Servo motor control method and system for high-voltage circuit breaker based on adaptive compensation

Abstract

The invention discloses a servo motor control method and system for a high-voltage circuit breaker based on adaptive compensation, and relates to the technical field of high-voltage switch equipment, and the method comprises the steps: estimating the current of a next control period through a current prediction model, and compensating the beat generated by the work of a controller; the influence caused by the parameter uncertainty of the servo motor is compensated through an adaptive neural network; and constructing a cost function, updating a weight matrix of the neural network, and inhibiting the motor parameter mismatch influence caused by the parameter uncertainty relationship and the influence caused by the beat work of the controller. According to the adaptive compensation-based servo motor control method for the high-voltage circuit breaker provided by the invention, the error between the reference signal and the predicted current is minimized by introducing the cost function, so that the control system can be adjusted in real time, and the uncertainty processing capability of the control system is further enhanced. By continuously adjusting the weight of the network and limiting the abnormal value, the system can keep high-level stability, and instability of the controller caused by excessive compensation is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of high-voltage switchgear, and in particular to a servo motor control method and system for a high-voltage circuit breaker based on adaptive compensation. Background Art

[0002] Servo motors can be used to drive the contact movement of high-voltage circuit breakers due to their advantages of high efficiency, high power factor and high torque density. However, using servo motors as actuators to open / close the contacts of high-voltage circuit breakers is a challenging task. This is because the control performance of servo motors is affected by parameter uncertainty caused by the operation of high-voltage circuit breakers in different states. In order to improve the control performance of servo motors with uncertainty and interference, many control strategies have been developed, such as sliding mode control, model predictive control and model reference adaptive systems, but attention should still be paid to the dynamic tracking and poor robustness of the beat current control due to parameter mismatch. This application proposes an adaptive model predictive control method. First, a current prediction model is designed to estimate the current of the next control cycle to realize the beat-free current predictive control of the permanent magnet synchronous motor; then, an adaptive law with high-voltage circuit breaker operating condition constraints is used to compensate for the influence of parameter uncertainty to minimize the error between the reference signal and the predicted current. The results show that this method can suppress the influence of motor parameter mismatch caused by parameter uncertainty and improve dynamic tracking and robustness. Summary of the invention

[0003] In view of the above-mentioned problems, the present invention is proposed.

[0004] Therefore, the technical problem solved by the present invention is that the existing servo motor control method for high-voltage circuit breakers has poor dynamic tracking capability and poor robustness, and the problem of how to reduce the influence of parameter uncertainty caused by operation under different states.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: A servo motor control method for a high-voltage circuit breaker based on adaptive compensation, comprising estimating the current of the next control cycle using a current prediction model to compensate for the beats generated by the operation of the controller. The influence caused by the uncertainty of the servo motor parameters is compensated by an adaptive neural network. A cost function is constructed, and the weight matrix of the neural network is updated to suppress the influence of motor parameter mismatch caused by the uncertainty relationship of the parameters and the influence caused by the beat operation of the controller.

[0006] As a preferred solution of the servo motor control method for high-voltage circuit breaker based on adaptive compensation described in the present invention, the current prediction model includes establishing a servo motor voltage equation, and performing discretization processing to obtain a differential equation. The servo motor voltage equation is expressed as:

[0007]

[0008] Among them, i d and i q Represent the d-axis and q-axis currents, pi d and pi q Respectively represent i d and i q The differential of d and u q Represent the d-axis and q-axis voltages, L d and L q They represent the equivalent inductance of the d-axis and q-axis, R represents the resistance, and ε d and ε q represents the uncertain value other than resistance and inductance, ω e represents the electromagnetic speed of the motor, ψ f Represents the permanent magnet flux of the servo motor.

[0009] x(k+1)=Ax(k)+Bu(k)+f(k)

[0010] Where x(k)=[i d (k)i q (k)] T represents the state vector at the kth moment, which contains the d-axis current i d (k) and q-axis current i q (k), u(k)=[u d (k)u q (k)] T represents the input vector at the kth moment, which contains the d-axis voltage u d (k) and q-axis voltage u q (k), A and B represent the state matrix and control matrix respectively, expressed as:

[0011]

[0012]

[0013] f(k)=[f d (k)f q (k)] T Contains two nonlinear functions, representing the influence of uncertainty and interference, expressed as:

[0014]

[0015] Among them, ε d (x(k)) and ε q (x(k)) represents unknown uncertainty and interference, ω e Represents the electromagnetic speed of the motor, Ts Indicates the controller processing cycle.

[0016] As a preferred solution of the servo motor control method for high-voltage circuit breaker based on adaptive compensation described in the present invention, wherein: the influence caused by the uncertainty of the servo motor parameters compensated by the adaptive neural network includes the uncertainty part of the nonlinear function being approximated by an adaptive neural network, and the model of the neural network is expressed as:

[0017]

[0018] in, is the weight matrix of the neural network, l represents the number of neural network nodes, and the matrix It includes the basis function of the neural network, which is a Gaussian function, expressed as:

[0019]

[0020] Among them, μ di and μ qi is the mean of the basis function of the ith node of the neural network, Σ di and Σ qi is the variance of the basis function of the ith node of the neural network.

[0021] As a preferred solution of the servo motor control method for high-voltage circuit breaker based on adaptive compensation described in the present invention, wherein: the current of the next control cycle and the beat generated by the operation of the compensated controller are estimated, and the actual current of the permanent magnet servo motor is measured, and i is obtained through abc-dq change. d (k) and i q (k), the current of the next control cycle is obtained by using the current prediction model with limitation, which is expressed as:

[0022]

[0023] in, The current x(k) = [i d (k)i q (k)] T and the control output of the previous cycle u(k-1)=[u d (k-1)u q (k-1)] T Get the predicted current for the next cycle.

[0024] Combined with the neural network approximation of the nonlinear function f(k), the final current prediction model is expressed as:

[0025]

[0026] As a preferred solution of the servo motor control method for a high-voltage circuit breaker based on adaptive compensation according to the present invention, wherein: the construction of the cost function and the updating of the weight matrix of the neural network include the controller obtained after the beat compensation using the predicted current:

[0027]

[0028] in, It is the current reference signal of the current controller processing cycle.

[0029] After using the neural network to approximate the nonlinear function f(k), the final controller is expressed as:

[0030]

[0031] As a preferred solution of the servo motor control method for high-voltage circuit breaker based on adaptive compensation according to the present invention, wherein: the construction of the cost function and the updating of the weight matrix of the neural network also include taking the reference signal x * (k) and predicted current The error between them is the smallest, and the cost function is constructed, which is expressed as:

[0032]

[0033] in, To use the weight matrix residual of the current controller processing cycle, is the estimated value of the neural network's weight matrix for the current cycle, is the actual value of the weight matrix of the neural network, and γ is the correction factor of the cost function.

[0034] Solve the cost function to obtain the current cycle weight matrix The update is expressed as:

[0035]

[0036] in, is the reference signal x * (k) and predicted current The error between , Γ is the diagonal matrix containing the correction factor γ.

[0037] As a preferred solution of the servo motor control method for a high-voltage circuit breaker based on adaptive compensation according to the present invention, the method of suppressing the influence of motor parameter mismatch caused by the parameter uncertainty relationship and the influence caused by the controller beat operation includes considering the high-voltage circuit breaker operating under short-circuit conditions, rated load and no-load conditions, so that the compensation amount does not affect the control of the servo motor for the high-voltage circuit breaker, and limiting the weight parameters of the neural network, which is expressed as:

[0038]

[0039]

[0040] Among them, i nl ,i rated and i sc They are the currents of the servo motor under no-load, rated load and short-circuit conditions. Δ nl and They are respectively when the permanent magnet asynchronous motor is running under no-load condition The lower and upper limits of Δ rated and The servo motor is running at rated load or short circuit. The lower and upper limits of Δ sc and The servo motor is running under short circuit or under short circuit respectively. lower and upper limits.

[0041] Another object of the present invention is to provide a servo motor control system for a high-voltage circuit breaker based on adaptive compensation, which can predict the current of the next cycle by utilizing a current prediction model, thereby reducing delays and achieving faster and more accurate adjustments during circuit breaker operation, thereby solving the problem of poor dynamic tracking capability of the current servo motor control for high-voltage circuit breakers.

[0042] As a preferred solution of the servo motor control system for high-voltage circuit breakers based on adaptive compensation described in the present invention, it includes a current prediction module, an uncertainty compensation module, and a control optimization module. The current prediction module is used to estimate the current of the next control cycle using a current prediction model to compensate for the beats generated by the operation of the controller. The uncertainty compensation module is used to compensate for the influence caused by the uncertainty of the servo motor parameters through an adaptive neural network. The control optimization module is used to construct a cost function, update the weight matrix of the neural network, and suppress the influence of motor parameter mismatch caused by the uncertainty relationship of the parameters and the influence caused by the beat operation of the controller.

[0043] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a step of a servo motor control method for a high-voltage circuit breaker based on adaptive compensation.

[0044] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a servo motor control method for a high-voltage circuit breaker based on adaptive compensation.

[0045] Beneficial effects of the present invention: The servo motor control method for high-voltage circuit breakers based on adaptive compensation provided by the present invention minimizes the error between the reference signal and the predicted current by introducing a cost function, ensuring that the control system can be adjusted in real time, thereby further enhancing its ability to handle uncertainty. By continuously adjusting the weights of the network and limiting outliers, the system can maintain a high level of stability and avoid controller instability caused by overcompensation. The present invention achieves better results in terms of stability, robustness, and dynamic tracking. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0047] Figure 1 An overall flow chart of a servo motor control method for a high-voltage circuit breaker based on adaptive compensation provided in the first embodiment of the present invention.

[0048] Figure 2 An overall control block diagram of a servo motor system of a servo motor control method for a high-voltage circuit breaker based on adaptive compensation is provided in accordance with a second embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0050] Example 1, reference Figure 1-Figure 2 , as an embodiment of the present invention, provides a servo motor control method for a high-voltage circuit breaker based on adaptive compensation, comprising:

[0051] S1: Use the current prediction model to estimate the current of the next control cycle and compensate for the beats generated by the controller operation.

[0052] Further, refer to Figure 2 The present invention adopts a current prediction model to estimate the current of the next control cycle to compensate for the beat produced by the operation of the controller, and at the same time uses an adaptive neural network to compensate for the influence of the uncertainty of the servo motor parameters on the controller performance.

[0053] The current prediction model includes establishing the servo motor voltage equation and performing discretization to obtain the differential equation. The servo motor voltage equation is expressed as:

[0054]

[0055] Among them, i d and i q Represent the d-axis and q-axis currents, pi d and pi q Respectively represent i d and i q The differential of d and u q Represent the d-axis and q-axis voltages, L d and L q They represent the equivalent inductance of the d-axis and q-axis, R represents the resistance, and ε d and ε q represents the uncertain value other than resistance and inductance, ω e represents the electromagnetic speed of the motor, ψ f Represents the permanent magnet flux of the servo motor.

[0056] x(k+1)=Ax(k)+Bu(k)+f(k)

[0057] Where x(k)=[i d (k)i q (k)] T represents the state vector at the kth moment, which contains the d-axis current i d (k) and q-axis current i q (k), u(k)=[u d (k)u q (k)] T represents the input vector at the kth moment, which contains the d-axis voltage u d (k) and q-axis voltage u q (k), A and B represent the state matrix and control matrix respectively, expressed as:

[0058]

[0059]

[0060] f(k)=[f d (k)f q (k)] T Contains two nonlinear functions, representing the influence of uncertainty and interference, expressed as:

[0061]

[0062] Among them, ε d (x(k)) and ε q (x(k)) represents unknown uncertainty and interference, ω e Represents the electromagnetic speed of the motor, T s Indicates the controller processing cycle.

[0063] It should be noted that the influence of the uncertainty of the servo motor parameters compensated by the adaptive neural network includes the uncertainty part of the nonlinear function approximated by an adaptive neural network, and the model of the neural network is expressed as:

[0064]

[0065] in, is the weight matrix of the neural network, l represents the number of neural network nodes, and the matrix It includes the basis function of the neural network, which is a Gaussian function, expressed as:

[0066]

[0067] Among them, μ di and μ qi is the mean of the basis function of the ith node of the neural network, Σ di and Σ qi is the variance of the basis function of the ith node of the neural network.

[0068] It should also be noted that estimating the current of the next control cycle and the beat generated by the compensated controller operation includes measuring the actual current of the permanent magnet servo motor and obtaining i after abc-dq changes. d (k) and i q (k), the current of the next control cycle is obtained by using the current prediction model with limitation, which is expressed as:

[0069]

[0070] in, The current x(k) = [i d (k)i q (k)] T and the control output of the previous cycle u(k-1)=[u d (k-1)u q (k-1)] T Get the predicted current for the next cycle.

[0071] Combined with the neural network approximation of the nonlinear function f(k), the final current prediction model is expressed as:

[0072]

[0073] When it is impossible to measure directly, it can be obtained by calculation and expressed as:

[0074]

[0075] Among them, T e and T L Represent electromagnetic torque and load torque respectively, J m Represents the moment of inertia. m represents the damping coefficient. p n Indicates the number of pole pairs of the servo motor.

[0076] S2: Compensate for the effects of servo motor parameter uncertainty through an adaptive neural network.

[0077] Furthermore, the cost function is constructed and the weight matrix of the neural network is updated, including the controller obtained after using the predicted current for beat compensation:

[0078]

[0079] in, It is the current reference signal of the current controller processing cycle.

[0080] After using the neural network to approximate the nonlinear function f(k), the final controller is expressed as:

[0081]

[0082] S3: Construct a cost function and update the weight matrix of the neural network to suppress the influence of motor parameter mismatch caused by parameter uncertainty and the influence caused by controller beat operation.

[0083] Furthermore, constructing the cost function and updating the weight matrix of the neural network also includes taking the reference signal x * (k) and predicted current The error between them is the smallest, and the cost function is constructed, which is expressed as:

[0084]

[0085] in, To use the weight matrix residual of the current controller processing cycle, is the estimated value of the neural network's weight matrix for the current cycle, is the actual value of the weight matrix of the neural network, and γ is the correction factor of the cost function.

[0086] Solve the cost function to obtain the current cycle weight matrix The update is expressed as:

[0087]

[0088] in, is the reference signal x * (k) and predicted current The error between , Γ is the diagonal matrix containing the correction factor γ.

[0089] It should be noted that suppressing the influence of motor parameter mismatch caused by parameter uncertainty relationship and the influence caused by controller beat operation includes considering the high-voltage circuit breaker operating under short-circuit conditions, rated load and no-load conditions, so that the compensation amount does not affect the control of the servo motor for the high-voltage circuit breaker, and limiting the weight parameters of the neural network, which is expressed as:

[0090]

[0091]

[0092] Among them, i nl ,i rated and i sc They are the currents of the servo motor under no-load, rated load and short-circuit conditions. Δ nl and They are respectively when the permanent magnet asynchronous motor is running under no-load condition The lower and upper limits of Δ rated and The servo motor is running at rated load or short circuit. The lower and upper limits of Δ sc and The servo motor is running under short circuit or under short circuit respectively. lower and upper limits.

[0093] When k = 1, the current i d (1) and i q (1) The corresponding control input is u d (0) and u q (0), at the time of implementation of this application d (0) and i q (0) is the initial value of the control input. In the initial operation of the neural network For f(k)=[f d (k)f q (k)] T The compensation effect is difficult to predict, and the use of the neural network weight limitation formula ensures the stability of the control system.

[0094] The output of the controller u d (k) and uq (k) needs to be stored to assist the current prediction model in making current predictions for the next cycle.

[0095] Embodiment 2, an embodiment of the present invention, provides a servo motor control method for a high-voltage circuit breaker based on adaptive compensation. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0096] First, the high-voltage circuit breaker simulation device used in the experiment is driven by a permanent magnet synchronous servo motor. The rated power of the motor is 3kW, the rated speed is 1500rpm, and the controller sampling period is set to 0.001 seconds. To simulate the actual working conditions, we conducted experiments under three different load conditions (no load, rated load, short circuit), and recorded parameters such as current, torque, and speed. For the existing technology, the traditional method is used for comparison. The experiment is divided into three groups of tests, which are carried out under no load, rated load and short circuit conditions respectively.

[0097] Table 1 Experimental data comparison table

[0098]

[0099]

[0100] The experimental data of our invention and the traditional model reference adaptive control method clearly demonstrate the performance advantages of the invention in motor control:

[0101] Under all load conditions, the d-axis and q-axis current control of the control method of the present invention showed higher accuracy. Under short-circuit conditions, the d-axis current of the conventional method is 7.8A, while the method of the present invention reduces this value to 7.4A. This shows that the adaptive compensation mechanism of the present invention can effectively cope with changes in motor parameters and reduce current fluctuations. In addition, the current prediction error is significantly reduced. The prediction error of the conventional method is as high as 22%, while the method of the present invention controls the error within 9%, significantly improving the accuracy of current prediction.

[0102] The electromagnetic torque generated by the method of the present invention is more stable, especially under rated load and short-circuit conditions. Under rated load, the electromagnetic torque generated by the method of the present invention is 2.0N·m, which is more accurate than the 1.9N·m of the traditional method. This means that the method of the present invention has better dynamic response capabilities when handling high loads, and can quickly adapt to changes in load and avoid large torque fluctuations.

[0103] The traditional method shows obvious parameter mismatch problems when facing load changes, especially under short-circuit conditions, the current prediction error of the traditional method is as high as 22%. In contrast, the present invention successfully reduces the error to 9% by adjusting the system parameters in real time through an adaptive neural network. This shows that the method of the present invention can effectively cope with load mutations and parameter uncertainties, and improve the robustness of the system.

[0104] The experimental results show that the method of the present invention exhibits good control performance under different load conditions. Even under the extreme condition of short circuit, the motor speed is maintained at 1100rpm, the same as the traditional method, but the current control accuracy and dynamic response capability of the method of the present invention are significantly better than the traditional control method, showing higher system robustness.

[0105] In summary, through the comparison of experimental data, it can be seen that the adaptive model predictive control method of the present invention has significant advantages in dealing with parameter uncertainty and load changes of servo motors. Compared with the traditional method control method, the method of the present invention can control the current more accurately, significantly reduce the current prediction error, and maintain high dynamic tracking performance and system robustness under different load conditions. This makes the present invention show better stability and reliability in the control of high-voltage circuit breaker servo motors, especially suitable for complex working conditions and variable load conditions.

[0106] Embodiment 3, an embodiment of the present invention, provides a servo motor control system for a high-voltage circuit breaker based on adaptive compensation, including a current prediction module, an uncertainty compensation module, and a control optimization module.

[0107] The current prediction module is used to estimate the current of the next control cycle using the current prediction model and compensate for the beats generated by the operation of the controller.

[0108] The uncertainty compensation module is used to compensate for the impact of servo motor parameter uncertainty through an adaptive neural network.

[0109] The control optimization module is used to construct the cost function, update the weight matrix of the neural network, and suppress the influence of motor parameter mismatch caused by parameter uncertainty relationship and the influence caused by controller beat operation.

[0110] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0111] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0112] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0113] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0114] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A servo motor control method for a high-voltage circuit breaker based on adaptive compensation, characterized in that: include: The current prediction model is used to estimate the current of the next control cycle and compensate for the beats generated by the controller operation; Compensate for the effects of servo motor parameter uncertainty through adaptive neural networks; Construct a cost function and update the weight matrix of the neural network to suppress the influence of motor parameter mismatch caused by parameter uncertainty relationship and the influence caused by controller beat operation.

2. The servo motor control method for a high-voltage circuit breaker based on adaptive compensation according to claim 1, characterized in that: The current prediction model includes establishing a servo motor voltage equation and performing discretization processing to obtain a differential equation. The servo motor voltage equation is expressed as: Among them, i d and i q Represent the d-axis and q-axis currents, pi d and pi q Respectively represent i d and i q The differential of d and u q Represent the d-axis and q-axis voltages, L d and L q They represent the equivalent inductance of the d-axis and q-axis, R represents the resistance, and ε d and ε q represents the uncertain value other than resistance and inductance, ω e represents the electromagnetic speed of the motor, ψ f Represents the permanent magnet flux of the servo motor; x(k+1)=Ax(k)+Bu(k)+f(k) Where x(k)=[i d (k)i q (k)] T represents the state vector at the kth moment, which contains the d-axis current i d (k) and q-axis current i q (k), u(k)=[u d (k)u q (k)] T represents the input vector at the kth moment, which contains the d-axis voltage u d (k) and q-axis voltage u q (k), A and B represent the state matrix and control matrix respectively, expressed as: f(k)=[f d (k)f q (k)] T Contains two nonlinear functions, representing the influence of uncertainty and interference, expressed as: Among them, ε d (x(k)) and ε q (x(k)) represents unknown uncertainty and interference, ω e Represents the electromagnetic speed of the motor, T s Indicates the controller processing cycle.

3. The servo motor control method for a high-voltage circuit breaker based on adaptive compensation according to claim 2, characterized in that: The effect caused by the uncertainty of the servo motor parameters compensated by the adaptive neural network includes the uncertainty part of the nonlinear function being approximated by an adaptive neural network, and the model of the neural network is expressed as: in, is the weight matrix of the neural network, l represents the number of neural network nodes, and the matrix It includes the basis function of the neural network, which is a Gaussian function, expressed as: Among them, μ di and μ qi is the mean of the basis function of the ith node of the neural network, Σ di and Σ qi is the variance of the basis function of the ith node of the neural network.

4. The servo motor control method for a high-voltage circuit breaker based on adaptive compensation according to claim 3, characterized in that: The current estimation of the next control cycle and the beat generated by the operation of the compensated controller include measuring the actual current of the permanent magnet servo motor and obtaining i through abc-dq changes. d (k) and i q (k), the current of the next control cycle is obtained using the current prediction model with limitation, which is expressed as: in, The current x(k) = [i d (k)i q (k)] T and the control output of the previous cycle u(k-1)=[u d (k-1)u q (k-1)] T Get the predicted current of the next cycle; Combined with the neural network approximation of the nonlinear function f(k), the final current prediction model is expressed as:

5. The servo motor control method for a high-voltage circuit breaker based on adaptive compensation according to claim 4, characterized in that: The construction of the cost function and updating of the weight matrix of the neural network include using the predicted current to perform beat compensation to obtain the controller: in, It is the current reference signal of the current controller processing cycle. After using the neural network to approximate the nonlinear function f(k), the final controller is expressed as:

6. The servo motor control method for a high voltage circuit breaker based on adaptive compensation according to claim 5, characterized in that: The construction of the cost function and updating the weight matrix of the neural network also include taking the reference signal x * (k) and predicted current The error between them is the smallest, and the cost function is constructed, which is expressed as: in, To utilize the weight matrix residual of the current controller processing cycle, is the estimated value of the neural network's weight matrix for the current cycle, is the actual value of the weight matrix of the neural network, and γ is the correction factor of the cost function; Solve the cost function to obtain the current cycle weight matrix The update is expressed as: in, is the reference signal x * (k) and predicted current The error between , Γ is the diagonal matrix containing the correction factor γ.

7. The servo motor control method for a high-voltage circuit breaker based on adaptive compensation according to claim 6, characterized in that: The method of suppressing the influence of motor parameter mismatch caused by parameter uncertainty relationship and the influence caused by controller beat operation includes considering that the high-voltage circuit breaker operates under short-circuit conditions, rated load and no-load conditions, so that the compensation amount does not affect the control of the servo motor for the high-voltage circuit breaker, and limiting the weight parameters of the neural network, which is expressed as: Among them, i nl ,i rated and i sc They are the currents of the servo motor under no-load, rated load and short-circuit conditions. Δ nl and They are respectively when the permanent magnet asynchronous motor is running under no-load condition The lower and upper limits of Δ rated and The servo motor is running at rated load or short circuit. The lower and upper limits of Δ sc and The servo motor is running under short circuit or under short circuit respectively. lower and upper limits.

8. A system using the servo motor control method for a high-voltage circuit breaker based on adaptive compensation as claimed in any one of claims 1 to 7, characterized in that: Including current prediction module, uncertainty compensation module, control optimization module; The current prediction module is used to estimate the current of the next control cycle using the current prediction model to compensate for the beat generated by the operation of the controller; The uncertainty compensation module is used to compensate for the influence caused by the uncertainty of the servo motor parameters through an adaptive neural network; The control optimization module is used to construct a cost function, update the weight matrix of the neural network, and suppress the influence of motor parameter mismatch caused by parameter uncertainty relationship and the influence caused by controller beat operation.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the servo motor control method for a high-voltage circuit breaker based on adaptive compensation as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the servo motor control method for a high-voltage circuit breaker based on adaptive compensation according to any one of claims 1 to 7 are implemented.

Images