Magnetic grid fixed-length adjusting system based on wireless transmission control

Abstract

The invention relates to the technical field of magnetic grid measurement optimization, and discloses a magnetic grid fixed-length adjusting system based on wireless transmission control, and the system comprises a digital twin simulation module which is used for constructing a 3D simulation model of a magnetic grid system through physical modeling, and synchronizing the data of a multi-source sensor; the hierarchical reinforcement learning control module is used for executing a macroscopic layer control strategy and a microcosmic layer control strategy on a macroscopic layer and a microcosmic layer respectively; the cross-domain migration evolution module is used for extracting common characteristics from macroscopic layer control strategies and microscopic layer control strategies trained under different equipment and different working conditions, constructing a parameter gene pool and obtaining control strategies suitable for new equipment according to the parameter gene pool; and the biological-like stress response module is used for performing real-time analysis on the data of the multi-source sensor according to the 3D simulation model of the magnetic grid system, and triggering a first preset control strategy when an abnormal behavior is detected. According to the invention, intelligent, self-adaptive, high-precision and cross-device compatible magnetic grid measurement adjustment is realized.

Description

Technical Field

[0001] The invention belongs to the technical field of magnetic grating measurement optimization, and in particular relates to a magnetic grating fixed-length adjustment system based on wireless transmission control. Background Art

[0002] Magnetic grating measurement systems are widely used in the fields of precision positioning and length measurement, such as industrial automation, CNC machine tools and precision measuring equipment. Current magnetic grating measurement systems usually rely on manually set control parameters to optimize measurement accuracy. However, this approach has the following problems: 1. Parameter adjustment relies on experience and has low optimization efficiency: Under different working conditions, it is difficult to find the global optimal control parameters through manual adjustment, resulting in poor system adaptability; 2. Weak environmental adaptability: Factors such as temperature changes, mechanical vibrations, and electromagnetic interference may affect measurement accuracy, and the existing system lacks an adaptive adjustment mechanism; 3. Cross-device and cross-scenario migration is difficult: Under different devices and application scenarios, the control strategy needs to be readjusted, increasing deployment costs. Summary of the invention

[0003] The present invention provides a magnetic grating fixed-length adjustment system based on wireless transmission control, which solves the technical problems in the related technology that the control parameters are manually set, the optimization efficiency is low, the environmental adaptability is weak, and the migration across devices and scenarios is difficult, resulting in limited measurement accuracy and system intelligence level.

[0004] The present invention provides a magnetic grid fixed-length adjustment system based on wireless transmission control, comprising:

[0005] A digital twin simulation module is used to construct a 3D simulation model of the magnetic grid system through physical modeling and synchronize multi-source sensor data, wherein the multi-source sensor data includes temperature, vibration, magnetic field strength and stress, and the 3D simulation model includes electromagnetic field simulation, mechanical vibration simulation and thermal deformation simulation;

[0006] A hierarchical reinforcement learning control module is used to execute a macro-layer control strategy and a micro-layer control strategy at the macro-layer and the micro-layer, respectively, wherein the macro-layer control strategy uses a multi-objective hierarchical evolutionary strategy to optimize a first control parameter; the micro-layer control strategy optimizes a second control parameter by constructing a reinforcement learning model; the first control parameter includes: a PID gain parameter, a filter coefficient, and a wireless communication power; the second control parameter includes: a temperature compensation parameter, a hysteresis compensation parameter, and an adaptive learning rate;

[0007] The cross-domain migration evolution module is used to extract common features from macro-level control strategies and micro-level control strategies trained under different equipment and different working conditions, build a parameter gene library, and obtain control strategies suitable for new equipment based on the parameter gene library;

[0008] The biological stress response module is used to perform real-time analysis of multi-source sensor data based on the 3D simulation model of the magnetic grid system, and trigger the first preset control strategy when abnormal behavior is detected.

[0009] Furthermore, a 3D simulation model of the magnetic grid system is constructed through physical modeling, and multi-source sensor data is synchronized in real time. The specific steps include:

[0010] S201, use CAD software to establish the 3D geometric structure of the magnetic grid system and perform finite element meshing;

[0011] S202, by simulating the electromagnetic mechanical and thermal coupling behaviors of the magnetic grid system, performing electromagnetic field simulation, mechanical vibration simulation and thermal deformation simulation on the magnetic grid system respectively;

[0012] S203, acquiring multi-source sensor data of real-time operation in a real environment, and inputting the multi-source sensor data into a 3D simulation model to achieve simulation-physical synchronization.

[0013] Furthermore, the specific steps of the multi-objective hierarchical evolution strategy include:

[0014] S301, using a Latin hypercube sampling method to initialize a population, the population including P individuals, each individual being represented by a first control parameter vector composed of first control parameters;

[0015] S302, constructing a multi-objective optimization function;

[0016] S303, optimizing individuals using a non-dominated sorting genetic algorithm.

[0017] Furthermore, the multi-objective optimization function includes: ; ; ; ;

[0018] Among them, F represents the comprehensive fitness of the individual, that is, the total loss value of the optimization target, a represents the index of the target, represents the weight coefficient of the ath target, represents the loss value of the a-th target, , and They represent the first fitness, the second fitness and the third fitness, namely the tracking error loss value, the energy consumption loss value and the noise suppression loss value, t represents the index of the time step, T represents the number of time steps, represents the preset target value expected by the magnetic grid system at the tth time step, represents the actual measurement result of the magnetic grid system at the tth time step, represents the wireless communication power of the magnetic grid system at the tth time step, represents the filtered sensor measurement value at the tth time step, represents the unfiltered sensor measurement at time step t.

[0019] Furthermore, the specific steps of step S303 include:

[0020] S501, calculating the first fitness, the second fitness, the third fitness and the comprehensive fitness of the individual according to the multi-objective optimization function;

[0021] S502, dividing the population into three groups according to the comprehensive fitness of individuals: high fitness individuals, medium fitness individuals and low fitness individuals;

[0022] S503, retaining high fitness individuals, performing crossover and mutation operations on medium fitness individuals, and performing high probability mutation operations on low fitness individuals;

[0023] S504, according to the first fitness, the second fitness and the third fitness of the individuals, non-dominated sorting is used to screen and select three Pareto optimal individuals, wherein the individual with the highest first fitness, second fitness and third fitness is taken as the Pareto optimal individual;

[0024] S505, when the number of iterations reaches the preset maximum number of iterations, output the current three Pareto optimal individuals, and select the individual that best meets the current application scenario according to actual needs, otherwise return to S502.

[0025] Furthermore, the crossover operation uses a simulated binary crossover method to generate new individuals. The calculation formula of the simulated binary crossover method is: ;

[0026] Where n represents the element index of the first control parameter vector of the individual, Represents the nth element value of the first control parameter vector of the newly generated offspring individual, Represents a random number between 0 and 1. represents the cross-distribution index that controls the search range, and represents the nth element value of the first control parameter vector of the two parent individuals, c represents the current number of iterations, and C represents the maximum number of iterations. It represents a Gaussian random variable with a mean of 0 and a standard deviation of 1.

[0027] The mutation operation uses the polynomial mutation method to update individuals. The calculation formula of polynomial mutation is: ;

[0028] in, Represents the nth element value of the first control parameter vector after the offspring individual mutation, represents the nth element value of the first control parameter vector of the offspring individual, Represents the variation distribution index.

[0029] Furthermore, the micro-level control strategy optimizes the second control parameter by constructing a reinforcement learning model. The specific steps include:

[0030] S601, constructing a state vector including a second control parameter according to the operating state of the magnetic grid system;

[0031] S602, using the TinyML model to build a policy network, the policy network takes the state vector as input and outputs the adjustment amount of the second control parameter, and the calculation formula of the adjustment amount is: , represents the adjustment amount of the second control parameter, represents the policy network, represents the state vector at the tth time step, Represents network parameters;

[0032] S603, constructing an action space, where the action space represents a geometric range of an adjustment amount of the second control parameter;

[0033] S604, constructing a reward function of a reinforcement learning model;

[0034] S605, update the policy network using a policy gradient method.

[0035] Furthermore, the macro-level control strategy and the micro-level control strategy are respectively converted into a macro-feature vector and a micro-feature vector, and concatenated to obtain a control strategy vector; for the control strategy vectors of different equipment and different working conditions, the standard deviation of each parameter in the control strategy vector is calculated in turn. When the standard deviation is less than a first preset threshold, it is determined that the parameter varies little between different equipment and working conditions, and is regarded as a common feature. The extracted common features are combined to obtain a parameter gene library, which provides a general control strategy framework for new equipment.

[0036] Furthermore, the biological stress response module performs real-time analysis on multi-source sensor data based on the 3D simulation model of the magnetic grating system. When the multi-source sensor data exceeds a preset safety threshold, the magnetic grating system is judged to be operating abnormally and a first preset control strategy is triggered. A preset time period is set and the number of times the same abnormality is triggered within the time period is counted. If the same abnormality occurs multiple times within the preset time period and the magnetic grating system is still operating stably, the triggering condition of the abnormality is adjusted.

[0037] The beneficial effects of the present invention are as follows: the present invention adopts a hierarchical reinforcement learning control strategy, optimizes PID gain, filter coefficient, wireless communication power at the macro level, optimizes temperature compensation, hysteresis compensation, and adaptive learning rate at the micro level, and realizes adaptive control parameter optimization; compared with the traditional method of manually setting parameters, the present invention can automatically learn and adjust the optimal control parameters, improve measurement accuracy, reduce human intervention, and improve the intelligence level of the system;

[0038] The present invention utilizes a cross-domain migration evolution method to extract common features from control strategies trained under different devices and working conditions, construct a parameter gene library, and generate control strategies suitable for new devices based on this. Compared with traditional magnetic grating measurement systems that require readjustment of control parameters, the present invention can quickly migrate optimal control strategies under different devices and different scenarios, reduce the cost of repeated debugging, and improve the versatility and deployment efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a module schematic diagram of a magnetic grid fixed-length adjustment system based on wireless transmission control of the present invention. DETAILED DESCRIPTION

[0040] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that the discussion of these embodiments is only to enable those skilled in the art to better understand and implement the subject matter described herein, and the functions and arrangements of the elements discussed may be changed without departing from the scope of protection of the contents of this specification. Each example may omit, replace or add various processes or components as needed. In addition, the features described relative to some examples may also be combined in other examples.

[0041] like Figure 1 As shown, a magnetic grid fixed length adjustment system based on wireless transmission control includes:

[0042] The digital twin simulation module 101 is used to construct a 3D simulation model of the magnetic grid system through physical modeling, and synchronize multi-source sensor data in real time to simulate the dynamic behavior of the magnetic grid control system and realize online testing and optimization. The multi-source sensor data includes: temperature, vibration, magnetic field strength and stress. The 3D simulation model includes: electromagnetic field simulation, mechanical vibration simulation and thermal deformation simulation;

[0043] Electromagnetic field simulation is used to simulate the propagation of magnetic grating signals and the influence of electromagnetic interference. Mechanical vibration simulation is used to evaluate the rigidity and dynamic stability of the system. Thermal deformation simulation is used to analyze the influence of temperature changes on the measurement accuracy of magnetic grating.

[0044] The hierarchical reinforcement learning control module 102 is used to execute the macro-layer control strategy and the micro-layer control strategy at the macro-layer and the micro-layer, respectively, wherein the macro-layer control strategy uses a multi-objective hierarchical evolutionary strategy to optimize the first control parameter; the micro-layer control strategy optimizes the second control parameter by constructing a reinforcement learning model; the first control parameter includes: PID gain parameter, filter coefficient and wireless communication power, and the second control parameter includes: temperature compensation parameter, hysteresis compensation parameter and adaptive learning rate;

[0045] The cross-domain migration evolution module 103 is used to extract common features from macro-level control strategies and micro-level control strategies trained under different equipment and different working conditions, build a parameter gene library, and obtain a control strategy suitable for a new equipment based on the parameter gene library;

[0046] The biological stress response module 104 is used to trigger a first preset control strategy when abnormal behavior is detected based on the real-time data of the sensor of the 3D simulation model of the magnetic grid system.

[0047] In one embodiment of the present invention, the vibration of multi-source sensor data is represented by vibration acceleration, and a MEMS sensor is used to obtain vibration acceleration; a thermocouple sensor is used to collect temperature; a Hall sensor is used to collect magnetic field strength; and a piezoresistive strain gauge is used to collect stress.

[0048] In one embodiment of the present invention, a 3D simulation model of a magnetic grid system is constructed by physical modeling, and multi-source sensor data is synchronized in real time. The specific steps include:

[0049] S201, using CAD software to establish a 3D geometric structure of the magnetic grid system and perform finite element meshing. Specifically, using AutoCAD software to create a 3D model of components such as a magnetic grid scale, a guide rail, and an actuator in the magnetic grid system, and using HyperMesh to perform finite element meshing;

[0050] S202, by simulating the electromagnetic mechanical and thermal coupling behaviors of the magnetic grid system, the electromagnetic field simulation, mechanical vibration simulation and thermal deformation simulation of the magnetic grid system are respectively performed. Specifically, ANSYS Maxwell is used to perform electromagnetic field finite element analysis, and boundary conditions are set: the magnetic induction intensity is defined, the magnetization direction, magnetic permeability, remanence and coercive force of the magnetic grid are set, and the magnetic field distribution and hysteresis error are calculated; ANSYS Mechanical is used to perform vibration modal analysis and transient analysis, and boundary conditions are set: the fixed boundary of the magnetic grid guide is constrained, a mechanical vibration source is applied, and the vibration frequency and stress distribution are calculated; ANSYS Fluent is used to perform thermal deformation simulation, and thermal boundary conditions are set: ambient temperature changes are applied, the thermal conductivity and specific heat capacity of the material are set, and the temperature distribution and measurement errors caused by thermal expansion are calculated;

[0051] S203, acquiring multi-source sensor data of real-time operation in a real environment, and inputting the multi-source sensor data into a 3D simulation model to achieve simulation-physical synchronization. Specifically, the multi-source sensor data is processed using a Kalman filter to reduce the impact of noise, and is input into the 3D simulation model to optimize the magnetic grating measurement accuracy.

[0052] In one embodiment of the present invention, the specific steps of the multi-objective hierarchical evolution strategy include:

[0053] S301, using a Latin hypercube sampling method to initialize a population, the population including P individuals, each individual being represented by a first control parameter vector composed of first control parameters;

[0054] The encoding format of an individual is: , where Q represents the individual represented by the first control parameter vector, , and Respectively represent the proportional gain, integral gain and differential gain of PID gain, represents the filter coefficient, Indicates wireless communication power;

[0055] S302, constructing a multi-objective optimization function;

[0056] S303, optimizing individuals using a non-dominated sorting genetic algorithm.

[0057] In one embodiment of the present invention, the specific steps of initializing the population using the Latin hypercube sampling method include:

[0058] S401, determining the range of each parameter in the first control parameter;

[0059] S402, evenly divide the range of each parameter into P intervals;

[0060] S403, randomly selecting a value in the P intervals of each parameter as the value of the individual parameter, and finally obtaining a population including P individuals.

[0061] In one embodiment of the present invention, the multi-objective optimization function includes: ; ; ; ;

[0062] Among them, F represents the comprehensive fitness of the individual, that is, the total loss value of the optimization target, a represents the index of the target, represents the weight coefficient of the ath target, represents the loss value of the a-th target, , and They represent the first fitness, the second fitness and the third fitness, namely the tracking error loss value, the energy consumption loss value and the noise suppression loss value, t represents the index of the time step, T represents the number of time steps, It represents the preset target value expected by the magnetic grid system at the tth time step, such as the expected position, expected speed, and expected state value. represents the actual measurement result of the magnetic grid system at the tth time step, represents the wireless communication power of the magnetic grid system at the tth time step, represents the filtered sensor measurement value at the tth time step, represents the unfiltered sensor measurement at time step t.

[0063] In one embodiment of the present invention, the specific steps of step S303 include:

[0064] S501, calculating the first fitness, the second fitness, the third fitness and the comprehensive fitness of the individual according to the multi-objective optimization function, wherein the weight coefficient in the multi-objective optimization function adopts an adaptive adjustment method, and the calculation formula of the weight coefficient is: , represents the weight coefficient of the ath target at the b+1th iteration, represents the weight coefficient of the ath target at the bth iteration, represents the learning rate that controls the speed of weight adjustment, Represents the gradient change of the loss value of the a-th target to the individual, represents an individual represented by a first control parameter vector;

[0065] S502, dividing the population into three groups according to the comprehensive fitness of individuals: high fitness individuals, medium fitness individuals and low fitness individuals;

[0066] S503, retaining high fitness individuals, performing crossover and mutation operations on medium fitness individuals, and performing high probability mutation operations on low fitness individuals;

[0067] S504, according to the first fitness, the second fitness and the third fitness of the individuals, non-dominated sorting is used to screen and select three Pareto optimal individuals, wherein the individual with the highest first fitness, second fitness and third fitness is taken as the Pareto optimal individual;

[0068] S505, when the number of iterations reaches the preset maximum number of iterations, output the current three Pareto optimal individuals, and select the individual that best suits the current application scenario according to actual needs, otherwise return to S502, where the actual needs include but are not limited to: reducing the tracking error loss value, reducing the energy consumption loss value, or reducing the noise suppression loss value.

[0069] In one embodiment of the present invention, the crossover operation uses a simulated binary crossover method to generate new individuals. The calculation formula of the simulated binary crossover method is: ;

[0070] Where n represents the element index of the first control parameter vector of the individual, Represents the nth element value of the first control parameter vector of the newly generated offspring individual, Represents a random number between 0 and 1. represents the cross-distribution index that controls the search range, The larger the value, the closer the offspring is to the parent. The smaller it is, the more dispersed the offspring are. and represents the nth element value of the first control parameter vector of the two parent individuals, c represents the current number of iterations, and C represents the maximum number of iterations. It represents a Gaussian random variable with a mean of 0 and a standard deviation of 1.

[0071] The mutation operation uses the polynomial mutation method to update individuals. The calculation formula of polynomial mutation is: ;

[0072] in, Represents the nth element value of the first control parameter vector after the offspring individual mutation, represents the nth element value of the first control parameter vector of the offspring individual, represents the variation distribution index, The larger the value, the smaller the change in individual updates. The smaller it is, the greater the change in individual updates.

[0073] The high probability mutation operation is based on the mutation operation and dynamically adjusts the mutation probability. The calculation formula for the high probability mutation operation is: , represents the mutation probability of high-probability mutation operations, represents the mutation probability of the mutation operation, Indicates the coefficient of variation increment, ranging from 0 to 1. represents the comprehensive fitness of an individual, It represents the maximum comprehensive fitness of individuals in the population.

[0074] In one embodiment of the present invention, at the microscopic level, the magnetic grid system needs to fine-tune the second control parameter in real time to compensate for the control deviation caused by temperature change, hysteresis effect or other disturbances. To this end, the present invention uses a lightweight reinforcement learning model to run on an embedded controller to achieve adaptive adjustment of the second control parameter, so that it can quickly respond to environmental changes and optimize system performance; the microscopic control strategy optimizes the second control parameter by constructing a reinforcement learning model, and the specific steps include:

[0075] S601, constructing a state vector including a second control parameter according to the operating state of the magnetic grid system, the state vector including factual information related to the adjustment of the second control parameter, and the expression of the state vector is: ,in, represents the state vector at the tth time step, Indicates temperature, It represents the error between the preset target value expected by the magnetic grid system at the tth time step and the actual measurement result. represents the vibration acceleration at the tth time step, represents the magnetic field intensity at the tth time step;

[0076] S602, using the TinyML model to build a policy network, the policy network takes the state vector as input and outputs the adjustment amount of the second control parameter, and the calculation formula of the adjustment amount is: , represents the adjustment amount of the second control parameter, represents the policy network, Represents network parameters;

[0077] S603, constructing an action space, where the action space represents the geometric range of the adjustment amount of the second control parameter, and the action represents the adjustment amount of the second control parameter. The second control parameter is updated by the adjustment amount, and the updating formula is: , represents the updated adjustment amount, Indicates the current value of the second control parameter;

[0078] S604, constructing a reward function for the reinforcement learning model, the reward function is: ,in, represents the value of the reward function at the tth time step, and denote the first weight coefficient and the second weight coefficient, respectively, and are used to balance the relationship between reducing the error and avoiding drastic adjustment;

[0079] S605, using the policy gradient method to update the policy network, the calculation formula of the policy gradient method is: , Indicates the network parameters The gradient calculation of , that is, adjusting the direction of the policy network so that it outputs a better adjustment amount, represents the performance index of the policy network, Indicates in status The adjustment amount is The probability distribution when Express The expected value of is the statistical estimation under different state and action combinations; through the policy gradient method, the policy network continuously optimizes its own parameters so that it can output a better adjustment amount, and finally realize the adaptive optimization of the magnetic grid system.

[0080] The macro-level control strategy is used for long-term, global optimization. It uses a multi-objective hierarchical evolutionary strategy to optimize the first control parameter and adjust the overall operating status of the equipment to achieve optimal performance under different working modes. The strategy adjustment time scale is long and will not be modified frequently. The micro-level control strategy is mainly responsible for real-time and adaptive adjustment of the second control parameter.

[0081] In one embodiment of the present invention, the macro-level control strategy and the micro-level control strategy are converted into a macro-feature vector and a micro-feature vector respectively, and then concatenated to obtain a control strategy vector; for example, the control strategy vector can be obtained by It indicates that, represents the temperature compensation parameter, represents the hysteresis compensation parameter, represents the adaptive learning rate; for control strategy vectors of different devices and different working conditions, the standard deviation of each parameter in the control strategy vector is calculated in turn. When the standard deviation is less than the first preset threshold value, it is determined that the parameter varies little between different devices and working conditions, and it is regarded as a common feature. The extracted common features are combined to obtain a parameter gene library, which provides a general control strategy framework for new devices; for example, the parameter gene library contains: the proportional gain is set to 1.5, and the differential gain is set to 0.8. When it is necessary to generate a control strategy for a new device, the control strategy framework is first extracted from the parameter gene library, and then fine-tuned according to the specific requirements of the new device. For example, if the temperature of the new device is high, the filter coefficient is adjusted to optimize the system performance.

[0082] In one embodiment of the present invention, the biological stress response module performs real-time analysis of multi-source sensor data based on a 3D simulation model of the magnetic grating system. When the multi-source sensor data exceeds a preset safety threshold, the magnetic grating system is determined to be operating abnormally and a first preset control strategy is triggered, wherein the safety threshold is pre-set based on historical operating data and equipment operating conditions; a preset time period is set, and the number of triggering of the same abnormality within the time period is counted. If the same abnormality occurs multiple times within the preset time period and the magnetic grating system is still operating stably, the triggering condition of the abnormality is adjusted; for example, when the temperature of the magnetic grating system exceeds a preset temperature threshold, the temperature compensation parameters of the magnetic grating system are adjusted, and the wireless communication power is reduced to reduce system heating; when the temperature of the magnetic grating system exceeds the preset temperature threshold and is triggered more than 5 times within 10 minutes, and the system is still operating stably, the preset temperature threshold is increased to the highest temperature among the triggering abnormalities.

[0083] The above describes an embodiment of the present embodiment, but the present embodiment is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present embodiment, ordinary technicians in this field can also make many forms, all of which are within the protection of the present embodiment.

Claims

1. A magnetic grid fixed length adjustment system based on wireless transmission control, characterized in that: include: A digital twin simulation module is used to construct a 3D simulation model of the magnetic grid system through physical modeling and synchronize multi-source sensor data, wherein the multi-source sensor data includes temperature, vibration, magnetic field strength and stress, and the 3D simulation model includes electromagnetic field simulation, mechanical vibration simulation and thermal deformation simulation; A hierarchical reinforcement learning control module is used to execute a macro-layer control strategy and a micro-layer control strategy at the macro-layer and the micro-layer, respectively, wherein the macro-layer control strategy uses a multi-objective hierarchical evolutionary strategy to optimize a first control parameter; the micro-layer control strategy optimizes a second control parameter by constructing a reinforcement learning model; the first control parameter includes: a PID gain parameter, a filter coefficient, and a wireless communication power; the second control parameter includes: a temperature compensation parameter, a hysteresis compensation parameter, and an adaptive learning rate; The cross-domain migration evolution module is used to extract common features from macro-level control strategies and micro-level control strategies trained under different equipment and different working conditions, build a parameter gene library, and obtain control strategies suitable for new equipment based on the parameter gene library; The biological stress response module is used to perform real-time analysis of multi-source sensor data based on the 3D simulation model of the magnetic grid system, and trigger the first preset control strategy when abnormal behavior is detected.

2. According to the magnetic grid fixed length adjustment system based on wireless transmission control according to claim 1, it is characterized in that: The 3D simulation model of the magnetic grid system is constructed through physical modeling, and multi-source sensor data is synchronized in real time. The specific steps include: S201, use CAD software to establish the 3D geometric structure of the magnetic grid system and perform finite element meshing; S202, by simulating the electromagnetic mechanical and thermal coupling behaviors of the magnetic grid system, performing electromagnetic field simulation, mechanical vibration simulation and thermal deformation simulation on the magnetic grid system respectively; S203, acquiring multi-source sensor data of real-time operation in a real environment, and inputting the multi-source sensor data into a 3D simulation model to achieve simulation-physical synchronization.

3. According to the magnetic grid fixed length adjustment system based on wireless transmission control according to claim 1, it is characterized in that: The specific steps of the multi-objective hierarchical evolution strategy include: S301, using a Latin hypercube sampling method to initialize a population, the population including P individuals, each individual being represented by a first control parameter vector composed of first control parameters; S302, constructing a multi-objective optimization function; S303, optimizing individuals using a non-dominated sorting genetic algorithm.

4. According to the magnetic grid fixed length adjustment system based on wireless transmission control according to claim 3, it is characterized in that: The multi-objective optimization functions include: ； ； ； ； Among them, F represents the comprehensive fitness of the individual, that is, the total loss value of the optimization target, a represents the index of the target, represents the weight coefficient of the ath target, represents the loss value of the a-th target, , and They represent the first fitness, the second fitness and the third fitness, namely the tracking error loss value, the energy consumption loss value and the noise suppression loss value, t represents the index of the time step, T represents the number of time steps, represents the preset target value expected by the magnetic grid system at the tth time step, represents the actual measurement result of the magnetic grid system at the tth time step, represents the wireless communication power of the magnetic grid system at the tth time step, represents the filtered sensor measurement value at the tth time step, represents the unfiltered sensor measurement at time step t.

5. According to the magnetic grid fixed length adjustment system based on wireless transmission control as claimed in claim 3, it is characterized in that: The specific steps of step S303 include: S501, calculating the first fitness, the second fitness, the third fitness and the comprehensive fitness of the individual according to the multi-objective optimization function; S502, dividing the population into three groups according to the comprehensive fitness of individuals: high fitness individuals, medium fitness individuals and low fitness individuals; S503, retaining high fitness individuals, performing crossover and mutation operations on medium fitness individuals, and performing high probability mutation operations on low fitness individuals; S504, selecting three Pareto optimal individuals by using non-dominated sorting according to the first fitness, the second fitness and the third fitness of the individuals, wherein the individual with the highest first fitness, the highest second fitness and the highest third fitness is selected as the Pareto optimal individual; S505, when the number of iterations reaches the preset maximum number of iterations, output the current three Pareto optimal individuals, and select the individual that best meets the current application scenario according to actual needs, otherwise return to S502.

6. A magnetic grid fixed length adjustment system based on wireless transmission control according to claim 5, characterized in that: The crossover operation uses the simulated binary crossover method to generate new individuals. The calculation formula of the simulated binary crossover method is: ； Where n represents the element index of the first control parameter vector of the individual, Represents the nth element value of the first control parameter vector of the newly generated offspring individual, Represents a random number between 0 and 1. represents the cross-distribution index that controls the search range, and represents the nth element value of the first control parameter vector of the two parent individuals, c represents the current number of iterations, and C represents the maximum number of iterations. It represents a Gaussian random variable with a mean of 0 and a standard deviation of 1. The mutation operation uses the polynomial mutation method to update individuals. The calculation formula of polynomial mutation is: ； in, Represents the nth element value of the first control parameter vector after the offspring individual mutation, represents the nth element value of the first control parameter vector of the offspring individual, Represents the variation distribution index.

7. The magnetic grid fixed length adjustment system based on wireless transmission control according to claim 1 is characterized in that: The micro-level control strategy optimizes the second control parameter by building a reinforcement learning model. The specific steps include: S601, constructing a state vector including a second control parameter according to the operating state of the magnetic grid system; S602, using the TinyML model to build a policy network, the policy network takes the state vector as input and outputs the adjustment amount of the second control parameter, and the calculation formula of the adjustment amount is: , represents the adjustment amount of the second control parameter, represents the policy network, represents the state vector at the tth time step, Represents network parameters; S603, constructing an action space, where the action space represents a geometric range of an adjustment amount of the second control parameter; S604, constructing a reward function of a reinforcement learning model; S605, update the policy network using a policy gradient method.

8. The magnetic grid fixed length adjustment system based on wireless transmission control according to claim 1 is characterized in that: The macro-level control strategy and the micro-level control strategy are respectively converted into a macro-feature vector and a micro-feature vector, and are concatenated to obtain a control strategy vector; for the control strategy vectors of different devices and different working conditions, the standard deviation of each parameter in the control strategy vector is calculated in turn. When the standard deviation is less than a first preset threshold, it is determined that the parameter varies little between different devices and working conditions, and is regarded as a common feature. The extracted common features are combined to obtain a parameter gene library, which provides a general control strategy framework for new devices.

9. The magnetic grid fixed length adjustment system based on wireless transmission control according to claim 1 is characterized in that: The biological stress response module performs real-time analysis on multi-source sensor data based on the 3D simulation model of the magnetic grid system. When the multi-source sensor data exceeds a preset safety threshold, the magnetic grid system is judged to be operating abnormally and the first preset control strategy is triggered. Set a preset time period and count the number of times the same abnormality is triggered within the time period. If the same abnormality occurs multiple times within the preset time period and the magnetic grid system is still running stably, adjust the triggering condition of the abnormality.

Images