Fuzzy neural network PID liquid level control method based on improved dung beetle algorithm

Abstract

The invention discloses a fuzzy neural network PID liquid level control method based on an improved dung beetle algorithm, and belongs to the technical field of automatic control. The technical problem that common chaotic mapping is insufficient in ergodicity is solved. According to the technical scheme, the method comprises the following steps: S1, establishing a mathematical model of the liquid level control system of the ozone dissolving tank; s2, designing an improved dung beetle algorithm; s3, designing a fuzzy neural network PID controller; and S4, performing simulation experiment and performance verification on the liquid level control system of the ozone dissolving tank. The beneficial effects of the invention are that the method employs a population initialization strategy combining ICMIC chaotic mapping and reverse learning in the dung beetle algorithm, and remarkably improves the uniformity and global traversal capability of an initial solution; the ICMIC mapping has the infinite folding chaotic characteristic, the problem that common chaotic mapping is insufficient in ergodicity can be solved, meanwhile, the search space is further expanded through the reverse learning strategy, and population distribution is more diversified.

Description

Technical Field

[0001] The invention relates to the technical field of automatic control, and in particular to a fuzzy neural network PID liquid level control method based on an improved dung beetle algorithm. Background Art

[0002] The liquid level control of ozone dissolution tank is a key technical link in the field of semiconductor cleaning. The stability of its liquid level directly affects the efficiency of ozone dissolution and cleaning effect. However, the liquid level control system generally has problems such as nonlinearity, dynamic hysteresis and insufficient anti-interference ability, making it difficult for traditional PID control to meet actual needs.

[0003] Among the existing methods, fuzzy PID and fuzzy neural network PID have been used for nonlinear system control, but fuzzy PID relies on manually set rules and is difficult to adapt to complex working conditions; while fuzzy neural networks can achieve online adjustment, they lack effective parameter optimization algorithm support, resulting in insufficient control accuracy. To solve these problems, intelligent optimization algorithms have been gradually introduced in recent years, but traditional optimization algorithms such as particle swarm optimization (PSO) are prone to fall into local optimality in high-dimensional search, limiting their application effect in liquid level control.

[0004] Therefore, a fuzzy neural network PID liquid level control method based on the improved dung beetle algorithm was developed to improve the dynamic response speed, control accuracy and anti-interference ability, and to provide a stable and efficient liquid level regulation solution for complex working conditions such as ozone dissolution tanks. Summary of the invention

[0005] In view of the problems of strong nonlinearity, dynamic hysteresis and insufficient anti-interference ability in the liquid level control system of the ozone dissolving tank, the present invention proposes a fuzzy neural network PID liquid level control method based on the improved dung beetle algorithm. By improving the optimization algorithm and online parameter adjustment, the dynamic response speed and steady-state accuracy of the liquid level control are improved to meet the demand for liquid level stability under complex working conditions.

[0006] To achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0007] The fuzzy neural network PID liquid level control method based on the improved dung beetle algorithm includes the following steps:

[0008] S1. Establishment of system mathematical model

[0009] The operation process of the ozone dissolving tank is a complex physical and chemical reaction process. Its liquid level control is affected by environmental conditions and the dynamic characteristics of the equipment, showing characteristics such as nonlinearity and dynamic hysteresis, which brings great challenges to the modeling of the control system. In order to achieve precise control of the liquid level of the ozone dissolving tank, this paper models the liquid level control system based on the principle of mass conservation, and simplifies it into a first-order inertial hysteresis model based on the actual operating characteristics of the system.

[0010] According to the law of conservation of mass, the dynamic rate of change of the liquid level in the tank can be expressed as the difference between the inflow flow and the outflow flow, that is:

[0011]

[0012] Where A is the cross-sectional area of ​​the tank, h is the height of the liquid level at any time, and Fi and Fo are the inflow and outflow rates, respectively.

[0013] Combining the analogy between the liquid level system and the electrical system, the cross-sectional area A of the tank can be replaced by the capacitor C, and we can get:

[0014]

[0015] The resistance R can be written as:

[0016]

[0017] The inflow flow rate Fi is proportional to the speed N of the magnetic levitation pump and can be expressed as:

[0018] F i =kN

[0019] At the same time, it is assumed that the speed N of the magnetic suspension pump is controlled by the control signal U, that is:

[0020] N=K m U

[0021] From this we can get:

[0022]

[0023] Perform a pull transformation and sort it out to get:

[0024]

[0025] Finally, the control signal U (s) With liquid level height H (s) The transfer function between:

[0026]

[0027] In the liquid level control process of the ozone dissolution tank, there is a certain response delay in the liquid level change caused by the liquid flow. The change of the inflow volume needs a delay time τ to have a significant impact on the liquid level in the tank. Its transfer function is expressed as:

[0028]

[0029] Where k is the system gain, K mis the motor gain, τ is the hysteresis time constant, R is the flow resistance, C is the equivalent capacitance, and according to the experimental measurement, k=6.35×10 -5 ,K m =600, R = 60, C = 2.59, τ = -7, after substituting the parameters into:

[0030]

[0031] S2. Improved Dung Beetle Algorithm (IDBO) Design

[0032] In order to improve the optimization accuracy and global search capability of the Dung Beetle Algorithm (DBO) in the parameter optimization of complex liquid level control systems, this paper improves the traditional DBO algorithm and designs an improved Dung Beetle Algorithm (IDBO) based on ICMIC chaos initialization, reverse learning strategy and nonlinear dynamic adjustment mechanism. The specific improvement design is as follows:

[0033] (1) Introducing ICMIC chaos initialization and reverse learning strategy

[0034] In the population initialization process of the Dung Beetle Algorithm (DBO), traditional methods usually generate initial population solutions randomly. However, the randomly generated initial solutions may lead to uneven population distribution, which limits the global search ability of the algorithm and affects the subsequent optimization accuracy and convergence speed. To solve this problem, this paper proposes an improved method based on ICMIC chaotic mapping and reverse learning strategy to improve the diversity and coverage of the population initialization stage.

[0035] First, the ICMIC chaotic map is used to generate the initial population solution. As an infinite folding chaotic map, the ICMIC map has higher global ergodicity and stronger chaotic characteristics. Compared with the common Tent map and Logistic map, it can cover the search space more evenly and avoid the problem of the initial population being too concentrated or unevenly distributed. The mathematical expression of the ICMIC chaotic map is:

[0036]

[0037] In the formula, Z n is the chaotic variable of the current population, α is the chaos control parameter, and its value range is (0, 1).

[0038] Secondly, based on the population solution generated by ICMIC, the reverse learning strategy is introduced to further expand the search space. The reverse learning strategy generates a reverse solution for each initial solution to increase population diversity, thereby improving the global search capability. The mathematical expression of the reverse learning strategy is:

[0039] OZ i =K×(Z max +Zmin )-Z i

[0040] In the formula, OZ i is the value corresponding to each initial solution Z i The inverse solution of Z max and Z min They represent the maximum and minimum values ​​in the initial solution respectively; K is a random value in the range of (0,1).

[0041] (2) Introducing ICMIC chaos initialization and reverse learning strategy

[0042] In the Dung Beetle Algorithm (DBO), parameter R is an important dynamic adjustment factor that determines the search range of the population, which directly affects the balance between global search and local development. The traditional DBO algorithm usually uses a linear decreasing strategy to update parameter R, and its calculation formula is:

[0043]

[0044] Among them, t represents the current number of iterations, and T represents the maximum number of iterations.

[0045] Although the linear decreasing strategy can maintain a large search range in the early stage and promote global search, the rapid decline of R in the later stage may cause the search range to shrink too quickly, limiting the optimization accuracy and convergence performance of the algorithm, thus causing the population to fall into a local optimal solution. In order to further improve the optimization ability of the algorithm, this paper draws on the idea of ​​the dynamic weight adjustment mechanism and makes nonlinear improvements to the calculation of parameter R so that it can adapt to the search needs of different optimization stages.

[0046] The improved nonlinear dynamic adjustment mechanism calculates the parameter R through the following formula:

[0047]

[0048] In this formula, the nonlinear dynamic adjustment mechanism introduces logarithmic functions and nonlinear variation terms to keep the parameter R at a larger value in the early stage to enhance the global search capability, and gradually reduces R in the later stage of iteration to improve the accuracy of local development, thereby achieving a dynamic balance between global search and local development.

[0049] Compared with the traditional linear decreasing strategy, the nonlinear dynamic adjustment mechanism further reduces the risk of local optimality, and makes the search range more adaptable to the optimization needs of different stages by dynamically adjusting the weight factor R. Experimental results show that this mechanism can significantly improve the global search capability and optimization efficiency of the DBO algorithm, and effectively improve the convergence performance and robustness of the algorithm in high-dimensional complex problems.

[0050] S3. Design of fuzzy neural network PID controller In order to solve the problems of nonlinearity, dynamic hysteresis and insufficient anti-interference ability in the ozone dissolving tank level control system, this paper designs a fuzzy neural network PID controller based on the improved dung beetle algorithm (IDBO), which mainly includes three parts: IDBO algorithm module, fuzzy neural network module and PID controller module:

[0051] (1) Controller design

[0052] First, the PID controller proportional factor CK is adjusted by the IDBO algorithm. p , CK i , CK d Perform global optimization and determine the initial parameter K based on the ZN tuning method and actual debugging results. p0 , K i0 , K d0 Then, the fuzzy neural network dynamically adjusts the PID parameter increment ΔK according to the liquid level error e and its change rate ec. p , ΔK i , ΔK d Finally, the PID controller generates a control signal u(t) based on the real-time adjusted parameters, and drives the magnetic levitation pump to adjust the water supply flow rate, thereby achieving stable control of the liquid level.

[0053] (2) Fuzzy control reasoning

[0054] This paper designs fuzzy control rules based on liquid level error e and error change rate ec, a total of 49 rules, which are used to dynamically adjust the PID control parameter ΔK p , ΔK i , ΔK d The input variables and output variables use 7 fuzzy subsets {NB, NM, NS, ZO, PS, PM, PB}.

[0055] (3) Fuzzy Neural Network

[0056] The topological structure of the fuzzy neural network includes the input layer, fuzzification layer, fuzzy reasoning layer, normalization layer and output layer. In the fuzzy neural network PID controller, the input signals e and ec are processed in each layer in turn, and finally the three adjustable parameters ΔK of the PID controller are generated in the output layer. p , ΔK i , ΔK d .

[0057] The first layer is the input layer, which has two nodes, error and error change rate, which is used to convert the input vector x i =[x1,x2] T The components of are transmitted to the next layer. The input and output are:

[0058]

[0059] In the formula, is the input value of the first layer node, is the output value of the first layer node.

[0060] The second layer is the fuzzification layer, which contains 2 inputs, each of which corresponds to 7 linguistic variable values. Its function is to calculate the membership function of the fuzzy set of each linguistic variable value to which each component of the input vector belongs, and map it to the fuzzy subset. The input and output are:

[0061]

[0062] In the formula, is the input value of the second layer node, is the output value of the second layer node, c ij is the central value of the membership function; σ ij is the width of the function curve, b ij is the shape parameter.

[0063] The third layer is the fuzzy reasoning layer. Each node of this layer represents a fuzzy rule in the fuzzy rule base. Its function is to calculate the fitness of each fuzzy rule. The input and output are:

[0064]

[0065] Where, l=1,2,…,49; i1=i2=1,2,…,7; is the input value of the third layer node; is the output value of the node in the third layer. The fourth layer is the normalization layer. The number of nodes in this layer is the same as that in the third layer. Its function is to realize the normalization operation on the output of the fuzzy inference layer. The input and output are:

[0066]

[0067] In the formula, is the input value of the 4th layer node; is the output value of the 4th layer node.

[0068] The fifth layer is the output layer, which performs weighted summation of the defuzzified output. Each node in this layer represents an output variable, and there are three nodes in total, namely, ΔK P , ΔK I , ΔK D The input and output are:

[0069]

[0070]

[0071] Where k = 1, 2, 3; ω ij is the network weight of the output layer; is the input value of the 5th layer node; is the output value of the 5th layer node.

[0072] (4) Parameter Adaptive Adjustment

[0073] The fuzzy neural network PID controller is completed through forward propagation calculation and outputs ΔK p , ΔK i , ΔK d These parameter changes act on the actuator through the PID controller to further adjust the system output. By comparing with the target value y(t), if the error does not meet the target requirements, the parameter adaptive adjustment process is entered. This process adjusts the central parameter C of the membership function in the fuzzy neural network through the error signal ij , width parameter σ ij , and the membership shape parameter w ij , so that the error signal is reduced, and the objective function of error correction is defined as:

[0074]

[0075] Where r(t) is the desired liquid level of the given system, and y(t) is the actual liquid level of the system.

[0076] In order to minimize the objective function E, the fuzzification layer parameters are dynamically adjusted based on error feedback, including the center, width and shape parameters of the membership function. The iterative update formula of each parameter is as follows:

[0077]

[0078] Where n is the iteration step of the network; λ is the inertia coefficient, which is used to balance historical information and current updates; η is the learning rate, which controls the parameter update speed; Δc ij (n), Δσ ij (n), Δω ij (n) represent the change of each parameter, which is calculated based on the current error feedback.

[0079] S4. Liquid level control system simulation experiment and performance verification

[0080] In order to verify the performance of the fuzzy neural network PID control method based on the improved dung beetle algorithm (IDBO-FNN-PID) in the ozone dissolution tank level control system, a simulation experiment based on the MATLAB / Simulink platform was designed and carried out, which mainly includes the following parts: the performance of the improved dung beetle algorithm (IDBO) is evaluated by standard unimodal functions and multimodal functions, focusing on testing its global optimization ability and convergence speed, and verifying its effectiveness as a controller parameter optimization tool; the algorithm in this paper is compared and analyzed with other control algorithms, and the dynamic response performance of each method in the liquid level control task is evaluated, including response time, overshoot and steady-state error; external disturbances such as water supply and drainage flow fluctuations and motor speed disturbances are simulated, and the recovery time and liquid level stability of different control algorithms under disturbance are tested to verify the anti-disturbance ability of the control method in this paper; through the sinusoidal signal following experiment, the response speed and following accuracy of each control algorithm in the dynamic input signal tracking task are tested, and its adaptability in complex dynamic working conditions is evaluated.

[0081] Compared with the prior art, the present invention has the following beneficial effects:

[0082] (1) The present invention adopts a population initialization strategy combining ICMIC chaotic mapping and reverse learning in the traditional Dung Beetle Algorithm (DBO), which significantly improves the uniformity and global traversal ability of the initial solution. ICMIC mapping has the characteristics of infinite folding chaos, which can solve the problem of insufficient traversal of common chaotic mapping. At the same time, the reverse learning strategy further expands the search space, making the population distribution more diversified, laying a good foundation for subsequent optimization.

[0083] (2) The present invention solves the problem that the traditional linear decreasing strategy is prone to fall into the local optimum in the later stage by performing nonlinear optimization on the key parameter R in the DBO algorithm. The improved dynamic adjustment mechanism maintains a larger search range in the early stage to enhance the global search capability, and gradually reduces R in the later stage to improve the local development accuracy and efficiency, thus achieving a dynamic balance between global search and local development.

[0084] (3) Through the combination of fuzzy neural network and PID controller, the present invention can dynamically adjust the controller parameters according to the liquid level error and error change rate. Especially under complex dynamic conditions, the improved PID controller effectively reduces the steady-state error and overshoot, shortens the response time, and its dynamic performance is far superior to the traditional method. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0086] Figure 1 This is a structural diagram of the ozone dissolving tank system in the present invention.

[0087] Figure 2 This is the structural diagram of the IDBO optimized fuzzy neural network PID controller in the present invention.

[0088] Figure 3 This is a topological structure diagram of the fuzzy neural network in the present invention.

[0089] Figure 4 It is a graph of the iterative convergence curve of the function in the present invention.

[0090] Figure 5 This is a comparison chart of the experiment of the present invention. DETAILED DESCRIPTION

[0091] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0092] Example 1

[0093] The present invention provides a fuzzy neural network PID liquid level control method based on an improved dung beetle algorithm, comprising the following steps:

[0094] S1. Establishment of system mathematical model

[0095] The liquid level control system of the ozone dissolving tank is a typical dynamic nonlinear system, and its liquid level is affected by the combined effects of the inlet flow rate, outlet flow rate and the dynamic characteristics of the system itself. In order to achieve precise liquid level control, this paper establishes a mathematical model of the system based on the principle of mass conservation, and fits the system parameters that meet the actual working conditions through experiments. Combined with the dynamic hysteresis characteristics of the liquid level in the tank, the first-order inertia hysteresis model is used to model it, and the transfer function of the system is obtained as follows:

[0096]

[0097] S2. Improved Dung Beetle Algorithm (IDBO) Design

[0098] In order to improve the global optimization ability and convergence accuracy of the traditional dung beetle algorithm (DBO) in the optimization of liquid level control parameters, the present invention improves it and designs an improved dung beetle algorithm (IDBO) based on ICMIC chaotic mapping, reverse learning strategy and nonlinear dynamic adjustment mechanism, which specifically includes the following steps:

[0099] (1) Population initialization based on ICMIC chaotic mapping and reverse learning

[0100] In the population initialization stage of the dung beetle algorithm, traditional methods usually generate population solutions randomly, but this may lead to uneven distribution of the initial population and affect the global search ability of the algorithm. The present invention proposes a population initialization method based on the combination of ICMIC chaotic mapping and reverse learning.

[0101] ICMIC chaotic mapping is an infinitely folded chaotic mapping with good global ergodicity. Compared with traditional Logistic mapping and Tent mapping, it can cover the search space more evenly. Its mathematical expression is as follows:

[0102]

[0103] In the formula, Z n is the chaotic variable of the current population, α is the chaotic control parameter of ICMIC mapping, and its value range is (0, 1). In order to further expand the population coverage, the reverse learning strategy is introduced to generate the reverse solution of each solution to supplement the diversity of the population. The formula for reverse learning is:

[0104] OZ i =K×(Z max +Z min )-Z i

[0105] In the formula, OZ i is the value corresponding to each initial solution Z i The inverse solution of Z max and Z min They represent the maximum and minimum values ​​in the initial solution respectively; K is a random value in the range of (0,1).

[0106] (2) Nonlinear dynamic adjustment of parameters

[0107] In the traditional DBO algorithm, the control parameter R is usually updated using a linear decreasing strategy, and its update formula is:

[0108]

[0109] Where t represents the current number of iterations, and T represents the maximum number of iterations.

[0110] In response to the above problems, this paper draws on the idea of ​​dynamic weight adjustment of the flood algorithm and performs nonlinear optimization on the calculation of parameter R. The weight parameter R is dynamically adjusted to adapt to the search requirements of different iteration stages. The formula is as follows:

[0111]

[0112] Where T is the maximum number of iterations and t is the current number of iterations.

[0113] This method can maintain a large global search capability in the early stage and gradually enhance the local development accuracy in the later stage, thereby achieving a dynamic balance in the search range and avoiding the population from falling into the local optimum.

[0114] S3. Design of fuzzy neural network PID controller

[0115] In order to solve the problems of nonlinearity, dynamic hysteresis and insufficient anti-interference ability in the ozone dissolution tank level control system, this paper designs a fuzzy neural network PID controller based on the improved dung beetle algorithm (IDBO). The controller mainly consists of three parts: IDBO algorithm module, fuzzy neural network module and PID controller module. The specific design is as follows:

[0116] (1) Device architecture design

[0117] The overall architecture of the fuzzy neural network PID controller based on IDBO optimization includes the following steps: first, the initial parameters of the PID controller are obtained by the ZN tuning method to meet the basic performance requirements of liquid level control; second, the initial parameters of the PID controller are globally optimized using the IDBO algorithm to obtain the optimal initial parameters; then, the fuzzy neural network dynamically adjusts the PID parameter increment according to the liquid level error and the error change rate, so that the controller can adapt to complex dynamic conditions; finally, the PID controller generates a control signal U(t) based on the optimized and dynamically adjusted parameters, which is used to drive the magnetic levitation pump to adjust the water supply flow rate, thereby achieving precise control of the liquid level.

[0118] (2) Fuzzy control rule design

[0119] The fuzzy control part is designed based on the liquid level error e and the error change rate ec. The fuzzy subsets of the input and output variables are defined as {NB, NM, NS, ZO, PS, PM, PB}, which represent large negative, medium negative, small negative, zero, small positive, medium positive, and large positive, respectively. The liquid level error represents the difference between the target liquid level and the actual liquid level, and the error change rate represents the changing trend of the liquid level error; the output is the dynamic adjustment amount (i.e., increment) of the PID parameter, corresponding to ΔK p , ΔK i , ΔK d The fuzzy rule base includes 49 control rules in the form of “IF-THEN” statements, such as “if e and ec then ΔK p , ΔK i andΔK d The rule base is obtained based on engineering experience and experimental debugging, and is used to describe the relationship between liquid level error and parameter adjustment.

[0120] (3) Fuzzy neural network structure design

[0121] Fuzzy neural network is used to realize online adjustment in PID controller, and its topology includes the following five layers:

[0122] The first layer is the input layer, which has two nodes, error and error change rate, which is used to convert the input vector x i =[x1,x2] T The components of are transmitted to the next layer. The input and output are:

[0123]

[0124]

[0125] In the formula, is the input value of the first layer node, is the output value of the first layer node.

[0126] The second layer is the fuzzification layer, which contains 2 inputs, each of which corresponds to 7 linguistic variable values. Its function is to calculate the membership function of the fuzzy set of each linguistic variable value to which each component of the input vector belongs, and map it to the fuzzy subset. The input and output are:

[0127]

[0128] In the formula, is the input value of the second layer node, is the output value of the second layer node, c ij is the central value of the membership function; σ ij is the width of the function curve, b ij is the shape parameter.

[0129] The third layer is the fuzzy reasoning layer. Each node of this layer represents a fuzzy rule in the fuzzy rule base. Its function is to calculate the fitness of each fuzzy rule. The input and output are:

[0130]

[0131] Where, l=1,2,…,49; i1=i2=1,2,…,7; is the input value of the third layer node; is the output value of the node in the third layer. The fourth layer is the normalization layer. The number of nodes in this layer is the same as that in the third layer. Its function is to realize the normalization operation on the output of the fuzzy inference layer. The input and output are:

[0132]

[0133] In the formula, is the input value of the 4th layer node; is the output value of the 4th layer node.

[0134] The fifth layer is the output layer, which performs weighted summation of the defuzzified output. Each node in this layer represents an output variable, and there are three nodes in total, namely, ΔK P , ΔK I , ΔK D The input and output are:

[0135]

[0136] Where k = 1, 2, 3; ω ij is the network weight of the output layer; is the input value of the 5th layer node; is the output value of the 5th layer node.

[0137] (4) Parameter Adaptive Adjustment

[0138] In order to further improve the adaptability of the controller under complex dynamic conditions, this paper designs a parameter adaptive adjustment mechanism based on error feedback. The specific method is as follows:

[0139] The membership function parameters of the fuzzy neural network are adjusted by error feedback to minimize the liquid level error. The objective function is defined as:

[0140]

[0141] Where r(t) is the desired liquid level of the given system, and y(t) is the actual liquid level of the system.

[0142] The gradient descent method is used to update the parameters of the fuzzy neural network, including the central parameter C of the membership function. ij , width parameter σ ij , and shape parameter w ij :

[0143]

[0144] Where n is the iteration step of the network; λ is the inertia coefficient, which is used to balance historical information and current updates; η is the learning rate, which controls the parameter update speed; Δc ij (n), Δσ ij (n), Δω ij (n) represent the change of each parameter, which is calculated based on the current error feedback.

[0145] S4. Liquid level control system simulation experiment and performance verification

[0146] In order to verify the performance of the fuzzy neural network PID control method based on the improved dung beetle algorithm (IDBO-FNN-PID) in the ozone dissolution tank level control system, a series of simulation experiments based on the MATLAB / Simulink platform were designed and carried out. The experimental contents include algorithm performance test, dynamic response test, anti-disturbance ability test and dynamic tracking ability test:

[0147] (1) Improved Dung Beetle Algorithm (IDBO) Performance Test

[0148] The performance of the improved IDBO algorithm was evaluated using standard test functions, and unimodal functions and multimodal functions were selected as test benchmarks. Each algorithm was run independently 50 times, with a population size of 30 and a maximum number of iterations of 500. The experimental results show that IDBO exhibits stronger global search capabilities and optimization accuracy in unimodal test functions, and higher local optimization capabilities and consistency in multimodal test functions. In addition, the IDBO algorithm converges significantly faster than other algorithms, and can quickly approach the theoretical optimal value in the initial stage while maintaining the smoothness of the convergence curve, showing the ability to jump out of the local optimum and higher optimization stability.

[0149] (2) Step response experiment

[0150] This experiment simulates the liquid level control process by step response and compares the performance of four control algorithms in terms of dynamic response performance. The experiment uses step signals as input to test the performance indicators of each control algorithm, such as overshoot, adjustment time and system response speed. The algorithm of the present invention (IDBO-FNN-PID) performs excellently in terms of dynamic performance, with an overshoot of only 2% and a system response time of 35 seconds. In contrast, the overshoot of traditional PID, fuzzy PID and fuzzy neural network PID are 17.6%, 12.6% and 7.7% respectively, and the adjustment time is 79 seconds, 70 seconds and 58 seconds respectively. Compared with other methods, the overshoot of IDBO-FNN-PID is reduced by 15.6%, 10.6% and 5.7% respectively, and the adjustment time is shortened by 55.7%, 50.0% and 39.7%. The experimental results show that the algorithm of the present invention shows significant advantages in response speed and overshoot suppression, and can improve the efficiency and stability of the liquid level control process of the ozone dissolution tank system.

[0151] (3) Anti-interference ability test

[0152] To verify the stability of the system under external disturbances, the experiment applied a disturbance signal with an amplitude of 0.2 and a duration of 7 seconds when the system ran for 100 seconds, simulating the impact of flow fluctuations on liquid level control in actual working conditions. The experiment compared the dynamic response performance of the four control algorithms under the action of disturbance signals.

[0153] The results show that the four control algorithms all have different degrees of overshoot under the action of disturbance signals, but this method (IDBO-FNN-PID) shows the best anti-disturbance ability. The overshoot after disturbance of this method is only 0.6%, which is 83.3%, 81.8% and 62.5% lower than that of traditional PID, fuzzy PID and fuzzy neural network PID respectively; the adjustment time is 31 seconds, which is 18.4%, 13.9% and 8.8% shorter than that of 38 seconds, 36 seconds and 34 seconds of other control methods respectively. The IDBO-FNN-PID control method can restore the system to a stable state in a shorter time, and the liquid level fluctuation amplitude is the smallest, which further demonstrates its excellent stability and rapid response ability.

[0154] (4) Dynamic signal tracking experiment

[0155] In order to verify the signal dynamic tracking performance of this method, a sinusoidal signal following experiment was designed. The dynamic response performance of four control algorithms in the sinusoidal signal following task was compared. The output of the traditional PID showed obvious hysteresis in the process of sinusoidal signal change, with large fluctuation amplitude and weak tracking ability; the fuzzy PID improved the tracking performance through fuzzy rules, but there was still a hysteresis problem in the stage of rapid signal change; the fuzzy neural network PID further improved the response ability of the system and reduced the phase lag, but there was still a slight tracking error in the high frequency band. This method (IDBO-FNN-PID) showed the best following performance, significantly reduced the phase lag and tracking error of the system, and the output trajectory was highly consistent with the target sinusoidal signal. The experimental results show that IDBO-FNN-PID can quickly and accurately track the dynamic input signal, the output signal waveform is smooth and stable, showing excellent real-time response ability and following accuracy, and provides a reliable solution for complex dynamic signal control tasks.

[0156] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A fuzzy neural network PID liquid level control method based on an improved dung beetle algorithm is characterized in that: The following steps are involved: S1. Establishment of mathematical model of liquid level control system of ozone dissolving tank In order to realize the control of the liquid level of the ozone dissolving tank, the liquid level control system of the ozone dissolving tank is modeled based on the principle of mass conservation, and combined with the actual operating characteristics of the liquid level control system of the ozone dissolving tank, it is simplified into a first-order inertial lag model. S2. Improved dung beetle algorithm design In order to improve the optimization accuracy and global search ability of the traditional dung beetle algorithm in the parameter optimization of complex liquid level control systems, the traditional dung beetle algorithm was improved, and an improved dung beetle algorithm based on ICMIC chaos initialization, reverse learning strategy and nonlinear dynamic adjustment mechanism was designed. S3. Design of fuzzy neural network PID controller In order to solve the problems of nonlinearity, dynamic hysteresis and insufficient anti-interference ability in the liquid level control system of the ozone dissolving tank, a fuzzy neural network PID controller based on the improved dung beetle algorithm was designed. S4. Simulation experiment and performance verification of the liquid level control system of the ozone dissolution tank In order to verify the performance of the improved dung beetle algorithm in the ozone dissolution tank level control system, a simulation experiment based on the MATLAB / Simulink platform was designed and carried out.

2. The fuzzy neural network PID liquid level control method based on the improved dung beetle algorithm according to claim 1 is characterized in that: In step S1, according to the law of conservation of mass, the dynamic rate of change of the liquid level in the tank can be expressed as the difference between the inflow rate and the outflow rate, that is: In the formula, A is the cross-sectional area of ​​the tank, h is the height of the liquid level at any time, Fi and Fo are the inflow and outflow flow rates respectively, and d is the differential sign; Combining the analogy between the liquid level system and the electrical system, the cross-sectional area A of the tank is replaced by the capacitance C, and we can get: The resistance R can be written as: The inflow flow rate Fi is proportional to the speed N of the magnetic levitation pump and can be expressed as: F i =kN At the same time, it is assumed that the speed N of the magnetic suspension pump is controlled by the control signal U, that is: N=K m U From this we can get: Perform a pull transformation and sort it out to get: Finally, the control signal U (s) With liquid level height H (s) The transfer function between: In the liquid level control process of the ozone dissolution tank, there is a certain response delay in the liquid level change caused by the liquid flow. The change of the inflow volume needs a delay time τ to have a significant impact on the liquid level in the tank. Its transfer function is expressed as: Where k is the system gain, K m is the motor gain, τ is the hysteresis time constant, R is the flow resistance, C is the equivalent capacitance, and according to the experimental measurement, k=6.35×10 -5 ,K m =600, R = 60, C = 2.59, τ = -7, after substituting the parameters into:

3. The fuzzy neural network PID liquid level control method based on the improved dung beetle algorithm according to claim 1 is characterized in that: In step S2, the specific improved design is as follows: (1) Introducing ICMIC chaos initialization and reverse learning strategy This paper proposes an improved method based on ICMIC chaotic mapping and reverse learning strategy to improve the diversity and coverage of the population initialization stage; First, the ICMIC chaotic map is used to generate the initial population solution; the mathematical expression of the ICMIC chaotic map is: In the formula, Z n is the chaotic variable of the current population, Z n+1 is the chaotic variable calculated in the next iteration, α chaos control parameter, with a value range of (0, 1); Secondly, based on the population solution generated by ICMIC, a reverse learning strategy is introduced to further expand the search space; the reverse learning strategy generates a reverse solution for each initial solution to increase population diversity, thereby improving the global search capability; the mathematical expression of the reverse learning strategy is: OZ i =K×(Z max +Z min )-Z i In the formula, OZ i is the value corresponding to each initial solution Z i The inverse solution of Z max and Z min Respectively represent the maximum and minimum values ​​in the initial solution; K is a random value in the range of (0,1); (2) Introducing ICMIC chaos initialization and reverse learning strategy In the traditional dung beetle algorithm, parameter R is an important dynamic adjustment factor that determines the search range of the population and directly affects the balance between global search and local development. The traditional dung beetle algorithm usually uses a linear decreasing strategy to update parameter R, and its calculation formula is: Among them, t represents the current number of iterations, and T represents the maximum number of iterations.

4. The fuzzy neural network PID liquid level control method based on the improved dung beetle algorithm according to claim 3 is characterized in that: In step S2, in order to further improve the optimization ability of the algorithm, the idea of ​​dynamic weight adjustment mechanism is borrowed to make nonlinear improvements to the calculation of parameter R so that it can adapt to the search requirements of different optimization stages; The improved nonlinear dynamic adjustment mechanism calculates the parameter R through the following formula: The nonlinear dynamic adjustment mechanism introduces logarithmic functions and nonlinear variation terms to keep the parameter R at a larger value in the early stage to enhance the global search capability. At the same time, it gradually reduces R in the later stage of iteration to improve the accuracy of local development, thereby achieving a dynamic balance between global search and local development.

5. The fuzzy neural network PID liquid level control method based on the improved dung beetle algorithm according to claim 1 is characterized in that: In step S3, a fuzzy neural network PID controller based on the improved dung beetle algorithm mainly includes three parts: IDBO algorithm module, fuzzy neural network module and PID controller module: (1) Controller design First, the PID controller proportional factor CK is adjusted by the improved dung beetle algorithm. p , CK i , CK d Perform global optimization and determine the initial parameter K based on the ZN tuning method and actual debugging results. p0 , K i0 , K d0 Get the optimal initial parameters; Then, the fuzzy neural network dynamically adjusts the PID parameter increment ΔK according to the liquid level error e and its change rate ec p , ΔK i , ΔK d ; Finally, the PID controller generates a control signal u(t) based on the real-time adjusted parameters, drives the magnetic suspension pump to adjust the water supply flow rate, and thus achieves stable control of the liquid level; (2) Fuzzy control reasoning This paper designs fuzzy control rules based on liquid level error e and error change rate ec, a total of 49 rules, which are used to dynamically adjust the PID control parameter ΔK p , ΔK i , ΔK d ; Input variables and output variables use 7 fuzzy subsets {NB, NM, NS, ZO, PS, PM, PB}; (3) Fuzzy Neural Network The topological structure of the fuzzy neural network includes the input layer, fuzzification layer, fuzzy reasoning layer, normalization layer and output layer. In the fuzzy neural network PID controller, the input signals e and ec are processed in each layer in turn, and finally the three adjustable parameters ΔK of the PID controller are generated in the output layer. p , ΔK i , ΔK d ; The first layer is the input layer, which has two nodes, error and error change rate, which is used to convert the input vector x i =[x1,x2] T The components of are transmitted to the next layer; the input and output are: In the formula, is the input value of the first layer node, is the output value of the first layer node; The second layer is the fuzzification layer, which contains 2 inputs, each of which corresponds to 7 linguistic variable values. Its function is to calculate the membership function of the fuzzy set of each linguistic variable value to which each component of the input vector belongs, and map it to the fuzzy subset. The input and output are: In the formula, is the input value of the second layer node, is the output value of the second layer node, c ij is the central value of the membership function; σ ij is the width of the function curve, b ij is the shape parameter; The third layer is the fuzzy reasoning layer. Each node of the fuzzy reasoning layer represents a fuzzy rule in the fuzzy rule base. Its function is to calculate the fitness of each fuzzy rule. The input and output are: Where, l=1,2,…,49; i1=i2=1,2,…,7; is the input value of the third layer node; is the output value of the third layer node; the fourth layer is the normalization layer, the number of nodes in this layer is the same as the third layer, and its function is to realize the normalization operation on the output of the fuzzy reasoning layer; the input and output are: In the formula, is the input value of the 4th layer node; is the output value of the 4th layer node; The fifth layer is the output layer, which performs weighted summation of the defuzzified output. Each node in the output layer represents an output variable, and there are three nodes in total, namely, ΔK P , ΔK I , ΔK D ; Input and output are: Where k = 1, 2, 3; ω ij is the network weight of the output layer; is the input value of the 5th layer node; is the output value of the 5th layer node; (4) Parameter Adaptive Adjustment The fuzzy neural network PID controller is completed through forward propagation calculation and outputs ΔK p , ΔK i , ΔK d ; The parameter change acts on the actuator through the PID controller to further adjust the system output; By comparing with the target value y(t), if the error does not meet the target requirement, the parameter adaptive adjustment process is entered; The parameter adaptive adjustment process adjusts the central parameter C of the membership function in the fuzzy neural network through the error signal ij , width parameter σ ij , and the membership shape parameter w ij , so that the error signal is reduced, and the objective function of error correction is defined as: In the formula, r(t) is the expected liquid level of the given system, and y(t) is the actual liquid level of the system; In order to minimize the objective function E, the fuzzification layer parameters are dynamically adjusted based on error feedback, including the center, width and shape parameters of the membership function; the iterative update formula of each parameter is as follows: Where n is the iteration step of the network; λ is the inertia coefficient, which is used to balance historical information and current updates; η is the learning rate, which controls the parameter update speed; Δc ij (n), Δσ ij (n), Δω ij (n) represent the change of each parameter, which is calculated based on the current error feedback.

6. The fuzzy neural network PID liquid level control method based on the improved dung beetle algorithm according to claim 1 is characterized in that: In step S4, the simulation experiment based on the MATLAB / Simulink platform includes the following parts: The performance of the improved dung beetle algorithm is evaluated by using standard unimodal functions and multimodal functions to test its global optimization capability and convergence speed, and verify its effectiveness as a controller parameter optimization tool; The improved dung beetle algorithm is compared and analyzed with other control algorithms to evaluate the dynamic response performance of each method in the liquid level control task, including response time, overshoot and steady-state error; The external disturbances of water supply and drainage flow fluctuations and motor speed disturbances were simulated to test the recovery time and liquid level stability of different control algorithms under disturbances, and to verify the anti-disturbance capability of the fuzzy neural network PID ozone dissolution tank liquid level control method based on the improved dung beetle algorithm; Through the sinusoidal signal following experiment, the response speed and following accuracy of each control algorithm in the dynamic input signal tracking task are tested, and its adaptability in complex dynamic working conditions is evaluated.

Images