Voice coil motor driving valve controller based on neural network active disturbance rejection control and control method thereof

Abstract

The invention provides a voice coil motor driving valve controller based on neural network active disturbance rejection control and a control method thereof. The controller comprises a target control signal preprocessing module, a valve element displacement sensor, a real-time error calculation unit, a controller module, an expansion state observer and an active disturbance rejection controller. According to the method, the target control signal is preprocessed to obtain a smooth target displacement control curve, so that system response overshoot is avoided; according to the invention, the control method combining the neural network, the active-disturbance-rejection control and the signal preprocessing is adopted, and the environmental adaptability and robustness of the high-precision high-response position control of the voice coil motor driving valve are improved through the real-time self-tuning of the parameters of the active-disturbance-rejection algorithm by the neural network. Setting parameters of the active-disturbance-rejection algorithm in real time according to different working conditions; system disturbance is observed and compensated in real time through active disturbance rejection control, and accurate position control over the main valve element of the voice coil motor driving valve is achieved.

Description

Technical Field

[0001] The present invention relates to the field of hydraulic control technology, and in particular to a voice coil motor driven valve controller based on neural network anti-disturbance control and a control method thereof. The control technology is suitable for high-precision, high-dynamic response voice coil motor driven proportional valves, and can significantly improve the response speed, control accuracy and dynamic stability of voice coil motor driven proportional valves in complex and frequently fluctuating load environments. Background Art

[0002] Hydraulic control systems have been widely used in engineering machinery, aerospace, precision manufacturing and other fields due to their strong power density and fast dynamic response characteristics. Among them, the voice coil motor driven proportional valve is one of the core components to achieve high dynamic and high precision control of the hydraulic system. The inherent nonlinear characteristics of the voice coil motor driven valve, load fluctuations and external disturbances lead to problems such as valve core motion control response lag, low control accuracy and valve core displacement overshoot. Traditional linear control methods, such as PID control, are difficult to balance stability and accuracy requirements in complex dynamic environments. For this reason, a new voice coil motor driven valve controller and its algorithm are needed to improve the control accuracy of the voice coil motor driven valve under complex working conditions.

[0003] Active disturbance rejection control achieves effective control of unknown external disturbances and internal nonlinearity of proportional valves by real-time observation and compensation of system disturbances. However, under fast dynamic commands, the active disturbance rejection controller may experience response lag or control overshoot. Neural networks have the ability to self-learn and model nonlinear systems and can effectively adapt to changes in proportional valve characteristics. However, their independent application makes it difficult to achieve rapid adjustment of dynamic response. Signal preprocessing algorithms can smooth control commands, reduce the impact of sudden command changes on valve core control during the control process, and improve the stability of dynamic response. Summary of the invention

[0004] In order to overcome the shortcomings of the prior art, the present invention proposes a voice coil motor driven valve controller based on neural network anti-disturbance control and a control method thereof. The controller and the control method can achieve high-precision valve core position control, fast dynamic response and excellent anti-disturbance performance.

[0005] The objective of the present invention is achieved through the following technical solutions:

[0006] The present invention provides a voice coil motor drive valve control method based on neural network self-disturbance rejection control, which comprises the following steps:

[0007] S1, obtaining a target control signal of a controlled voice coil motor driving valve, preprocessing the target control signal, and processing the target control signal into a smooth target displacement control curve including an acceleration phase, a constant speed phase, and a deceleration phase;

[0008] S2, real-time acquisition of the valve core displacement of the controlled voice coil motor driven valve, subtraction of the valve core displacement signal and the smoothed target displacement input signal obtained by S1, and calculation of the real-time error signal;

[0009] S3, based on the current working state of the voice coil motor driven valve, the controller module uses the trained neural network model to obtain the feedback gain parameters of the ADRC and the working parameters of the extended state observer;

[0010] S4, the extended state observer outputs the total disturbance estimate of the current system according to the working parameters obtained in S3;

[0011] S5. Based on the real-time error signal, the total disturbance estimation value and the feedback gain parameter, the controller module uses an anti-disturbance control controller to dynamically adjust the real-time error signal and outputs a control instruction to drive the voice coil motor drive valve.

[0012] The present invention also provides a voice coil motor driven valve control system for implementing the method, which comprises:

[0013] A target control signal preprocessing module is used to preprocess the target control signal to obtain a smooth target displacement control curve;

[0014] The valve core displacement sensor obtains the valve core displacement of the controlled voice coil motor driven valve in real time;

[0015] The real-time error calculation unit calculates the difference between the valve core displacement signal and the smooth target displacement input signal to calculate the real-time error signal;

[0016] The controller module uses the trained neural network model to obtain the feedback gain parameters of the ADRC and the operating parameters of the extended state observer;

[0017] The extended state observer outputs the total disturbance estimate of the current system according to the working parameters obtained by the controller module;

[0018] The anti-disturbance controller dynamically adjusts the real-time error signal based on the real-time error signal, the total disturbance estimation value and the feedback gain parameter, and outputs a control instruction to drive the voice coil motor drive valve.

[0019] Compared with the prior art, the present invention has the following beneficial effects:

[0020] (1) The present invention performs smoothing preprocessing on the target control signal, and the preprocessed target control signal avoids system response overshoot;

[0021] (2) The present invention adopts a control method that combines neural network, anti-disturbance control and signal preprocessing. Through signal preprocessing, the control instructions are made smoother and the impact caused by sudden changes in instructions is mitigated. The real-time self-tuning of the anti-disturbance algorithm parameters by the neural network improves the environmental adaptability and robustness of the high-precision and high-response position control of the voice coil motor drive valve. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 The figure is a flow chart of the voice coil motor drive valve control method based on neural network anti-disturbance control.

[0023] Figure 2 Schematic diagram of a controller in an embodiment. DETAILED DESCRIPTION

[0024] The present invention will be further described and illustrated in conjunction with specific embodiments. The technical features of each embodiment of the present invention can be combined accordingly without conflicting with each other.

[0025] like Figure 1 and Figure 2 As shown, the voice coil motor drive valve control method based on neural network anti-disturbance control of the present invention includes the following steps:

[0026] S1. Obtain a target control signal of a controlled voice coil motor driving valve, pre-process the target control signal, and process the target control signal into a smooth target displacement control curve including an acceleration phase, a constant speed phase, and a deceleration phase.

[0027] The target control signal is the control task given by the outside world, that is, the valve core needs to reach a certain position at a certain time. Therefore, the target control signal can usually be expressed as the relationship between the valve core target displacement and time.

[0028] The purpose of preprocessing the target control signal is to avoid the valve core from overshooting during the control process. Specifically, the present invention uses a tracking differentiator to perform first-order or second-order differentiation on the target control signal, extract the dynamic change rate of the signal, and generate a smooth target displacement control curve to avoid system response overshoot. The smooth target displacement control curve is a curve of the relationship between time and the target displacement of the valve core, including an acceleration stage, a constant speed stage, and a deceleration stage; in the acceleration stage, the valve core speed smoothly accelerates from zero, and the valve core displacement increases rapidly; in the constant speed stage, the valve core speed remains constant, and the valve core displacement gradually reaches the vicinity of the target displacement; in the deceleration stage, the valve core speed decreases smoothly, the valve core decelerates and finally reaches the target displacement. This three-stage speed change curve can not only improve the response speed of the valve core, but also maintain a low movement speed when the valve core is about to reach the target displacement, thereby avoiding valve core overshoot and oscillation.

[0029] In one embodiment of the present invention, the smooth target displacement control curve is expressed by the following formula:

[0030] S(t)=A / 2(1-cos(2πt / T))

[0031] Among them, A is the target control signal amplitude, T is the acceleration stage and deceleration stage time, and smooth control of the target control signal can be achieved by adjusting A and T.

[0032] S2, real-time acquisition of the valve core displacement of the controlled voice coil motor driven valve, subtraction of the valve core displacement signal and the smoothed target displacement input signal obtained by S1, and calculation of the real-time error signal;

[0033] The valve core displacement of the controlled voice coil motor driven valve can be obtained by any method in the prior art. In one embodiment of the present invention, the valve core displacement signal of the controlled voice coil motor driven valve is obtained by an LVDT sensor, and a sinusoidal wave with a fixed frequency and amplitude is used to excite the LVDT sensor through a multivibrator circuit and an amplitude adjustment circuit; the rectifier amplifier circuit processes the sinusoidal signal of the LVDT and outputs a DC voltage signal proportional to the LVDT; the acquisition circuit uses an operational amplifier with an adjustable amplification factor to finally obtain the main valve core displacement information of the voice coil motor.

[0034] The present invention further adopts a filtering and denoising unit to perform data filtering and denoising on the obtained valve core displacement signal to obtain an accurate feedback signal; the filtering algorithm adopts adaptive Kalman filtering and sliding mean filtering to reduce noise and transient interference and ensure high-precision transmission of the feedback signal.

[0035] The real-time error signal adjustment formula is as follows:

[0036] e(t)=y ref (t)-y(t)

[0037] Among them, e(t) is the error, y ref (t) is the target position command generated by the smooth target displacement control curve, and y(t) is the actual position of the valve core.

[0038] S3, based on the current working state of the voice coil motor driven valve, the controller module uses the trained neural network model to obtain the feedback gain parameters of the ADRC and the working parameters of the extended state observer;

[0039] The neural network model is used for nonlinear modeling and dynamic regulation of the voice coil motor driven valve, and is trained using the historical working data of the voice coil motor driven valve. In an embodiment of the present invention, the neural network model adopts a three-layer feedforward neural network structure, the input layer includes valve core displacement, valve core speed and valve core acceleration signals, the middle hidden layer adopts the ReLU activation function, and the output layer is the feedback gain parameter of the self-disturbance rejection controller and the working parameters of the extended state observer. During the training process, the neural network model can be trained alone, or it can be trained together with the self-disturbance rejection controller and the extended state observer to form an overall control system; the error back propagation (BP) algorithm is used in the training to optimize the network parameters.

[0040] The training process updates parameters through the following formula:

[0041]

[0042] Among them, θ is the network parameter, η is the learning rate, and L is the loss function. In real-time applications, the neural network model can adaptively adjust parameters according to the dynamic changes of the system.

[0043] S4, the extended state observer (ESO) outputs the total disturbance estimate of the current system according to the working parameters obtained in S3;

[0044] The extended state observer (ESO) estimates the disturbance, nonlinear dynamic characteristics and unmodeled errors of the voice coil motor drive valve, and then realizes dynamic compensation through nonlinear feedback. The output of the extended state observer is the estimated total disturbance, which is defined as follows:

[0045] d^(t)=Lo·(yy^)

[0046] Among them, d^(t) is the total disturbance estimate, Lo is the observation gain matrix, that is, the working parameters of the extended state observer, y is the actual displacement of the valve core, and y^ is the estimated valve core displacement; by adjusting the size of Lo, the response speed of the extended state observer to the disturbance is controlled, thereby optimizing the control effect.

[0047] S5. Based on the real-time error signal, the total disturbance estimation value and the feedback gain parameter, the controller module uses an anti-disturbance control controller to dynamically adjust the real-time error signal and outputs a control instruction to drive the voice coil motor drive valve.

[0048] The main task of the Active Disturbance Rejection Control (ADRC) is to adjust the compensated error through a nonlinear feedback formula based on the disturbance estimation result of the ESO. The output signal of the ADRC drives the actuator to achieve precise control of the valve core.

[0049] The feedback formula of the ADRC is:

[0050] u(t)=-K·e(t)-Kd·e(t)+d^(t)

[0051] Where u(t) is the control input signal, e(t) is the error between the expected value and the actual value, d^(t) is the disturbance estimate, and K and Kd are the feedback gain coefficients respectively.

[0052] The neural network model of the present invention provides a nonlinear estimation value of the system, which is used to adjust the feedback gain and ESO parameters of the active disturbance rejection controller in real time, so that the active disturbance rejection controller can respond quickly under complex working conditions. The working principle of the collaborative control mechanism is that the neural network continuously updates the nonlinear modeling results of the system dynamic characteristics and feeds back to the gain adjustment unit of the ADRC. According to the modeling results, the feedback gain and extended state observer (ESO) parameters of the ADRC change adaptively with the system state to optimize the dynamic response performance of the control system.

[0053] The present invention makes the control instructions smoother by preprocessing the control signal and the feedback signal; self-learning and modeling the nonlinear system of the voice coil motor driven valve are performed through the neural network algorithm, and the setting parameters of the self-disturbance rejection algorithm are adjusted in real time according to different working conditions; and the system disturbance is observed and compensated in real time through the self-disturbance rejection control to realize the precise position control of the main valve core of the voice coil motor driven valve.

[0054] like Figure 2 As shown, the present invention also provides a voice coil motor driven valve control system for implementing the method, which comprises:

[0055] A target control signal preprocessing module is used to preprocess the target control signal to obtain a smooth target displacement control curve;

[0056] The valve core displacement sensor obtains the valve core displacement of the controlled voice coil motor driven valve in real time;

[0057] The real-time error calculation unit calculates the difference between the valve core displacement signal and the smooth target displacement input signal to calculate the real-time error signal;

[0058] The controller module uses the trained neural network model to obtain the feedback gain parameters of the ADRC and the operating parameters of the extended state observer;

[0059] The extended state observer outputs the total disturbance estimate of the current system according to the working parameters obtained by the controller module;

[0060] The anti-disturbance controller dynamically adjusts the real-time error signal based on the real-time error signal, the total disturbance estimation value and the feedback gain parameter, and outputs a control instruction to drive the voice coil motor drive valve.

[0061] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0062] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, and the various modules in the device are a kind of logical function division. There may be other division methods in actual implementation, for example, multiple modules can be combined or integrated into another unit. Another point is that the connection between the modules shown or discussed can be a communication connection through some interfaces, which can be electrical or other forms. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present application scheme. Ordinary technicians in this field can understand and implement it without paying creative work.

[0063] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the attached claims.

Claims

1. A voice coil motor drive valve control method based on neural network anti-disturbance control, characterized in that: The steps include: S1, obtaining a target control signal of a controlled voice coil motor driving valve, preprocessing the target control signal, and processing the target control signal into a smooth target displacement control curve including an acceleration phase, a constant speed phase, and a deceleration phase; S2, real-time acquisition of the valve core displacement of the controlled voice coil motor driven valve, subtraction of the valve core displacement signal and the smoothed target displacement input signal obtained by S1, and calculation of the real-time error signal; S3, based on the current working state of the voice coil motor driven valve, the controller module uses the trained neural network model to obtain the feedback gain parameters of the ADRC and the working parameters of the extended state observer; S4, the extended state observer outputs the total disturbance estimate of the current system according to the working parameters obtained in S3; S5. Based on the real-time error signal, the total disturbance estimation value and the feedback gain parameter, the controller module uses an anti-disturbance control controller to dynamically adjust the real-time error signal and outputs a control instruction to drive the voice coil motor drive valve.

2. The voice coil motor drive valve control method based on neural network anti-disturbance control according to claim 1 is characterized in that: The smooth target displacement control curve is a curve of the relationship between time and valve core target displacement, including an acceleration stage, a constant speed stage, and a deceleration stage; In the acceleration phase, the valve core speed accelerates smoothly from zero, and the valve core displacement increases rapidly; In the constant speed stage, the valve core speed remains constant, and the valve core displacement gradually reaches the vicinity of the target displacement; During the deceleration phase, the valve core speed decreases smoothly, the valve core decelerates and eventually reaches the target displacement, avoiding valve core overshoot and oscillation.

3. The voice coil motor drive valve control method based on neural network anti-disturbance control according to claim 1 or 2, characterized in that: The smooth target displacement control curve is expressed by the following formula: S(t)=A / 2(1-cos(2πt / T)) Among them, A is the target control signal amplitude, T is the acceleration stage and deceleration stage time, and smooth control of the target control signal can be achieved by adjusting A and T.

4. The voice coil motor drive valve control method based on neural network anti-disturbance control according to claim 1, characterized in that: In S2, the valve core displacement signal of the controlled voice coil motor driven valve is obtained through the LVDT sensor, and the obtained valve core displacement signal is processed by adaptive Kalman filtering and sliding mean filtering to reduce noise and transient interference and ensure high-precision transmission of the feedback signal.

5. The voice coil motor drive valve control method based on neural network anti-disturbance control according to claim 1, characterized in that: In S3, the neural network model adjusts the feedback gain and extended state observer parameters of the active disturbance rejection controller in real time based on the current valve core displacement, valve core speed and valve core acceleration signal of the voice coil motor driven valve; The neural network model adopts a three-layer feedforward neural network structure. The input layer inputs the valve core displacement, valve core speed and valve core acceleration signals, the middle hidden layer adopts the ReLU activation function, and the output of the output layer is the system nonlinear estimation value. The error back propagation algorithm is used in the neural network model training process to optimize the model parameters.

6. The voice coil motor drive valve control method based on neural network anti-disturbance control according to claim 1, characterized in that: In S4, the extended state observer estimates the disturbance, nonlinear dynamic characteristics and unmodeled errors of the voice coil motor drive valve. The output of the extended state observer is the estimated total disturbance, which is defined as follows: d^(t)=Lo·(yy^) Among them, d^(t) is the total disturbance estimate, Lo is the observation gain matrix, that is, the working parameters of the extended state observer, y is the actual displacement of the valve core, and y^ is the estimated valve core displacement; by adjusting the size of Lo, the response speed of the extended state observer to the disturbance is controlled, thereby optimizing the control effect.

7. The voice coil motor drive valve control method based on neural network anti-disturbance control according to claim 1, characterized in that: In S5, the ADRC adjusts the real-time error signal through a nonlinear feedback formula based on the disturbance estimation result of the extended state observer: u(t)=-K·e(t)-Kd·e˙(t)+d^(t) Among them, u(t) is the control command, e(t) is the real-time error signal, d^(t) is the disturbance estimate, and K and Kd are feedback gain coefficients.

8. A voice coil motor driven valve control system implementing the method according to any one of claims 1 to 7, characterized in that include: A target control signal preprocessing module is used to preprocess the target control signal to obtain a smooth target displacement control curve; The valve core displacement sensor obtains the valve core displacement of the controlled voice coil motor driven valve in real time; The real-time error calculation unit calculates the difference between the valve core displacement signal and the smooth target displacement input signal to calculate the real-time error signal; The controller module uses the trained neural network model to obtain the feedback gain parameters of the ADRC and the operating parameters of the extended state observer; The extended state observer outputs the total disturbance estimate of the current system according to the working parameters obtained by the controller module; The anti-disturbance controller dynamically adjusts the real-time error signal based on the real-time error signal, the total disturbance estimation value and the feedback gain parameter, and outputs a control instruction to drive the voice coil motor drive valve.

Images