A generator fault diagnosis method based on vibration trend prediction and related products

Abstract

The present invention discloses a generator fault diagnosis method based on vibration trend prediction and related products, belonging to the technical field of generator fault diagnosis. The generator fault diagnosis method based on vibration trend prediction provided by the present invention can capture the characteristic information in the vibration signal more meticulously by decomposing the historical vibration signal sequence of the generator into multiple subsequences, and performing random function generation and residual function calculation on each subsequence respectively, thereby improving the accuracy of fault diagnosis; using a neural network model for prediction, and combining iterative loops and residual function minimization strategies, it can gradually approach the real vibration trend and improve the accuracy of diagnosis; through iterative loops and multiple random function generation, and selecting the optimal result, the nonlinearity and non-periodicity of the vibration signal are overcome, and the stability and reliability of the prediction are enhanced; the introduction of the residual sequence plays a role in smoothing the vibration signal, reducing noise interference, and improving the stability of the prediction.

Description

Technical Field

[0001] The present invention relates to the technical field of generator fault diagnosis, and particularly relates to a generator fault diagnosis method and related products based on vibration trend prediction. Background Art

[0002] In the field of motor fault diagnosis, vibration signal analysis is a key technology, which can reveal abnormal conditions inside the motor. When an inter-turn short circuit fault occurs in the motor, due to the uneven distribution of current, the dynamic response of the motor will change, and this change will be reflected through the vibration signal. Therefore, the monitoring and analysis of vibration signals are crucial for the early detection and diagnosis of motor faults.

[0003] However, the vibration signal itself has the characteristics of non-periodicity, which makes it complex to directly analyze and predict. Non-periodicity means that the frequency and amplitude of the vibration signal will change over time without a fixed pattern; non-linearity means that the generation and propagation process of the vibration signal may be affected by various non-linear factors, which makes the prediction and analysis of the signal more difficult. Summary of the Invention

[0004] The purpose of the present invention is to provide a generator fault diagnosis method and related products based on vibration trend prediction to overcome the problem of inaccurate prediction caused by the non-periodicity and non-linearity of the generator vibration signal in the prior art.

[0005] The present invention solves the above technical problems through the following technical solutions:

[0006] A generator fault diagnosis method based on vibration trend prediction includes the following steps:

[0007] S1. Obtain the historical vibration signal sequence of the generator, and divide the historical vibration signal sequence of the generator into a prediction set sequence and a verification set sequence according to a preset ratio; input the prediction set sequence into a trained neural network model for prediction to obtain a predicted value, and calculate the baseline prediction error SSE based on the predicted value and the actual value in the verification set sequence;

[0008] S2. Decompose the prediction set sequence to obtain a number of subsequences IMF 1 ~IMF K ,IMF 1 is the first subsequence obtained by decomposition, IMF K is the Kth subsequence obtained by decomposition, and K is the total number of subsequences obtained by decomposition;

[0009] S3. Through an iterative loop, perform M times of random function generation on each subsequence in turn. Based on the random function of each subsequence that conforms to the periodic function law, calculate the residual function; select the random function corresponding to the minimum value of the residual function of each subsequence as the subsequence of the Y-th prediction set.

[0010] S4. Sum up the minimum values of the residual functions of the K subsequences to obtain the residual sequence Q.

[0011] S5. Input the first to K-th subsequences in the Y-th prediction set and the residual sequence Q into the trained neural network model for prediction to obtain the Y-th predicted value; Y is the number of prediction sets generated based on the random function.

[0012] S6. Based on the Y-th predicted value and the actual value in the validation set sequence, calculate the prediction error SSE(Y). SSE(Y) is the prediction error of the Y-th prediction set generated based on the random function; determine whether the prediction error SSE(Y) is less than the benchmark prediction error SSE. If the determination result is yes, diagnose the generator fault based on the Y-th predicted value; if the determination result is no, execute step S7.

[0013] S7. Based on the correction formula, correct the first to K-th subsequences in the Y-th prediction set, let Y = Y + 1, obtain the subsequences in the Y-th prediction set, and repeat steps S5 and S6.

[0014] A further improvement of the present invention lies in: Step S3 is specifically as follows:

[0015] Step S3 is specifically as follows:

[0016] S31. Preset the number of loop times M, M is at least equal to 100000, let i = 0, j = 0, i is the i-th subsequence among several subsequences, and j is the j-th loop of the i-th subsequence.

[0017] S32. Let i = i + 1;

[0018] S33. Let j = j + 1, and generate the corresponding random function f(t) based on the subsequence IMF i , ij ;

[0019] S34. Determine whether the random function f(t) ij conforms to the law of the periodic function. If the determination is yes, then based on the random function f(t) ij , calculate the residual function Q(t) ij corresponding to the random function f(t) ij , and execute step S35; if the determination is no, directly execute step S35.

[0020] S35. Determine whether j is equal to M. If the determination result is no, return to step S33; if the determination result is yes, calculate the subsequence IMF i The values of all residual functions, and the residual function with the smallest value is Q(t) min , Q(t) min The corresponding random function f(t) ij Is the i-th subsequence in the Y-th prediction set, Y = 1, execute step S36;

[0021] S36. Determine whether i is equal to K. If the determination result is yes, execute step S4; if the determination result is no, set j = 0 and return to step S32;

[0022] Step S4 is specifically: Calculate the sum of all the residual functions Q(t) with the smallest values obtained in step S35 min To obtain the residual sequence Q.

[0023] A further improvement of the present invention is that the trained neural network model is an ELM (Extreme Learning Machine) model;

[0024] The benchmark prediction error SSE is specifically:

[0025]

[0026] Where N is the number of subsequences in the validation set sequence; Is the n-th actual value in the validation set sequence, Is the n-th value in the predicted values.

[0027] A further improvement of the present invention is that in step S1, the preset ratio is 9:1; in step S2, the variational mode decomposition (VMD) method is used to decompose the prediction set sequence.

[0028] A further improvement of the present invention is that based on the subsequence IMF i , generate the corresponding random function f(t) ij Specifically:

[0029] Let IMF i =

x 1i , x 2i , x 3i , …, x 9Ni

【t 1i , t 2i, t 3i , …, t 9Ni =

rand(0.1x 1i ~1.9x 1i ), rand(0.1x 2i ~1.9x 2i ), rand(0.1x 3i ~1.9x 3i ), …, rand(0.1x 9Ni ~1.9x 9Ni )

[0030] where rand() is a random function; x 1i , x 2i , x 3i , …, x 9Ni are the 1st, 2nd, 3rd, …, 9Nth values of the subsequence IMF i respectively; t 1i , t 2i , t 3i , …, t 9Ni are the 1st, 2nd, 3rd, …, 9Nth values of the random function f(t) ij respectively.

[0031] A further improvement of the present invention lies in that: the law of the periodic function is specifically:

[0032]

[0033] where t wi is the wth value of the random function of the subsequence IMF i ; t (w+T)i is the (w + T)th value of the random function of the subsequence IMF i ; T is the period; is the law parameter.

[0034] A further improvement of the present invention lies in that: the residual function Q(t) ij is specifically:

[0035] Q(t) ij = IMF i - f(t) ij =

x 1i -t 1i , x 2i -t 2i , x 3i -t 3i , …, x 9Ni -t 9Ni

[0036] The value A of the residual function is specifically:

[0037]

[0038] The residual sequence Q is specifically as follows:

[0039] Q =

x 11 - t 11 + x 12 - t 12 + x 13 - t 13 +…+ x 1k - t 1k , x 21 - t 21 + x 22 - t 22 + x 23 - t 23 +…+ x 2k - t 2k , x 31 - t 31 + x 32 - t 32 + x 33 - t 33 +…+ x 3k - t 3k ,…, x 9N1 - t 9N1 + x 9N2 - t 9N2 + x 9N3 - t 9N3 +…+ x 9Nk - t 9Nk

[0040] Among them, x 11 - t 11 , x 12 - t 12 , x 13 - t 13 ,…, x 1k - t 1k are respectively the first values of the residual functions with the smallest values corresponding to the subsequences IMF 1 , IMF 2 , IMF 3 ,…, IMF k ; x 21 - t 21 , x 22 - t 22 , x 23 - t 23 ,…, x 2k - t 2k are respectively the subsequences IMF 1 , IMF 2 , IMF 3, …, IMF k The second value of the residual function with the smallest corresponding value; x 31 -t 31 , x 32 -t 32 , x 33 -t 33 , …, x 3k -t 3k Are respectively the third value of the residual function with the smallest corresponding value of the subsequences IMF 1 , IMF 2 , IMF 3 , …, IMF k ; x 9N1 -t 9N1 , x 9N2 -t 9N2 , x 9N3 -t 9N3 , …, x 9Nk -t 9Nk Are respectively the 9N-th value of the residual function with the smallest corresponding value of the subsequences IMF 1 , IMF 2 , IMF 3 , …, IMF k .

[0041] A further improvement of the present invention lies in that: the correction formula is specifically:

[0042]

[0043] Wherein, f(t)' ij Is the corrected random function; sin() is the sine function; ln is the natural logarithm.

[0044] The present invention also provides a computer device, including a processor and a memory, and the processor is used to execute a computer program stored in the memory to implement the steps of the generator fault diagnosis method based on vibration trend prediction as described above.

[0045] The present invention also provides a computer-readable storage medium, and the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the steps of the generator fault diagnosis method based on vibration trend prediction as described above are implemented.

[0046] Compared with the prior art, the positive and progressive effects of the present invention are as follows:

[0047] The generator fault diagnosis method based on vibration trend prediction provided by the present invention can automatically adjust the subsequences in the prediction set according to the prediction error, and continuously optimize the prediction result through iterative correction to meet the fault diagnosis requirements under different generators and different operating conditions. By decomposing the generator historical vibration signal sequence into multiple subsequences, and respectively generating random functions and calculating residual functions for each subsequence, it can capture the characteristic information in the vibration signal more meticulously, thereby improving the accuracy of fault diagnosis; using a neural network model for prediction, and combining the strategies of iterative loop and residual function minimization, it can gradually approach the real vibration trend and enhance the accuracy of diagnosis; through iterative loop and multiple random function generations, and selecting the optimal result, it overcomes the nonlinearity and non-periodicity of the vibration signal, enhancing the stability and reliability of the prediction; the introduction of the residual sequence plays a role in smoothing the vibration signal and reducing noise interference, improving the stability of the prediction; through vibration trend prediction, it can capture the abnormal changes in the vibration signal at the initial stage of the generator fault, thereby realizing early warning of the generator fault, which helps to detect and handle potential faults in time and avoid equipment damage and production interruption caused by the further development of the fault. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings in the specification are used to provide a further understanding of the present invention, and constitute a part of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention, and do not constitute an improper limitation to the present invention.

[0049] Figure 1 It is a schematic flow chart of a generator fault diagnosis method based on vibration trend prediction of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0050] The following further describes the present invention in detail with reference to the accompanying drawings and specific embodiments, which is an explanation rather than a limitation of the present invention.

[0051] See Figure 1 , a generator fault diagnosis method based on vibration trend prediction, includes the following steps:

[0052] S1. Obtain the generator historical vibration signal sequence, divide the generator historical vibration signal sequence into a prediction set sequence and a verification set sequence according to a preset ratio; input the prediction set sequence into a trained neural network model for prediction to obtain a predicted value, and calculate the baseline prediction error SSE based on the predicted value and the actual value in the verification set sequence;

[0053] S2. Decompose the prediction set sequence to obtain a number of subsequences IMF 1 ~IMF K , IMF 1 is the first subsequence obtained by decomposition, IMF Kis the Kth subsequence obtained by decomposition, where K is the total number of subsequences obtained by decomposition;

[0054] S3. Through an iterative loop, perform M random function generations on each subsequence in turn. Based on the random functions of each subsequence that conform to the periodic function law, calculate the residual function; select the random function corresponding to the minimum value of the residual function of each subsequence as the subsequence of the Yth prediction set;

[0055] S4. Sum the minimum values of the residual functions of the K subsequences to obtain the residual sequence Q;

[0056] S5. Input the 1st to Kth subsequences in the Yth prediction set and the residual sequence Q into the trained neural network model for prediction to obtain the Yth predicted value; Y is the number of prediction sets generated based on random functions;

[0057] S6. Based on the Yth predicted value and the actual value in the validation set sequence, calculate the prediction error SSE(Y), where SSE(Y) is the prediction error of the Yth prediction set generated based on random functions; determine whether the prediction error SSE(Y) is less than the benchmark prediction error SSE. If the determination result is yes, diagnose the generator fault based on the Yth predicted value; if the determination result is no, execute step S7;

[0058] S7. Based on the correction formula, correct the 1st to Kth subsequences in the Yth prediction set, let Y = Y + 1, obtain the subsequences in the Yth prediction set, and repeat steps S5 and S6.

[0059] The generator fault diagnosis method based on vibration trend prediction provided by the present invention can automatically adjust the subsequences in the prediction set according to the prediction error, and continuously optimize the prediction result through iterative correction to meet the fault diagnosis requirements under different generators and different operating conditions. By decomposing the generator historical vibration signal sequence into multiple subsequences, and respectively performing random function generation and residual function calculation on each subsequence, it can capture the characteristic information in the vibration signal more meticulously, thereby improving the accuracy of fault diagnosis; using the neural network model for prediction, and combining the strategies of iterative loop and residual function minimization, it can gradually approach the real vibration trend and enhance the accuracy of diagnosis; through iterative loop and multiple random function generations, and selecting the optimal result, it overcomes the nonlinearity and non-periodicity of the vibration signal, enhancing the stability and reliability of the prediction; the introduction of the residual sequence plays a role in smoothing the vibration signal and reducing noise interference, improving the stability of the prediction; through vibration trend prediction, it can capture the abnormal changes in the vibration signal at the initial stage of the generator fault, thereby realizing the early warning of the generator fault, which helps to timely discover and handle potential faults and avoid equipment damage and production interruption caused by the further development of the fault.

[0060] Specifically, step S3 is specifically as follows:

[0061] S31. Preset the number of loop times M, where M is at least equal to 100000. Let i = 0 and j = 0. i is the i-th subsequence among a number of subsequences, and j is the j-th loop of the i-th subsequence;

[0062] S32. Let i = i + 1;

[0063] S33. Let j = j + 1, and based on the subsequence IMF i , generate the corresponding random function f(t) ij ;

[0064] S34. Determine whether the random function f(t) ij conforms to the law of a periodic function. If the judgment is yes, then based on the random function f(t) ij , calculate the corresponding residual function Q(t) ij of the random function f(t) ij , and execute step S35; if the judgment is no, then directly execute step S35;

[0065] S35. Determine whether j is equal to M. If the judgment is no, then return to step S33; if the judgment is yes, then calculate all the values of the residual functions of the subsequence IMF i . The residual function with the smallest value is Q(t) min , and the random function f(t) min corresponding to Q(t) ij is the i-th subsequence in the Y-th prediction set, where Y = 1, and execute step S36;

[0066] S36. Determine whether i is equal to K. If the judgment is yes, then execute step S4; if the judgment is no, then let j = 0 and return to step S32;

[0067] Step S4 is specifically as follows: Calculate the sum of all the residual functions Q(t) min with the smallest values obtained in step S35 to obtain the residual sequence Q.

[0068] In step S34, regardless of whether the random function f(t) ij conforms to the law of a periodic function, step S35 must be executed to enter the next loop; M is at least equal to 100000. Since the number of loop times M is set large enough, it is defaulted that within M loops, there must be a random function f(t) ij that conforms to the periodic law.

[0069] Specifically, the trained neural network model is an ELM model;

[0070] The benchmark prediction error SSE is specifically as follows:

[0071]

[0072] Among them, N is the number of subsequences in the validation set sequence; is the nth actual value in the validation set sequence, and is the nth value in the predicted values.

[0073] Specifically, in step S1, the preset ratio is 9:1; in step S2, the variational mode decomposition (VMD) method is used to decompose the prediction set sequence.

[0074] Specifically, based on the subsequence IMF i , a corresponding random function f(t) is generated ij Specifically:

[0075] Let IMF i = [x 1i , x 2i , x 3i , …, x 9Ni , and IMF i is the ith subsequence among several subsequences IMF 1 ~IMF K , then f(t) ij = [t 1i , t 2i , t 3i , …, t 9Ni = [rand(0.1x 1i ~1.9x 1i ), rand(0.1x 2i ~1.9x 2i ), rand(0.1x 3i ~1.9x 3i ), …, rand(0.1x 9Ni ~1.9x 9Ni )];

[0076] Among them, rand() is the random function; x 1i , x 2i , x 3i , …, x 9Ni are respectively the 1st, 2nd, 3rd, …, 9Nth values of the subsequence IMF i ; t 1i , t 2i , t 3i , …, t 9Ni are respectively the 1st, 2nd, 3rd, …, 9Nth values of the random function f(t) ij .

[0077] Specifically, the rule of the periodic function is specifically:

[0078]

[0079] where t wi is the w-th value of the random function of the subsequence IMF i ; t (w+T)i is the (w + T)-th value of the random function of the subsequence IMF i ; T is the period; is the regularity parameter.

[0080] Specifically, the residual function Q(t) ij is specifically:

[0081] Q(t) ij = IMF i - f(t) ij =

x 1i - t 1i ,x 2i - t 2i ,x 3i - t 3i ,…,x 9Ni - t 9Ni

[0082] The value A of the residual function is specifically:

[0083]

[0084] The residual sequence Q is specifically:

[0085] Q =

x 11 - t 11 + x 12 - t 12 + x 13 - t 13 +…+ x 1k - t 1k ,x 21 - t 21 + x 22 - t 22 + x 23 - t 23 +…+ x 2k - t 2k ,x 31 - t 31 + x 32 - t 32 + x 33 - t 33 +…+ x 3k - t 3k ,…,x 9N1 - t 9N1 + x 9N2 - t 9N2 + x9N3 -t 9N3 +…+x 9Nk -t 9Nk

[0086] Among them, x 11 -t 11 、x 12 -t 12 、x 13 -t 13 、…、x 1k -t 1k are respectively the first values of the residual functions with the smallest values corresponding to the subsequences IMF 1 、IMF 2 、IMF 3 、…、IMF k ; x 21 -t 21 、x 22 -t 22 、x 23 -t 23 、…、x 2k -t 2k are respectively the second values of the residual functions with the smallest values corresponding to the subsequences IMF 1 、IMF 2 、IMF 3 、…、IMF k ; x 31 -t 31 、x 32 -t 32 、x 33 -t 33 、…、x 3k -t 3k are respectively the third values of the residual functions with the smallest values corresponding to the subsequences IMF 1 、IMF 2 、IMF 3 、…、IMF k ; x 9N1 -t 9N1 、x 9N2 -t 9N2 、x 9N3 -t 9N3 、…、x 9Nk -t 9Nk are respectively the 9Nth values of the residual functions with the smallest values corresponding to the subsequences IMF 1 、IMF 2 、IMF 3 、…、IMF k .

[0087] Specifically, the correction formula is specifically as follows:

[0088]

[0089] where f(t)' ij is the corrected random function; sin() is the sine function; ln is the natural logarithm.

[0090] To further verify the advantages of this method, the historical vibration signals of the generator are predicted using the method of this application and the traditional prediction method respectively. The traditional prediction method is as follows: after the historical vibration signal prediction set sequence is decomposed by VMD, it is directly input into the ELM model for prediction; in the experiment of this application, MAPE (Mean Absolute Percentage Error) is selected as the evaluation criterion for each model, and the prediction results (i.e., MAPE values) are shown in Table 1:

[0091] Table 1 Prediction Results

[0092]

[0093] It can be seen that the method of this application has higher accuracy and reliability in predicting the vibration signals of the generator.

[0094] Based on the same inventive concept, an embodiment of this application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the generator fault diagnosis method based on vibration trend prediction. Among them, the memory may include internal memory, such as high-speed random access memory, and may also include non-volatile memory, such as at least one disk memory, etc.; the processor, network interface, and memory are interconnected through an internal bus, and this internal bus can be an Industry Standard Architecture bus, a Peripheral Component Interconnect standard bus, an Extended Industry Standard Architecture bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The memory is used to store programs. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory may include internal memory and non-volatile memory, and provides instructions and data to the processor.

[0095] Based on the same inventive concept, embodiments of the present application provide a computer-readable storage medium storing a computer program, which when executed by a processor implements the steps of the generator fault diagnosis method based on vibration trend prediction. Specifically, the computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may include RAM (Random Access Memory) and / or cache, etc. The non-volatile memory may include ROM (Read-Only Memory), hard disk, flash memory, optical disc, magnetic disk, etc.

[0096] Those skilled in the art should understand that embodiments of the present invention may be provided as a method, a computer program product, or a combination thereof. Therefore, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM (Compact Disc Read-Only Memory), optical storage, etc.) containing computer-usable program code.

[0097] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer device or other programmable data processing device produce means for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or combinations of blocks.

[0098] These computer program instructions can also be stored in a computer-readable memory that can direct a computer device or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or combinations of blocks.

[0099] These computer program instructions may also be loaded onto a computer device or other programmable data processing device, so that a series of operation steps are executed on the computer device or other programmable device to generate a process implemented by the computer device, and thus the instructions executed on the computer device or other programmable device provide for implementing in the process Figure 1 one process or a plurality of processes and / or blocks Figure 1 steps for the functions specified in one block or a plurality of blocks.

[0100] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0101] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A generator fault diagnosis method based on vibration trend prediction, characterized in that: The following steps are involved: S1. Obtain the historical vibration signal sequence of the generator, and divide the historical vibration signal sequence of the generator into a prediction set sequence and a verification set sequence according to a preset ratio; input the prediction set sequence into the trained neural network model for prediction to obtain a prediction value, and calculate the benchmark prediction error SSE based on the prediction value and the actual value in the verification set sequence; S2. Decompose the prediction set sequence to obtain several subsequences IMF1~IMF K , IMF1 is the first subsequence obtained by decomposition, IMF K is the Kth subsequence obtained by decomposition, and K is the total number of subsequences obtained by decomposition; S3, through iterative loops, generate random functions for each subsequence M times in turn, and calculate the residual function based on the random function of each subsequence that conforms to the law of periodic functions; select the random function corresponding to the minimum value of the residual function of each subsequence as the subsequence of the Yth prediction set; S4, summing up the minimum values ​​of the residual functions of the K subsequences to obtain a residual sequence Q; S5, input the 1st to Kth subsequences and the residual sequence Q in the Yth prediction set into the trained neural network model for prediction, and obtain the Yth prediction value; Y is the number of prediction sets generated based on the random function; S6. Based on the Yth predicted value and the actual value in the validation set sequence, calculate the prediction error SSE(Y), where SSE(Y) is the prediction error of the Yth prediction set generated based on the random function; determine whether the prediction error SSE(Y) is less than the reference prediction error SSE. If the determination result is yes, diagnose the generator fault based on the Yth predicted value; if the determination result is no, execute step S7; S7. Based on the correction formula, correct the 1st to Kth subsequences in the Yth prediction set, set Y=Y+1, obtain the subsequences in the Yth prediction set, and repeat steps S5 and S6.

2. A generator fault diagnosis method based on vibration trend prediction according to claim 1, characterized in that: Step S3 is specifically as follows: S31, preset the number of cycles M, M is at least equal to 100000, let i=0, j=0, i is the i-th subsequence among a plurality of subsequences, j is the j-th cycle of the i-th subsequence; S32, let i=i+1; S33, let j = j + 1, based on the subsequence IMF i , generate the corresponding random function f(t) ij ; S34. Determine the random function f(t) ij Does it conform to the law of periodic function? If it is judged to be yes, then based on the random function f(t) ij , calculate the random function f(t) ij The corresponding residual function Q(t) ij , execute step S35; if the judgment is no, directly execute step S35; S35, determine whether j is equal to M, if not, return to step S33; If the judgment is yes, calculate the subsequence IMF i The value of all residual functions, the residual function with the smallest value is Q(t) min , Q(t) min The corresponding random function f(t) ij For the i-th subsequence in the Y-th prediction set, Y=1, execute step S36; S36, determine whether i is equal to K, if it is, execute step S4; if it is not, set j=0 and return to step S32; Step S4 is specifically: calculating the residual function Q(t) with the minimum value among all values ​​obtained in step S35 min The sum of , we get the residual sequence Q.

3. A generator fault diagnosis method based on vibration trend prediction according to claim 2, characterized in that: The trained neural network model is the ELM model; The baseline prediction error SSE is specifically: Where N is the number of subsequences in the validation set sequence; is the nth actual value in the validation set sequence, is the nth value in the prediction.

4. A generator fault diagnosis method based on vibration trend prediction according to claim 3, characterized in that: In step S1, the preset ratio is 9:1; in step S2, the VMD method is used to decompose the prediction set sequence.

5. A generator fault diagnosis method based on vibration trend prediction according to claim 4, characterized in that: Subsequence-based IMF i , generate the corresponding random function f(t) ij Specifically: IMF i =【x 1i , x 2i , x 3i , …, x 9Ni 】, IMF i is a number of subsequences IMF1~IMF K The ith subsequence in , then f(t) ij =【t 1i , t 2i , t 3i ,…,t 9Ni 】=【rand(0.1x 1i ~1.9x 1i ), rand (0.1x 2i ~1.9x 2i ), rand (0.1x 3i ~1.9x 3i ), …, rand (0.1x 9Ni ~1.9x 9Ni )]; Among them, rand() is a random function; x 1i , x 2i , x 3i , …, x 9Ni The subsequences IMF are i The 1st, 2nd, 3rd, ..., 9Nth values ​​of t 1i , t 2i , t 3i ,…,t 9Ni They are random functions f(t) ij The 1st, 2nd, 3rd, …, 9Nth values ​​of .

6. A generator fault diagnosis method based on vibration trend prediction according to claim 5, characterized in that: The specific rules of periodic functions are: Among them, t wi IMF is the subsequence i The w-th value of the random function; t (w+T)i IMF is the subsequence i The w+Tth value of the random function; T is the period; is the regularity parameter.

7. The generator fault diagnosis method based on vibration trend prediction according to claim 6, characterized in that: Residual function Q(t) ij Specifically: Q(t) ij = IMF i - f(t) ij = 【x 1i -t 1i ,x 2i -t 2i ,x 3i -t 3i ,…,x 9Ni -t 9Ni 】 The value A of the residual function is specifically: The residual sequence Q is specifically: Q=【x 11 -t 11 +x 12 -t 12 +x 13 -t 13 +…+x 1k -t 1k ,x 21 -t 21 +x 22 -t 22 +x 23 -t 23 +…+x 2k -t 2k ,x 31 -t 31 +x 32 -t 32 +x 33 -t 33 +…+x 3k -t 3k ,…,x 9N1 -t 9N1 +x 9N2 -t 9N2 +x 9N3 -t 9N3 +…+x 9Nk -t 9Nk 】 Among them, x 11 -t 11 、x 12 -t 12 、x 13 -t 13 , …, x 1k -t 1k They are subsequences IMF1, IMF2, IMF3, …, IMF k The first value of the residual function with the smallest value; x 21 -t 21 、x 22 -t 22 、x 23 -t 23 , …, x 2k -t 2k They are subsequences IMF1, IMF2, IMF3, …, IMF k The second value of the residual function with the smallest value; x 31 -t 31 、x 32 -t 32 、x 33 -t 33 , …, x 3k -t 3k They are subsequences IMF1, IMF2, IMF3, …, IMF k The third value of the residual function with the smallest value; x 9N1 -t 9N1 、x 9N2 -t 9N2 、x 9N3 -t 9N3 , …, x 9Nk -t 9Nk They are subsequences IMF1, IMF2, IMF3, …, IMF k The corresponding value is the 9Nth value of the residual function with the smallest value.

8. A generator fault diagnosis method based on vibration trend prediction according to claim 7, characterized in that: The specific correction formula is: Where, f(t)' ij is the modified random function; sin() is the sine function; ln is the natural logarithm.

9. A computer device, characterized in that: It comprises a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement the steps of the generator fault diagnosis method based on vibration trend prediction as claimed in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by the processor, the steps of the generator fault diagnosis method based on vibration trend prediction as described in any one of claims 1 to 8 are implemented.

Images