of the target motor, and carrying out model parameter optimization on the speed regulation control analysis model according to the real-time running state to obtain an optimized speed regulation control analysis model.
7. A speed regulation control apparatus of an electric motor, characterized in that the speed regulation control apparatus of an electric motor comprises: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invokes the instructions in the memory to cause the motor's throttle control apparatus to perform the motor's throttle control method of any of claims 1-5.
8. A computer readable storage medium having instructions stored thereon, wherein the instructions when executed by a processor implement the method of regulating speed control of an electric machine according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311341548.8A CN117097227B (en) | 2023-10-17 | 2023-10-17 | Speed regulation control method and related device for motor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311341548.8A CN117097227B (en) | 2023-10-17 | 2023-10-17 | Speed regulation control method and related device for motor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117097227A CN117097227A (en) | 2023-11-21 |
| CN117097227B true CN117097227B (en) | 2024-01-26 |
Family
ID=88772021
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311341548.8A Active CN117097227B (en) | 2023-10-17 | 2023-10-17 | Speed regulation control method and related device for motor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117097227B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117614323B (en) * | 2024-01-24 | 2024-04-02 | 深圳禄华科技有限公司 | Brushless motor rotation speed control method, device, equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106325062A (en) * | 2016-08-26 | 2017-01-11 | 武汉科技大学 | Constant grinding force PID (Proportion Integration Differentiation) control optimization method based on improved firefly algorithm |
| CN107367937A (en) * | 2017-08-07 | 2017-11-21 | 陕西科技大学 | A kind of pid parameter optimization method based on adaptive drosophila optimized algorithm |
| CN108365784A (en) * | 2017-11-24 | 2018-08-03 | 天津大学 | Based on the control method for brushless direct current motor for improving PSO-BP neural networks |
| CN109193075A (en) * | 2018-09-28 | 2019-01-11 | 合肥工业大学 | Power battery of pure electric automobile method for controlling cooling system based on intensified learning |
| CN111628687A (en) * | 2020-05-28 | 2020-09-04 | 武汉理工大学 | Entropy weight method based permanent magnet synchronous motor multi-target parameter optimization method |
| CN112000116A (en) * | 2020-07-24 | 2020-11-27 | 西北工业大学 | Heading angle control method of autonomous underwater vehicle based on improved firefly PID method |
| CN113741566A (en) * | 2021-08-31 | 2021-12-03 | 上海电机学院 | Brushless direct current motor rotating speed control method based on genetic ant colony optimization |
| CN114995105A (en) * | 2022-04-27 | 2022-09-02 | 贵州乌江水电开发有限责任公司 | Water turbine regulating system PID parameter optimization method based on improved genetic algorithm |
| CN115411989A (en) * | 2022-08-30 | 2022-11-29 | 广东Tcl智能暖通设备有限公司 | Control parameter setting method, device, equipment and computer readable storage medium |
-
2023
- 2023-10-17 CN CN202311341548.8A patent/CN117097227B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106325062A (en) * | 2016-08-26 | 2017-01-11 | 武汉科技大学 | Constant grinding force PID (Proportion Integration Differentiation) control optimization method based on improved firefly algorithm |
| CN107367937A (en) * | 2017-08-07 | 2017-11-21 | 陕西科技大学 | A kind of pid parameter optimization method based on adaptive drosophila optimized algorithm |
| CN108365784A (en) * | 2017-11-24 | 2018-08-03 | 天津大学 | Based on the control method for brushless direct current motor for improving PSO-BP neural networks |
| CN109193075A (en) * | 2018-09-28 | 2019-01-11 | 合肥工业大学 | Power battery of pure electric automobile method for controlling cooling system based on intensified learning |
| CN111628687A (en) * | 2020-05-28 | 2020-09-04 | 武汉理工大学 | Entropy weight method based permanent magnet synchronous motor multi-target parameter optimization method |
| CN112000116A (en) * | 2020-07-24 | 2020-11-27 | 西北工业大学 | Heading angle control method of autonomous underwater vehicle based on improved firefly PID method |
| CN113741566A (en) * | 2021-08-31 | 2021-12-03 | 上海电机学院 | Brushless direct current motor rotating speed control method based on genetic ant colony optimization |
| CN114995105A (en) * | 2022-04-27 | 2022-09-02 | 贵州乌江水电开发有限责任公司 | Water turbine regulating system PID parameter optimization method based on improved genetic algorithm |
| CN115411989A (en) * | 2022-08-30 | 2022-11-29 | 广东Tcl智能暖通设备有限公司 | Control parameter setting method, device, equipment and computer readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| Vector Control of Induction Machines via Firefly Algorithm for Speed Application;LingZhi Yi et al;《2016 3rd International Conference on Information Science and Control Engineering》;第1175-1178页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117097227A (en) | 2023-11-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117097227B (en) | Speed regulation control method and related device for motor | |
| US10564611B2 (en) | Control system and machine learning device | |
| CN106325073B (en) | Position Closed Loop for Servo System IP controller model-free automatic correcting method based on fractional order | |
| GirirajKumar et al. | PSO based tuning of a PID controller for a high performance drilling machine | |
| JP2016100009A (en) | Method for controlling operation of machine and control system for iteratively controlling operation of machine | |
| JP2017528848A (en) | Method and system for controlling the operation of a machine | |
| CN110286645B (en) | Machine learning device, servo control system, and machine learning method | |
| US20200041160A1 (en) | Air conditioning system and method for controlling same | |
| US11009837B2 (en) | Machine learning device that adjusts controller gain in a servo control apparatus | |
| WO2016047118A1 (en) | Model evaluation device, model evaluation method, and program recording medium | |
| KR101920251B1 (en) | Method for the computer-aided control and/or regulation of a technical system | |
| KR20210052412A (en) | Reinforcement learning model construction method, device, electronic equipment and medium | |
| JP6927446B1 (en) | Control devices, control methods and programs | |
| JP6901037B1 (en) | Control devices, control methods and programs | |
| JPWO2016092872A1 (en) | Control device, program thereof, and plant control method | |
| CN113597582A (en) | Tuning PID parameters using causal models | |
| JP7014330B1 (en) | Controls, control methods, and programs | |
| CN110454322B (en) | Water turbine speed regulation control method, device and system based on multivariable dynamic matrix | |
| JPWO2016203757A1 (en) | Control apparatus, information processing apparatus using the same, control method, and computer program | |
| JP7115654B1 (en) | Control device, control method and program | |
| KR102004749B1 (en) | Method and system for yaw control of WindTurbin | |
| JPWO2020121494A1 (en) | Arithmetic logic unit, action determination method, and control program | |
| Liu et al. | Online expectation maximization for reinforcement learning in POMDPs | |
| JP2022151563A (en) | Extremal value seek control by stochastic gradient estimation | |
| Ruan et al. | Human operator decision support for highly transient industrial processes: a reinforcement learning approach |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |