Intelligent equipment adaptive power supply control method and system

Abstract

The invention discloses a self-adaptive power supply control method and system for intelligent equipment, and belongs to the field of electrical automation control, and the method comprises the steps: configuring an initialized PID control parameter of target equipment, and carrying out the calculation to obtain a voltage error and a voltage error change rate; according to the voltage error and the voltage error change rate, a self-adaptive adjustment coefficient of a PID control parameter is obtained by combining fuzzy logic calculation; historical control data and real-time control data of PID control equipment of target equipment are collected, predicted PID parameters are obtained through a feedforward neural network, and final control parameters are obtained through calculation in combination with an adaptive adjustment result; and calculating a voltage regulation value according to the final control parameter obtained by calculation, and controlling a power supply module of the target equipment to regulate the output voltage to ensure that the output voltage is stabilized at a target value. The defects that parameters of a traditional PID controller are fixed and cannot be adjusted in a self-adaptive mode are overcome, and the control precision and stability are improved.

Description

Technical Field

[0001] The present invention relates to the field of electrical automation control, and in particular to an adaptive power supply control method and system for intelligent equipment. Background Art

[0002] In the field of electrical automation control, PID controllers are widely used in various control systems, but traditional PID controllers have some shortcomings. In the prior art, the parameters of PID controllers are usually fixed or determined by trial and error, and the control parameters cannot be adaptively adjusted according to changes in system status, resulting in poor control accuracy and stability, making it difficult to meet the needs of high-precision control. Summary of the invention

[0003] One of the purposes of the present invention is to provide an adaptive power supply control method for intelligent equipment to solve the problem that the PID controller parameters in the prior art are fixed or determined by trial and error, and the control parameters cannot be adaptively adjusted according to changes in the system state, resulting in poor control accuracy and stability.

[0004] The present invention is implemented through the following technical scheme, an adaptive power supply control method for intelligent equipment, comprising the following steps: S100, configuring the initialization PID control parameters of the target equipment, and analyzing the voltage required by each component in the target equipment, setting a target voltage value for each component of the target equipment, reading the data voltage of each component of the voltage sensor to obtain the actual voltage value, and calculating the voltage error and the voltage error change rate; S200, according to the voltage error and the voltage error change rate, combined with fuzzy logic calculation to obtain the adaptive adjustment coefficient of the PID control parameter; S300, collecting the historical control data and real-time control data of the PID control device of the target equipment, cleaning and standardizing the collected data, sending the cleaned and standardized data to the feedforward neural network to obtain the predicted PID parameters, and calculating the final control parameters in combination with the adaptive adjustment results; S400, calculating the voltage adjustment value according to the calculated final control parameters, controlling the power module of the target equipment to adjust the output voltage to ensure stability at the target value.

[0005] Furthermore, the PID control parameters include: proportional parameter K p , integration parameter K i And the differential parameter K d .

[0006] Furthermore, the voltage error is expressed by:

[0007] e V (t) = V target (t) - V acutual (t), where e V (t) is the voltage error, Vtarget (t) is the target voltage value, V acutual (t) is the actual voltage value; the error change rate is expressed by the following formula:

[0008] , where Δe V (t) is the voltage error change rate.

[0009] Furthermore, step S200 includes the following sub-steps: S210, converting the voltage error and the voltage error change rate into fuzzy variables and defining fuzzy sets to describe the value range of the voltage error and the error change rate, and the value range of the fuzzy variables is defined as different fuzzy sets; S220, setting a fuzzy rule base according to the division of the fuzzy sets, and using a fuzzy controller to perform fuzzy reasoning on the input and output the fuzzy value of the PID parameter according to the rules in the fuzzy rule base; S230, converting the output fuzzy value into an actual parameter value according to the output fuzzy value of the PID parameter.

[0010] Furthermore, the rules of the fuzzy rule base are: Rule 1: If e V (t) is positive and Δe V (t) is positive, then increase K p , reduce K i , increase K d ; Rule 2: If e V (t) is zero and Δe V (t) is zero, then keep K p , increase K i , reduce K d ; Rule 3: If e V (t) is negative and Δe V If (t) is negative, reduce K p , keep K i , reduce K d .

[0011] Furthermore, the output fuzzy value is converted into the actual parameter value by the following calculation:

[0012] ,

[0013] ,

[0014] , where K p (t+1) is the scale parameter of the next moment, K p is the proportional parameter, α is the adaptive adjustment coefficient of the proportional parameter, K i (t+1) is the integration parameter at the next moment, K i is the integral parameter, β is the adaptive adjustment coefficient of the integral parameter, Kd (t+1) is the differential parameter of the next moment, K d is the differential parameter, and γ is the adaptive adjustment coefficient of the differential parameter.

[0015] Furthermore, the final control parameters are calculated by the following formula:

[0016] ,

[0017] ,

[0018] ,in, is the final scale parameter, is the scale parameter predicted by the neural network model, is the final integration parameter, is the integral parameter predicted by the neural network model, is the final differential parameter, is the differential parameter predicted by the neural network model, and λ is a weight factor between 0 and 1, which is used to balance the contribution ratio of the adaptive adjustment result and the model prediction result to the final parameter.

[0019] Further, the voltage regulation value is calculated by the following formula:

[0020] ,in, is the calculated voltage regulation value. is the integral of the error, which indicates the accumulation of error over time. is the derivative of the error, which represents the rate at which the error changes over time.

[0021] Another aspect of the present invention provides an adaptive power control system for intelligent equipment, the system comprising a processor; a memory storing a computer program, and when the computer program is executed by the processor, the adaptive power control method for intelligent equipment as described above is implemented.

[0022] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0023] 1. The present invention adjusts the parameters of the PID controller in real time according to the system error and the error change rate through fuzzy logic calculation, so that the control parameters can adaptively match the current system state, overcomes the defects of the traditional PID controller that the parameters are fixed and cannot be adaptively adjusted, and improves the control accuracy and stability.

[0024] 2. The present invention uses a neural network model to analyze and predict historical data, and combines the adaptive adjustment results to calculate the final control parameters, making full use of historical data to optimize the control parameters, further improving the control accuracy and stability, and by weighted averaging the real-time adaptive adjustment results and the neural network model prediction results, ensuring that the final control parameters can both adapt to the current system state and take advantage of the historical data and prediction model, thereby achieving a better control effect.

[0025] 3. The present invention is suitable for electrical automation control systems that require high control accuracy, and can adjust control parameters in real time according to changes in system status, thus meeting the needs of high-precision control. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0027] Figure 1 This is a flow chart of the method provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0029] Embodiment 1,

[0030] This embodiment discloses an adaptive power control method for intelligent equipment. Figure 1 The flowchart of this embodiment is shown. It can be seen from the figure that this method includes the following steps:

[0031] Step 1: Configure and initialize PID control parameters according to the specific conditions of the target device.

[0032] Among them, the PID control parameters include the proportional parameter K p , integration parameter K i And the differential parameter K d At the same time, the corresponding adaptive adjustment coefficient is configured for each PID control parameter, including the adaptive adjustment coefficient α of the proportional parameter, the adaptive adjustment coefficient β of the integral parameter and the adaptive adjustment coefficient γ of the differential parameter.

[0033] Analyze the voltage required by each component in the target device and set a target voltage value V for each component of the target device target(t), then read the data voltage of each component of the voltage sensor to obtain the actual voltage value V acutual (t), the voltage error e is calculated based on the target voltage value and the actual voltage value V (t) and error change rate Δe V (t),

[0034] In this implementation, the voltage error e V (t) is represented by the following formula:

[0035] e V (t) = V target (t) - V acutual (t),

[0036] Error change rate Δe V (t) is the derivative of the above equation with respect to time t, which can be expressed as follows:

[0037] ,

[0038] If the target voltage value of the target device is V target (t) is constant, that is, the target voltage remains unchanged, then the error change rate is mainly determined by the change rate of the actual voltage:

[0039] ,

[0040] Therefore, in specific applications, the voltage error change rate Δe V (t) Usually by the actual voltage value V acutual (t) is sampled and calculated, or it can be approximated by measured data. The specific calculation method depends on the accuracy and frequency of data acquisition. For example, commonly used numerical approximation methods may include: difference method or sliding average method. Among them, the difference method calculates between discrete time points [t, t+Δt], , Δt is the time interval or time increment between two discrete time points. The sliding average method averages the most recent error changes to reduce the impact of noise on the error change rate.

[0041] Step 2: Based on the calculated error size and change rate, the adaptive adjustment coefficient of the PID control parameters is calculated in combination with fuzzy logic.

[0042] Specifically, fuzzy logic calculations include,

[0043] 1) First, convert the voltage error and error change rate calculated in step 1 into fuzzy variables and define fuzzy sets to describe the value range of the voltage error and error change rate. The value range (range) of the fuzzy variable is defined as different fuzzy sets, such as high, medium and low. These fuzzy sets are used to describe the voltage error and error change rate. The division of these fuzzy sets is to enable the fuzzy controller to automatically adjust the parameters of the PID controller according to the current error and error change rate, so that it can better meet the needs of the current control system.

[0044] 2) According to the division of fuzzy sets, a fuzzy rule base is set, and a fuzzy controller is used to perform fuzzy reasoning on the input to output the fuzzy values ​​of the PID parameters according to the rules in the fuzzy rule base.

[0045] In this embodiment, the fuzzy rules in the fuzzy rule base are set as:

[0046] Rule 1: If e V (t) is positive and Δe V (t) is positive, then increase K p , reduce K i , increase K d .

[0047] Rule 2: If e V (t) is zero and Δe V (t) is zero, then keep K p , increase K i , reduce K d .

[0048] Rule 3: If e V (t) is negative and Δe V If (t) is negative, reduce K p , keep K i , reduce K d .

[0049] It should be noted that by accurately defining and adjusting these fuzzy rules, the response speed and stability of the control system can be effectively improved. The rules in the fuzzy rule base can be freely defined by the user according to the different target devices. The specific definition of the rules needs to be combined with the application experience and system requirements of the specific target device to ensure the control effect.

[0050] 3) According to the output fuzzy value of the PID parameter, the output fuzzy value is converted into the actual parameter value through the weighted average method.

[0051] In this embodiment, the actual parameter value is calculated by the following formula:

[0052] ,

[0053] ,

[0054] ,

[0055] Among them, K p (t+1) is the scale parameter of the next moment, K p is the proportional parameter, and α is the adaptive adjustment coefficient of the proportional parameter.

[0056] K i (t+1) is the integration parameter at the next moment, K i is the integral parameter, and β is the adaptive adjustment coefficient of the integral parameter.

[0057] K d (t+1) is the differential parameter of the next moment, K d is the differential parameter, and γ is the adaptive adjustment coefficient of the differential parameter.

[0058] Step 3: Collect the historical control data and real-time control data of the PID control device of the target device, clean and standardize the collected data, send the cleaned and standardized data to the trained feedforward neural network, predict the PID parameters, and calculate the final control parameters based on the adaptive adjustment results.

[0059] In this embodiment, the final control parameters are calculated by the following formula:

[0060] ,

[0061] ,

[0062] ,

[0063] in, is the final scale parameter, is the scale parameter predicted by the neural network model, is the final integration parameter, is the integral parameter predicted by the neural network model, is the final differential parameter, is the differential parameter predicted by the neural network model, and λ is a weight factor between 0 and 1, which is used to balance the contribution ratio of the adaptive adjustment result and the model prediction result to the final parameter.

[0064] It should be noted that the real-time adaptive adjustment results and the prediction results of the neural network model are weighted averaged. The weight factor is used to balance the contributions of the two, ensuring that the final control parameters can adapt to the current system state and take advantage of the historical data and prediction model to achieve better control effects.

[0065] Step 4: After obtaining the final control parameters, the voltage adjustment value is calculated according to the calculated final control parameters. The power module of the target device is controlled to adjust the output voltage to ensure that it is stable at the target value through the calculated voltage adjustment value.

[0066] Specifically, the voltage regulation value can be calculated according to the following formula:

[0067] ,

[0068] in, is the calculated voltage regulation value. is the integral of the error, which indicates the accumulation of error over time. is the derivative of the error, which represents the rate at which the error changes over time.

[0069] It should be noted that in this formula is the final proportional parameter, which is used to represent the product of the current error, reflecting the deviation of the current system state and is proportional to the error. Through this term, it can quickly respond to changes in the current error. It is an integral term, which is used to reflect the accumulation of errors over time. The integral term can eliminate the steady-state error of the system because it accumulates all past errors to ensure that the output of the system can reach the target value. is a differential term, which is used to reflect the rate of error change. The differential term can predict the error change trend, improve the dynamic response speed of the system, and reduce overshoot. Adjust the controller output voltage V output (t), so that the actual voltage V acutual (t) Closer to the target voltage V target (t), it should be noted that V output (t) = V acutual (t)+ΔV(t).

[0070] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An adaptive power control method for intelligent equipment, characterized in that: The adaptive power supply control method comprises: S100, configuring the initialization PID control parameters of the target device, and analyzing the voltage required by each component in the target device, setting a target voltage value for each component of the target device, reading the data voltage of each component of the voltage sensor to obtain the actual voltage value, and calculating the voltage error and the voltage error change rate; S200, obtaining an adaptive adjustment coefficient of a PID control parameter according to a voltage error and a voltage error change rate in combination with fuzzy logic calculation; S300, collecting historical control data and real-time control data of the PID control device of the target device, cleaning and standardizing the collected data, sending the cleaned and standardized data to the feedforward neural network to obtain predicted PID parameters, and calculating the final control parameters in combination with the adaptive adjustment results; S400: Calculate a voltage adjustment value according to the calculated final control parameter, and control the power module of the target device to adjust the output voltage to ensure that it is stable at the target value.

2. The adaptive power control method for intelligent equipment according to claim 1, characterized in that: The PID control parameters include: Scale parameter K p , integration parameter K i And the differential parameter K d .

3. The adaptive power control method for intelligent equipment according to claim 1, characterized in that: The voltage error is expressed by the following formula: e V (t)= V target (t) - V acutual (t), Among them, e V (t) is the voltage error, V target (t) is the target voltage value, V acutual (t) is the actual voltage value; The voltage error change rate is expressed by the following formula: ， Among them, Δe V (t) is the voltage error change rate.

4. The method for adaptive power control of intelligent equipment according to claim 1, characterized in that: The step S200 includes the following sub-steps: S210, converting the voltage error and the voltage error change rate into fuzzy variables and defining fuzzy sets to describe the value ranges of the voltage error and the error change rate, wherein the value ranges of the fuzzy variables are defined as different fuzzy sets; S220, setting a fuzzy rule base according to the division of fuzzy sets, and using a fuzzy controller to perform fuzzy reasoning on the input to output fuzzy values ​​of PID parameters according to the rules in the fuzzy rule base; S230. According to the output fuzzy value of the PID parameter, convert the output fuzzy value into an actual parameter value.

5. The method for adaptive power control of intelligent equipment according to claim 4, characterized in that: The rules of the fuzzy rule base are: Rule 1: If e V (t) is positive and Δe V (t) is positive, then increase K p , reduce K i , increase K d ; Rule 2: If e V (t) is zero and Δe V (t) is zero, then keep K p , increase K i , reduce K d ; Rule 3: If e V (t) is negative and Δe V If (t) is negative, reduce K p , keep K i , reduce K d .

6. The method for adaptive power control of intelligent equipment according to claim 4, characterized in that: The conversion of the output fuzzy value into the actual parameter value is calculated by the following formula: ， ， ， Among them, K p (t+1) is the scale parameter of the next moment, K p is the proportional parameter, α is the adaptive adjustment coefficient of the proportional parameter, K i (t+1) is the integration parameter at the next moment, K i is the integral parameter, β is the adaptive adjustment coefficient of the integral parameter, K d (t+1) is the differential parameter of the next moment, K d is the differential parameter, and γ is the adaptive adjustment coefficient of the differential parameter.

7. The method for adaptive power control of intelligent equipment according to claim 1, characterized in that: The final control parameters are calculated by the following formula: ， ， ， in, is the final scale parameter, is the scale parameter predicted by the neural network model, is the final integration parameter, is the integral parameter predicted by the neural network model, is the final differential parameter, is the differential parameter predicted by the neural network model, and λ is a weight factor between 0 and 1, which is used to balance the contribution ratio of the adaptive adjustment result and the model prediction result to the final parameter.

8. The method for adaptive power control of intelligent equipment according to claim 1, characterized in that: The voltage regulation value is calculated by the following formula: ， in, is the calculated voltage regulation value, is the integral of the error, which indicates the accumulation of error over time. is the derivative of the error, which represents the rate at which the error changes over time.

9. An adaptive power supply control system for intelligent equipment, characterized in that: The adaptive power control system comprises: processor; The memory stores a computer program, and when the computer program is executed by the processor, the adaptive power supply control method for intelligent devices according to any one of claims 1 to 8 is implemented.

Images