Rolling bearing weak fault enhanced diagnosis method, device, equipment and storage medium

Abstract

The present invention discloses a rolling bearing weak fault enhanced diagnosis method, device, equipment and storage medium. The method adopts an improved differential search algorithm and uses the minimum mean square envelope entropy as the optimization objective function to perform variational modal decomposition on the rolling bearing acceleration vibration signal to obtain the optimal decomposition level and the optimal quadratic penalty factor of the variational modal decomposition; the rolling bearing acceleration vibration signal, the optimal decomposition level and the optimal quadratic penalty factor are substituted into the variational modal decomposition parameters to obtain the natural modal components of the rolling bearing acceleration vibration signal after decomposition; the optimal component among the natural modal components is selected by correlation kurtosis, and a reconstructed signal is generated based on the optimal component; the reconstructed signal is input into a stochastic resonance model optimized by the improved differential search algorithm, and an enhanced rolling bearing acceleration vibration signal is output. The enhanced rolling bearing acceleration vibration signal is subjected to envelope spectrum analysis. The present invention can better identify the characteristics of weak faults.

Description

Technical Field

[0001] The present invention belongs to the technical field of bearing fault diagnosis, and in particular relates to a rolling bearing weak fault enhanced diagnosis method, device, equipment and storage medium. Background Art

[0002] Rotating machinery is widely used in high-tech industries such as aerospace and national defense. It also plays a fundamental role as a power machine in pillar industries such as petrochemicals, metallurgy, and high-speed rail. Bearings, as core components of rotating machinery, are subject to internal and external excitations, such as friction and transient impact, making them susceptible to various common vibration faults. Failures not only shorten the equipment's service life but also reduce production efficiency. Furthermore, bearing vibration signals often exhibit weak energy and are accompanied by nonlinearity, nonstationarity, and noise interference. Extracting useful information from these nonlinear and nonstationary vibration signals is crucial for identifying early-stage, subtle bearing faults.

[0003] In recent years, many researchers have applied adaptive signal decomposition methods, such as EMD and its derivatives, EEMD, LMD, LCD, SVD, and EWT, to fault diagnosis of bearing system fault signals. While these methods have been effective and successful in fault diagnosis of rolling bearings in rotating machinery, they still suffer from several drawbacks, such as modal aliasing, endpoint effects, unclear added noise intensity, and artificially selected frequency bands.

[0004] At the same time, many researchers have used the theory of stochastic resonance to effectively enhance the low-frequency characteristic frequency information with the help of noise energy to identify weak fault characteristics. However, the premise for the applicability of the stochastic resonance system is that it is a small parameter system that satisfies the adiabatic approximation condition (that is, the signal amplitude, frequency and noise intensity are all far less than 1). It has a good weak signal detection effect, but in actual working environments, it faces nonlinearity and non-stationarity, and is mixed with a large amount of useless noise interference. The general fault frequency is also far greater than 1, and the selection of system parameters and scale parameters has a great influence on the final output results. As a result, the current analysis methods have certain shortcomings and deficiencies, which may cause misdiagnosis or missed diagnosis, bringing new challenges to the extraction of bearing fault characteristics. Summary of the Invention

[0005] In response to the problems existing in the prior art, the present invention provides a rolling bearing weak fault enhanced diagnosis method, device, equipment and storage medium, which can better identify weak fault characteristics.

[0006] In order to solve the above technical problems, the present invention is implemented through the following technical solutions:

[0007] A rolling bearing weak fault enhanced diagnosis method, comprising:

[0008] Obtaining rolling bearing acceleration vibration signal;

[0009] Under a set number of iterations, an improved differential search algorithm is used, and the minimum mean square envelope entropy is used as the optimization objective function to perform variational modal decomposition on the acceleration vibration signal of the rolling bearing, and the optimal number of decomposition levels and the optimal quadratic penalty factor of the variational modal decomposition are obtained;

[0010] Substituting the rolling bearing acceleration vibration signal, the optimal decomposition level, and the optimal quadratic penalty factor into variational modal decomposition parameters to obtain each natural modal component after decomposition of the rolling bearing acceleration vibration signal;

[0011] Selecting an optimal component from among the natural mode components according to the correlation kurtosis, and generating a reconstructed signal according to the optimal component;

[0012] The reconstructed signal is input into the stochastic resonance model optimized by the improved differential search algorithm, and an enhanced rolling bearing acceleration vibration signal is output. Envelope spectrum is performed on the enhanced rolling bearing acceleration vibration signal to obtain the fault spectrum characteristics of the rolling bearing.

[0013] Furthermore, the improved differential search algorithm includes initial positions of swarm intelligent biological individuals and position updates and searches of swarm intelligent biological individuals;

[0014] The initial positions of the individual intelligent creatures in the group are:

[0015] x ij =z n (up j -low j )+low j

[0016] in,

[0017] In the formula, r is the system parameter; mod is the modulus operator; z n Indicates the chaotic mapping result after the nth iteration; up j and low j Respectively represent the upper and lower bounds of the j-th dimension search space; x ij represents the position of the i-th individual in the j-th dimension;

[0018] The position update and search of the group intelligent biological individuals are as follows:

[0019] Stopover=Superorganism+L·(donor-Superorganism)

[0020] in,

[0021] L=Levy(s,λ)·map

[0022] Levy(s,λ)~|s| -λ-1 ,0<λ≤2

[0023] In the formula, Stopover represents the temporary stop position of this random process; Superorganism represents the initial population position set; donor represents the population target movement, through (donor-x ij ) controls the direction; L is the search step factor, which controls the change of the organism's search position; Levy(s,λ) represents the path that obeys the Levy distribution, where s represents the step size and λ represents the power; map is the element selection strategy, and its value range is a random integer in [0, 1], where 0 represents an unselected element and 1 represents a selected element.

[0024] Furthermore, the expression of the minimum mean square envelope entropy is:

[0025]

[0026] In the formula, a s (j) is the square envelope of the jth decomposition component of the original signal s(j); K is the number of decomposition modes; N is the sampling length; p ij represents the normalized envelope value of the i-th decomposition component; E ij and E m They represent the square envelope entropy and average square envelope entropy of the i-th decomposition component respectively, and both i and j are positive integers.

[0027] Furthermore, selecting the optimal component among the natural modal components by using the relevant kurtosis includes:

[0028] Obtaining the relevant kurtosis value of each of the inherent modal components;

[0029] The intrinsic mode component corresponding to the maximum correlation kurtosis value is taken as the optimal component.

[0030] Furthermore, the improved differential search algorithm is used to optimize the stochastic resonance model, specifically as follows:

[0031] The improved differential search algorithm is used to select the optimal component as the input signal, and the maximum correlation kurtosis is used as the fitness function to optimize the parameters of the stochastic resonance model;

[0032] Substituting the optimized parameters into the stochastic resonance model to obtain the optimized stochastic resonance model;

[0033] The optimized stochastic resonance model is as follows:

[0034]

[0035]

[0036] In the formula, U(x), s(t), and Γ(t) represent the potential function, input signal, and noise signal of the bistable system, respectively, where n = 0, 1, 2, …, N-1, where N is the length of the input signal; x n Represents the output signal; a and b represent the system parameters of the stochastic resonance system respectively; h is the calculation step size.

[0037] Furthermore, the reconstructed signal is input into the stochastic resonance model optimized by the improved differential search algorithm to output the enhanced rolling bearing acceleration vibration signal, specifically:

[0038] The reconstructed signal is input into the optimized stochastic resonance model, and the reconstructed signal is solved by using the fourth-order Runge-Kutta method to output an enhanced rolling bearing acceleration vibration signal.

[0039] A rolling bearing weak fault enhanced diagnosis device, comprising:

[0040] An acquisition module is used to acquire the acceleration vibration signal of the rolling bearing;

[0041] A variational modal decomposition module is used to perform variational modal decomposition on the acceleration vibration signal of the rolling bearing using an improved differential search algorithm under a set number of iterations and taking the minimum mean square envelope entropy as the optimization objective function to obtain the optimal number of decomposition levels and the optimal quadratic penalty factor of the variational modal decomposition;

[0042] A parameter substitution module is used to substitute the rolling bearing acceleration vibration signal, the optimal decomposition level and the optimal quadratic penalty factor into the variational modal decomposition parameters to obtain the natural modal components after the rolling bearing acceleration vibration signal is decomposed;

[0043] a reconstructed signal generating module, configured to select an optimal component from among the inherent modal components by using the relevant kurtosis, and generate a reconstructed signal according to the optimal component;

[0044] An output module is used to input the reconstructed signal into the stochastic resonance model optimized by the improved differential search algorithm, output the enhanced rolling bearing acceleration vibration signal, perform envelope spectrum on the enhanced rolling bearing acceleration vibration signal, and obtain the fault spectrum characteristics of the rolling bearing.

[0045] A device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method for enhancing the diagnosis of weak faults of rolling bearings are implemented.

[0046] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a rolling bearing weak fault enhanced diagnosis method.

[0047] Compared with the prior art, the present invention has at least the following beneficial effects:

[0048] The present invention provides a method for enhancing the diagnosis of weak faults in rolling bearings. The method uses an improved differential search algorithm to perform adaptive variational mode decomposition on the input signal, selects the optimal component from each natural mode component by maximum correlation kurtosis, and generates a reconstructed signal with the optimal component to overcome the problem of multi-scale noise interference under a strong noise background; uses the improved differential search algorithm to perform stochastic resonance adaptive scaling processing on the reconstructed signal to achieve the best match between system parameters and calculated scaling factors, enhance the system output response and extract the actual fault frequency; and introduces chaos mapping and Levy flight strategy to improve the poor optimization ability and slow convergence speed of the original differential search. In summary, the present invention combines the improved differential search algorithm with the variational mode decomposition method and the stochastic resonance method to achieve intelligent parameter optimization, which not only overcomes the shortcomings of adaptive parameter selection in the variational mode decomposition and stochastic resonance methods, but also effectively solves the problem that the fault characteristic frequency of the rolling bearing fault vibration signal under strong background noise is difficult to extract and the enhancement effect is poor, and can better perform weak fault feature recognition, which has important reference value and practical significance for the early diagnosis of weak faults in rolling bearings.

[0049] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the specific embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the specific embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 This is a flow chart of a rolling bearing weak fault enhanced diagnosis method of the present invention;

[0052] Figure 2This is a main flow chart of the rolling bearing weak fault enhanced diagnosis method according to an embodiment of the present invention;

[0053] Figure 3 A comparison diagram of the convergence process of VMD parameters optimized by the differential search algorithm of the present invention and the improved differential search algorithm;

[0054] Figure 4 The adaptive variational modal decomposition of each component of a signal of a specific example of the present invention is a time domain diagram and a spectrum diagram;

[0055] Figure 5 A schematic diagram showing a specific embodiment of the present invention in which the correlation kurtosis of a signal is used as a screening criterion;

[0056] Figure 6 It is an iterative convergence diagram of stochastic resonance parameter optimization using an improved differential search algorithm for a specific example signal of the present invention;

[0057] Figure 7 This is a time domain diagram and envelope spectrum diagram of the enhanced Microsoft fault signal of a specific example signal of the present invention. DETAILED DESCRIPTION

[0058] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0059] As a specific embodiment of the present invention, Figure 1 As shown, a rolling bearing weak fault enhanced diagnosis method specifically includes the following steps:

[0060] Step 1: Collect the rolling bearing acceleration vibration signal from the bearing test bench.

[0061] In this embodiment, the sampling frequency is 20480 Hz, the sampling time is 1 s, the bearing rotation frequency is 25 Hz, and theoretical calculation shows that the characteristic frequency of the bearing outer ring fault is 78 Hz.

[0062] Step 2: Under the set number of iterations, an improved differential search algorithm is used, and the minimum mean square envelope entropy is used as the optimization objective function to perform variational modal decomposition on the acceleration vibration signal of the rolling bearing, and the optimal decomposition layer number K and the optimal quadratic penalty factor α of the variational modal decomposition are obtained.

[0063] Preferably, the minimum mean square envelope entropy is defined using the following formula (1):

[0064]

[0065] In the formula, a s (j) is the square envelope of the jth decomposition component of the original signal s(j); K is the number of decomposition modes; N is the sampling length; p ij represents the normalized envelope value of the i-th decomposition component; E ij and E m They represent the square envelope entropy and average square envelope entropy of the i-th decomposition component respectively, and both i and j are positive integers.

[0066] The improved differential search algorithm includes the initial position of individual swarm intelligent organisms and the position update and search of individual swarm intelligent organisms;

[0067] The initial positions of the individual intelligent creatures in the group are:

[0068] x ij =z n (up j -low j )+low j

[0069] in,

[0070] In the formula, r is the system parameter; mod is the modulus operator; z n Indicates the chaotic mapping result after the nth iteration; up j and low j Respectively represent the upper and lower bounds of the j-th dimension search space; x ij represents the position of the i-th individual in the j-th dimension.

[0071] The position update and search of the group intelligent biological individuals are as follows:

[0072] Stopover=Superorganism+L·(donor-Superorganism)

[0073] in,

[0074] L=Levy(s,λ)·map

[0075] Levy(s,λ)~|s| -λ-1 ,0<λ≤2

[0076] In the formula, Stopover represents the temporary stop position of this random process; Superorganism represents the initial population position set; donor represents the population target movement, through (donor-x ij) controls the direction; L is the search step factor, which controls the change of the organism's search position; Levy(s,λ) represents the path that obeys the Levy distribution, where s represents the step size and λ represents the power; map is the element selection strategy, and its value range is a random integer in [0, 1], where 0 represents an unselected element and 1 represents a selected element.

[0077] In this embodiment, under a set number of iterations, an improved differential search algorithm is used, and the minimum mean square envelope entropy is used as the optimization objective function to perform variational modal decomposition on the rolling bearing acceleration vibration signal to obtain the optimal decomposition level K and the optimal quadratic penalty factor α of the variational modal decomposition. The specific steps are as follows:

[0078] Step 2.1: Initialize the initial positions of the swarm intelligent creatures, set the population size to 20, the search space dimension to 2, and the maximum number of algorithm iterations to 30. At the same time, set the optimization parameters K and α search boundaries to [3, 10] and [1000, 5000] respectively. The initial positions of the swarm intelligent creatures are generated by the Logistic-tent chaotic mapping method to generate a one-dimensional pseudo-random vector z in the range of [0, 1]. n , iteratively generate N-1 vectors according to the following formula (2);

[0079]

[0080] Among them, r is the system parameter.

[0081] Step 2.2, generate the initial positions of the individual intelligent creatures in the initialization group according to the following formula (3);

[0082] x ij =z n (up j -low j )+low j ⑶

[0083] Superorganism g =[x ij ]⑷

[0084] Among them, up j and low j The upper and lower limits of the individual range; Superorganism g It is a super population collection of intelligent organisms.

[0085] Step 2.3, update and search the position of the swarm intelligent organism individuals according to the following formula (5);

[0086] Stopover=Superorganism+L·(donor-Superorganism)⑸

[0087] In the above formula, Stopover represents the temporary stop position of this random process; donor represents the target movement of the population, through (donor-x ij ) controls the direction; L is the search step factor, which controls the change of the organism's search position, and its expression is as follows (6):

[0088] L=Levy(s,λ)·map ⑹

[0089] Where Levy(λ) represents a series of non-Gaussian random walk paths, which can be expressed by the power law equation:

[0090] Levy(s,λ)~|s| -λ-1 ,0<λ≤2⑺

[0091] Where s is a variable; λ is a stability control index; and map is a random integer vector consisting of 0 and 1.

[0092] In step 2.4, if the value of a biological search individual exceeds the boundary range, the position of the intelligent organism is revalued according to the following formula (8):

[0093] Stopover ij =rand(up j -low j )+low j ⑻

[0094] Step 2.5, by comparing Stopover i with x ij The fitness value of the intelligent organism is determined by the greedy selection mechanism. The search individuals with the best fitness values ​​are selected and retained. The optimal solution is updated and the position is recorded to complete one iteration. When the number of iterations reaches the maximum number, the global optimal value of the intelligent organism output corresponding to the minimum mean squared envelope entropy is used as the mode number K of the variational mode decomposition and the quadratic penalty factor α for adaptive optimization.

[0095] This embodiment takes the bearing outer ring fault signal as an example. The fault signal is collected as input through relevant experiments. The standard differential search algorithm and the improved differential search algorithm are used to compare the optimization effects of the variational modal decomposition parameters. The results are as follows: Figure 3 As shown, curve 1 is the iterative curve result of the standard differential search algorithm, and curve 2 is the optimized iterative curve result of the improved differential search algorithm. Figure 3 It can be clearly seen that the use of the improved differential search algorithm can find the optimal solution quickly and accurately.

[0096] Step 3: Substitute the rolling bearing acceleration vibration signal, the optimal decomposition level and the optimal quadratic penalty factor into variational modal decomposition parameters to obtain the natural modal components of the rolling bearing acceleration vibration signal after decomposition.

[0097] Step 4: If Figure 5 As shown, the optimal component among the inherent modal components is selected by the correlation kurtosis, and a reconstructed signal is generated according to the optimal component.

[0098] In this embodiment, the adaptive variational modal decomposition of the original vibration signal is performed with the number of modes K=3 and the quadratic penalty factor α=1850 after parameter optimization. The process is as follows: Figure 4 As shown. And according to formula (9), the relevant kurtosis values ​​of each decomposed natural mode component are obtained, including:

[0099]

[0100] Where y is the input signal; T is the pulse period of the fault signal; and M is the offset period.

[0101] Step 5: Input the reconstructed signal into the stochastic resonance model optimized by the improved differential search algorithm, output the enhanced rolling bearing acceleration vibration signal, perform envelope spectrum on the enhanced rolling bearing acceleration vibration signal, and obtain the fault spectrum characteristics of the rolling bearing.

[0102] Specifically, the improved differential search algorithm is used to optimize the stochastic resonance model as follows:

[0103] The improved differential search algorithm is used to select the optimal component as the input signal, and the maximum correlation kurtosis is used as the fitness function to optimize the parameters of the stochastic resonance model;

[0104] Substituting the optimized parameters into the stochastic resonance model, an optimized stochastic resonance model is obtained. The optimized stochastic resonance model is as follows:

[0105]

[0106]

[0107] In the formula, U(x), s(t) and Γ(t) represent the potential function, input signal and noise signal of the bistable system respectively. Where n = 0, 1, 2, ..., N-1, N is the length of the input signal; x n Represents the output signal; a and b represent the system parameters of the stochastic resonance system respectively; h is the calculation step size.

[0108] That is, initialize the parameters of the improved differential search algorithm according to steps 2.1 to 2.4. In this embodiment, the population size is set to 20, the maximum number of iterations is 20, the number of variables is 3, the maximum correlation kurtosis value is selected as the fitness function, and global optimization is performed with system parameter a, system parameter b and scale factor R, and the value ranges are set to [0.001, 10], [0.001, 10] and [1000, 50000] respectively.

[0109] The iterative process of the improved differential search algorithm is as follows Figure 6 As shown in the figure, after 20 iterations, the solution has good convergence. The improved differential search algorithm is used to intelligently find the optimal solution, and the obtained results are a=0.1822,b=1.0688,R=59500.

[0110] The reconstructed signal is input into the optimized stochastic resonance model, and the reconstructed signal is solved by the fourth-order Runge-Kutta method. After the scale change, the enhanced rolling bearing acceleration vibration signal is output. Specifically, the time domain diagram and envelope spectrum of the enhanced rolling bearing acceleration vibration signal are output, such as Figure 7 As shown. Figure 7 It can be seen that the final fault signal characteristic frequency f p =77.98 Hz and its 1 to 4 times frequency clearly show obvious peaks, which are consistent with the preset characteristic frequency of the simulated bearing outer ring fault signal. Therefore, it can be concluded that there is an outer ring fault, verifying the accuracy of the method proposed in the present invention.

[0111] The present invention takes the rolling bearing system as the research object, introduces an improved differential search algorithm to adaptively optimize the variational modal decomposition parameters, selects the optimal component among the natural modal components through the correlation kurtosis, generates a reconstructed signal based on the optimal component, performs system parameter optimization and adaptive scaling processing of the reconstructed signal through adaptive stochastic resonance, enhances the system output response, and finally realizes diagnosis and identification of the bearing fault signal through envelope spectrum analysis.

[0112] The present invention provides a rolling bearing weak fault enhanced diagnosis device, which is used to implement the above-mentioned rolling bearing weak fault enhanced diagnosis method, specifically comprising:

[0113] An acquisition module is used to acquire the acceleration vibration signal of the rolling bearing;

[0114] A variational modal decomposition module is used to perform variational modal decomposition on the acceleration vibration signal of the rolling bearing using an improved differential search algorithm under a set number of iterations and taking the minimum mean square envelope entropy as the optimization objective function to obtain the optimal number of decomposition levels and the optimal quadratic penalty factor of the variational modal decomposition;

[0115] A parameter substitution module is used to substitute the rolling bearing acceleration vibration signal, the optimal decomposition level and the optimal quadratic penalty factor into the variational modal decomposition parameters to obtain the natural modal components after the rolling bearing acceleration vibration signal is decomposed;

[0116] a reconstructed signal generating module, configured to select an optimal component from among the inherent modal components by using the relevant kurtosis, and generate a reconstructed signal according to the optimal component;

[0117] An output module is used to input the reconstructed signal into the stochastic resonance model optimized by the improved differential search algorithm, output the enhanced rolling bearing acceleration vibration signal, perform envelope spectrum on the enhanced rolling bearing acceleration vibration signal, and obtain the fault spectrum characteristics of the rolling bearing.

[0118] In one embodiment of the present invention, a computer device is provided, which includes a processor and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to implement corresponding method processes or corresponding functions; the processor described in the embodiment of the present invention can be used to implement the operation of a rolling bearing weak fault enhanced diagnosis method.

[0119] In one embodiment of the present invention, a method for enhanced diagnosis of weak faults in rolling bearings, if implemented in the form of a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, it can implement the steps of the above-mentioned method embodiments. The computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. Computer-readable storage media include permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data.

[0120] The computer storage medium can be any available medium or data storage device that can be accessed by a computer, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO)), optical storage (such as CDs, DVDs, BDs, HVDs, etc.), and semiconductor storage (such as ROMs, EPROMs, EEPROMs, non-volatile memories (NANDFLASH), solid-state drives (SSDs)), etc.

[0121] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0122] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products of the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0123] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0124] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0125] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed by the present invention, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A rolling bearing weak fault enhanced diagnosis method, characterized in that: include: Obtaining rolling bearing acceleration vibration signal; Under a set number of iterations, an improved differential search algorithm is used, and the minimum mean square envelope entropy is used as the optimization objective function to perform variational modal decomposition on the acceleration vibration signal of the rolling bearing, and the optimal number of decomposition levels and the optimal quadratic penalty factor of the variational modal decomposition are obtained; Substituting the rolling bearing acceleration vibration signal, the optimal decomposition level, and the optimal quadratic penalty factor into variational modal decomposition parameters to obtain each natural modal component after decomposition of the rolling bearing acceleration vibration signal; Selecting an optimal component from among the natural mode components according to the correlation kurtosis, and generating a reconstructed signal according to the optimal component; Inputting the reconstructed signal into the stochastic resonance model optimized by the improved differential search algorithm, outputting an enhanced rolling bearing acceleration vibration signal, performing envelope spectrum analysis on the enhanced rolling bearing acceleration vibration signal, and obtaining a fault spectrum feature of the rolling bearing; The improved differential search algorithm includes the initial position of the swarm intelligent biological individuals and the position update and search of the swarm intelligent biological individuals; The initial positions of the individual intelligent creatures in the group are: in, In the formula, is the system parameter; is the modulo operator; Indicates the Chaotic mapping results after iterations; Respectively represent The lower and upper bounds of the dimensional search space; Indicates the Individuals in The location of the dimension; The position update and search of the group intelligent biological individuals are as follows: in, In the formula, Indicates the temporary stop position of this random process; represents the initial population position set; Indicates the movement of population targets, through Control direction; is the search step factor, which controls the change of the organism's search position; represents a path that follows the Levy distribution, where represents the step length, Indicates the power; The element selection strategy is a random integer in the range of [0, 1], where 0 indicates an unselected element and 1 indicates a selected element.

2. A rolling bearing weak fault enhanced diagnosis method according to claim 1, characterized in that: The expression of the minimum mean square envelope entropy is: In the formula, The original signal No. The square envelope of the decomposition components; K is the number of decomposition modes; N is the sampling length; Indicates the Normalized envelope value of the decomposition components; Respectively represent The squared envelope entropy and average squared envelope entropy of the decomposition components, and All are positive integers.

3. The method for enhanced diagnosis of rolling bearing weak faults according to claim 1, characterized in that: The selecting the optimal component among the natural modal components by using the relevant kurtosis includes: Obtaining the relevant kurtosis value of each of the inherent modal components; The intrinsic mode component corresponding to the maximum correlation kurtosis value is taken as the optimal component.

4. The method for enhanced diagnosis of rolling bearing weak faults according to claim 1, characterized in that: The improved differential search algorithm is used to optimize the stochastic resonance model, as follows: The improved differential search algorithm is used to select the optimal component as the input signal, and the maximum correlation kurtosis is used as the fitness function to optimize the parameters of the stochastic resonance model; Substituting the optimized parameters into the stochastic resonance model to obtain the optimized stochastic resonance model; The optimized stochastic resonance model is as follows: In the formula, 、 and denote the potential function, input signal and noise signal of the bistable system respectively, where , is the input signal length; Indicates the output signal; and represent the system parameters of the stochastic resonance system respectively; is the calculation step size.

5. The method for enhanced diagnosis of rolling bearing weak faults according to claim 1, characterized in that: The reconstructed signal is input into the stochastic resonance model optimized by the improved differential search algorithm to output the enhanced rolling bearing acceleration vibration signal, specifically: The reconstructed signal is input into the optimized stochastic resonance model, and the reconstructed signal is solved by using the fourth-order Runge-Kutta method to output an enhanced rolling bearing acceleration vibration signal.

6. A rolling bearing weak fault enhanced diagnosis device, characterized in that: For implementing the method for enhanced diagnosis of rolling bearing weak faults according to any one of claims 1 to 5, the diagnostic device comprises: An acquisition module is used to acquire the acceleration vibration signal of the rolling bearing; A variational modal decomposition module is used to perform variational modal decomposition on the acceleration vibration signal of the rolling bearing using an improved differential search algorithm under a set number of iterations and taking the minimum mean square envelope entropy as the optimization objective function to obtain the optimal number of decomposition levels and the optimal quadratic penalty factor of the variational modal decomposition; A parameter substitution module is used to substitute the rolling bearing acceleration vibration signal, the optimal decomposition level and the optimal quadratic penalty factor into the variational modal decomposition parameters to obtain the natural modal components after the rolling bearing acceleration vibration signal is decomposed; a reconstructed signal generating module, configured to select an optimal component from among the inherent modal components by using the relevant kurtosis, and generate a reconstructed signal according to the optimal component; An output module is used to input the reconstructed signal into the stochastic resonance model optimized by the improved differential search algorithm, output the enhanced rolling bearing acceleration vibration signal, perform envelope spectrum on the enhanced rolling bearing acceleration vibration signal, and obtain the fault spectrum characteristics of the rolling bearing.

7. A device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method for enhanced diagnosis of rolling bearing weak faults as described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the rolling bearing weak fault enhanced diagnosis method according to any one of claims 1 to 5 are implemented.

Images