CN115514290A - Motor control method, device, equipment and storage medium - Google Patents
Motor control method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115514290A CN115514290A CN202211188943.2A CN202211188943A CN115514290A CN 115514290 A CN115514290 A CN 115514290A CN 202211188943 A CN202211188943 A CN 202211188943A CN 115514290 A CN115514290 A CN 115514290A
- Authority
- CN
- China
- Prior art keywords
- motor
- motor control
- model
- motor system
- abnormal
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000012544 monitoring process Methods 0.000 claims abstract description 61
- 230000002159 abnormal effect Effects 0.000 claims abstract description 58
- 238000011217 control strategy Methods 0.000 claims abstract description 44
- 238000012549 training Methods 0.000 claims description 37
- 238000004590 computer program Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 14
- 238000003062 neural network model Methods 0.000 claims description 11
- 230000002787 reinforcement Effects 0.000 claims description 5
- 238000004891 communication Methods 0.000 description 8
- 238000004519 manufacturing process Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004907 flux Effects 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000001172 regenerating effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Power Engineering (AREA)
- Control Of Electric Motors In General (AREA)
Abstract
The invention discloses a motor control method, a device, equipment and a storage medium, wherein the motor control method comprises the following steps: acquiring operation feedback parameters of the motor system, using the operation feedback parameters as input quantity of a motor control strategy model, and generating motor system operation state monitoring quantity through the motor control strategy model; judging whether the motor system normally operates or not according to the operation feedback parameters, the motor system operation state monitoring quantity and the safe operation threshold value; and if the motor system is abnormal, generating an abnormal state indicating signal of the motor system. In the motor control method provided by the invention, whether the motor system is abnormal or not is judged based on the motor control strategy model, so that the real-time local monitoring for the motor system can be realized, complicated hardware equipment does not need to be configured, and the monitoring cost is low.
Description
Technical Field
Embodiments of the present invention relate to control technologies, and in particular, to a motor control method, apparatus, device, and storage medium.
Background
In an application scenario of an electric vehicle, for example, the function of the motor controller is to convert electric energy stored in a power battery into electric energy required for driving the motor according to instructions such as a gear, an accelerator, and a brake to control a running state such as starting operation, a forward/backward speed, and a climbing force of the electric vehicle, or to assist the electric vehicle to brake, and store part of braking energy in the power battery.
At present, the running state of a motor system is usually monitored by configuring a remote monitoring system, but the remote monitoring system has high configuration cost, high difficulty in acquiring monitoring data and poor monitoring real-time performance.
Disclosure of Invention
The invention provides a motor control method, a motor control device, motor control equipment and a storage medium, and aims to reduce the monitoring cost of a motor system and improve the real-time performance and accuracy of monitoring.
In a first aspect, an embodiment of the present invention provides a motor control method, including:
acquiring operation feedback parameters of a motor system, taking the operation feedback parameters as input quantities of a motor control strategy model, and generating motor system operation state monitoring quantities through the motor control strategy model;
judging whether the motor system normally operates or not according to the operation feedback parameters, the motor system operation state monitoring quantity and a safe operation threshold value;
and if the motor system is abnormal, generating an abnormal state indicating signal of the motor system.
Optionally, the motor control strategy model adopts a neural network model, and training the motor control strategy model includes:
and constructing a motor operation environment model, establishing a loss function of the motor control strategy model according to the motor operation environment model, and training the motor control strategy model based on the loss function.
Optionally, a motor operating environment model is constructed based on reinforcement learning, and a loss function of the motor control strategy model is established according to the motor operating environment model.
Optionally, the motor system running state monitoring amount at least includes a motor control amount and a motor control target amount of the motor system.
Optionally, the safe operation threshold includes a first threshold and a second threshold, and determining whether the motor system operates normally includes:
judging whether the operation feedback parameters are abnormal or not according to the first threshold value;
acquiring running state parameters of the motor system, and judging whether the running state parameters are abnormal or not according to the motor control target quantity and the second threshold value;
and if the operation feedback parameters or the operation state parameters are abnormal, judging that the motor system is abnormal.
In a second aspect, an embodiment of the present invention further provides a motor control method, including:
obtaining operation feedback parameters of a motor system, taking the operation feedback parameters as input quantity of a first model, and generating motor control quantity through the first model;
taking the motor control quantity as an input quantity of a second model, and generating a motor system running state monitoring quantity through the second model;
judging whether the motor system normally operates or not according to the motor system operation state monitoring quantity and a safe operation threshold value;
and if the motor system is abnormal, generating an abnormal state indicating signal of the motor system.
Optionally, the monitoring amount of the running state of the motor system at least includes a predicted time length when the current state of the motor system is set to the designated state.
In a third aspect, an embodiment of the present invention further provides a motor control apparatus, including a motor control unit, where the motor control unit configures the motor control method described in the embodiment of the present invention.
In a fourth aspect, an embodiment of the present invention further provides a computer readable medium including at least one processor, and a memory communicatively coupled to the at least one processor;
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform a motor control method according to an embodiment of the present invention.
In a fifth aspect, the embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores computer instructions, and the computer instructions are used for enabling a processor to implement the motor control method according to the embodiment of the present invention when executed.
Compared with the prior art, the invention has the beneficial effects that: the invention provides a motor control method, which comprises the steps of obtaining operation feedback parameters of a motor system, using the operation feedback parameters as input quantities of a motor control strategy model, generating motor system operation state monitoring quantities through the motor control strategy model, judging whether the motor system is abnormal or not through the motor system operation state monitoring quantities, and judging whether the motor system is abnormal or not based on the motor control strategy model, so that the real-time local monitoring aiming at the motor system can be realized, complex hardware equipment does not need to be configured, the monitoring cost is low, and meanwhile, the problem that the motor system is abnormal or cannot be found in time when the motor system is abnormal or has abnormal trend due to some system factors which are difficult to directly measure in the motor system can be avoided.
Drawings
FIG. 1 is a flowchart of a motor control method in an embodiment;
FIG. 2 is a flow chart of another motor control method in an embodiment;
fig. 3 is a schematic structural diagram of an electronic device in the embodiment.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a motor control method in the embodiment, and referring to fig. 1, the motor control method includes:
s101, obtaining operation feedback parameters of the motor system, using the operation feedback parameters as input quantities of a motor control strategy model, and generating motor system operation state monitoring quantities through the motor control strategy model.
For example, in this embodiment, the operation feedback parameter is used to represent a parameter of the motor system other than the controlled quantity in the motor system, for example, if the controlled quantity is the motor speed, the operation feedback parameter may be the motor voltage, the motor current, and the like.
For example, in this embodiment, the motor control strategy model may adopt a closed-loop control model, a neural network model, or the like.
S102, judging whether the motor system normally operates or not according to the motor system operation state monitoring quantity and the safe operation threshold value.
For example, the monitored value of the operating state of the motor system may include one or more of a control target value of the motor system, a predicted time period when the motor system is set from a current state to a specified state (e.g., a specified output power, a specified motor voltage, etc.), a predicted state change amount of the motor system from the current state after a period, a predicted temperature of the motor after a period, and a predicted rotating speed of the motor.
And S103, if the motor system is abnormal, generating an abnormal state indicating signal of the motor system.
In the present embodiment, the abnormal state indicating signal of the motor system is used for warning, and the warning may be in the form of an acoustic warning, an optical warning, or the like.
The embodiment provides a motor control method, which includes obtaining operation feedback parameters of a motor system, using the operation feedback parameters as input quantities of a motor control strategy model, generating a motor system operation state monitoring quantity through the motor control strategy model, judging whether the motor system is abnormal through the motor system operation state monitoring quantity, and judging whether the motor system is abnormal based on the motor control strategy model, so that real-time local monitoring for the motor system can be realized, complicated hardware equipment does not need to be configured, the monitoring cost is low, and meanwhile, the problem that the motor system cannot be found out in time when the motor system is abnormal or the motor system has an abnormal trend due to some system factors which are difficult to be directly measured in the motor system can be avoided.
On the basis of the scheme shown in fig. 1, as an implementable scheme, the motor control strategy model adopts a neural network model, and the training of the motor control strategy model includes:
the method comprises the steps of constructing a motor operation environment model based on reinforcement learning, establishing a loss function of a motor control strategy model according to the motor operation environment model, and training the motor control strategy model based on the loss function.
Specifically, in this scheme, the training motor control strategy model includes:
step 1, collecting a target calculation graph and characteristic information of target service characteristics according to a target service scene controlled by a specific motor.
And 2, determining a motor operation environment model of the target service scene based on the characteristic information.
And 3, training a motor control strategy model based on the virtualization of the motor operating environment model and the setting of a target by the service logic.
On the basis of the scheme shown in fig. 1, in the scheme, training of the motor control strategy model is realized based on reinforcement learning, a training sample is provided for the motor control strategy model through the motor operation environment model constructed based on reinforcement learning, simulation verification of a training set of the motor control strategy model in a non-production environment can be supported, the training sample data acquisition difficulty is low, the trial-and-error cost is low, meanwhile, the motor control strategy model has strong adaptability, and monitoring service for a motor system can be effectively realized.
On the basis of the scheme shown in fig. 1, as an implementation scheme, the motor system operation state monitoring amount at least comprises a motor control amount and a motor control target amount of the motor system, and the safe operation threshold comprises a first threshold and a second threshold.
For example, in this scheme, determining whether the motor system is operating normally includes:
step 1, judging whether the operation feedback parameters are abnormal or not through a first threshold value.
Illustratively, in this step, when determining whether the operation feedback parameter is abnormal, determining whether the operation feedback parameter exceeds a set range by making a difference between the first threshold and the operation feedback parameter, and if so, determining that the operation feedback parameter is abnormal.
And 2, acquiring running state parameters of the motor system, and judging whether the running state parameters are abnormal or not according to the motor control target quantity and a second threshold value.
In this step, the operating state parameter is differentiated from the motor control target value, the difference value is compared with a second threshold value, and if the difference value is greater than the second threshold value, it is determined that the operating state parameter is abnormal.
And 3, if the operation feedback parameters or the operation state parameters are abnormal, judging that the motor system is abnormal.
On the basis of the beneficial effects of the scheme shown in fig. 1, in the scheme, whether the motor system is abnormal or not is judged according to the input quantity and the output quantity of the motor control strategy model, so that the real-time monitoring and safety guarantee capacity of the motor system can be improved.
Example two
Fig. 2 is a flowchart of another motor control method in the embodiment, and referring to fig. 2, the motor control method includes:
s201, obtaining operation feedback parameters of the motor system, using the operation feedback parameters as input quantities of a first model, and generating motor control quantities through the first model.
For example, in this embodiment, the control of the motor system is implemented by using a first model, where the first model may be a closed-loop control function model, a neural network model, or the like.
Exemplarily, in this embodiment, the input of the configuration first model is an operation feedback parameter of the motor system, where the operation feedback parameter may be a motor parameter such as a motor current, a motor voltage, a motor rotation speed, a motor torque, and a motor flux linkage;
the output of the first model is configured as a motor control quantity, and the motor control quantity is used for controlling the motor to be in a specified working state, such as controlling the motor to work according to a specified rotating speed, outputting specified power or outputting specified torque, and the like.
And S202, taking the motor control quantity as an input quantity of a second model, and generating a motor system running state monitoring quantity through the second model.
In this embodiment, the second model is a neural network model, the input quantity of the second model is configured as the motor control quantity output by the first model, and the output of the second model is configured as the motor system operating state monitoring quantity.
For example, in this embodiment, the monitoring amount of the operating state of the motor system includes one of a predicted time period when the motor system is set to a specified state (for example, a specified output power, a specified motor voltage, and the like) from the current state, and a predicted state change amount of the motor system from the current state after a period;
in addition, the motor system running state monitoring quantity can also comprise parameters such as motor predicted temperature and motor predicted rotating speed after one period.
For example, in this embodiment, the structure of the second model may be designed by referring to any one of neural networks in the prior art.
For example, in this embodiment, taking the predicted time length adopted by the monitoring quantity of the operating state of the motor system as an example, when the second model is trained, configuring the adopted training sample data (including the verification data) includes:
the control quantity-duration data set is obtained through a motor test and comprises paired control quantity data and duration data;
the control quantity data corresponds to motor control quantity, and the duration data corresponds to duration of the motor which is changed to a specified state when the motor is controlled by the motor control quantity.
Illustratively, in this embodiment, when the monitoring quantity of the running state of the motor system adopts other parameters, the training sample data is correspondingly set according to the adopted parameters.
S203, judging whether the motor system normally operates or not according to the motor system operation state monitoring quantity and the safe operation threshold value.
For example, in this embodiment, if the running state monitoring amount of the motor system adopts the predicted time length, determining whether the motor system is running normally includes:
acquiring motor control of a motor system, setting the current state as the actual time length of the specified state, and subtracting the predicted time length from the actual time length to obtain a time difference;
and comparing the time difference with a safe operation threshold, if the time difference is smaller than the safe operation threshold, judging that the motor system normally operates, and otherwise, judging that the motor system is abnormal.
For example, in this embodiment, if the monitored value of the operating state of the motor system adopts a state variable, the determining whether the motor system is operating normally includes:
when the motor system is controlled by the motor control amount, after a calculation period, the actual state variation of the motor system is obtained, and the predicted state variation and the actual state variation are differed to obtain a state variation difference value;
and comparing the state change difference with a safe operation threshold, if the state change difference is smaller than the safe operation threshold, judging that the motor system normally operates, and otherwise, judging that the motor system is abnormal.
And S204, if the motor system is abnormal, generating an abnormal state indicating signal of the motor system.
In the present embodiment, the abnormal state indicating signal of the motor system is used for warning, and the warning may be in the form of an acoustic warning, an optical warning, or the like.
The embodiment provides a motor control method, which comprises the steps of generating a motor control quantity through a first model, using the motor control quantity generated by the first model as input of a second model, generating a motor system running state monitoring quantity through the second model, judging whether a motor system is abnormal or not through the motor system running state monitoring quantity, and judging whether the motor system is abnormal or not based on the second model, so that real-time local monitoring for the motor system can be realized, complex hardware equipment does not need to be configured, the monitoring cost is low, and meanwhile, the problem that the motor system cannot be found out in time when the motor system is abnormal or an abnormal trend of the motor system occurs due to system factors which are difficult to directly measure in the motor system can be avoided.
On the basis of the scheme shown in fig. 2, as an implementation, when an abnormality occurs in the motor system, the motor control method further includes:
step 1, obtaining state parameters of the motor system, using the state parameters as input quantities of a third model, and generating model running state monitoring quantities through the third model.
In this embodiment, the state parameter of the motor system includes one or more of a current motor current, a current motor voltage, a current motor speed, a current motor torque, and a current motor flux linkage of the motor system when the motor control amount needs to be generated.
For example, in the present embodiment, the model operation state monitoring amount is the same type as the motor control amount output by the first model, for example, if the motor control amount represents the duty ratio of the PWM signal (or the duration of a high level in the PWM signal in one cycle), the model operation state monitoring amount also represents the duty ratio of the PWM signal.
In the present embodiment, the third model is a neural network model, and the structure of the third model may be designed by referring to any one of neural networks in the prior art.
In this exemplary embodiment, when training the third model, configuring the adopted training sample data (including the check data) includes:
a state quantity-controlled quantity data set, wherein the state quantity-controlled quantity data set comprises paired state quantity data and controlled quantity data;
and when the control quantity data is correspondingly input as the state parameter, the motor control quantity output by the first model.
And 2, judging whether the first model is abnormal or not according to the monitoring quantity of the running state of the model.
In the scheme, whether the first model is abnormal is determined by comparing the model running state monitoring quantity with the motor control quantity;
for example, if the difference between the model operation state monitoring amount and the motor control amount is larger than a set threshold, it is determined that the first model is abnormal.
On the basis of the beneficial effects of the scheme shown in fig. 2, in the scheme, when the motor system is abnormal, whether the first model is abnormal or not is further judged, and in the process that the motor control method is put into practical production, the reason of the motor system when the motor system is abnormal is accurately determined by monitoring the running state of the first model.
On the basis of the scheme shown in fig. 2, as an implementation, when an abnormality occurs in the motor system, the motor control method further includes:
and obtaining model parameters of the first model, and judging whether the first model is abnormal or not according to the model parameters.
For example, in the present solution, the first model adopts a neural network model, the first model may include an input layer, an intermediate layer and an output layer, and the model parameter may be a weight parameter of the intermediate layer.
Based on the scheme shown in fig. 2, as an implementation, the first model adopts a neural network model, and the training process of the first model includes:
step 1, constructing a control quantity prediction model, a control state prediction model and a discriminator model.
And 2, configuring the output of the control quantity prediction model to comprise first class data, and configuring the control state prediction model to generate second class data through the first class data.
And 3, generating a first training data sequence and a second training data sequence through the first class data and the second class data.
And 4, inputting the first training data sequence and the second training data sequence into the discriminator model, and adjusting the model parameters of the control quantity prediction model according to the discrimination result of the discriminator model.
In the present embodiment, for example, a neural network model is used as the control quantity prediction model, the control state prediction model, and the discriminator model.
For example, in combination with steps 1 to 4, configuring the control quantity prediction model and the control state prediction model includes:
configuring a control quantity prediction model, wherein the input of the control quantity prediction model is a state parameter which can be collected from a motor system, and the output of the control quantity prediction model is a motor control quantity for controlling the motor system;
the input of the configuration control state prediction model is the state parameter and the motor control quantity at the current moment, and the output is the state parameter at the next moment.
In the present embodiment, for example, the first type of data is configured as a state parameter, and the second type of data is configured as a motor control amount.
Illustratively, in this scheme, the first training data sequence and the second training data sequence include:
s1, inputting the first type data at the first moment into a control quantity prediction model to obtain second type data at the first moment.
And S2, inputting the first class data and the second class data at the first moment into a control state prediction model to obtain the first class data at the second moment.
And S3, repeating the steps from S1 to S2 to obtain first class data and second class data from the first moment to the Nth moment, and storing the first class data and the second class data from the first moment to the Nth moment into a first training data sequence.
And setting the form of the second training data sequence to be the same as that of the first training data sequence, and setting the second training data sequence to be artificial marked true data.
Illustratively, in this embodiment, the input of the configured discriminator model includes the data (set) to be discriminated, and the configured discriminator model is used for implementing true discrimination, false discrimination, confidence calculation or classification, etc. of the data (set) to be discriminated.
In this embodiment, the training process of the discriminator model includes:
according to the time sequence, acquiring state parameters and motor control quantities of the motor system from a first time to an Nth time, and storing the acquired state parameters and the motor control quantities into a motor system data sequence in sequence;
and taking the first training data sequence as a motor system false data sequence, inputting the motor system data sequence and the motor system false data sequence into a discriminator model, and training the discriminator model.
In this embodiment, the output of the discriminator model is set as the confidence level, and the model parameters (the weight parameters of each layer in the neural network model) of the discriminator model are repeatedly adjusted before the set confidence level is output by the discriminator model.
In this embodiment, the training process of the control state prediction model includes:
selecting first type data at the ith (i is not equal to 1) moment and randomly generated target data;
and updating the parameters of the model, determining a function value of a loss function of the control state prediction model according to the first data and the target data, and determining whether the parameters of the model are trained according to whether the function value is converged.
In this exemplary embodiment, after completing the training of the arbiter model and the control state prediction model, the training of the control quantity prediction model based on the arbiter model and the control state prediction model includes:
inputting the first training data sequence and the second training data sequence into a discriminator model, and determining whether the output of the discriminator model is a preset discrimination result;
if not, adjusting the prediction parameters of the control quantity prediction model, then regenerating the first training data sequence by using the control quantity prediction model and the control state prediction model, bringing the first training data sequence into the discriminator model, and repeating the steps until the discriminator model outputs a preset discrimination result.
In this embodiment, for example, the trained control quantity prediction model is used as the first model.
EXAMPLE III
The present embodiment provides a motor control apparatus, which includes a motor control unit, and the motor control unit configures any one of the motor control methods described in the first embodiment and the second embodiment.
In this embodiment, the beneficial effects of the motor control unit are the same as the corresponding contents recorded in the first embodiment or the second embodiment, and detailed descriptions are omitted.
As an exemplary implementation, the motor control apparatus may also be configured to include an equipment management unit, a model management unit, a parameter configuration unit, an entry configuration unit, an exit configuration unit, a debugging management unit, and a generation monitoring unit;
configuring a device management unit to: the method is used for providing a login interface and a motor controller management page, wherein a user enters the motor controller management page after logging in, and the motor controller management page is used for modifying basic information (such as motor controller numbers, names and the like) of the motor controller by the user;
the configuration model management unit is used for: providing a model import interface and a model information editing interface, wherein the model import interface is used for importing the motor control strategy model into the edge controller, and the model information editing interface is used for a worker to edit model information of the motor control strategy model, such as model version, model name, model description, uploading time and other information;
the configuration parameter configuration unit is used for: providing a model parameter editing page used for implementing personnel to edit parameter data required by importing the motor control strategy model in operation;
a configuration parameter configuration unit for: providing a model parameter editing page used for implementing personnel to edit parameter data required by importing the motor control strategy model in operation;
configuring a debug management unit to: providing a model debugging interface and a model debugging page, wherein the model debugging interface is used for simulating a test to run the motor control strategy model and acquiring a test running result (such as debugging end, debugging failure, execution failure and the like) of the motor control strategy model, and the model debugging page is used for displaying model information, parameter entering data, parameter exiting data, debugging time, debugging states (such as input generation, debugging and the like) and the like;
configuring a production monitoring unit for: the production monitoring interface is used for executing any one of the motor control methods described in the first embodiment, the monitoring page is used for displaying a production monitoring result (for example, whether a motor control strategy model is abnormal or not, whether a motor system is abnormal or not, and the like), and the monitoring editing page is used for editing monitoring information (for example, an alarm mode and a safe operation threshold value when the motor control strategy model is abnormal or not).
For example, in the present embodiment, the motor control device may be configured in a motor controller, and the motor controller may be configured according to table 1.
TABLE 1
Example four
FIG. 3 illustrates a schematic diagram of an electronic device 10 that may be used to implement an embodiment of the present invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 3, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 may also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to the bus 14.
A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. The processor 11 performs the various methods and processes described above, such as the motor control method.
In some embodiments, the motor control method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the motor control method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the motor control method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user may provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the Internet.
The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
It is to be noted that the foregoing description is only exemplary of the invention and that the principles of the technology may be employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A motor control method, characterized by comprising:
acquiring operation feedback parameters of a motor system, taking the operation feedback parameters as input quantities of a motor control strategy model, and generating motor system operation state monitoring quantities through the motor control strategy model;
judging whether the motor system normally operates or not according to the operation feedback parameters, the motor system operation state monitoring quantity and a safe operation threshold value;
and if the motor system is abnormal, generating an abnormal state indicating signal of the motor system.
2. The motor control method of claim 1, wherein the motor control strategy model employs a neural network model, and wherein training the motor control strategy model comprises:
and constructing a motor operation environment model, establishing a loss function of the motor control strategy model according to the motor operation environment model, and training the motor control strategy model based on the loss function.
3. The motor control method according to claim 2, wherein the motor operating environment model is constructed based on reinforcement learning.
4. The motor control method according to claim 1, wherein the motor system operation state monitoring amount includes at least a motor control amount of the motor system, a motor control target amount.
5. The motor control method of claim 4, wherein the safe operation threshold comprises a first threshold and a second threshold, and wherein determining whether the motor system is operating normally comprises:
judging whether the operation feedback parameters are abnormal or not through the first threshold;
acquiring running state parameters of the motor system, and judging whether the running state parameters are abnormal or not according to the motor control target quantity and the second threshold value;
and if the operation feedback parameters or the operation state parameters are abnormal, judging that the motor system is abnormal.
6. A motor control method, characterized by comprising:
acquiring an operation feedback parameter of a motor system, taking the operation feedback parameter as an input quantity of a first model, and generating a motor control quantity through the first model;
taking the motor control quantity as an input quantity of a second model, and generating a motor system running state monitoring quantity through the second model;
judging whether the motor system normally operates or not according to the motor system operation state monitoring quantity and a safe operation threshold value;
and if the motor system is abnormal, generating an abnormal state indicating signal of the motor system.
7. The motor control method according to claim 6, wherein the motor system operating state monitoring amount includes at least a predicted time period when the motor system is set from a current state to a specified state.
8. A motor control apparatus characterized by comprising a motor control unit that configures the motor control method of claim 1 or claim 6.
9. An electronic device comprising at least one processor, and a memory communicatively coupled to the at least one processor;
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the motor control method of any one of claims 1 or 6.
10. A computer readable storage medium storing computer instructions for causing a processor to implement the motor control method of any one of claims 1 or 6 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211188943.2A CN115514290A (en) | 2022-09-28 | 2022-09-28 | Motor control method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211188943.2A CN115514290A (en) | 2022-09-28 | 2022-09-28 | Motor control method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115514290A true CN115514290A (en) | 2022-12-23 |
Family
ID=84506207
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211188943.2A Pending CN115514290A (en) | 2022-09-28 | 2022-09-28 | Motor control method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115514290A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5563790A (en) * | 1994-03-17 | 1996-10-08 | Mitsubishi Denki Kabushiki Kaisha | Control apparatus for motor-driven power steering system of motor vehicle |
| CN107478989A (en) * | 2017-08-18 | 2017-12-15 | 深圳怡化电脑股份有限公司 | A kind of monitoring method of motor, system and terminal device |
| CN112823471A (en) * | 2020-04-15 | 2021-05-18 | 深圳市大疆创新科技有限公司 | Motor control method, motor control device, movable platform and storage medium |
| CN113839603A (en) * | 2020-06-08 | 2021-12-24 | 杭州先途电子有限公司 | Control method, control system and controller |
| CN114070146A (en) * | 2020-07-30 | 2022-02-18 | 中移(苏州)软件技术有限公司 | Fault detection method, device, equipment and storage medium |
| CN114851859A (en) * | 2022-05-09 | 2022-08-05 | 合肥巨一动力***有限公司 | Safety monitoring system and method for output torque of electric drive system |
-
2022
- 2022-09-28 CN CN202211188943.2A patent/CN115514290A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5563790A (en) * | 1994-03-17 | 1996-10-08 | Mitsubishi Denki Kabushiki Kaisha | Control apparatus for motor-driven power steering system of motor vehicle |
| CN107478989A (en) * | 2017-08-18 | 2017-12-15 | 深圳怡化电脑股份有限公司 | A kind of monitoring method of motor, system and terminal device |
| CN112823471A (en) * | 2020-04-15 | 2021-05-18 | 深圳市大疆创新科技有限公司 | Motor control method, motor control device, movable platform and storage medium |
| WO2021207988A1 (en) * | 2020-04-15 | 2021-10-21 | 深圳市大疆创新科技有限公司 | Motor control method and apparatus, movable platform, and storage medium |
| CN113839603A (en) * | 2020-06-08 | 2021-12-24 | 杭州先途电子有限公司 | Control method, control system and controller |
| CN114070146A (en) * | 2020-07-30 | 2022-02-18 | 中移(苏州)软件技术有限公司 | Fault detection method, device, equipment and storage medium |
| CN114851859A (en) * | 2022-05-09 | 2022-08-05 | 合肥巨一动力***有限公司 | Safety monitoring system and method for output torque of electric drive system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115437339A (en) | Remote diagnosis method and device, electronic equipment and storage medium | |
| CN116562156B (en) | Training method, device, equipment and storage medium for control decision model | |
| CN117784832A (en) | Control method and device for testing vehicle speed of test vehicle and electronic equipment | |
| CN115514290A (en) | Motor control method, device, equipment and storage medium | |
| CN114165430B (en) | Edge-computing-based computer pump health monitoring method, system, equipment and medium | |
| CN116009397A (en) | Brake pressure model training method, device, equipment and storage medium | |
| CN116148666A (en) | Battery SOC signal processing method, device, vehicle, computer readable storage medium and computer program product | |
| CN115598967B (en) | Parameter setting model training, parameter determining method, device, equipment and medium | |
| CN113177077B (en) | Abnormal event determination method and device for automatic driving and electronic equipment | |
| CN116279535A (en) | Vehicle control method and device, electronic equipment and computer storage medium | |
| CN116476851B (en) | Vehicle data processing method and device, electronic equipment and storage medium | |
| CN116737494B (en) | Method and device for monitoring functional safety of vehicle, electronic equipment and storage medium | |
| CN116541187A (en) | Buffer space management method, device, equipment and medium of electronic control unit | |
| CN117720043B (en) | Verification system, method, device and medium for driver in-place state | |
| CN116176737B (en) | Vehicle control method and device, vehicle and storage medium | |
| CN117349747A (en) | Offline fault reason classification method for electric power Internet of things intelligent terminal | |
| CN113918430A (en) | Server hardware running state determination method, related device and program product | |
| CN117993275A (en) | Training method and device of data generation model, electronic equipment and storage medium | |
| CN117125566A (en) | Dynamic diagnosis maintenance method, system, electronic equipment and storage medium | |
| CN117168843A (en) | Unmanned vehicle chassis line control performance testing system, method and medium | |
| CN116880357A (en) | Equipment debugging method, device, equipment and storage medium | |
| CN116559680A (en) | Battery fault diagnosis method and device, electronic equipment and storage medium | |
| CN117215862A (en) | Early warning method, device and system for hard disk faults and related equipment thereof | |
| CN117246312A (en) | Parking control method, device, equipment and storage medium | |
| CN115291111A (en) | Training method of battery standing time prediction model and standing time prediction method |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221223 |