ELM-based dual-parameter collaborative optimization chaos control method and device, and medium

Abstract

The invention relates to an ELM-based double-parameter collaborative optimization chaos control method, device and medium, and the method comprises the steps: firstly building a three-degree-of-freedom locomotive traction gear system dynamical model under the condition of cracks, then analyzing the chaos phenomenon generation condition, and designing a double-parameter collaborative chaos controller based on an ELM (extreme learning machine); parameters of the controller are optimized by using an ESS-SMA algorithm (a myxobacteria optimization algorithm based on an elite selection strategy). The chaos controller outputs small disturbance to be applied to controllable parameters of the system, so that the chaos phenomenon of the three-degree-of-freedom traction gear transmission system is rapidly controlled. According to the double-parameter cooperative intelligent optimization control strategy provided by the invention, the gear system can be rapidly controlled from chaotic motion to target periodic motion, the operability is high in the practical engineering problem, and meanwhile, the dependence of controller design on human intervention is reduced.

Description

Technical Field

[0001] The present invention relates to the field of gear system chaos control, and in particular to a dual-parameter collaborative optimization chaos control method, device and medium based on ELM (extreme learning machine). Background Art

[0002] With the rapid economic growth and the improvement of people's living standards, the society's demand for fast, safe and comfortable railway transportation is growing. Railway transportation is bound to bear huge pressure. Therefore, the research on various parts of the locomotive has become very important. The gear system is one of the most important structures on the locomotive. It maintains a high-speed and heavy-load operation state for a long time, and its operation state is affected by many factors. To ensure the normal operation of the locomotive, the good state of the gear system is a prerequisite. Therefore, it is of great significance to study the locomotive gear system. Tooth root cracks are a major hidden danger in the operation of locomotive gears. The appearance of tooth root cracks will cause abnormal vibrations in the system, such as chaotic vibrations, affecting the dynamic characteristics of the locomotive traction drive system during service. Chaos control is an effective measure to suppress the adverse effects of chaotic motion on the system's operating performance. Therefore, the dynamic analysis and chaos control research of cracked gear systems has important theoretical significance and engineering application value.

[0003] At present, there are relatively few studies on the dynamics and control of traction gear systems. At present, there are still few studies on the introduction of intelligent control methods and intelligent optimization algorithms into chaos control, and the control methods are mainly based on the single parameter feedback principle. However, the rich and complex motion properties of traction gear systems (such as bifurcation, chaos, etc.) are often the result of multi-parameter coupling. The control method based on the single parameter feedback principle does not fully consider the impact of the nonlinear coupling relationship between parameters on the changes in the system's dynamic properties, and it is often difficult to obtain the desired control results. In addition, according to previous studies, it is known that the traction gear system is difficult to accurately model due to the complex service environment, and chaos is also difficult to predict in the long term. This makes the chaos control of the traction gear system not only require the controller design to get rid of the dependence on the precise mathematical model of the controlled system, but also requires the controller to have the ability of self-learning and self-adaptation. Summary of the invention

[0004] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and to provide a dual-parameter collaborative optimization chaos control method, equipment, and medium based on ELM. Through dual-parameter collaborative intelligent optimization control, the gear system can quickly control from chaotic motion to target periodic motion.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] In one aspect of the present invention, a dual-parameter collaborative optimization chaos control method based on ELM is provided, wherein the meshing frequency and meshing damping adjustment of the controlled gear transmission system are calculated by using the ELM-based chaos controller after parameter optimization, so as to realize dual-parameter collaborative optimization chaos control, wherein the acquisition process of the chaos controller comprises the following steps:

[0007] Construct a tooth root crack model and solve the time-varying mesh stiffness;

[0008] Based on the time-varying meshing stiffness, a dynamic model of the controlled gear transmission system including tooth root cracks is constructed to solve the dynamic evolution law of the system and the distribution law of interval vibration amplitude;

[0009] Taking the distance between two adjacent projection points on the Poincaré section as input and the control target of controlling the chaotic motion into a regular periodic motion and reducing the relative torsional vibration of the gear pair, a chaos controller based on ELM and a fitness function are constructed.

[0010] Based on the fitness function, the parameters of the chaos controller are optimized using a slime mold optimization algorithm based on an elite selection strategy.

[0011] As a preferred technical solution, in the tooth root crack model, the crack extends along the tooth width and the gear center direction at the same time.

[0012] As a preferred technical solution, under the premise of considering friction, tooth side clearance, time-varying meshing stiffness and comprehensive meshing error, a dynamic model of the controlled gear transmission system is constructed and the dynamic equations are solved.

[0013] As a preferred technical solution, the process of solving the system period and chaotic motion conditions includes the following steps:

[0014] By constructing a dual-parameter plane with meshing frequency and meshing damping as parameters, the maximum Lyapunov index diagram and the maximum torsional displacement amplitude cloud diagram in the dual-parameter plane are obtained, and the dynamic evolution law and the distribution law of vibration amplitude in different parameter intervals are obtained.

[0015] As a preferred technical solution, the ELM-based chaos controller includes an input layer, a hidden layer and an output layer connected in sequence, wherein the input layer is the distance between two adjacent projection points on the Poincaré section, the hidden layer is a radial basis kernel function, and the output layer is the adjustment amount of the meshing frequency and meshing damping of the controlled gear transmission system.

[0016] As a preferred technical solution, the fitness function is:

[0017]

[0018] Among them, α i (i=1,2,3) is the relative weight; ||X(k)-X(k-1)|| is the distance between two adjacent iterative projection points on the Poincaré section, d * is the expected value of the distance between two adjacent points on the Poincaré section, γ is a random number in the interval (0,1], u(k) is the output of the chaos controller, It is the coefficient representing the relative torsional vibration degree of the gear pair.

[0019] As a preferred technical solution, the process of optimizing the parameters of the chaos controller using the slime mold optimization algorithm based on the elite selection strategy includes the following steps:

[0020] Based on the fitness function, the fitness of the slime mold at the initial position is calculated, the position of the slime mold is updated by enhanced search, the fitness of the slime mold after enhanced search is calculated, and the slime mold is ranked based on the fitness, that is, if the fitness of the new individual position is less than the fitness of the original individual position, or the individual belongs to the elite subgroup of the last 1 / 3 of all individual rankings in the fitness ranking, the newly generated individual position replaces the original search slime mold individual position, and the above steps are repeated to achieve parameter optimization of the chaos controller.

[0021] As a preferred technical solution, the state equation of the kinetic model is:

[0022]

[0023] Among them, x 1 、x 3 、x 5 and x 2 、x 4 、x 6 Respectively represent the dimensionless displacement and velocity of the relative torsional vibration of the driving and driven gears and the gear pair, y g is the dynamic transmission error on the gear meshing line, and η is the crack degree characterization coefficient.

[0024] Another aspect of the present invention provides an electronic device, comprising: one or more processors and a memory, wherein the memory stores one or more programs, and the one or more programs include instructions for executing the aforementioned ELM-based dual-parameter collaborative optimization chaos control method.

[0025] Another aspect of the present invention provides a computer-readable storage medium, comprising one or more programs for execution by one or more processors of an electronic device, wherein the one or more programs include instructions for executing the aforementioned ELM-based dual-parameter collaborative optimization chaos control method.

[0026] Compared with the prior art, the present invention has at least one of the following beneficial effects:

[0027] (1) Strong operability: The present invention realizes control based on the dual-parameter coordination of ELM, does not rely on the precise mathematical model of the system, and only uses the system input / output data for controller design. It has strong operability in practical engineering problems and provides theoretical guidance and method reference for the chaos control of the traction gear system of rail transit.

[0028] (2) Fully consider the characteristics of gear meshing operation in practice: The present invention takes into account that it is almost impossible for the load distribution of the gear in the tooth width direction to be completely uniform. Therefore, based on the actual situation, a tooth root crack model is established in which the crack extends along both the tooth width and the center direction of the tooth. At the same time, the model also takes into account the changes in bending stiffness and shear stiffness during the meshing transmission process. By accurately modeling the time-varying meshing stiffness, the accuracy and effectiveness of chaos control are guaranteed.

[0029] (3) Good controller parameter optimization effect: The present invention uses a slime mold optimization algorithm based on an elite selection strategy to optimize the parameters of the chaos controller. The basic slime mold algorithm is improved by an elite selection strategy, which solves the problem that the slime mold algorithm is prone to fall into local optimality and has low convergence accuracy, thereby improving the optimization efficiency of the algorithm. Through simulation, under the guidance of the established fitness function, the controller parameters can be effectively and automatically adjusted.

[0030] (4) Good chaos control effect: The present invention takes into account that the current main control method is based on the feedback of system state variables and single parameter feedback. However, through dynamic analysis, it can be seen that the gear system is jointly affected by the coupling of multiple parameters. Under certain specific parameters, it is impossible to control the target periodic motion by relying solely on a single parameter control. To address the above problem, the present invention adopts dual-parameter collaborative control, which can improve the efficiency of the gear system from chaos control to periodic motion, and can control chaos to a parameter region with a smaller displacement amplitude. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a control system structure block diagram corresponding to the dual-parameter collaborative intelligent optimization chaos control method based on ELM in the embodiment;

[0032] Figure 2 is a schematic diagram of a tooth root crack model in an embodiment;

[0033] Figure 3 is a schematic diagram of a model of a three-degree-of-freedom gear transmission system with cracks in an embodiment;

[0034] Figure 4 It is a structural diagram of the ELM dual-parameter collaborative controller in the embodiment;

[0035] Figure 5This is a flow chart of optimizing a chaotic controller using an SMA algorithm based on an elite selection strategy in an embodiment;

[0036] Figure 6 It is a comparison chart of single and double parameter control results in the embodiment. DETAILED DESCRIPTION

[0037] 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 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 ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0038] Example 1

[0039] The three-degree-of-freedom gear system has an extremely complex dynamic response. Under certain conditions, it will exhibit chaotic behavior. The appearance of this chaotic oscillation behavior will destroy the performance of the gear system and affect the normal operation of the gear. See Figure 1 , this embodiment provides a dual-parameter collaborative optimization chaos control method based on ELM, taking a cracked traction gear system as the controlled object, obtaining the motion distribution diagram of the system in the dual-parameter plane, the dual-parameter Lyapunov index diagram and the maximum displacement amplitude cloud diagram, and analyzing the optimal way for the system to move from chaos to periodic motion from the parameter plane. On this basis, a control idea of ​​dual-parameter synergy for the gear system is provided to control the chaotic behavior of the system. In the controller design based on ELM (extreme learning machine), the distance between two adjacent projection points on the Poincaré section is selected as the input of the controller, and the slight adjustment amount of the system parameters is used as the output variable of the controller. Utilizing the strong nonlinear mapping characteristics of ELM, the comprehensive influence of the parameters of meshing frequency and damping on the dynamic behavior of the system is reflected in the controller output variable, and the ESS-SMA (i.e. slime mold optimization based on elite selection strategy) algorithm is provided to optimize the controller parameters to realize the transmission of chaotic motion to expected periodic motion. The following will describe each part of the scheme in detail.

[0040] (1) Establishing the tooth root crack model and solving the time-varying mesh stiffness

[0041] In the actual gear meshing operation process, due to the influence of manufacturing, assembly errors, shaft misalignment, bearing deformation and other complex factors, it is almost impossible for the gear load distribution in the tooth width direction to be completely uniform. The tooth root crack model established is that it will extend along the tooth width and the gear center direction at the same time. Figure 2Schematic diagram of the crack extension direction and crack shape at the root of the gear tooth, where (a) is a schematic diagram of the gear tooth crack model, and (b) is a schematic diagram of the extension size along the A and B directions. c ,q c 、b c They represent the crack angle, crack depth and crack width respectively. The crack will extend in both directions A and B at the same time, that is, along the tooth width and the tooth center direction at the same time.

[0042] In order to accurately simulate the actual situation of gear meshing stiffness and damping changes, the following formula is used to solve the gear system meshing stiffness. The calculation method of the overall time-varying meshing stiffness of the gear is as follows:

[0043]

[0044] Among them, the Hertz contact stiffness K h , the axial compression stiffness K of the driving and driven gears a1 , K a2 , bending stiffness K b1 , K b2 , shear stiffness K s1 , K s2 , matrix deformation stiffness K f1 , K f2 (Subscripts 1 and 2 represent the driving and driven gears, respectively). For gears with root cracks, during the meshing transmission process, the Hertz contact stiffness, axial compression stiffness, and matrix deformation stiffness remain unchanged, and only the bending stiffness and shear stiffness will change. Under different conditions, the bending stiffness K of the gear teeth for the crack propagation method selected in this paper is bc and shear stiffness K sc The calculation formula is as follows:

[0045]

[0046] Where: E is the gear elastic modulus, L is the gear width, v is the Poisson's ratio, α 2 Related to the active and passive gears, it is half of the single tooth angle, α 1 is the gear meshing position related angle, α g for Figure 2 (a) The pressure angle corresponding to the contact point between the end of the crack and the gear tooth in the vertical direction. W is the crack extension depth along the tooth width. When the crack penetrates the entire tooth width, W = L, q 1 ,q 2 are the depths of the crack starting side and extension side along the tooth width, respectively; l is the distance between any point of the crack in the tooth width direction and the starting point.

[0047] (2) Establish the dynamic model and state equation of the gear transmission system containing slight cracks.

[0048] Figure 3 The parameters of the three-degree-of-freedom locomotive traction gear dynamic model with slight cracks are defined as follows: gears 1 and 2 are the master and driven gears respectively; T i (i=1,2) represents the torque acting on the driving and driven gears; y i ,θ i 、m i ,I i , R i 、c bi , k bi 、f bi 、F bi (i=1,2) represent the center displacement, torsional angular displacement, mass, moment of inertia, base circle radius of the master and slave wheels, as well as the damping, average stiffness, bearing clearance function and support force on the gear of the bearing support on the master and slave shafts respectively; c g 、b g , e(t), k g (t), L, f ui (t) represent meshing damping, gear tooth clearance, static transmission error, time-varying meshing stiffness, tooth width and time-varying friction coefficient respectively; α c ,q c 、b c They represent crack angle, crack depth and crack width respectively.

[0049] The state equation of the system is solved as follows:

[0050]

[0051] where x 1 、x 3 、x 5 and x 2 、x 4 、x 6 Respectively represent the dimensionless displacement and velocity of the relative torsional vibration of the driving and driven gears and the gear pair, y g is the dynamic transmission error on the gear meshing line, and η is the crack degree characterization coefficient.

[0052] (3) Analyze the chaotic motion in the gear system through dynamic analysis methods.

[0053] In order to deeply reveal the dynamic evolution law of the gear system, the meshing frequency ω and meshing damping ζ are selected as the research objects (i.e., dual-parameter coordinated control). When the meshing frequency ω and meshing damping ζ change simultaneously, the dynamic characteristics of the system on the ω-ζ parameter plane are considered. The average divergence or average convergence of the adjacent trajectories of the system is measured by drawing the maximum Lyapunov exponent diagram (Top Lyapunov Expo-nents, TLE) to describe the stability of the system's equilibrium point, periodic motion and quasi-periodic motion, and to quantitatively analyze the chaotic motion of the system. The maximum Lyapunov exponent is calculated by selecting the same parameters as those for analyzing the Poincare section. When TLE is less than zero, it is a stable periodic motion; when TLE is equal to zero, it is quasi-periodic or bifurcation; when TLE is greater than zero, it represents chaos. By drawing the maximum torsional displacement amplitude cloud map in the dual-parameter plane, the distribution of the maximum vibration amplitude of the system in different parameter regions is observed to avoid the high-amplitude parameter region, and the coupling effect on the system vibration amplitude under the influence of different parameters can also be calculated. Through the analysis of the main factors affecting the nonlinear dynamics of the gear system, it can be found that the reasonable selection of nonlinear parameter intervals can effectively reduce the probability of multi-period and chaos in the system. The appearance of these areas will cause noise, vibration and impact in the system, affecting the normal operation of the gear, so they must be controlled. At the same time, the low-amplitude area can be found according to the amplitude cloud map so as to control it to a periodic orbit with a lower amplitude.

[0054] This step analyzes the chaotic motion in the controlled gear system to find out the distribution area of ​​the system's chaotic motion as the object of chaos control.

[0055] (4) Design a chaos controller based on ELM.

[0056] Aiming at the chaotic motion in the gear system, a three-layer neural network chaos controller including input layer, hidden layer and output layer is designed to control the chaos. Figure 4 As shown. According to the chaotic motion control goal (controlling the chaotic motion into a regular periodic motion, and the relative torsional vibration of the gear pair is small), the distances d(k) and d(k-1) between two adjacent projection points on the Poincaré section are selected as the input of the controller, that is, d(k) = ||X(k)-X(k-1)||, d(k-1) = ||X(k-1)-X(k-2)||, where X(k) represents the value of the state variable of the controlled system at time k, that is, X = [x 5 ,x 6 ], the number of hidden layer nodes is selected as 5, and the Gaussian radial basis function is determined as the activation function of the neural network.

[0057]

[0058] The output of the controller is defined as the slight adjustment of the meshing frequency and damping of the gear system, that is,

[0059]

[0060] To maintain control effectiveness, set u max is the maximum disturbance, then -u max <u<u max .

[0061] (5) Construct fitness function.

[0062] Construct a weighted fitness function as follows:

[0063]

[0064] Among them, α i (i=1,2,3) is the relative weight; ||X(k)-X(k-1)|| is the distance between two adjacent iterative projection points on the Poincaré section, which reflects the distribution trend of the point set of the Poincaré section diagram; d * is the expected value of the distance between two adjacent points on the Poincaré section; γ is a random number in the interval (0,1]; u(k) is the controller output, which represents the control energy loss during control; It is the coefficient representing the relative torsional vibration degree of the gear pair.

[0065] (6) Optimize controller parameters using the SMA algorithm based on elite selection strategy.

[0066] In the slime mold algorithm, the slime mold i s According to the objective conditions of the current position (the quality of the fitness function), the weight of each individual's position is determined, and then the individual will update the position according to the weight. Drawing on the biological behavior of slime mold, three rules can be abstracted: approaching food, surrounding food, and grabbing food. The slime mold algorithm realizes the intelligent optimization function by simulating the predatory behavior of slime mold. In order to speed up the global optimization in the early stage, the position update formula is used Update the slime mold position. After the first position update, calculate the original position fitness, and then use the enhanced search formula Get the new position, and then calculate the fitness after the enhanced search update. After the enhanced search, the fitness is ranked, and the update formula is as follows: As shown, if the fitness value of the new individual position is less than the fitness value of the original individual position, or the elite subgroup whose fitness ranking is in the last 1 / 3 of all individual rankings is searched, the newly generated individual position will replace the original search slime mold individual position.

[0067] The slime mold algorithm uses weights to simulate the change in vein width and the fluctuation of the oscillator's oscillation frequency. When the food concentration is not high, it slowly approaches the food to expand the global search space. When high-quality food is identified, it quickly approaches the food to enhance the local search capability, calculate the fitness value, and update the global optimal solution Gbest. The ESS-SMA algorithm optimizes the controller process as follows: Figure 5 shown.

[0068] (7) Update and optimize the parameters of the ELM, and output the perturbation to the controlled system through the updated ELM chaos controller.

[0069] This example uses a dual-parameter motion distribution diagram to analyze the distribution area of ​​the system period and chaotic motion, and uses an amplitude cloud diagram to analyze the parameter range of low-amplitude periodic motion. Based on this, dual-parameter collaborative intelligent optimization control is used to achieve rapid response of the system from chaotic control to low-amplitude periodic motion by adjusting dual parameters at the same time. It can be seen from simulation experiments that compared with traditional single-parameter control, the method proposed in this embodiment can make the system quickly stabilize to a periodic orbit, and the amplitude after control is small, such as Figure 6 shown.

[0070] In summary, this method takes the gear system as the controlled object, establishes a dynamic model of a three-degree-of-freedom gear transmission system with slight pitting, and reveals the dynamic evolution mechanism of the system through numerical simulation. Considering the harm of chaotic motion to train safety, a chaotic motion control strategy based on ELM is provided. It can be seen from the simulation results that under the guidance of the established fitness function, the SMA algorithm can effectively and automatically adjust the controller parameters. The ELM adaptive collaborative adjustment parameters optimized by the SMA algorithm improve the performance of the controller. The control method proposed in the present invention does not rely on the precise mathematical model of the system, and only uses the system input / output data for controller design. It has strong operability in practical engineering problems and provides theoretical guidance for the chaos control of the traction gear system of rail transit. The present invention gives full play to the advantages of neural network control that it does not rely on the precise mathematical model of the controlled system and has self-learning and adaptive capabilities, as well as the advantages of dual-parameter collaborative control in tracking the changes in the dynamic characteristics of the system compared to single-parameter control, and can achieve the expected control effect. The present invention is very important for the development of the research on the theory and method of chaos control of gear systems.

[0071] Example 2

[0072] This embodiment provides an electronic device, including: one or more processors and a memory, wherein the memory stores one or more programs, and the one or more programs include instructions for executing the dual-parameter collaborative optimization chaos control method based on ELM as described in Example 1.

[0073] Example 3

[0074] This embodiment provides a computer-readable storage medium, including one or more programs for execution by one or more processors of an electronic device, wherein the one or more programs include instructions for executing the dual-parameter collaborative optimization chaos control method based on ELM as described in Example 1.

[0075] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A dual-parameter collaborative optimization chaos control method based on ELM, characterized in that: The meshing frequency and meshing damping adjustment of the controlled gear transmission system are calculated by using the ELM-based chaos controller after parameter optimization to realize dual-parameter collaborative optimization chaos control, wherein the acquisition process of the chaos controller includes the following steps: Construct a tooth root crack model and solve the time-varying mesh stiffness; Based on the time-varying meshing stiffness, a dynamic model of the controlled gear transmission system including tooth root cracks is constructed to solve the dynamic evolution law of the system and the distribution law of interval vibration amplitude; Taking the distance between two adjacent projection points on the Poincaré section as input and the control target of controlling the chaotic motion into a regular periodic motion and reducing the relative torsional vibration of the gear pair, a chaos controller based on ELM and a fitness function are constructed. Based on the fitness function, the parameters of the chaos controller are optimized using a slime mold optimization algorithm based on an elite selection strategy.

2. The method of chaos control based on ELM dual-parameter collaborative optimization according to claim 1 is characterized in that: In the tooth root crack model, the crack extends along the tooth width and the gear center direction at the same time.

3. The dual-parameter collaborative optimization chaos control method based on ELM according to claim 1 is characterized in that: Under the premise of considering friction, tooth side clearance, time-varying meshing stiffness and comprehensive meshing error, a dynamic model of the controlled gear transmission system is constructed and the dynamic equations are solved.

4. The dual-parameter collaborative optimization chaos control method based on ELM according to claim 1 is characterized in that: The process of solving the system period and chaotic motion conditions includes the following steps: By constructing a dual-parameter plane with meshing frequency and meshing damping as parameters, the maximum Lyapunov index diagram and the maximum torsional displacement amplitude cloud diagram in the dual-parameter plane are obtained, and the dynamic evolution law and the distribution law of vibration amplitude in different parameter intervals are obtained.

5. The dual-parameter collaborative optimization chaos control method based on ELM according to claim 1 is characterized in that: The ELM-based chaos controller includes an input layer, a hidden layer and an output layer connected in sequence, wherein the input layer is the distance between two adjacent projection points on the Poincaré section, the hidden layer is a radial basis kernel function, and the output layer is the adjustment amount of the meshing frequency and meshing damping of the controlled gear transmission system.

6. The ELM-based dual-parameter collaborative optimization chaos control method according to claim 1 is characterized in that: The fitness function is: Among them, α i (i=1,2,3) is the relative weight; ||X(k)-X(k-1)|| is the distance between two adjacent iterative projection points on the Poincaré section, d * is the expected value of the distance between two adjacent points on the Poincaré section, γ is a random number in the interval (0,1], u(k) is the output of the chaos controller, It is the coefficient representing the relative torsional vibration degree of the gear pair.

7. The dual-parameter collaborative optimization chaos control method based on ELM according to claim 1 is characterized in that: The process of optimizing the parameters of the chaos controller using the slime mold optimization algorithm based on the elite selection strategy comprises the following steps: Based on the fitness function, the fitness of the slime mold at the initial position is calculated, the position of the slime mold is updated by enhanced search, the fitness of the slime mold after enhanced search is calculated, and the slime mold is ranked based on the fitness, that is, if the fitness of the new individual position is less than the fitness of the original individual position, or the individual belongs to the elite subgroup of the last 1 / 3 of all individual rankings in the fitness ranking, the newly generated individual position replaces the original search slime mold individual position, and the above steps are repeated to achieve parameter optimization of the chaos controller.

8. The ELM-based dual-parameter collaborative optimization chaos control method according to claim 1 is characterized in that: The state equation of the kinetic model is: Among them, x1, x3, x5 and x2, x4, x6 represent the dimensionless displacement and velocity of the relative torsional vibration of the driving and driven gears and the gear pair, respectively, and y g is the dynamic transmission error on the gear meshing line, and η is the crack degree characterization coefficient.

9. An electronic device, characterized in that: include: One or more processors and a memory, wherein the memory stores one or more programs, and the one or more programs include instructions for executing the ELM-based dual-parameter collaborative optimization chaos control method as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that: It includes one or more programs for execution by one or more processors of an electronic device, and the one or more programs include instructions for executing the ELM-based dual-parameter collaborative optimization chaos control method as described in any one of claims 1-8.

Images