Servo motor control method and related device

Abstract

This application discloses a servo motor control method and related equipment, relating to the field of automatic control technology. The method includes: acquiring the current motor state and tracking error corresponding to the servo motor; calculating the total disturbance value using a preset disturbance observer to obtain a disturbance estimate; calculating the equivalent control input using a preset sliding mode controller; calculating the finite-time control input based on a preset finite-time control strategy; and controlling the servo motor based on the finite-time control input and the equivalent control input. This application treats the unknown load disturbance and frictional nonlinearity in the system as a unified "lumped disturbance" and designs an adaptive observer based on a radial basis function neural network to estimate this lumped disturbance online in real time. Then, this estimate is introduced into the control law as a feedforward compensation quantity, thereby actively offsetting the influence of the disturbance on the system without relying on a specific mathematical model of the disturbance or a known upper bound, fundamentally improving the system's anti-interference capability and control accuracy.

Description

Technical Field

[0001] This application relates to the field of automatic control technology, and in particular to servo motor control methods and related equipment. Background Technology

[0002] Servo motors, as core actuators in industrial automation, precision machining, and robotics, directly determine the accuracy, response speed, and stability of the entire system's motion trajectory through their control performance. To achieve high-precision and high-dynamic-response motion control, robust control methods, such as sliding mode variable structure control, have been widely applied. This method designs sliding surfaces to ensure the system state reaches and maintains the desired dynamic characteristics within a finite time, exhibiting inherent robustness against parameter perturbations and external disturbances. To further improve performance, related technologies have evolved along two main paths: first, introducing adaptive laws to estimate the upper bound of system uncertainties online, forming adaptive sliding mode control to reduce reliance on precise prior knowledge; second, combining disturbance observer techniques, such as extended state observers, to estimate the lumped disturbances of the system and implement feedforward compensation, forming a composite control architecture based on disturbance observers, aiming to improve control smoothness while ensuring robustness. These methods collectively constitute the mainstream technical framework for addressing nonlinearity and uncertainty issues in servo systems.

[0003] However, the aforementioned technical solutions still have several inherent limitations in practical engineering applications. First, regarding disturbance resistance, the effectiveness of both traditional sliding mode control and its combination with disturbance observers often depends on accurate knowledge of the upper bound of the disturbance or the precise establishment of the disturbance model. However, in actual servo systems, frictional nonlinearity and unknown load disturbances are deeply coupled and highly time-varying, making it difficult to obtain accurate models and boundaries, thus limiting the effectiveness of compensation strategies based on models or fixed boundaries. Second, regarding dynamic performance, methods such as adaptive sliding mode control can usually only guarantee asymptotic convergence of the tracking error. The convergence time increases with the increase of initial conditions, making it difficult to meet the stringent timeliness requirements of ultrafast, high-precision machining tasks for achieving stable tracking within a finite time. Furthermore, in balancing control quality and robustness, the high-gain switching required by traditional sliding mode control to suppress disturbances can cause significant chattering, deteriorating tracking accuracy and equipment lifespan. Meanwhile, linear observers, designed for smooth control, lack sufficient ability to estimate complex nonlinear high-frequency disturbances. Finally, existing strategies generally rely on parameter tuning for specific controlled objects or operating conditions, lacking an online self-adjustment mechanism. When faced with complex and variable operating conditions such as changes in load inertia and friction state transitions, their performance and adaptability will significantly decrease. Summary of the Invention

[0004] The main purpose of this application is to provide a servo motor control method and related equipment, aiming to solve the technical problem of how to control servo motors quickly and accurately.

[0005] To achieve the above objectives, this application proposes a servo motor control method, which includes: In response to the servo motor control command, the current motor state corresponding to the servo motor is obtained, and the tracking error corresponding to the servo motor is obtained; Based on the preset disturbance value calculation strategy and the current motor state, the preset disturbance observer is used to calculate the total disturbance value corresponding to the servo motor and obtain the disturbance estimate value within a finite time. The preset disturbance observer is constructed based on the RBFNN neural network. The RBFNN neural network is used to converge the observation error interval corresponding to the servo motor to reduce the time for obtaining the observation error. The observation error is used to calculate the total disturbance value. Based on the preset equivalent control strategy and the tracking error, the equivalent control input corresponding to the servo motor is calculated using a preset sliding mode controller; and based on the disturbance estimate and the preset finite-time control strategy, the finite-time control input corresponding to the servo motor is calculated. The servo motor is controlled based on the finite-time control input and the equivalent control input.

[0006] In one embodiment, before the step of calculating the total disturbance value corresponding to the servo motor using a preset disturbance observer based on a preset disturbance value calculation strategy and the current motor state, and obtaining the disturbance estimate within a finite time, the method further includes: Based on the unknown load and frictional nonlinearity, a servo motor dynamic model is obtained through modeling. The unknown load and the frictional nonlinearity are combined into a lumped disturbance. Based on the total disturbance and the servo motor dynamics model, the servo motor system and the lumped disturbance are modeled to obtain the system model. Based on the system model and RBFNN neural network, a preset perturbation observer is constructed.

[0007] In one embodiment, the step of calculating the total disturbance value corresponding to the servo motor using a preset disturbance observer based on a preset disturbance value calculation strategy and the current motor state, and obtaining the disturbance estimate within a finite time, further includes: Obtain the current observation error range corresponding to the servo motor; Based on the preset disturbance value calculation strategy, the current motor state, and the current observation error range, the current observation error value corresponding to the servo motor is calculated using the preset disturbance observer; Based on the current observation error value, the total disturbance value corresponding to the servo motor is calculated, and the disturbance estimate is obtained within a finite time.

[0008] In one embodiment, after the step of calculating the current observation error value corresponding to the servo motor using a preset disturbance value calculation strategy, the current motor state, and the current observation error range, the method further includes: Based on the current observation error value, the current observation error interval is converged.

[0009] In one embodiment, the step of obtaining the tracking error corresponding to the servo motor further includes: Obtain the reference trajectory corresponding to the servo motor; Based on the reference trajectory and the motor state, the tracking error corresponding to the servo motor is determined.

[0010] In one embodiment, the step of controlling the servo motor based on the finite-time control input and the equivalent control input further includes: Based on the finite-time control input and the equivalent control input, the total control input is obtained; The total control input is limited, and based on the DSP's PWM module and the limited total control input, a signal with the corresponding duty cycle is output to the driver to drive the servo motor.

[0011] Furthermore, to achieve the above objectives, this application also proposes a servo motor control device, which includes: The acquisition module is used to acquire the current motor state corresponding to the servo motor and the tracking error corresponding to the servo motor in response to the servo motor control command. The first calculation module is used to calculate the total disturbance value corresponding to the servo motor based on the preset disturbance value calculation strategy and the current motor state, using a preset disturbance observer, and obtain the disturbance estimate value within a finite time. The preset disturbance observer is constructed based on the RBFNN neural network, which is used to converge the observation error interval corresponding to the servo motor to reduce the time for obtaining the observation error. The observation error is used to calculate the total disturbance value. The second calculation module is used to calculate the equivalent control input corresponding to the servo motor using a preset sliding mode controller based on a preset equivalent control strategy and the tracking error; and to calculate the finite time control input corresponding to the servo motor based on the disturbance estimate and the preset finite time control strategy. A control module is provided for controlling the servo motor based on the finite-time control input and the equivalent control input.

[0012] In addition, to achieve the above objectives, this application also proposes a servo motor control device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the servo motor control method as described above.

[0013] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the servo motor control method described above.

[0014] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the servo motor control method described above.

[0015] One or more technical solutions proposed in this application have at least the following technical effects: This application discloses a servo motor control method and related equipment, relating to the field of automatic control technology. In terms of disturbance rejection capability, the effectiveness of both traditional sliding mode control and its combination with a disturbance observer often depends on accurate knowledge of the upper bound of the disturbance or precise establishment of the disturbance model. However, in actual servo systems, frictional nonlinearity and unknown load disturbances are deeply coupled and highly time-varying, making it difficult to obtain accurate models and boundaries. This limits the effectiveness of compensation strategies based on models or fixed boundaries. Secondly, regarding dynamic performance, methods such as adaptive sliding mode control can usually only guarantee asymptotic convergence of the tracking error. The convergence time increases with the increase of initial conditions, making it difficult to meet the stringent timeliness requirements of ultra-fast, high-precision machining tasks for achieving stable tracking within a finite time. Furthermore, in balancing control quality and robustness, the high-gain switching required by traditional sliding mode control to suppress disturbances can cause significant chattering, deteriorating tracking accuracy and equipment lifespan. Linear observers, designed for smooth control, lack sufficient estimation capability for complex nonlinear high-frequency disturbances. Finally, existing strategies generally rely on parameter tuning for specific controlled objects or operating conditions, lacking the ability to... Compared to traditional self-adjusting mechanisms, whose performance and adaptability significantly decrease when facing complex and variable operating conditions such as load inertia changes and friction state transitions, this application first obtains the current motor state and tracking error of the servo motor in response to the servo motor control command. Then, based on a preset disturbance value calculation strategy and the current motor state, a preset disturbance observer is used to calculate the total disturbance value of the servo motor and obtain a disturbance estimate within a finite time. The preset disturbance observer is constructed based on an RBFNN neural network, which is used to converge the observation error interval of the servo motor to reduce the time for obtaining the observation error. The observation error is used to calculate the total disturbance value. Further, based on a preset equivalent control strategy and the tracking error, a preset sliding mode controller is used to calculate the equivalent control input of the servo motor. Based on the disturbance estimate and the preset finite time control strategy, a finite time control input of the servo motor is calculated. Finally, the servo motor is controlled based on the finite time control input and the equivalent control input.

[0016] Understandably, this application treats the unknown load disturbance and frictional nonlinearity in the system as a unified "lumped disturbance" and designs an adaptive observer based on a radial basis function neural network to estimate this lumped disturbance online in real time. Then, this estimate is introduced into the control law as a feedforward compensation quantity, thereby actively counteracting the impact of the disturbance on the system without relying on the specific mathematical model of the disturbance or a known upper bound, fundamentally improving the system's anti-interference capability and control accuracy. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating an embodiment of the servo motor control method of this application. Figure 2 This is a flowchart illustrating Embodiment 2 of the servo motor control method of this application; Figure 3 This is a flowchart illustrating Embodiment 3 of the servo motor control method of this application; Figure 4 This is a schematic diagram of the module structure of the servo motor control device according to an embodiment of this application; Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the servo motor control method in the embodiments of this application.

[0020] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solution in this application embodiment is: In this embodiment, for ease of description, the servo motor control device will be used as the execution subject in the following description.

[0024] Due to the limitations of related technologies: In terms of disturbance rejection capability, the effectiveness of both traditional sliding mode control and its combination with disturbance observers often depends on accurate knowledge of the upper bound of the disturbance or precise establishment of the disturbance model. However, in actual servo systems, frictional nonlinearity and unknown load disturbances are deeply coupled and highly time-varying, making it difficult to obtain accurate models and boundaries. This limits the effectiveness of compensation strategies based on models or fixed boundaries. Secondly, in terms of dynamic performance, methods such as adaptive sliding mode control can usually only guarantee asymptotic convergence of the tracking error. The convergence time increases with the increase of initial conditions, making it difficult to meet the requirements of ultrafast and high-precision operation. The high-precision machining task has stringent timeliness requirements for achieving stable tracking within a limited time. Furthermore, in balancing control quality and robustness, the high-gain switching required by traditional sliding mode control to suppress disturbances can cause significant chattering, deteriorating tracking accuracy and equipment lifespan. On the other hand, linear observers, which aim to smooth control, are insufficient in estimating complex nonlinear high-frequency disturbances. Finally, existing strategies generally rely on parameter tuning for specific controlled objects or operating conditions, lacking online self-adjustment mechanisms. When facing complex and variable operating conditions such as load inertia changes and friction state transitions, their performance and adaptability will significantly decrease.

[0025] This application provides a solution in which: first, in response to a servo motor control command, the current motor state corresponding to the servo motor is obtained, and the tracking error corresponding to the servo motor is also obtained; then, based on a preset disturbance value calculation strategy and the current motor state, a preset disturbance observer is used to calculate the total disturbance value corresponding to the servo motor, and a disturbance estimate is obtained within a finite time. The preset disturbance observer is constructed based on an RBFNN neural network, which is used to converge the observation error interval corresponding to the servo motor to reduce the time for obtaining the observation error. The observation error is used to calculate the total disturbance value. Further, based on a preset equivalent control strategy and the tracking error, a preset sliding mode controller is used to calculate the equivalent control input corresponding to the servo motor; and based on the disturbance estimate and the preset finite time control strategy, the finite time control input corresponding to the servo motor is calculated; finally, based on the finite time control input and the equivalent control input, the servo motor is controlled.

[0026] Understandably, this application treats the unknown load disturbance and frictional nonlinearity in the system as a unified "lumped disturbance" and designs an adaptive observer based on a radial basis function neural network to estimate this lumped disturbance online in real time. Then, this estimate is introduced into the control law as a feedforward compensation quantity, thereby actively counteracting the impact of the disturbance on the system without relying on the specific mathematical model of the disturbance or a known upper bound, fundamentally improving the system's anti-interference capability and control accuracy.

[0027] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or servo motor control device capable of performing the above functions. The following description uses a servo motor control device as an example to illustrate this embodiment and the subsequent embodiments.

[0028] Based on this, the embodiments of this application provide a servo motor control method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the servo motor control method of this application.

[0029] In this embodiment, the servo motor control method includes steps S10 to S40: Step S10: In response to the servo motor control command, obtain the current motor state corresponding to the servo motor, and obtain the tracking error corresponding to the servo motor; It should be noted that servo motor control commands refer to the target commands sent to the servo motor by the host computer or control system, which usually include information such as the desired position, speed or torque.

[0030] It should be noted that motor status refers to the real-time operating parameters of the servo motor, including physical quantities such as current position, actual speed, current, and temperature.

[0031] It should be noted that tracking error refers to the deviation between the expected value and the actual value. In this application, tracking error refers to position tracking error. and speed tracking error .in, , , Refers to the reference trajectory. and Indicating the motor state corresponding to the servo motor, in this application, the motor angular position is obtained by reading the photoelectric encoder signal through eQEP. The angular velocity is obtained through differential calculation. .

[0032] In this embodiment, the feedback signal of the servo motor is collected in real time by detection elements such as encoders and current sensors, and the tracking error value at the current moment is calculated to provide basic data for subsequent control algorithms.

[0033] Specifically, the step of obtaining the tracking error corresponding to the servo motor further includes steps S11 to S12: Step S11: Obtain the reference trajectory corresponding to the servo motor; It should be noted that the reference trajectory refers to the ideal motion curve that the servo motor is expected to follow. It is the target trajectory set by the control system and usually includes expected information such as position, speed, and acceleration changing over time. Depending on the application scenario, it can be a smooth point-to-point motion curve, a periodic motion trajectory, or a complex contour curve.

[0034] In this embodiment, reference trajectory data is obtained through host computer instruction parsing, trajectory planning algorithms, or preset motion programs. The obtained reference trajectory is typically represented as a function of time, including the desired position, desired velocity, and, if necessary, desired acceleration, forming complete motion reference information.

[0035] It is understandable that establishing an ideal target benchmark for servo motor motion provides a reference standard for subsequent error calculation. The quality of the acquired reference trajectory directly affects control accuracy; a smooth and continuous reference trajectory helps reduce mechanical shock and tracking overshoot.

[0036] Step S12: Based on the reference trajectory and the motor state, determine the tracking error corresponding to the servo motor.

[0037] It should be noted that, in this embodiment, the reference trajectory obtained in step S11 is compared and calculated dimension by dimension with the actual motor state obtained in step S10 to obtain the tracking error. and .

[0038] Understandably, the qualitative requirement of "precise tracking" is transformed into a calculable quantitative error signal, providing the controller with a clear basis for adjustment. Simultaneously, utilizing both position and velocity errors, compared to single position feedback, can more comprehensively reflect tracking quality, predict error change trends, and achieve proactive adjustment. The generated tracking error is the core variable in step S30 where the sliding mode controller calculates the equivalent control input. Accurate acquisition of error information directly determines the switching timing and equivalent control accuracy of the sliding mode control.

[0039] Step S20: Based on the preset disturbance value calculation strategy and the current motor state, the preset disturbance observer is used to calculate the total disturbance value corresponding to the servo motor and obtain the disturbance estimate value within a limited time. The preset disturbance observer is constructed based on the RBFNN neural network. The RBFNN neural network is used to converge the observation error interval corresponding to the servo motor to reduce the time for obtaining the observation error. The observation error is used to calculate the total disturbance value. It should be noted that the disturbance value refers to the uncertainty and external disturbances present in the system, including load changes, friction, parameter perturbations, and unmodeled dynamics.

[0040] It should be noted that the preset disturbance observer refers to the algorithm module used to estimate the total disturbance of the system.

[0041] It should be noted that RBFNN stands for Radial Basis Function Neural Network, which is a feedforward neural network with a single hidden layer that uses radial basis functions as activation functions.

[0042] It should be noted that the observation error range refers to the possible range of deviation between the observed disturbance value and the actual disturbance value.

[0043] In this application, the current motor state (position, speed, etc.) is input into the RBFNN neural network. The RBFNN utilizes its local approximation characteristics to quickly learn and fit the nonlinear uncertainty of the system. Based on the preset perturbation value calculation strategy, combined with the output of the RBFNN, a perturbation observer with finite-time convergence is constructed. Within a defined finite time, the perturbation estimate is output, rather than the asymptotic convergence result of the traditional observer.

[0044] It is understood that in this embodiment, the universal approximation capability of neural networks is used to handle complex factors such as nonlinear friction and load disturbances that are difficult to model in servo systems, compressing the observation error to a smaller range. Compared with traditional disturbance observers, which require an infinite amount of time to theoretically converge completely, this application can obtain accurate disturbance estimates in a limited time, greatly shortening the observation waiting time and improving the system response speed. At the same time, it can accurately estimate the disturbance in advance, providing accurate data for subsequent feedforward compensation.

[0045] Step S30: Based on the preset equivalent control strategy and the tracking error, calculate the equivalent control input corresponding to the servo motor using a preset sliding mode controller; and calculate the finite-time control input corresponding to the servo motor based on the disturbance estimate and the preset finite-time control strategy. It should be noted that the preset equivalent control strategy refers to the equivalent control part in sliding mode control, which is used to maintain the ideal motion of the system state on the sliding surface.

[0046] It should be noted that the preset sliding mode controller refers to a controller designed based on the sliding mode variable structure control theory, which has the characteristic of being insensitive to system parameter perturbations and external disturbances.

[0047] It should be noted that the equivalent control input refers to the control quantity required to make the system state slide on the sliding surface, representing the ideal control behavior of the system.

[0048] It should be noted that finite-time control strategy refers to a control design method that ensures the system state converges to the origin or sliding surface within a finite time.

[0049] It should be noted that the input is a finite-time control. It refers to the control component used to drive the system state to the sliding surface and maintain the sliding motion within a finite time.

[0050] In this embodiment, based on the tracking error, the equivalent control input required for the system to slide ideally along the sliding surface is calculated using the sliding surface function of the preset sliding mode controller. ,in, , It is a constant. This is a saturation function used to smooth control signals and suppress chattering. For inertia, variable It is a 2-norm.

[0051] in, , It is a constant; , For adaptive laws, It is a positive number.

[0052] In this embodiment, the disturbance estimate obtained in step S20 is used as a feedforward compensation term, and combined with a preset finite-time control strategy (usually including a nonlinear switching term or a terminal sliding mode term), the finite-time control input is calculated. This ensures that the system state reaches the sliding surface within a finite time and suppresses the effects of disturbances.

[0053] Understandably, equivalent control ensures ideal tracking performance, while finite-time control ensures fast convergence and strong robustness. The observed disturbance values ​​are directly used for control input calculation, realizing an active disturbance rejection mechanism of "observation-compensation" rather than passively waiting for errors to occur before adjusting. At the same time, the system state stabilizes within a defined finite time, rather than asymptotically approaching the target, significantly improving the dynamic response quality and steady-state accuracy.

[0054] Step S40: Control the servo motor based on the finite-time control input and the equivalent control input.

[0055] It should be noted that the total control input U refers to the equivalent control input. With finite time control input The amount of synthesis, of which, .

[0056] In this embodiment, the equivalent control input calculated in step S30 is combined with the finite-time control input (usually by addition) to obtain the final total control command, which is converted into a voltage or current signal by the driver and applied to the servo motor to achieve closed-loop control.

[0057] Understandably, this application integrates the robustness of sliding mode control, the intelligent approximation capability of RBFNN, and the fast convergence characteristics of finite-time control. It eliminates the influence of major interference sources through disturbance feedforward compensation, realizes high-precision position / speed tracking of servo motors, has strong anti-interference capability against nonlinear factors such as load changes, parameter variations, and friction, and the finite-time mechanism ensures that the system reaches a stable state in the shortest time. It is suitable for high-speed and high-precision servo application scenarios.

[0058] Specifically, the step of controlling the servo motor based on the finite-time control input and the equivalent control input further includes steps S41-S42: Step S41: Based on the finite-time control input and the equivalent control input, obtain the total control input; It should be noted that the equivalent control input refers to the control component calculated in step S30 based on the tracking error and the equivalent control strategy. It represents the control quantity required to make the system state slide ideally along the sliding surface, thus ensuring the ideal tracking performance of the system.

[0059] It should be noted that the total control input refers to the final control command that combines the two control components mentioned above, which is the actual control signal applied to the servo motor.

[0060] In this embodiment, the finite-time control input calculated in step S30 is linearly superimposed with the equivalent control input to obtain the total control input U. This synthesis method embodies the classic structure of sliding mode control: the equivalent control maintains the ideal motion, and the finite-time control handles the arrival phase and disturbance compensation. The synthesized total control input is in the form of a current command or a torque command, corresponding to the control requirements of the servo motor.

[0061] Understandably, equivalent control ensures steady-state tracking accuracy, while finite-time control ensures dynamic convergence speed and disturbance rejection capability. The combination of the two achieves a balance between high accuracy and strong robustness. Equivalent control possesses feedforward characteristics, while finite-time control has feedback compensation characteristics; the synthesized structure balances the system's deterministic and uncertainty handling capabilities.

[0062] Step S42: Limit the total control input, and based on the DSP's PWM module and the limited total control input, output a signal with the corresponding duty cycle to the driver to drive the servo motor.

[0063] It should be noted that amplitude limiting refers to constraining the amplitude of the control input to prevent the control quantity from exceeding the physical limits or safety thresholds of the actuator, thus protecting the motor and drive from damage caused by overcurrent or overtorque.

[0064] DSP stands for Digital Signal Processor. It has high-speed computing power and rich peripheral interfaces. It is the core computing unit of servo control system and is responsible for real-time control algorithm execution and power conversion control.

[0065] PWM module refers to pulse width modulation module, a hardware peripheral built into DSP, which controls the output voltage amplitude of power converter by adjusting the duty cycle of switching signals.

[0066] Duty cycle refers to the ratio of the switching on time to the period within a PWM cycle. It determines the average output voltage and is a key parameter connecting digital control and power drive.

[0067] A driver is a power electronic converter that converts PWM signals into the three-phase AC or DC voltage required by a servo motor to drive the motor.

[0068] In this embodiment, the total control input U obtained in step S41 is compared with the preset upper and lower limits, and saturation constraints are performed. The limiting threshold is set according to the motor rated current, driver capacity and system safety margin.

[0069] The DSP converts the limited control input into a corresponding voltage command and generates a pulse width modulation signal with the appropriate duty cycle through its built-in PWM module. The driver receives the PWM signal and controls the switching on and off of the IGBT or MOSFET power switches, chopping the DC bus voltage into the variable voltage required by the servo motor to drive the motor to generate the desired torque, thus achieving closed-loop motion control.

[0070] Understandably, the limiting circuit prevents overcurrent surges caused by abnormal control algorithms or sudden disturbances, thus extending the lifespan of the motor and driver; the DSP hardware PWM module ensures precise control cycles and stable signal output, meeting the microsecond-level real-time requirements of servo control; the PWM duty cycle serves as the interface between the digital control domain and the power electronics domain, enabling the physical implementation of the control algorithm; and the driver converts weak current control signals into strong current driving capabilities, completing the final execution of the servo motor.

[0071] This application discloses a servo motor control method and related equipment, relating to the field of automatic control technology. In terms of disturbance rejection capability, the effectiveness of both traditional sliding mode control and its combination with a disturbance observer often depends on accurate knowledge of the upper bound of the disturbance or precise establishment of the disturbance model. However, in actual servo systems, frictional nonlinearity and unknown load disturbances are deeply coupled and highly time-varying, making it difficult to obtain accurate models and boundaries. This limits the effectiveness of compensation strategies based on models or fixed boundaries. Secondly, regarding dynamic performance, methods such as adaptive sliding mode control can usually only guarantee asymptotic convergence of the tracking error. The convergence time increases with the increase of initial conditions, making it difficult to meet the stringent timeliness requirements of ultra-fast, high-precision machining tasks for achieving stable tracking within a finite time. Furthermore, in balancing control quality and robustness, the high-gain switching required by traditional sliding mode control to suppress disturbances can cause significant chattering, deteriorating tracking accuracy and equipment lifespan. Linear observers, designed for smooth control, lack sufficient estimation capability for complex nonlinear high-frequency disturbances. Finally, existing strategies generally rely on parameter tuning for specific controlled objects or operating conditions, lacking the ability to... Compared to traditional self-adjusting mechanisms, whose performance and adaptability significantly decrease when facing complex and variable operating conditions such as load inertia changes and friction state transitions, this application first obtains the current motor state and tracking error of the servo motor in response to the servo motor control command. Then, based on a preset disturbance value calculation strategy and the current motor state, a preset disturbance observer is used to calculate the total disturbance value of the servo motor and obtain a disturbance estimate within a finite time. The preset disturbance observer is constructed based on an RBFNN neural network, which is used to converge the observation error interval of the servo motor to reduce the time for obtaining the observation error. The observation error is used to calculate the total disturbance value. Further, based on a preset equivalent control strategy and the tracking error, a preset sliding mode controller is used to calculate the equivalent control input of the servo motor. Based on the disturbance estimate and the preset finite time control strategy, a finite time control input of the servo motor is calculated. Finally, the servo motor is controlled based on the finite time control input and the equivalent control input.

[0072] Understandably, this application treats the unknown load disturbance and frictional nonlinearity in the system as a unified "lumped disturbance" and designs an adaptive observer based on a radial basis function neural network to estimate this lumped disturbance online in real time. Then, this estimate is introduced into the control law as a feedforward compensation quantity, thereby actively counteracting the impact of the disturbance on the system without relying on the specific mathematical model of the disturbance or a known upper bound, fundamentally improving the system's anti-interference capability and control accuracy.

[0073] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 The step of calculating the total disturbance value corresponding to the servo motor using a preset disturbance value calculation strategy and the current motor state, and obtaining the disturbance estimate within a finite time, further includes steps A10 to A30: Step A10: Obtain the current observation error range corresponding to the servo motor; It should be noted that the observation error interval refers to the possible range of deviation between the observed disturbance value and the actual disturbance value. It is usually expressed as an interval or upper bound of error, reflecting the quantitative range of the current observation uncertainty.

[0074] In this embodiment, the possible distribution range of the disturbance observation error at the current moment is determined based on the observation results of the previous moment, historical system data, or the output characteristics of the RBFNN neural network. This range can be dynamically determined through adaptive adjustment of the neural network weights, or it can be a preset boundary value based on the system operating conditions. This provides error boundary constraints for subsequent disturbance observers, enabling the observation algorithm to perform optimized calculations within the known uncertainty range, avoiding blind estimation, and improving the reliability and stability of the observation.

[0075] Step A20: Based on the preset disturbance value calculation strategy, the current motor state, and the current observation error range, use the preset disturbance observer to calculate the current observation error value corresponding to the servo motor; It should be noted that the current observation error value refers to the instantaneous deviation between the actual disturbance and the observed disturbance, which is a core indicator for evaluating the performance of the observer.

[0076] In this embodiment, the current motor state (position, speed, current, etc.) is input into a preset disturbance observer. The disturbance observer calculates based on a preset disturbance value strategy, and uses the current observation error interval obtained in step A10 as a constraint. Utilizing the approximation capability of the RBFNN neural network, it converges quickly within a finite error interval and outputs the observation error value at the current moment. .

[0077] It should be noted that the observation error value ,in, Is the system for The observation results.

[0078] Based on this, we can conclude:

[0079] in, Is the system for The observation results and For positive integers, It is an unknown optimal weight vector. It is a weight vector.

[0080] It should be noted that the preset disturbance value calculation strategy includes: state estimation based on the motor dynamics model; online learning of nonlinear uncertainties by RBFNN; and a finite-time convergence mechanism to ensure that the error is compressed to the target interval within a certain time.

[0081] It is understood that in this embodiment, the search space of the RBFNN is limited by the observation error interval, which accelerates the convergence speed of the neural network and obtains the current observation error in a limited time, rather than asymptotic convergence, to meet the real-time control requirements. The RBFNN is dynamically adjusted according to the current motor state to adapt to changes in system parameters and external disturbances.

[0082] Specifically, after the step of calculating the current observation error value corresponding to the servo motor using a preset disturbance value calculation strategy, the current motor state, and the current observation error range, the method further includes step A21: Step A21: Based on the current observation error value, converge the current observation error interval.

[0083] It should be noted that convergence refers to making the current observation error range tend to a smaller range, rather than mathematical sequence convergence.

[0084] It should be noted that the current observation error range refers to the possible range of the perturbation observation error obtained in step A10, reflecting the upper and lower bounds of the current observation uncertainty.

[0085] In this embodiment, the original observation error range is dynamically compressed and updated based on the current observation error value calculated in step A20.

[0086] Understandably, the error range is gradually narrowed from a conservative, wide range to near the true error, thus improving the observation resolution; the error range is dynamically adjusted as the system operates to adapt to changes in disturbance characteristics under different operating conditions; it provides a more compact search space for the neural network, reduces invalid computation, and accelerates the convergence process; and it avoids excessively large intervals that could lead to excessively high observer gain or estimation oscillations, thereby improving numerical stability.

[0087] Step A30: Based on the current observation error value, calculate the total disturbance value corresponding to the servo motor and obtain the disturbance estimate value within a finite time.

[0088] It should be noted that the total disturbance value D refers to the collection of all uncertainties and disturbances in the servo motor system, including: external load disturbances and nonlinear friction.

[0089] It should be noted that the disturbance estimate refers to the total disturbance estimate calculated by the observer, which is used for subsequent control compensation.

[0090] In this embodiment, the current observation error value obtained in step A20 is used as the basis. By combining the internal state equations of the disturbance observer, the total disturbance value of the system is derived. Through the design of a finite-time convergence mechanism, it is ensured that the disturbance estimate reaches stability within a defined finite time T.

[0091] Understandably, unlike traditional asymptotic observers, this method can obtain accurate disturbance estimates within a finite time, providing timely disturbance information for the control system. The total disturbance value covers all sources of uncertainty in the system, achieving "one-stop" disturbance estimation without the need to model various disturbances separately. The output disturbance estimate can be directly used for feedforward compensation in step S30, forming an "observation-compensation" closed loop, significantly improving the system's anti-interference capability.

[0092] Based on the first and second embodiments of this application, in the third embodiment of this application, the content that is the same as or similar to that in embodiments one and two above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 Before the step of calculating the total disturbance value corresponding to the servo motor using a preset disturbance value calculation strategy and the current motor state, and obtaining the disturbance estimate within a finite time, steps B10 to B40 are further included: Step B10: Based on the unknown load and frictional nonlinearity, a model is constructed to obtain the dynamic model of the servo motor; It should be noted that unknown loads refer to unpredictable external loads encountered during the servo motor drive process, including sudden changes in load torque, changes in workpiece quality, and fluctuations in cutting resistance. The magnitude and variation patterns of these loads are difficult to know precisely in advance.

[0093] It should be noted that triboelectric nonlinearity refers to the complex friction phenomena existing in servo systems, including nonlinear characteristics such as static friction, Coulomb friction, viscous friction, and the Stribeck effect. These friction behaviors cannot be described by a simple linear model and vary with factors such as temperature, speed, and time.

[0094] It should be noted that the servo motor dynamics model refers to the mathematical equations describing the relationship between the mechanical motion and electromagnetic torque of a servo motor, which usually includes physical parameters such as moment of inertia, damping coefficient, and motor torque.

[0095] In this embodiment, a dynamic equation considering unknown load and frictional nonlinearity is established based on the physical structure and working principle of the servo motor.

[0096] In this embodiment, the servo motor dynamics model is as follows:

[0097] Where, in the formula and These are the rotational inertia of the drive motor and the rotational inertia of the load, respectively. Let n be the angular position of the load, and n be the gear ratio. Let be the viscous friction coefficient of the motor. It is an unknown load. denoted as frictional torque, and u as the control input.

[0098] Understandably, establishing a mathematical framework that includes the main sources of uncertainty lays the foundation for the unified handling of unknown factors in the future. By explicitly distinguishing between the known parameter parts and the unknown nonlinear parts, over-reliance on complex friction models and variable loads is avoided, enhancing the model's engineering applicability.

[0099] Step B20: Combine the unknown load and the frictional nonlinearity into a lumped disturbance. Based on the total disturbance and the servo motor dynamics model, perform servo motor system modeling with the lumped disturbance to obtain the system model. It should be noted that lumped disturbance refers to the unification of various types of uncertainties and disturbances in the system into an equivalent total disturbance term, with a single variable representing the combined impact of all unmodeled dynamics and external disturbances.

[0100] It should be noted that the system model refers to the state-space description of the servo motor after lumped disturbance transformation, which transforms the original complex nonlinear system into a standard form with matched disturbances.

[0101] In this embodiment, based on the servo motor dynamics model, let , , , , Then the above formula can be transformed into:

[0102] in, This includes all nonlinear terms and uncertainties of the system, which are uniformly defined as the lumped disturbance D. Therefore, the system model can be rewritten as:

[0103] Understandably, in this embodiment, the two factors that are difficult to model precisely separately, namely frictional nonlinearity and load disturbance, are unified into a single lumped disturbance term, which greatly reduces the modeling complexity. The original system is transformed into the standard form of an affine nonlinear system with matched disturbance, which facilitates the application of mature nonlinear control theory tools. As an extended state, the lumped disturbance can be directly applied to the extended state observer or the intelligent observer design method based on RBFNN, providing a standard problem framework for the construction of the disturbance observer in step B30.

[0104] Step B30: Based on the system model and the RBFNN neural network, construct a preset perturbation observer.

[0105] It should be noted that the preset disturbance observer refers to a disturbance estimation module that is designed offline before control implementation and has a defined structure and algorithm. Unlike the online adjustment of the adaptive law, its "preset" characteristic is reflected in its fixed structure and parameters determined through training.

[0106] In this embodiment, based on the system model obtained in step B20, an RBFNN-enhanced perturbation observer is designed. The specific construction process includes: Network structure design: The input to the RBFNN is determined to be the system state (position, velocity), and the output is an estimate of the lumped perturbation. The number of hidden layer neurons is determined based on the approximation accuracy requirements and computational resource constraints, while the center point and width of the radial basis function are determined through offline training or online adaptive adjustment.

[0107] Observer equation construction: Design a state observer to estimate the system state, and at the same time use RBFNN to approximate the lumped disturbance.

[0108] Embedded finite-time convergence mechanism: Introduce finite-time control theory into the observer design, and ensure that the observation error converges to zero or a sufficiently small neighborhood within a finite time by designing nonlinear switching terms or terminal sliding mode structures, rather than asymptotically converging.

[0109] Understandably, RBFNN, leveraging its universal approximation characteristic, can learn and approximate complex nonlinear friction and time-varying loads online without needing to know the specific mathematical form of the lumped disturbance, thus solving the problem of traditional observers relying on accurate models. The local response characteristics of RBFNN give the network weight adjustment a "localized" feature, and the learning of new samples does not affect the mapping relationship of the already learned region, making it suitable for real-time online applications with high computational efficiency. Compared with traditional asymptotically convergent observers, the finite-time mechanism ensures that the disturbance estimation is completed within a defined time limit, providing the control system with a predictable disturbance compensation opportunity and improving the real-time performance and reliability of the overall control. The combination of RBFNN's ability to compensate for unmodeled dynamics and the observer's ability to filter measurement noise enables the preset disturbance observer to maintain high estimation accuracy and stability under complex operating conditions.

[0110] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the servo motor control method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0111] This application also provides a servo motor control device; please refer to [reference needed]. Figure 4 The servo motor control device includes: The acquisition module 10 is used to acquire the current motor state corresponding to the servo motor and the tracking error corresponding to the servo motor in response to the servo motor control command. The first calculation module 20 is used to calculate the total disturbance value corresponding to the servo motor based on a preset disturbance value calculation strategy and the current motor state, using a preset disturbance observer to obtain a disturbance estimate within a finite time. The preset disturbance observer is constructed based on an RBFNN neural network, which is used to converge the observation error interval corresponding to the servo motor to reduce the time for obtaining the observation error. The observation error is used to calculate the total disturbance value. The second calculation module 30 is used to calculate the equivalent control input corresponding to the servo motor using a preset sliding mode controller based on a preset equivalent control strategy and the tracking error; and to calculate the finite time control input corresponding to the servo motor based on the disturbance estimate and the preset finite time control strategy. Control module 40, the control module is used to control the servo motor based on the finite time control input and the equivalent control input.

[0112] In one embodiment, the servo motor control device further includes a construction module, which further includes: The first modeling unit is used to perform modeling based on unknown load and frictional nonlinearity to obtain the dynamic model of the servo motor; The second modeling unit is used to combine the unknown load and the frictional nonlinearity into a lumped disturbance, and to perform servo motor system and lumped disturbance modeling based on the total disturbance and the servo motor dynamics model to obtain the system model; The construction unit is used to construct a preset perturbation observer based on the system model and the RBFNN neural network.

[0113] In one embodiment, the first computing module further includes: The first acquisition unit is used to acquire the current observation error range corresponding to the servo motor; The first calculation unit is used to calculate the current observation error value corresponding to the servo motor using a preset disturbance value calculation strategy, the current motor state, and the current observation error range; The second calculation unit is used to calculate the total disturbance value corresponding to the servo motor based on the current observation error value, and obtain the disturbance estimate value within a finite time.

[0114] In one embodiment, the first computing module further includes: A convergence unit is used to converge the current observation error interval based on the current observation error value.

[0115] In one embodiment, the acquisition module further includes: The second acquisition unit is used to acquire the reference trajectory corresponding to the servo motor; The determining unit is used to determine the tracking error corresponding to the servo motor based on the reference trajectory and the motor state.

[0116] In one embodiment, the control module further includes: The obtaining unit is used to obtain the total control input based on the finite-time control input and the equivalent control input; The drive unit is used to limit the total control input, and based on the DSP's PWM module and the limited total control input, output a signal with a corresponding duty cycle to the driver to drive the servo motor.

[0117] The servo motor control device provided in this application, employing the servo motor control method in the above embodiments, can solve the technical problems of servo motor control. Compared with related technologies, the beneficial effects of the servo motor control device provided in this application are the same as those of the servo motor control method provided in the above embodiments, and other technical features in the servo motor control device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0118] This application provides a servo motor control device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the servo motor control method in Embodiment 1 above.

[0119] The following is for reference. Figure 5The diagram illustrates a structural schematic of a servo motor control device suitable for implementing embodiments of this application. The servo motor control device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 5 The servo motor control device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0120] like Figure 5 As shown, the servo motor control device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the servo motor control device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. The communication device 1009 allows the servo motor control device to communicate wirelessly or wiredly with other devices to exchange data. Although the figures show servo motor control devices with various systems, it should be understood that implementing or having all of the systems shown is not required. More or fewer systems may be implemented alternatively.

[0121] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0122] The servo motor control device provided in this application, employing the servo motor control method in the above embodiments, can solve the technical problems of servo motor control. Compared with related technologies, the beneficial effects of the servo motor control device provided in this application are the same as those of the servo motor control method provided in the above embodiments, and other technical features in this servo motor control device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0123] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0124] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0125] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the servo motor control method in the above embodiments.

[0126] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0127] The aforementioned computer-readable storage medium may be included in the servo motor control device; or it may exist independently and not assembled into the servo motor control device.

[0128] The aforementioned computer-readable storage medium carries one or more programs that, when executed by a servo motor control device, cause the servo motor control device to: In response to the servo motor control command, the current motor state corresponding to the servo motor is obtained, and the tracking error corresponding to the servo motor is obtained; Based on the preset disturbance value calculation strategy and the current motor state, the preset disturbance observer is used to calculate the total disturbance value corresponding to the servo motor and obtain the disturbance estimate value within a finite time. The preset disturbance observer is constructed based on the RBFNN neural network. The RBFNN neural network is used to converge the observation error interval corresponding to the servo motor to reduce the time for obtaining the observation error. The observation error is used to calculate the total disturbance value. Based on the preset equivalent control strategy and the tracking error, the equivalent control input corresponding to the servo motor is calculated using a preset sliding mode controller; and based on the disturbance estimate and the preset finite-time control strategy, the finite-time control input corresponding to the servo motor is calculated. The servo motor is controlled based on the finite-time control input and the equivalent control input.

[0129] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0130] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0131] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0132] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described servo motor control method, thereby solving the technical problem of servo motor control. Compared with related technologies, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the servo motor control method provided in the above embodiments, and will not be repeated here.

[0133] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the servo motor control method described above.

[0134] The computer program product provided in this application can solve the technical problem of servo motor control. Compared with related technologies, the beneficial effects of the computer program product provided in this application are the same as those of the servo motor control method provided in the above embodiments, and will not be repeated here.

[0135] The above description is only a part of the embodiments of this application and does not limit the scope of protection of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included in the scope of protection of this application.

Claims

1. A servo motor control method, characterized in that, The servo motor control method includes: In response to the servo motor control command, the current motor state corresponding to the servo motor is obtained, and the tracking error corresponding to the servo motor is obtained; Based on the preset disturbance value calculation strategy and the current motor state, the preset disturbance observer is used to calculate the total disturbance value corresponding to the servo motor and obtain the disturbance estimate value within a finite time. The preset disturbance observer is constructed based on the RBFNN neural network. The RBFNN neural network is used to converge the observation error interval corresponding to the servo motor to reduce the time for obtaining the observation error. The observation error is used to calculate the total disturbance value. Based on the preset equivalent control strategy and the tracking error, the equivalent control input corresponding to the servo motor is calculated using a preset sliding mode controller; and based on the disturbance estimate and the preset finite-time control strategy, the finite-time control input corresponding to the servo motor is calculated. The servo motor is controlled based on the finite-time control input and the equivalent control input.

2. The servo motor control method as described in claim 1, characterized in that, Before the step of calculating the total disturbance value corresponding to the servo motor using a preset disturbance value calculation strategy and the current motor state, and obtaining the disturbance estimate within a finite time, the method further includes: Based on the unknown load and frictional nonlinearity, a servo motor dynamic model is obtained through modeling. The unknown load and the frictional nonlinearity are combined into a lumped disturbance. Based on the total disturbance and the servo motor dynamics model, the servo motor system and the lumped disturbance are modeled to obtain the system model. Based on the system model and RBFNN neural network, a preset perturbation observer is constructed.

3. The servo motor control method as described in claim 1, characterized in that, The step of calculating the total disturbance value corresponding to the servo motor using a preset disturbance value calculation strategy and the current motor state, and obtaining the disturbance estimate within a finite time, further includes: Obtain the current observation error range corresponding to the servo motor; Based on the preset disturbance value calculation strategy, the current motor state, and the current observation error range, the current observation error value corresponding to the servo motor is calculated using the preset disturbance observer; Based on the current observation error value, the total disturbance value corresponding to the servo motor is calculated, and the disturbance estimate is obtained within a finite time.

4. The servo motor control method as described in claim 3, characterized in that, After the step of calculating the current observation error value corresponding to the servo motor using a preset disturbance value calculation strategy, the current motor state, and the current observation error range, the method further includes: Based on the current observation error value, the current observation error interval is converged.

5. The servo motor control method as described in claim 1, characterized in that, The step of obtaining the tracking error corresponding to the servo motor further includes: Obtain the reference trajectory corresponding to the servo motor; Based on the reference trajectory and the motor state, the tracking error corresponding to the servo motor is determined.

6. The servo motor control method as described in claim 1, characterized in that, The step of controlling the servo motor based on the finite-time control input and the equivalent control input further includes: Based on the finite-time control input and the equivalent control input, the total control input is obtained; The total control input is limited, and based on the DSP's PWM module and the limited total control input, a signal with the corresponding duty cycle is output to the driver to drive the servo motor.

7. A servo motor control device, characterized in that, The servo motor control device includes: The acquisition module is used to acquire the current motor state corresponding to the servo motor in response to the servo motor control command, and to acquire the tracking error corresponding to the servo motor. The first calculation module is used to calculate the total disturbance value corresponding to the servo motor based on the preset disturbance value calculation strategy and the current motor state, using a preset disturbance observer, and obtain the disturbance estimate value within a finite time. The preset disturbance observer is constructed based on the RBFNN neural network, which is used to converge the observation error interval corresponding to the servo motor to reduce the time for obtaining the observation error. The observation error is used to calculate the total disturbance value. The second calculation module is used to calculate the equivalent control input corresponding to the servo motor using a preset sliding mode controller based on a preset equivalent control strategy and the tracking error; and to calculate the finite time control input corresponding to the servo motor based on the disturbance estimate and the preset finite time control strategy. A control module is provided for controlling the servo motor based on the finite-time control input and the equivalent control input.

8. A servo motor control device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the servo motor control method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the servo motor control method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the servo motor control method as described in any one of claims 1 to 6.

Images