Diesel generating set bearing fault diagnosis system combining TTAO-VMD and IWOA-BP

Abstract

The invention discloses a diesel generating set bearing fault diagnosis system combining TTAO-VMD and IWOA-BP, and the system comprises a signal collection module which is used for collecting a vibration signal of a bearing of a monitored diesel generating set, and serves as an input signal of a TTAO-VMD fault feature extraction module; the TTAO-VMD fault feature extraction module is used for receiving the bearing vibration signal, calculating feature parameters of the bearing vibration signal in a time domain and a frequency domain according to the optimal component, and constructing a feature vector data set; the IWOA-BP fault mode recognition module is used for classifying the faults of the rolling bearing according to the feature vector data set; and the man-machine interface module is used for displaying the data analysis result and the fault type.

Description

TECHNICAL FIELD

[0001] The application relates to a diesel generator set bearing fault diagnosis system combining TTAO-VMD and IWOA-BP, in particular to a diesel generator set bearing fault diagnosis system based on variational mode decomposition and whale optimization algorithm. BACKGROUND

[0002] Rolling bearings are the most common key components in mechanical equipment, and once a fault occurs, it may cause serious industrial accidents and cause incalculable economic losses. Therefore, the fault diagnosis of rolling bearings is of great significance. Generally speaking, the fault diagnosis of rolling bearings includes two key steps: fault feature extraction and fault pattern recognition.

[0003] In the aspect of fault feature extraction of rolling bearings, the vibration signal needs to be collected first, and then the information containing the fault features is extracted and decomposed. In view of the problems of signal distortion and modal aliasing in the traditional signal decomposition method, the variational mode decomposition method is proposed, which effectively solves the problem of modal aliasing in the traditional signal decomposition method. However, in the process of feature signal extraction, the decomposition effect of the variational mode decomposition method is highly dependent on the decomposition order k and the penalty factor alpha. Since these parameters are usually set by experience, the method is prone to over-decomposition or under-decomposition, which affects the decomposition precision and fault diagnosis effect.

[0004] In the aspect of fault pattern recognition, many scholars have carried out researches in view of the problems of slow convergence speed and easy falling into local optimum of the traditional whale optimization algorithm. For example, by introducing the inertia weight in the particle swarm optimization algorithm, the problem of the whale optimization algorithm falling into local optimum is solved. By combining the Von Neumann topological structure and the adaptive weight, the convergence speed and accuracy of the whale optimization algorithm are improved. By introducing the inertia weight and the adaptive convergence factor, the risk of the algorithm falling into local optimum and premature convergence is reduced. By using the nonlinear inertia weight, the global search ability and convergence speed of the whale optimization algorithm are improved. However, the above methods all improve the performance of the whale optimization algorithm by introducing adaptive weights. When the pace of adaptive weight adjustment is too large or too frequent, the direction of the algorithm will change dramatically in the iteration process, causing the solution to fluctuate greatly in the target space or even deviate from the optimal region, and the algorithm cannot converge to the optimal solution effectively. In addition, the whale optimization algorithm also has the problems of high function complexity, slow convergence speed, easy falling into local optimum in high-dimensional optimization, and the diversity of the population decreases with the increase of the iteration number, which leads to the problems of insufficient exploration ability and low global search ability of the algorithm in the later stage.

[0005] In summary, in actual use, the existing diesel generator set bearing fault diagnosis method has the following disadvantages:

[0006] 1. The decomposition order k and the penalty factor a in the variational mode decomposition method have a great influence on the decomposition effect; since these parameters are usually set by experience, the method is prone to over-decomposition or under-decomposition, thereby affecting the decomposition precision and fault diagnosis effect.

[0007] 2. When the intelligent optimization algorithm is used to optimize the decomposition order k and the penalty factor a in the variational mode decomposition method, there are defects such as slow convergence speed, low global search ability and easy to fall into local optimum.

[0008] 3. The fault pattern recognition method based on the whale optimization algorithm has defects such as poor stability of algorithm iteration, low optimization efficiency and global search ability. SUMMARY

[0009] The diesel generator set bearing fault diagnosis system combining TTAO-VMD and IWOA-BP provided by the embodiment has a reasonable structure and method design, the decomposition order k and the penalty factor a of the variational mode decomposition method are optimized by introducing the triangular topology aggregation optimization algorithm, a TTAO-VMD fault feature extraction module is constructed, the precision of the variational mode decomposition method is reduced due to improper parameter setting is avoided, and simultaneously, an IWOA-BP fault pattern recognition module is also constructed, the whale optimization algorithm is improved based on the inertia weight strategy of the sigmoid function, the stability of algorithm iteration is improved, the optimization efficiency and the global search ability of the whale optimization algorithm are further improved by introducing the chaotic mapping initialization population and the elite reservation and disturbance mechanism in the IWOA-BP fault pattern recognition module, and the problems in the prior art are solved.

[0010] The technical scheme adopted by the embodiment to solve the above technical problems is:

[0011] The diesel generator set bearing fault diagnosis system combining TTAO-VMD and IWOA-BP, the diagnosis system comprises:

[0012] A signal acquisition module, the signal acquisition module is used for acquiring the monitored diesel generator set bearing vibration signal and serving as an input signal of the TTAO-VMD fault feature extraction module;

[0013] A TTAO-VMD fault feature extraction module, the TTAO-VMD fault feature extraction module is used for receiving the bearing vibration signal and calculating the characteristic parameters of the bearing vibration signal in the time domain and the frequency domain according to the optimal component to construct a characteristic vector dataset;

[0014] An IWOA-BP fault pattern recognition module, the IWOA-BP fault pattern recognition module is used for classifying the fault of the rolling bearing according to the characteristic vector dataset;

[0015] Human-machine interface module, which is used to display data analysis results and fault types;

[0016] In the TTAO-VMD fault feature extraction module, a triangular aggregation topology optimization algorithm is introduced to optimize the two parameters of the variational mode decomposition method, namely the decomposition order k and the penalty factor α. In the IWOA-BP fault mode recognition module, a chaotic mapping strategy is introduced to initialize the population position in order to improve the global search capability of the whale optimization algorithm.

[0017] The chaotic mapping strategy is as follows:

[0018]

[0019] Where, x i This indicates the position where the i-th individual was generated.

[0020] The IWOA-BP fault mode recognition module introduces an adaptive inertial weight based on the Sigmoid function to improve the whale optimization algorithm's ability to balance exploration and development, and accelerate its convergence speed. The adaptive inertial weight is as follows:

[0021]

[0022] Where, ω max and ω min These represent the maximum and minimum values ​​of the weights, respectively. The coefficient z is used to adjust the steepness of the sigmoid function; m and n are two parameter coefficients; T is the maximum number of iterations.

[0023] An elite retention and perturbation mechanism is introduced in the IWOA-BP fault mode identification module to prevent the whale optimization algorithm from getting trapped in local optima. The perturbation mechanism is as follows:

[0024]

[0025]

[0026] in, γ represents the position of the elite solution; γ is a constant that defines the perturbation amplitude.

[0027] The data displayed on the human-machine interface module includes variational mode decomposition results in the time and frequency domains, variational mode decomposition results in the frequency domain, signal reconstruction results in the time domain, signal reconstruction results in the frequency domain, and fault diagnosis results.

[0028] The application adopts the above structure, optimizes the decomposition order k and the penalty factor alpha of the variational mode decomposition method through the triangular topology polymerization optimization algorithm, avoids the reduction of the precision of the variational mode decomposition method due to improper parameter setting, improves the stability of algorithm iteration through the improved whale optimization algorithm based on the inertia weight strategy of the sigmoid function, introduces the chaos mapping initialization population, and the elite reservation and disturbance mechanism, improves the optimization efficiency and global search ability of the whale optimization algorithm, adds the local disturbance mechanism on the basis of reserving the elite individual, slightly disturbs the position of the elite individual, explores the potential optimal candidate solution near the position, and thus more accurately approaches the global optimal solution, and has the advantages of high precision, high efficiency, practicality and reliability. BRIEF DESCRIPTION OF DRAWINGS

[0029] Figure 1 It is a structural schematic diagram of the application.

[0030] Figure 2 It is a time domain vibration signal decomposition result displayed by the man-machine interface module of the application.

[0031] Figure 3 It is a frequency domain vibration signal decomposition result displayed by the man-machine interface module of the application.

[0032] Figure 4 It is a time domain signal reconstruction result displayed by the man-machine interface module of the application.

[0033] Figure 5 It is a frequency domain signal reconstruction result displayed by the man-machine interface module of the application.

[0034] Figure 6 It is a fault prediction result displayed by the man-machine interface module of the application. DETAILED DESCRIPTION

[0035] In order to clearly illustrate the technical features of the scheme, the application will be described in detail below with reference to the specific embodiments and the accompanying drawings.

[0036] As shown in the Figures 1-6 The diesel generator set bearing fault diagnosis system combining TTAO-VMD and IWOA-BP includes:

[0037] A signal acquisition module is configured to acquire the monitored diesel generator set bearing vibration signal and serve as an input signal of the TTAO-VMD fault feature extraction module.

[0038] The TTAO-VMD fault feature extraction module is configured to receive a bearing vibration signal and calculate characteristic parameters of the bearing vibration signal in a time domain and a frequency domain according to an optimal component, and construct a characteristic vector data set.

[0039] The IWOA-BP fault mode recognition module is configured to classify a fault of the rolling bearing according to the characteristic vector data set.

[0040] The human-computer interface module is configured to display a data analysis result and a fault type.

[0041] In the TTAO-VMD fault feature extraction module, a triangular aggregation topology optimization algorithm is introduced to optimize two parameters, i.e., a decomposition order k and a penalty factor a, of a variational mode decomposition method; and in the IWOA-BP fault mode recognition module, a chaotic mapping strategy is introduced to initialize a population position, so as to improve a global search ability of a whale optimization algorithm.

[0042] The chaotic mapping strategy is as follows:

[0043]

[0044] wherein x i represents a position generated by an ith individual.

[0045] The IWOA-BP fault mode recognition module introduces an adaptive inertia weight based on a Sigmoid function, so as to improve a balance ability between exploration and development of the whale optimization algorithm, accelerate a convergence speed of the whale optimization algorithm, and the adaptive inertia weight is as follows:

[0046]

[0047] wherein ω max and ω min are a maximum value and a minimum value of the weight respectively, a coefficient z is used to adjust a steepness of the sigmoid function, m and n are two parameter coefficients, and T is a maximum iteration number.

[0048] In the IWOA-BP fault mode recognition module, an elite reservation and disturbance mechanism is introduced, so as to prevent the whale optimization algorithm from falling into a local optimum, and the disturbance mechanism is as follows:

[0049]

[0050]

[0051] wherein x is a position of an elite solution, and γ is a constant defining a disturbance amplitude.

[0052] The data displayed on the human-computer interface module includes the variational mode decomposition result in the time domain and the frequency domain, the variational mode decomposition result in the frequency domain, the signal reconstruction result in the time domain, the signal reconstruction result in the frequency domain and the fault diagnosis result.

[0053] The working principle of the diesel generator set bearing fault diagnosis system combined with TTAO-VMD and IWOA-BP in the embodiment of the application is as follows: the decomposition order k and the penalty factor a of the variational mode decomposition method are optimized by introducing the triangular topology aggregation optimization algorithm, a TTAO-VMD fault feature extraction module is constructed, the precision of the variational mode decomposition method is avoided to be reduced due to improper parameter setting, and a IWOA-BP fault mode recognition module is also constructed, the whale optimization algorithm is improved based on the inertia weight strategy of the sigmoid function, the stability of algorithm iteration is improved, the chaos mapping initialization population and the elite reservation and disturbance mechanism are introduced in the IWOA-BP fault mode recognition module, and the optimization efficiency and the global search ability of the whale optimization algorithm are further improved.

[0054] At present, in view of the problem that the decomposition effect of the variational mode decomposition method is highly dependent on the decomposition order k and the penalty factor a, the existing technical means is to select the penalty factor a of each mode by using the whale optimization algorithm, to perform adaptive decomposition on the variational mode decomposition method by using the whale optimization algorithm, to optimize the parameters of the variational mode decomposition method by using the subtractive average optimizer algorithm, to optimize the parameters of the variational mode decomposition method by using the particle swarm algorithm, to perform adaptive optimization on the parameters of the variational mode decomposition method by using the locust algorithm, to propose the parameters of the variational mode decomposition method optimized based on the sparrow search algorithm, to optimize the parameters of the variational mode decomposition method by using the improved firefly algorithm, to adaptively obtain the optimal parameter combination by using the grey wolf algorithm, and to optimize the parameters of the variational mode decomposition method by using the genetic algorithm.

[0055] From the above analysis, at present, intelligent swarm optimization algorithm is often used to optimize the parameters of variational mode decomposition method. However, the intelligent swarm optimization algorithm itself has many limitations, such as the optimization performance of the particle swarm algorithm is highly dependent on the setting of its inertia weight, improper parameter selection can easily make the algorithm converge too fast, resulting in the inability to find the global optimal solution; the optimization effect of the genetic algorithm is affected by the crossover rate and mutation rate, and different parameter combinations have a significant impact on the optimization result; although the sparrow search algorithm shows certain advantages, it is relatively weak in local development, and in the late iteration, due to the rapid assimilation of sparrow individuals, local optimal phenomenon is easy to appear; when solving complex engineering optimization problems, the locust optimization algorithm is difficult to balance between global search and local development; the convergence speed of the whale optimization algorithm is slow when dealing with multi-peak or complex constraint problems, and it is easy to fall into local optimum. When the search space is large, the subtraction mechanism of the subtractive average optimizer algorithm may lead to a decrease in population diversity, thereby weakening the global exploration ability and leading to falling into local optimum in complex or high-dimensional optimization problems.

[0056] Compared with the prior art, the diesel generator set bearing fault diagnosis system is improved from the following three aspects: the triangular topology aggregation optimization algorithm is introduced to optimize the decomposition order k and the penalty factor a of the variational mode decomposition method, so as to avoid the reduction of the precision of the variational mode decomposition method due to improper parameter setting; the improved whale optimization algorithm based on the inertia weight strategy of the sigmoid function is proposed, so as to improve the stability of algorithm iteration; the chaos mapping is introduced to initialize the population, and the elite reservation and disturbance mechanism are introduced, so as to improve the optimization efficiency and global search ability of the whale optimization algorithm.

[0057] In the overall scheme, the diagnosis system comprises: a signal acquisition module, which is used to acquire the monitored diesel generator set bearing vibration signal and serve as the input signal of the TTAO-VMD fault feature extraction module; a TTAO-VMD fault feature extraction module, which is used to receive the bearing vibration signal and calculate the characteristic parameters of the bearing vibration signal in the time domain and the frequency domain according to the optimal component, and construct a characteristic vector dataset; an IWOA-BP fault mode recognition module, which is used to classify the faults of the rolling bearing according to the characteristic vector dataset; a man-machine interface module, which is used to display the data analysis result and the fault type; the triangular aggregation topology optimization algorithm is introduced into the TTAO-VMD fault feature extraction module to optimize the two parameters of the decomposition order k and the penalty factor a of the variational mode decomposition method; the chaos mapping strategy is introduced into the IWOA-BP fault mode recognition module to initialize the population position, so as to improve the global search ability of the whale optimization algorithm.

[0058] Specifically, the triangular topology aggregation optimization algorithm optimizes the parameters of the variational modal decomposition method, including two stages of global aggregation and local aggregation; first, the population size N and the parameter dimension D need to be defined; when the design variables are k and a, the parameter dimension D is 2, and the population size N is divided into [N / 3] triangular topology units in the initialization stage, where [] represents rounding down; each triangular topology unit contains three vertices and a randomly generated internal vertex, a total of four search individuals, and similar triangular topology units are generated through geometric transformation to enhance population diversity.

[0059] Taking the decomposition order k as an example, [N / 3] individuals are randomly generated in the definition domain of k, and the initial position of each individual is generated as follows:

[0060]

[0061] wherein, represents the first search individual in the i-th triangular topology unit; and are the upper and lower bounds of the decomposition order k, respectively; h is a random number in [0, 1].

[0062] A direction vector is defined from the initial position converted to the normal coordinate system through the trigonometric function, forming the second vertex; then the direction vector is counterclockwise rotated by π / 3, and the third vertex is obtained through coordinate system transformation.

[0063] The expressions of the second and third vertices are as follows:

[0064]

[0065]

[0066] wherein, l represents the size of the triangular topology unit; and are the direction vectors of the other two edges guided by the first vertex, specifically expressed as:

[0067]

[0068]

[0069] wherein, is a random number in [0, π].

[0070] Further, in order to achieve a balance between global search and local development, the value range of the triangular topology unit l needs to be:

[0071]

[0072] where t represents the current iteration number; T represents the maximum iteration number.

[0073] For the fourth vertex, which is the interior search point, it can be generated by linear weighting, which is:

[0074]

[0075] where r1, r2 and r3 are random numbers between 0 and 1, and the sum is 1, so as to ensure that the generated fourth vertex is always located within the triangular topology unit.

[0076] Further, in order to comprehensively search for potential optimal k values, in the global aggregation stage, the optimal individual of each triangular topology unit needs to be linearly combined with the optimal individual of another random unit to generate a new individual, which can be represented as:

[0077]

[0078] where r4 is a random number between 0 and 1, and represent the optimal individual of unit i and the optimal individual of a random unit at the tth iteration, respectively. is the new individual of unit i at the t+1th iteration.

[0079] For the link of retaining the optimal k value, the newly generated individual needs to be compared with the current optimal individual or the suboptimal individual, and the optimal individual or the suboptimal individual at the next iteration is represented as:

[0080]

[0081] where and represent the optimal individual and the suboptimal individual of unit i at the t+1th iteration; y is the fitness value of the individual.

[0082] In order to search for potential excellent k values in a specific area, in the local aggregation stage, the optimal or suboptimal individual obtained in the previous stage will form a temporary triangular topology unit with the other two vertices in the group with better fitness values. Based on the position vector difference between the optimal and suboptimal individuals, a small perturbation is made to realize the development of each triangular topology unit, which is represented as:

[0083]

[0084] where ε represents the set range parameter; represents the second new individual of unit i at the t+1th iteration.

[0085] In order to ensure the optimality of the convergence direction, the position of the update is determined by comparing the fitness values of the two bodies before and after aggregation, so as to select the optimal convergence direction, which is represented as:

[0086]

[0087] For the IWOA-BP fault mode identification module, in order to solve the problems of insufficient global search ability, slow convergence speed and easy to fall into local optimum of the traditional WOA, the chaos mapping strategy is introduced to initialize the population position, improve the global search ability of WOA; the adaptive inertia weight based on Sigmoid function is introduced to improve the balance ability between exploration and development of WOA, and accelerate the convergence speed; the elite reservation and disturbance mechanism is introduced to prevent WOA from falling into local optimum. The specific ways include:

[0088] (1) Initial population position based on chaos mapping strategy

[0089] The chaos sequence is generated by using Sine, Tent and Cosine three mapping methods to initialize the population position of whale, which increases the distribution range of initial solution; this method can make the whale search more areas, which helps to improve the global search ability of WOA, and the chaos mapping strategy is represented as:

[0090]

[0091] Wherein, x i represents the position generated by the ith individual.

[0092] (2) Inertia weight based on sigmoid function

[0093] The weight is a dynamic adjustment parameter, which can guide the search direction of WOA at different stages and control the balance between global exploration and local development; in view of the problems of slow convergence speed and low solution accuracy existing in the traditional WOA, the adaptive weight based on sigmoid function is introduced in the hunting stage and random search stage of WOA.

[0094] In the early hunting stage of the algorithm, a larger weight is given to make it perform large step search in the search space, so as to avoid falling into local optimal solution too early; in the later random search stage, the weight gradually decreases and tends to be stable, allowing the algorithm to perform fine search with small step, so as to improve the solution quality; in addition, since the sigmoid function is introduced, the change of weight value in the iteration process is very smooth, which avoids the instability of algorithm iteration caused by the sharp fluctuation of weight, and the adaptive weight is represented as:

[0095]

[0096] Wherein, ω max and ωmin The maximum and minimum values of the weight respectively, the coefficient z is used for adjusting the steepness of the control sigmoid function, m and n are two parameter coefficients, and T is the maximum iteration number.

[0097] Further, the improved WOA position updating formula is as follows:

[0098]

[0099]

[0100]

[0101] (3) Elite reservation and local disturbance mechanism

[0102] In the traditional WOA algorithm, the individual is updated in position with the optimal individual of the current iteration number as the target, and due to the influence of the control parameters and random numbers in the updating formula, in the iteration process, even if the individual takes the current optimal solution as the target, the updated position may deviate from the optimal direction, and a poor solution is generated; therefore, the elite reservation mechanism is introduced in the traditional WOA, so as to ensure that the optimal solution is not replaced by a poor solution in the iteration process, thereby improving the convergence and stability of the algorithm; in addition, in order to further improve the accuracy of the algorithm, the local disturbance mechanism is added on the basis of reserving the elite individual, the position of the elite individual is slightly disturbed, the potential optimal candidate solution near the position is explored, and the global optimal solution is more accurately approximated, and the improvement is represented as:

[0103]

[0104]

[0105] Wherein, The position of the elite solution is γ, which is a constant for defining the disturbance amplitude.

[0106] Specifically, in order to verify the effectiveness of the diesel generator set bearing fault diagnosis system proposed in the present application, the bearing data set disclosed by Case Western Reserve University is used for verification, so that the corresponding performance is analyzed and evaluated.

[0107] The intrinsic mode function (IMF) components in the time domain and the frequency domain are respectively shown in Figure 2 and Figure 3 According to the attached Figure 2 and the attached Figure 3It can be seen that the kurtosis values of IMF1, IMF2, IMF3, IMF4 and IMF5 are 2.603, 3.379, 4.257, 3.042 and 3.066 respectively, according to the maximum kurtosis criterion, the component with the maximum kurtosis is selected for signal reconstruction, since the kurtosis value of IMF3 is the largest, IMF3 is selected as the optimal component for signal reconstruction.

[0108] As shown in the accompanying Figure 4 It can be seen that the reconstructed signal is highly consistent with the original signal in the amplitude and change trend of the waveform, and the original signal contains more high-frequency components and fluctuations, which shows that the reconstructed signal not only effectively retains the main features of the original signal, but also significantly reduces the interference of high-frequency noise, and the reconstruction effect of the signal is ideal.

[0109] As shown in the accompanying Figure 5 It can be clearly seen that the rotation frequency of the rolling bearing, its double frequency, the inner ring fault frequency and its double frequency, which shows that the diagnostic system of the application can accurately extract the fault characteristic frequency, and ensures the accuracy of fault diagnosis.

[0110] As shown in the accompanying Figure 6 As shown in the accompanying

[0111] The experimental results show that TTAO-VMD significantly improves the accuracy and reliability of fault feature extraction, and further, the application introduces the inertia weight strategy based on Sigmoid function, chaos mapping initialization, elite reservation and disturbance mechanism in the whale algorithm, and invents an improved whale optimization algorithm, which optimizes the initial weight and bias of the BP neural network, and invents an IWOA-BP fault pattern recognition module, which is superior to the traditional method in convergence speed and global search ability.

[0112] In summary, the diesel generator set bearing fault diagnosis system combined with TTAO-VMD and IWOA-BP in the embodiment of the application introduces a triangular topology aggregation optimization algorithm to optimize the decomposition order k and the penalty factor alpha of the variational mode decomposition method, constructs a TTAO-VMD fault feature extraction module, avoids reducing the accuracy of the variational mode decomposition method due to improper parameter setting, simultaneously corresponds to construct an IWOA-BP fault mode recognition module, can improve the whale optimization algorithm based on the inertia weight strategy of the sigmoid function, improves the stability of algorithm iteration, and introduces the chaos mapping initialization population and the elite reservation and disturbance mechanism in the IWOA-BP fault mode recognition module, further improves the optimization efficiency and global search ability of the whale optimization algorithm.

[0113] The above detailed embodiment cannot be regarded as a limitation on the protection scope of the present application, and any alternative improvement or transformation made by the skilled in the art to the embodiment of the present application falls within the protection scope of the present application.

[0114] The details not described in the present application are the known technology of the skilled in the art.

Claims

1. A diesel generator set bearing fault diagnosis system combining TTAO-VMD and IWOA-BP, characterized in that, The diagnostic system includes: The signal acquisition module is used to acquire the vibration signal of the bearing of the monitored diesel generator set and use it as the input signal of the TTAO-VMD fault feature extraction module. The TTAO-VMD fault feature extraction module is used to receive bearing vibration signals and calculate the feature parameters of the bearing vibration signals in the time and frequency domains based on the optimal components, thereby constructing a feature vector dataset. The IWOA-BP fault mode recognition module is used to classify rolling bearing faults based on a feature vector dataset. Human-machine interface module, which is used to display data analysis results and fault types; In the TTAO-VMD fault feature extraction module, a triangular aggregation topology optimization algorithm is introduced to optimize the two parameters of the variational mode decomposition method, namely the decomposition order k and the penalty factor α. In the IWOA-BP fault mode recognition module, a chaotic mapping strategy is introduced to initialize the population position in order to improve the global search capability of the whale optimization algorithm.

2. The diesel generator set bearing fault diagnosis system combining TTAO-VMD and IWOA-BP as described in claim 1, characterized in that, The chaotic mapping strategy is as follows: Where, x i This indicates the position where the i-th individual was generated.

3. The diesel generator set bearing fault diagnosis system combining TTAO-VMD and IWOA-BP according to claim 1, characterized in that, The IWOA-BP fault mode recognition module introduces an adaptive inertial weight based on the Sigmoid function to improve the whale optimization algorithm's ability to balance exploration and development, and accelerate its convergence speed. The adaptive inertial weight is as follows: Where, ω max and ω min These represent the maximum and minimum values ​​of the weights, respectively. The coefficient z is used to adjust the steepness of the sigmoid function; m and n are two parameter coefficients; and T is the maximum number of iterations.

4. The diesel generator set bearing fault diagnosis system combining TTAO-VMD and IWOA-BP as described in claim 1, characterized in that: An elite retention and perturbation mechanism is introduced in the IWOA-BP fault mode identification module to prevent the whale optimization algorithm from getting trapped in local optima. The perturbation mechanism is as follows: in, γ represents the position of the elite solution; γ is a constant that defines the perturbation amplitude.

5. The diesel generator set bearing fault diagnosis system combining TTAO-VMD and IWOA-BP as described in claim 1, characterized in that: The data displayed on the human-machine interface module includes variational mode decomposition results in the time and frequency domains, variational mode decomposition results in the frequency domain, signal reconstruction results in the time domain, signal reconstruction results in the frequency domain, and fault diagnosis results.

Images