Rolling bearing early fault feature extraction method based on CHHO-VMD

Abstract

The invention discloses a CHHO-VMD-based rolling bearing early fault feature extraction method. The method comprises the following steps of obtaining an original vibration signal of a bearing; identifying an early fault signal in the original vibration signal; the CHHO algorithm is applied to adaptively optimize VMD parameters, and an optimal parameter combination [K, alpha] is generated; decomposing the fault signal by using the parameter-optimized VMD, and extracting an IMF component of the fault signal; selecting an IMF component to reconstruct a fault signal based on the kurtosis and the correlation coefficient; and extracting the fault characteristic frequency of the rolling bearing by using envelope demodulation. The method has the beneficial effects that the CHHO algorithm is introduced to adaptively determine the optimal parameter combination of the VMD, the problems of modal component loss and modal aliasing caused by manual parameter selection and incorrect setting are avoided, the fault feature frequency of the rolling bearing early fault signal is effectively extracted by combining the CHHO and the VMD, and the accuracy and timeliness of fault detection are high.

Description

Technical Field

[0001] The invention relates to a bearing fault detection technology, in particular to a rolling bearing early fault feature extraction method based on CHHO-VMD. Background Art

[0002] As a basic component of large industrial rotating machinery, rolling bearings are crucial to improving the efficiency of mechanical systems, and their condition directly affects the stable operation of the equipment. Variational mode decomposition (VMD) is based on a rigorous mathematical model and exhibits strong noise robustness. It can effectively extract signal components and is widely used for rolling bearing fault feature extraction. However, VMD is sensitive to parameter selection, especially the number of modes K and the penalty factor α. Improper selection can lead to over-decomposition or under-decomposition. Therefore, many scholars at home and abroad have introduced intelligent optimization algorithms to adaptively search for the optimal values ​​of K and α, such as the beetle antenna search (BAS) algorithm, genetic mutation particle swarm optimization, and variational mode decomposition (GM-PSO) algorithm.

[0003] Although the traditional intelligent optimization algorithm can effectively optimize VMD parameters, it still faces problems such as long calculation time and weak early fault features that are difficult to extract. Therefore, there is an urgent need for a technology that can adaptively optimize VMD parameters and quickly and effectively extract the weak features of early rolling bearing faults to improve the accuracy and timeliness of fault detection. Summary of the invention

[0004] The purpose of the present invention is to provide a rolling bearing early fault feature extraction method based on CHHO-VMD, which has the advantages of efficient and accurate fault detection.

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

[0006] The method for extracting early fault features of rolling bearings based on CHHO-VMD includes the following steps:

[0007] S1, obtaining the original vibration signal of the bearing;

[0008] S2, identifying early fault signals in the original vibration signal;

[0009] S3, using CHHO algorithm to adaptively optimize VMD parameters and generate the best parameter combination [K, α];

[0010] S4. Decompose the fault signal using parameter-optimized VMD to extract its IMF (intrinsic mode function) component;

[0011] S5, selecting IMF components based on kurtosis and correlation coefficient to reconstruct fault signals;

[0012] S6. Apply envelope demodulation to extract the fault characteristic frequency of the rolling bearing.

[0013] Furthermore, in step S3, the CHHO algorithm introduces a chaotic map as the initial energy E 0 Generate chaotic values ​​to help the algorithm break the fixed search mode during the exploration phase; introduce exponential decreasing factors to dynamically adjust algorithm parameters to improve the balance between exploration and development; introduce Gaussian mutation to increase population diversity and prevent the algorithm from falling into local optimality.

[0014] Furthermore, the chaotic mapping is conducive to the optimization algorithm to maintain population diversity, so that they can get rid of local optimality and improve global search performance. The expression is as follows:

[0015] x n+1 =ux n (1-x n ), u∈[0,4], x n ∈(0, 1)

[0016] Among them, x n represents the proportion of the population at the nth moment to the maximum possible population size, x n+1 represents the population ratio at the n+1th moment, x is a random number between 0 and 1, and u represents the control parameter, which determines the behavior of the chaotic mapping;

[0017] The exponential reduction factor refers to a parameter that is gradually reduced in a nonlinear way during the iteration process. The purpose is to gradually reduce the global search capability as the iteration proceeds, while enhancing the local search capability to improve the convergence performance of the algorithm and the quality of the solution;

[0018] The Gaussian mutation is an improvement on the genetic algorithm, which aims to use the mean μ and variance σ in the mutation operation. 2 The random number drawn from the normal distribution replaces the original parameter value. The expression is as follows:

[0019] X mutated (t+1)=X(t)(1+N(μ,σ 2 ))

[0020] Among them, X mutated (t+1) represents the position of the individual after the mutation, X(t) represents the position of the individual before the mutation, N represents the mean μ and the variance σ 2 Gaussian distribution.

[0021] Furthermore, the chaotic map is introduced to generate the chaotic value for the initial energy. The chaotic map is used to generate the initial energy E of the eagle. 0 Generate chaotic values ​​to give the algorithm chaos to help break the fixed search mode in the global search phase. The update formula of the initial energy is as follows:

[0022] E 0 =x n+1 =ux n (1-x n ), x n ∈(0, 1)

[0023] The update formula of escape energy is as follows:

[0024]

[0025] Among them, sign is a random value of -1 or 1, t represents the current number of iterations, and T represents the maximum number of iterations.

[0026] Furthermore, the exponential decay factor is used to dynamically adjust the algorithm parameters to improve the balance between the exploration and development stages. The exponential decay weight is calculated as follows:

[0027] ω i =e -λ·i

[0028] Among them, ω i is the weight of the i-th data point, λ is the decay coefficient, and i is the time interval.

[0029] Furthermore, Gaussian variation is randomly applied to some individuals to cause slight movement of their positions, enhance the diversity of the population, and avoid falling into the local optimum. The population position update formula is as follows:

[0030]

[0031] Among them, rand is a random number between 0 and 1, p represents the mutation probability, X(t) represents the current population position, X(t+1) represents the population position after iteration, and f(.) represents the fitness function.

[0032] Furthermore, the S3 step specifically includes the following steps:

[0033] Step 1, setting the initial parameters of the CHHO algorithm;

[0034] Step 2, decomposing the early fault signal through VMD;

[0035] Step 3, identify the optimal individual;

[0036] Step 4, restore the prey's escape energy;

[0037] Step 5, determine whether the escape energy is less than or equal to 1. If it is less than or equal to 1, it enters the development stage; if it is greater than 1, it enters the exploration stage;

[0038] Step 6, determine whether the maximum number of iterations has been reached;

[0039] Step 7: If the maximum number of iterations is reached, output K and α; if the maximum number of iterations is not reached, repeat steps 2 to 6.

[0040] Furthermore, in step S3, the average minimum energy entropy is used as the iteration index in the optimization process, and the calculation formula is as follows:

[0041]

[0042] Among them, u k is the kth IMF component, H mean (u k ) is the component u k The average energy entropy of k represents the kth component u k The proportion of total energy, E k is the energy of each component, E is the sum of the energies of K components, E i is the energy of the ith component.

[0043] Furthermore, in step S5, the kurtosis calculation formula is as follows:

[0044]

[0045] Where μ and σ represent the mean and standard deviation of the signal, respectively, E(·) is the expected value of the signal, and x represents the value of the signal;

[0046] The calculation formula of the correlation coefficient is as follows:

[0047]

[0048] Among them, θ i represents the value of the i-th data point in the IMF component, represents the mean of the IMF component, δ i represents the value of the i-th data point in the original signal, Represents the average value of the original signal.

[0049] The present invention has the following advantages:

[0050] 1. The CHHO algorithm is introduced to adaptively determine the optimal parameter combination of VMD, avoiding the modal component loss and modal aliasing problems caused by manual parameter selection and incorrect settings. By combining CHHO and VMD, the fault characteristic frequency of the early fault signal of the rolling bearing can be effectively extracted, and the accuracy and timeliness of fault detection are high.

[0051] 2. By introducing chaotic mapping to give the algorithm chaos, the algorithm is helped to break the fixed exploration mode during global exploration. The nonlinear decreasing factor is introduced to dynamically adjust the algorithm parameters, which improves the balance between exploration and development. The introduction of Gaussian mutation can effectively prevent the algorithm from falling into the local optimum. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a flow chart of the present invention.

[0053] Figure 2 This is a life graph of the outer ring rolling bearing with the mean square value as the performance indicator.

[0054] Figure 3 The graph shows the change of escape energy E during two runs and 500 iterations of the HHO algorithm.

[0055] Figure 4 The graph shows the change of the escape energy E during two runs and 500 iterations of the CHHO algorithm.

[0056] Figure 5 It is a convergence curve of the average energy entropy relative to the number of iterations during the VMD parameter optimization process.

[0057] Figure 6 In order to obtain the optimal parameter combination after CHHO optimization, the time domain diagram of each IMF component obtained by VMD decomposition of the rolling bearing vibration signal using the optimal parameters.

[0058] Figure 7 In order to obtain the optimal parameter combination after CHHO optimization, the optimal parameters are used to perform VMD decomposition on the rolling bearing vibration signal to obtain the spectrum of each IMF component.

[0059] Figure 8 It is the envelope spectrum diagram after reconstructing IMF1 and IMF2. DETAILED DESCRIPTION

[0060] 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.

[0061] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0063] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0064] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inside", "outside", etc. indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, or the positions or positional relationships in which the product of the invention is usually placed when in use, or the positions or positional relationships commonly understood by those skilled in the art, which are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0065] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0066] refer to Figure 1-8 As shown, one embodiment of the present invention is:

[0067] The method for extracting early fault features of rolling bearings based on CHHO-VMD includes the following steps:

[0068] S1. Obtain the original vibration signal of the bearing.

[0069] This embodiment uses the bearing data set of the University of Cincinnati. The tested bearing is Rexnord ZA-2115, the sampling frequency is 20kHz, the rotation frequency is 33.3Hz, and the following Table 1 shows the detailed parameters of the bearing.

[0070] Table 1: Parameters of the tested bearings

[0071] parameter Numeric Pitch diameter 71.5mm Rolling element diameter 8.4mm Number of scroll elements per row 16 Contact Angle 15.17° Static load 26690N

[0072] The calculation formula for the fault characteristic frequency of inner and outer ring rolling bearings is as follows:

[0073]

[0074] Where N is the bearing rotation frequency, n is the number of rolling elements, d is the diameter of the rolling element, D is the average diameter of the bearing, and α is the contact angle of the bearing. Substituting the data in Table 1 into the calculation formula of the characteristic frequency of rolling bearing fault, the characteristic frequency of the inner ring fault is 297Hz and the characteristic frequency of the outer ring fault is 236Hz.

[0075] S2. Identify early fault signals in the original vibration signal.

[0076] In order to identify the early fault signal in the original bearing vibration data, the root mean square (RMS) value is used for analysis. 4000 (0.2fs) points of the original vibration signal constitute a sample, and the root mean square value of each sample is used as the ordinate and the sample number is used as the abscissa. The outer ring rolling bearing life graph is shown in the figure below. Figure 2 shown.

[0077] S3. Apply the CHHO algorithm to adaptively optimize VMD parameters and generate the best parameter combination [K, α].

[0078] The HHO algorithm divides the eagle's hunting behavior into three stages: global exploration, transition from global exploration to local exploitation, and local exploitation, during which four distinct hunting strategies are demonstrated. The CHHO algorithm optimizes the HHO by introducing chaotic mapping, exponential decreasing factor, and Gaussian mutation.

[0079] Global exploration phase: In the HHO algorithm, each Harris hawk is considered as a candidate solution, and in each iteration, the optimal solution is considered as the target prey location. Harris hawks randomly perch in different locations, waiting to locate prey using two different strategies. The position of Harris hawks at this stage is updated as follows:

[0080]

[0081] Among them, X(t+1) represents the position of Harris Hawk after the tth update, X rand (t) represents the position of a random individual in the eagle group, Xrabbit (t) represents the position of the current optimal individual, X m (t) represents the average energy of the current Harris Hawk population, ub and lb represent the upper and lower bounds of the search space, respectively, and r 1 , r 2 , r 3 , r 4 and q are random numbers in the range (0, 1), r 3 is the shrinkage coefficient, which enhances the randomness of the rule, r 4 is a value assumed to be close to 1. When q ≥ 0.5, the eagles randomly roost in tall trees (random locations within the population), and when q < 0.5, each eagle moves according to the locations of other members and prey.

[0082] Transition from global exploration to local exploitation: Transition from exploration to exploitation Based on the remaining escape energy of the prey, the HHO algorithm transitions from global exploration to local exploitation. When the prey tries to escape, its energy will be consumed greatly. Let E denote the escape energy of the prey, E 0 Indicates that its initial energy state changes randomly within the range of (-1, 1). The specific formula describing this phenomenon is as follows:

[0083]

[0084] Among them, t represents the current iteration number, and T represents the maximum iteration number.

[0085] Development phase: In the development phase, the algorithm randomly generates a number between 0 and 1. The value of r and the parameter E together determine the position update mechanism of the Harris Hawk. This update process is divided into four different methods, which are as follows:

[0086] 1) When r ≥ 0.5 and |E| ≥ 0.5, the position update formula of Harris Hawk is:

[0087] X(t+1)=X rabbit (t)-X(t)-E|JX rabbit (t)-X(t)|

[0088] Where J is a random number in the interval (0, 2), X rabbit (t) represents the position of the current optimal individual, and X(t) represents the current position of the eagle.

[0089] 2) When r ≥ 0.5 and |E| < 0.5, the position update formula of Harris Hawk is:

[0090] X(t+1)=X rabbit (t)-E|X rabbit -X(t)|

[0091] 3) When r < 0.5 and |E| ≥ 0.5, the position update formula of Harris Hawk is:

[0092]

[0093] Where D represents the dimension, S is a random vector of D dimension, LF is the expression of Levy flight function, μ and v are random values ​​in the interval (0, 1), β is a constant with a value of 1.5, F(.) is the fitness function, σ represents the scale factor used to control the size of Levy flight step, and Γ(.) represents the gamma function.

[0094] 4) When r < 0.5 and |E| < 0.5, the position update formula of Harris Hawk is:

[0095]

[0096] According to the escape energy E of the prey and the random factors q and r, the HHO algorithm develops a variety of position update strategies, and finally finds the optimal solution in the search space by repeatedly adjusting the position of the eagle.

[0097] HHO mainly changes the escape energy factor through linear decay, which will lead to an imbalance between exploration and development, and cannot accurately represent the actual multiple rounds of hunting and escape between the eagle and the prey. Because |E| must be less than 1 in the later iterations, only local search is performed, so the search is not global. If the initial population is close to the local optimum, it may cause the algorithm to fall into the local optimum in the later stage and cannot escape. The nonlinear decay method can be used to dynamically adjust the algorithm parameters. Therefore, the present invention adopts chaotic mapping to update the initial escape energy E 0 , helping the algorithm to break the fixed search pattern during the exploration phase.

[0098] Chaotic mapping helps optimization algorithms maintain population diversity, enabling them to escape local optimality and improve global search performance. The expression is as follows:

[0099] x n+1 =un n (1-x n ), u∈[0,4], x n ∈(0, 1)

[0100] Among them, x n represents the proportion of the population at the nth moment to the maximum possible population size, x n+1 represents the population proportion at the n+1th moment, x is a random number between 0 and 1, and u represents the control parameter, which determines the behavior of the chaotic mapping.

[0101] Chaos mapping is used to calculate the initial energy E of the eagle 0Generate chaotic values ​​to give the algorithm chaos to help break the fixed search mode in the global search phase. The update formula of the initial energy is as follows:

[0102] E 0 =x n+1 =ux n (1-x n ), x n ∈(0, 1)

[0103] The update formula of escape energy is as follows:

[0104]

[0105] Among them, sign is a random value of -1 or 1, t represents the current number of iterations, and T represents the maximum number of iterations.

[0106] The variation of the escape energy E with the number of iterations in the two runs of the HHO algorithm is as follows: Figure 3 As shown in the figure, the variation of the escape energy E with the number of iterations in the two runs of the CHHO algorithm is as follows: Figure 4 As shown in Figure 2, in the subsequent iterations of the CHHO algorithm, the value |E| fluctuates around 1 instead of being strictly maintained below 1, achieving a balanced transition between exploration and exploitation.

[0107] At the same time, the present invention uses an exponential decay factor for updating, and dynamically adjusts the algorithm parameters by introducing an exponential decreasing factor to improve the balance between exploration and development, thereby ensuring sufficient population diversity in the global exploration stage. The exponential decreasing factor refers to a parameter that is gradually reduced in a nonlinear manner during the iteration process, with the purpose of gradually reducing the global search capability as the iteration proceeds, while enhancing the local search capability, so as to improve the convergence performance of the algorithm and the quality of the solution.

[0108] The exponential decay weight is calculated as follows:

[0109] ω i =e -λ·i

[0110] Among them, ω i is the weight of the i-th data point, λ is the decay coefficient, and i is the time interval.

[0111] Furthermore, the present invention also increases population diversity by introducing Gaussian mutation to prevent the algorithm from falling into local optimum. Gaussian mutation is an improvement on genetic algorithm, which aims to use the mean μ and variance σ in the mutation operation process. 2 The random number drawn from the normal distribution replaces the original parameter value. The expression is as follows:

[0112] X mutated (t+1)=X(t)(1+N(μ,σ2))

[0113] Among them, X mutated (t+1) represents the position of the individual after the mutation, X(t) represents the position of the individual before the mutation, N represents the mean μ and the variance σ 2 Gaussian distribution.

[0114] Gaussian variation is randomly applied to some individuals to cause slight movement of their positions, enhance the diversity of the population, and avoid falling into local optimality. The population position update formula is as follows:

[0115]

[0116] Among them, rand is a random number between 0 and 1, p represents the mutation probability, X(t) represents the current population position, X(t+1) represents the population position after iteration, and f(.) represents the fitness function.

[0117] In implementation, the process of applying the CHHO algorithm to determine the optimal parameter combination of the number of modes and penalty factors of VMD includes the following steps:

[0118] Step 1, setting the initial parameters of the CHHO algorithm;

[0119] Step 2, decomposing the early fault signal through VMD;

[0120] Step 3, identify the optimal individual;

[0121] Step 4, restore the prey's escape energy;

[0122] Step 5, determine whether the escape energy is less than or equal to 1. If it is less than or equal to 1, it enters the development stage; if it is greater than 1, it enters the exploration stage;

[0123] Step 6, determine whether the maximum number of iterations has been reached;

[0124] Step 7: If the maximum number of iterations is reached, output K and α; if the maximum number of iterations is not reached, repeat steps 2 to 6.

[0125] The smaller energy entropy in the bearing signal containing the fault indicates that the vibration or impact signal caused by the fault is significant and concentrated, resulting in the enhancement of the periodic signal, making the fault characteristics more obvious. Therefore, the present invention adopts the average minimum energy entropy as the iterative indicator in the optimization process, and the calculation formula is as follows:

[0126]

[0127] Among them, u k is the kth IMF component, H mean (u k ) is the component u k The average energy entropy ofk represents the kth component u k The proportion of total energy, E k is the energy of each component, E is the sum of the energies of K components, E i is the energy of the ith component.

[0128] The CHHO-VMD algorithm is used to extract early fault features from the vibration signal of the outer ring rolling bearing. During the VMD parameter optimization process, the convergence curve of the average energy entropy relative to the number of iterations is shown in the figure. Figure 5 shown.

[0129] After CHHO optimization, the best parameter combination [k, α] is [3, 400], which makes the minimum average energy entropy 7.4027.

[0130] S4. Decompose the fault signal using the VMD with optimized parameters and extract its IMF components.

[0131] Using these optimal parameter combinations for VMD decomposition, the time domain diagram and spectrum diagram of the rolling bearing are obtained. The time domain diagram of the rolling bearing vibration signal decomposed by the CHHO-VMD algorithm is shown in the figure below: Figure 6 As shown, the spectrum diagram is Figure 7 shown.

[0132] S5. Select IMF components based on kurtosis and correlation coefficient to reconstruct the fault signal.

[0133] The kurtosis calculation formula is as follows:

[0134]

[0135] Where μ and σ represent the mean and standard deviation of the signal, respectively, E(·) is the expected value of the signal, and x represents the value of the signal;

[0136] The calculation formula of the correlation coefficient is as follows:

[0137]

[0138] Among them, θ i represents the value of the i-th data point in the IMF component, represents the mean of the IMF component, δ i represents the value of the i-th data point in the original signal, Represents the average value of the original signal.

[0139] The kurtosis and correlation coefficient values ​​of each IMF component are shown in Table 2 below.

[0140] Table 2: Kurtosis and correlation coefficient values ​​for each IMF component

[0141] IMF Components IMF1 IMF2 IMF3 Kurtosis value 2.4627 5.2053 4.0739 Correlation coefficient 0.4261 0.5473 0.7746

[0142] Select IMFs with kurtosis values ​​greater than 3 and correlation coefficients greater than 0.45 for signal reconstruction. For the outer loop results, select IMF2 and IMF3 for signal reconstruction. The envelope spectrum of the reconstructed signal is as follows: Figure 8 shown.

[0143] S6. Apply envelope demodulation to extract the fault characteristic frequency of the rolling bearing.

[0144] like Figure 8 As shown in the figure, the characteristic frequency of the outer ring rolling bearing is 230Hz, which is very close to its theoretical value of 236Hz, indicating that the envelope spectrum successfully extracts the fault characteristic frequency of the early signal in the outer ring.

[0145] For comparison, PSO-VMD and ACO-VMD algorithms are used to optimize VMD parameters. The time required for different algorithms is shown in Table 3.

[0146] Table 3: Time required for different optimization algorithms to complete VMD parameter optimization

[0147]

[0148] It can be seen from Table 3 that the CHHO-VMD algorithm of the present application converges faster and more accurately than the PSO-VMD and ACO-VMD algorithms.

[0149] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A rolling bearing early fault feature extraction method based on CHHO-VMD, characterized by: The following steps are involved: S1, obtaining the original vibration signal of the bearing; S2, identifying early fault signals in the original vibration signal; S3, using CHHO algorithm to adaptively optimize VMD parameters and generate the best parameter combination [K, α]; S4, using parameter-optimized VMD to decompose the fault signal and extract its IMF components; S5, selecting IMF components based on kurtosis and correlation coefficient to reconstruct fault signals; S6. Apply envelope demodulation to extract the fault characteristic frequency of the rolling bearing.

2. The method for extracting early-stage fault features of rolling bearings based on CHHO-VMD according to claim 1 is characterized in that: In the step S3, the CHHO algorithm introduces chaotic mapping to generate chaotic values ​​for initial energy, introduces an exponential decreasing factor to dynamically adjust algorithm parameters, and introduces Gaussian mutation to increase population diversity.

3. The method for extracting early-stage rolling bearing fault features based on CHHO-VMD according to claim 2 is characterized in that: The chaos map is as follows: x n+1 =ux n (1-x n ),u∈[0,4],x n ∈(0,1) Among them, x n represents the proportion of the population at the nth moment to the maximum possible population size, x n+1 represents the population proportion at the n+1th moment, u represents the control parameter, and x is a random number between 0 and 1; The Gaussian variation is as follows: X mutated (t+1)=X(t)(1+N(μ,σ) 2 )) Among them, X mutated (t+1) represents the position of the individual after the mutation, X(t) represents the position of the individual before the mutation, N represents the mean μ and the variance σ 2 Gaussian distribution.

4. The method for extracting early-stage fault features of rolling bearings based on CHHO-VMD according to claim 3 is characterized in that: The chaotic map is introduced to generate the chaotic value for the initial energy, and the updating formula of the initial energy is as follows: E0=x n+1 =ux n (1-x n ),x n ∈(0,1) The update formula of escape energy is as follows: Among them, sign is a random value of -1 or 1, t represents the current number of iterations, and T represents the maximum number of iterations.

5. The method for extracting early-stage rolling bearing fault features based on CHHO-VMD according to claim 2, characterized in that: In the exponential decay factor dynamic adjustment algorithm parameters, the exponential decay weight is calculated as follows: oh i =e -λ·i Among them, ω i is the weight of the i-th data point, λ is the decay coefficient, and i is the time interval.

6. The method for extracting early-stage fault features of rolling bearings based on CHHO-VMD according to claim 3, characterized in that: In the Gaussian mutation to increase population diversity, the population position update formula is as follows: Among them, rand is a random number between 0 and 1, p represents the mutation probability, X(t) represents the current population position, X(t+1) represents the population position after iteration, and f(.) represents the fitness function.

7. The method for extracting early-stage fault features of rolling bearings based on CHHO-VMD according to claim 1, characterized in that: The S3 step specifically includes the following steps: Step 1, setting the initial parameters of the CHHO algorithm; Step 2, decomposing the early fault signal through VMD; Step 3, identify the optimal individual; Step 4, restore the prey's escape energy; Step 5, determine whether the escape energy is less than or equal to 1. If it is less than or equal to 1, it enters the development stage; if it is greater than 1, it enters the exploration stage; Step 6, determine whether the maximum number of iterations has been reached; Step 7: If the maximum number of iterations is reached, output K and α; if the maximum number of iterations is not reached, repeat steps 2 to 6.

8. The method for extracting early-stage rolling bearing fault features based on CHHO-VMD according to claim 7, characterized in that: In the step S3, the average minimum energy entropy is used as the iteration index in the optimization process, and the calculation formula is as follows: Among them, u k is the kth IMF component, H mean (u k ) is the component u k The average energy entropy of k represents the kth component u k The proportion of total energy, E k is the energy of each component, E is the sum of the energies of K components, E i is the energy of the ith component.

9. The method for extracting early-stage rolling bearing fault features based on CHHO-VMD according to claim 1, characterized in that: In the step S5, the kurtosis calculation formula is as follows: Where μ and σ represent the mean and standard deviation of the signal, respectively, E(·) is the expected value of the signal, and x represents the value of the signal; The calculation formula of the correlation coefficient is as follows: Among them, θ i represents the value of the i-th data point in the IMF component, represents the mean of the IMF component, δ i represents the value of the i-th data point in the original signal, Represents the average value of the original signal.

Images