A method, system and device for extracting vibration signal characteristics of a hydro-generating unit

Abstract

The present invention discloses a method, a system and a device for extracting vibration signal characteristics of a hydropower unit, relating to the field of feature extraction, including: obtaining the vibration signal of the hydropower unit; hierarchically decomposing the time series of the vibration signal by using moving average and moving difference methods based on conditional bubble entropy to obtain the matrix form of the corresponding operator for each layer; constructing a vector of non-negative integers e and obtaining the matrix form of the corresponding operator for the vector at each layer, and obtaining the hierarchical component at each layer node e by multiplying the matrix form of the corresponding operator for each layer by the time series; calculating the CBE value of each layer, and defining the set of CBE values of all components as the improved hierarchical conditional bubble entropy value HCBE; finding the optimal parameter of HCBE, and when the non-negative integer e is less than the threshold, outputting IHCBE as the feature characterizing the fault. The present invention proposes an improved hierarchical conditional bubble entropy, which makes the obtained information more detailed and improves the accuracy of hierarchical bubble entropy calculation.

Description

Technical Field

[0001] The present invention relates to the field of feature extraction, and particularly to a method, a system and a device for extracting vibration signal features of a hydropower unit. Background Art

[0002] The complex operating environment and frequently changing operating conditions of hydropower units make the vibration signals contain a large amount of noise signals. Therefore, effective feature expression of the non-linear and non-stationary signals generated by such non-linear systems as hydropower units is an important and difficult problem in the field of feature extraction.

[0003] Bubble entropy is a mathematical index for measuring signal complexity. Compared with other entropy theory-based feature extraction methods, it is more suitable for analyzing and extracting features in non-linear systems. However, the state information of the vibration of the hydropower unit contained in the bubble entropy value is insufficient and cannot fully express the state information of the hydropower unit. Summary of the Invention

[0004] The purpose of the present invention is to provide a feature extraction method, a system and a device based on improved hierarchical conditional bubble entropy in view of the deficiencies of the above-mentioned prior art, so as to solve the problems in the prior art.

[0005] The present invention specifically provides the following technical solutions. A method for extracting vibration signal features of a hydropower unit includes:

[0006] Obtaining the vibration signal of the hydropower unit;

[0007] Based on the conditional bubble entropy CBE, using the methods of moving average and moving difference to hierarchically decompose the time series of the vibration signal, and obtaining the matrix form of the corresponding operator for each layer; the operator includes the low-frequency component and the high-frequency component of the time series;

[0008] Constructing a vector representing non-negative integers e and obtaining the matrix form of the vector for the corresponding operator of each layer, and obtaining the hierarchical component at each layer node e by multiplying the matrix form of the corresponding operator of each layer by the time series;

[0009] Based on the hierarchical components at each layer node e , calculating the conditional bubble entropy CBE value of each layer, and defining the set of conditional bubble entropy CBE values of all components as the improved hierarchical conditional bubble entropy value HCBE;

[0010] Using a multi-strategy fusion Harris hawk algorithm to find the optimal parameters of HCBE, and when the non-negative integer e is less than the threshold, outputting the final improved hierarchical conditional bubble entropy value IHCBE as the feature for characterizing faults in different states of the hydropower unit.

[0011] Preferably, the process of obtaining the conditional bubble entropy CBE is specifically as follows:

[0012] Based on the bubble entropy BE, the conditional entropy is used to replace the Rényi entropy to calculate the vector sorting distribution, and the conditional bubble entropy CBE is obtained;

[0013] Among them, the conditional entropy replacing the Rényi entropy The expression of is:

[0014] ;

[0015] Among them, the specific expression of the conditional bubble entropy CBE is:

[0016] ;

[0017] Among them, is the embedding dimension set for the conditional bubble entropy, is the i conditional probability of the row vector appearing, n is the time series the maximum number of rows, i is a natural number of, represents the conditional entropy with a conditional coefficient of 2 and an embedding dimension of , represents the conditional entropy with a conditional coefficient of 2 and an embedding dimension of .

[0018] Preferably, the method of using moving average and moving difference is used to hierarchically decompose the time series of the vibration signal to obtain the matrix form of the corresponding operator for each layer, specifically as follows:

[0019] For the time series , define the operators and , and the specific expressions are:

[0020] ;

[0021] Among them, is the time series length; and respectively represent the low-frequency component and the high-frequency component of the time series, is the th time point, is the th time point;

[0022] The method of using moving average and moving difference is used to hierarchically decompose the time series of the vibration signal to obtain the matrix form of the corresponding operator for each layer, and the specific expression is:

[0023] ;

[0024] Among them, is the number of decomposition layers, is the operator corresponding to the th layer. .

[0025] Preferably, the constructed vector represents a non - negative integer e , and the specific expression is:

[0026] ;

[0027] Among them, when a given integer e exists, there is a unique vector , where , represents the rd vector value.

[0028] Preferably, the hierarchical component at each layer node e is obtained by multiplying the matrix form of the operator corresponding to each layer by the time series, and the specific expression is:

[0029] ;

[0030] Among them, is the hierarchical component at the th layer node , is the matrix form of the vector corresponding to each layer.

[0031] Preferably, calculate the conditional bubble entropy CBE value of each layer, and define the set of conditional bubble entropy CBE values of all components as the improved hierarchical conditional bubble entropy value HCBE, specifically:

[0032] ;

[0033] Among them, h represents the hierarchy, k represents the number of decomposition layers, e represents a non - negative integer, is the embedding dimension set for the conditional bubble entropy, represents the vector of non - negative integer e with the calculation hierarchy number of k for the conditional bubble entropy at the embedding dimension.

[0034] Preferably, use the multi - strategy fusion Harris hawk optimization algorithm to find the optimal parameters of HCBE, and when the non - negative integer e is less than the threshold, output the final improved hierarchical conditional bubble entropy value IHCBE, specifically:

[0035] Use the multi - strategy fusion Harris hawk optimization algorithm to set the hierarchical conditional bubble entropy When the entropy value of HCBE is input into the kernel extreme learning machine for classification, the classification accuracy of the test set is obtained. ;

[0036] The multi-strategy fusion Harris hawk optimization algorithm is used to make the hierarchical conditional bubble entropy , and the obtained entropy value is input into the kernel extreme learning machine for classification, and the classification accuracy of the test set is obtained , if , then the current value is output. At this time the value is the optimal number of levels, and the final improved hierarchical conditional bubble entropy value IHCBE is obtained.

[0037] The present invention provides a vibration signal feature extraction system for a hydropower unit, including:

[0038] A data acquisition module for acquiring the vibration signal of the hydropower unit;

[0039] A matrix acquisition module for hierarchically decomposing the time series of the vibration signal by using the moving average and moving difference methods based on the conditional bubble entropy CBE, and obtaining the matrix form of the corresponding operator for each layer; the operator includes the low-frequency component and the high-frequency component of the time series;

[0040] A hierarchical component module for constructing a vector representing non-negative integers e , and obtaining the matrix form of the corresponding operator for each layer of the vector, and obtaining the hierarchical component at each layer node e through the product of the matrix form of the corresponding operator for each layer and the time series;

[0041] An entropy value calculation module for calculating the conditional bubble entropy CBE value of each layer based on the hierarchical component at each layer node e , and defining the set of conditional bubble entropy CBE values of all components as the improved hierarchical conditional bubble entropy value HCBE;

[0042] A feature extraction module for using the multi-strategy fusion Harris hawk optimization algorithm to find the optimal parameters of HCBE, and when the non-negative integer e is less than the threshold, outputting the final improved hierarchical conditional bubble entropy value IHCBE as a feature characterizing the fault.

[0043] The present invention provides a computer device, including a memory and a processor. When the program stored in the memory is executed by the processor, the processor executes the steps of the above-mentioned vibration signal feature extraction method for a hydropower unit.

[0044] Compared with the prior art, the present invention has the following remarkable advantages:

[0045] Based on the conditional bubble entropy (CBE), the present invention uses the methods of moving average and moving difference to hierarchically decompose the original time series of the vibration signals of a hydropower unit, making the obtained vibration signal information more detailed and providing data support for subsequent feature extraction. Additionally, by constructing vectors and hierarchical components representing non - negative integers e the conditional bubble entropy (CBE) values of each layer are obtained, and the set of conditional bubble entropy (CBE) values of all components is defined as the improved hierarchical conditional bubble entropy value (HCBE). By finding the optimal parameters of HCBE, and when the non - negative integer e is less than the threshold, the final improved hierarchical conditional bubble entropy value (IHCBE) is output as the extracted feature. That is, by the above - mentioned adaptive optimization algorithm, the optimal number of hierarchies is found, which can distinguish and express valuable information in the high - frequency and low - frequency component time series of the original signal. While making the obtained information more detailed through the optimization algorithm, the accuracy of the hierarchical bubble entropy calculation is improved, and different state information of the hydropower unit can be expressed in a more detailed form, enabling better control of the health state of the hydropower unit. Description of the Drawings

[0046] Figure 1 It is a fault signal diagram of a hydraulic generator set provided in an embodiment of the present invention; where Figure 1 (a) is the original signal, Figure 1 (b) is the noise signal, Figure 1 (c) is the original signal spectrogram, Figure 1 (d) is the noise signal spectrogram;

[0047] Figure 2 It is an entropy mean distribution diagram under different decibel noises provided in an embodiment of the present invention; where Figure 2 (a) is the diagram under HPE, Figure 2 (b) is the diagram under HBE, Figure 2 (c) is the diagram under IHCBE;

[0048] Figure 3 It is a vibration signal waveform diagram provided in an embodiment of the present invention; where Figure 3 (a), Figure 3 (b), Figure 3 (c), and Figure 3 (d) are vibration signal waveform diagrams under 4 different unit states respectively;

[0049] Figure 4 It is a different entropy visualization result diagram provided in an embodiment of the present invention; where Figure 4 (a) is the diagram under IHCBE, Figure 4 (b) is the diagram under HBE, Figure 4 (c) is the diagram under HPE;

[0050] Figure 5 This is the KELM classification result diagram provided in the embodiment of the present invention; among them Figure 5 (a) of which is the diagram under IHCBE-KELM, Figure 5 (b) of which is the diagram under HBE-KELM;

[0051] Figure 6 This is an additional attached drawing of the KELM classification result provided in the embodiment of the present invention, which is the diagram under HPE-KELM;

[0052] Figure 7 This is the overall flowchart of a method for extracting vibration signal characteristics of a hydro-generator unit provided by the present invention;

[0053] Figure 8 This is the flowchart of IHCBE-KELM provided by the present invention;

[0054] Figure 9 This is the overall flowchart of a method for extracting vibration signal characteristics of a hydro-generator unit provided by the present invention. Specific embodiments

[0055] Next, in combination with the attached drawings in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0056] As Figure 7 、 Figure 8 and Figure 9 shown, a method for extracting vibration signal characteristics of a hydro-generator unit in this embodiment includes the following steps:

[0057] Step S1: Obtain the vibration signal of the hydro-generator unit.

[0058] Step S2: Based on the conditional bubble entropy CBE, use the methods of moving average and moving difference to hierarchically decompose the time series of the vibration signal to obtain the matrix form of the corresponding operator for each layer; the operator includes the low-frequency component and the high-frequency component of the time series.

[0059] Bubble entropy is an algorithm based on permutation entropy. It sorts the vectors embedded in the space with permutation entropy. The metric used by bubble entropy is the number of steps of the sorting algorithm. In the sorting process, bubble sort is used to calculate the vectors, and the number of exchanges required to sort them in ascending order. Then calculate the Rényi entropy of the vector sorting distribution to obtain the bubble entropy value. For a given time series signal , the calculation method of BE is as follows:

[0060] (1);

[0061] For BE, Set it to 2, then under this condition, the Rényi entropy can be expressed as:

[0062] (2);

[0063] Use to represent the conditional Rényi entropy value, and represent the vector sorting distribution through it. Similar to the approximate entropy, the expression of the bubble entropy is:

[0064] (3);

[0065] Since the bubble entropy only focuses on the sorting of the signal and cannot effectively transmit the signal information, in view of this problem, the present invention combines the conditional entropy and the bubble entropy theory and proposes the conditional bubble entropy. The conditional bubble entropy is to replace the permutation entropy in the bubble entropy with the conditional entropy, and the conditional entropy The expression is as follows:

[0066] (4);

[0067] Among them, The embedding dimension set for the conditional bubble entropy, Is the i Conditional probability of the occurrence of the row vector, n Is the time series The maximum number of rows, i Is Natural number, Indicates that the conditional coefficient is 2 and the embedding dimension is Conditional entropy, Indicates that the conditional coefficient is 2 and the embedding dimension is Conditional entropy.

[0068] Among them, Figure 7 The enlarged views of HCBE and HPE in Figure 4 As shown in Figure 8 The enlargement of the test set in Figure 5 As shown in

[0069] Based on the traditional CBE, HCBE uses the methods of moving average and moving difference to perform hierarchical decomposition on the original time series, and finds the optimal number of levels through the multi-strategy fusion Harris hawk optimization algorithm, making the obtained fault information more detailed and also improving the calculation accuracy of CBE. The main steps to calculate the IHCBE of the given time series Are as follows:

[0070] For the original time series , Define the operators And is:

[0071] ;

[0072] In the formula, is the length of the time series; and respectively represent the low-frequency component and the high-frequency component of the time series, is the th time point, is the th time point.

[0073] (2) The matrix form of the operator corresponding to the th layer can be expressed as:

[0074] ;

[0075] In the formula, is the decomposition layer number. If is too small, the frequency band of the time series is not divided in detail enough to obtain sufficient low-frequency and high-frequency components. If is too large, the calculation efficiency is low. Considering comprehensively, is taken as 4.

[0076] Step S3: Construct a vector representing the non-negative integer e , and obtain the matrix form of the vector corresponding to each layer of the operator. Obtain the hierarchical component at each layer node e through the product of the matrix form of the operator corresponding to each layer and the time series.

[0077] Construct a vector used to represent the non-negative integer , where , as shown in the following formula:

[0078] ;

[0079] It can be seen that given an integer , there is a unique corresponding to it, where , represents the th vector value.

[0080] The hierarchical component at the th layer node can be obtained from the following formula:

[0081] ;

[0082] When the decomposition level is 4, the time series hierarchical decomposition process is as Figure 1 shown

[0083] Step S4: Based on the hierarchical components at each layer node e calculate the conditional bubble entropy CBE value for each layer, and define the set of conditional bubble entropy CBE values of all components as the improved hierarchical conditional bubble entropy value HCBE.

[0084] Calculate the CBE value of each layer through equations (4) - (8), and define the set of CBE values of all components as HCBE. The specific process is shown in equation (9):

[0085] (9);

[0086] where h represents the level, k represents the decomposition level, e represents a non - negative integer, is the embedding dimension set for the conditional bubble entropy, represents the vector of non - negative integer e with the conditional bubble entropy calculation level k at the embedding dimension.

[0087] Step S5: Use the multi - strategy fusion Harris hawks optimization algorithm to find the optimal parameters of HCBE, and when the non - negative integer e is less than the threshold, output the final improved hierarchical conditional bubble entropy value IHCBE as the feature for characterizing faults in different states of the hydropower unit.

[0088] Since the feature extraction results of IHCBE, HBE, and HPE are all feature vectors and it is not intuitive to compare their data processing effects, TSNE is introduced to visually analyze the features they extract. TSNE is an embedding model that can map data in a high - dimensional space to a low - dimensional space and preserve the local characteristics of the data set. This algorithm is very common in papers and is mainly used for the dimensionality reduction and visualization of high - dimensional data.

[0089] Algorithm verification and data classification:

[0090] Verify the stability of IHCBE against different types of noise and its recognition ability respectively, and conduct a comparative analysis using HBE and HPE. The experimental results show that the stability of IHCBE is the best, followed by HBE, and the stability of HPE is the worst among the three; IHCBE still has stability for different types of noise and has good anti - noise performance.

[0091] Furthermore, classify the extracted results with the help of two classifiers, the extreme learning machine (ELM) and the kernel extreme learning machine (KELM). The results show that the feature extraction effect of IHCBE is the best, and the diagnostic rate of IHCBE - KELM is the highest.

[0092] Classifiers: Extreme Learning Machine (ELM) and Kernel Extreme Learning Machine (KELM):

[0093] The Extreme Learning Machine (ELM) does not require gradient-based backpropagation to adjust weights. Its structure is a new type of single-hidden-layer feedforward neural network, as Figure 2 shown. Compared with traditional neural networks, ELM has good generalization performance and extremely fast learning ability. The calculation process of ELM is as follows:

[0094] ;

[0095] The above formula can be abbreviated as:

[0096] ;

[0097] In the formula, is the number of hidden units; is the output of the network; is the number of samples; is the weight vector between the th hidden layer and the output; is the activation function; is the input vector; is the bias vector.

[0098] Using the least squares method, we can solve:

[0099] ;

[0100] Among them, is the regularization factor; is the diagonal matrix; is the expected output.

[0101] KELM is an algorithm that improves ELM by introducing a kernel function. It has higher stability and stronger performance while retaining the advantages of ELM. The KELM regression model can be expressed as:

[0102] ;

[0103] Among them, is the kernel matrix; is the kernel function, and the radial basis kernel function RBF is selected in the present invention.

[0104] When setting the hierarchical conditional bubble entropy using the multi-strategy fusion Harris hawk optimization algorithm, the entropy value of HCBE is input into the kernel extreme learning machine for classification to obtain the classification accuracy of the test set; Using the multi-strategy fusion Harris hawk optimization algorithm to make the hierarchical conditional bubble entropy The obtained entropy value is input into the kernel extreme learning machine for classification to obtain the classification accuracy of the test set. If Repeat If Output the current value. At this time the value is the optimal number of levels, and the final improved hierarchical conditional bubble entropy value IHCBE is obtained. The present invention uses multi-class and multi-group data of a rotor vibration test bench to verify the feature extraction ability of the proposed method, and the comparative experiment and visualization results verify the effectiveness of the proposed method.

[0105] In one embodiment, the stability of IHCBE against different types of noise.

[0106] The complex operating environment and frequently changing working conditions of the hydropower unit make the vibration signal contain a large amount of noise signals. This requires IHCBE, as a feature extraction tool, to have good anti-noise performance. The present invention simulates the vibration fault signal caused by uneven guide vane opening through Equation (14):

[0107] ;

[0108] In the formula, is the simulated noisy vibration fault signal; is Gaussian white noise, and in the present invention, 45 dB, 50 dB, 55 dB, and 60 dB are taken. As Figure 1 shown, the vibration signal after being contaminated by noise is more complex, and it is more difficult to extract the fault information features.

[0109] By analyzing and comparing the distribution of IHCBE, HBE, and hierarchical permutation entropy (HPE) under different noises, the results are as Figure 2 shown.

[0110] It can be seen from Figure 2 that the HBE and HPE of the vibration signal have large fluctuations, indicating that the two entropy models of HBE and HPE are greatly affected by noise and have weak anti-noise performance. While at any scale, the overall distribution of the IHCBE of the vibration signal fluctuates less and is relatively stable, indicating that IHCBE has better anti-noise performance.

[0111] Simulation experiment: HPE, HBE, and IHCBE are introduced for comparative experiments, and the parameter settings are as follows: the number of levels = 4.

[0112] Rotor vibration test bench: The rotor of the hydropower unit has the characteristics of high-speed rotation and a complex operating environment, resulting in its easy damage, thus bringing great potential safety hazards to the operation and production of rotating machinery.

[0113] This experiment mainly simulates the normal state of the unit and three common faults of hydro-generator units, namely rubbing, imbalance, and misalignment, through a rotor test bench. (For the convenience of representing these four states, they are abbreviated as Nor, Rub, Imb, and Mis respectively). Among them, the Rub state is simulated by screwing the rubbing bolt into the rubbing thread box and contacting the rotating shaft; the Imb state is achieved by placing mass blocks on the shaft; the Mis state is simulated by misplacing the positions of the two shafts on the coupling. When collecting signals, the unit speed is set to 1200 r / min, and the sampling frequency is 2048 Hz. 100 groups of data are collected for each of the four unit states through the rotor test bench. Each group of data contains 2048 points. The vibration signals of the four unit states are as Figure 3 shown.

[0114] Use T-SNE to visually analyze the characteristic information extracted by IHCBE, HBE, and HPE. The specific results are as Figure 4 shown. The states are normal, rubbing, imbalance, and misalignment respectively. It can be seen that the coupling characteristics of different states of the unit extracted by IHCBE are not aliased; however, there are different degrees of aliasing between rubbing and misalignment in HBE; and there are different degrees of aliasing among the four states in HPE. It can be seen that IHCBE has better characteristic extraction ability.

[0115] Classifiers: ELM and KELM. To further compare the characteristic extraction effects of IHCBE, HBE, and HPE, the extreme learning machine (ELM) and kernel extreme learning machine are used to classify the above characteristic extraction results. The results are as Figure 8 and Table 1.

[0116] Figure 5 and Figure 6 are the confusion matrix diagrams of IHCBE-KELM, HBE-KELM, and HPE-KELM. It can be seen that the classification accuracy of IHCBE-KELM reaches 100%. The following comparison methods for other feature extraction and classification are shown in Table 1.

[0117] It can be seen that the diagnostic accuracy of IHCBE-ELM is 93.0, higher than 82.9 of HBE-ELM and 68.5 of HPE-ELM. The diagnostic accuracy of IHCBE-KELM is 100, higher than 92.5 of HBE-KELM and 89.5 of HPE-KELM, further proving the effectiveness of IHCBE feature extraction and indicating that the classification effect of KELM is better than that of ELM.

[0118] Table 1 Diagnostic accuracies of different methods

[0119]

[0120] The present invention proposes a vibration signal feature extraction system for a hydroelectric generating unit, comprising: a data acquisition module, a matrix acquisition module, a hierarchical component module, an entropy value calculation module, and a feature extraction module.

[0121] Among them, the data acquisition module is used to acquire the vibration signal of the hydroelectric generating unit; the matrix acquisition module is used to perform hierarchical decomposition on the time series of the vibration signal by using the moving average and moving difference methods based on the conditional bubble entropy (CBE) to obtain the matrix form of the corresponding operator for each layer; the operator includes the low-frequency component and the high-frequency component of the time series; the hierarchical component module is used to construct a vector representing non-negative integers e and obtain the matrix form of the vector corresponding to the operator for each layer, and obtain the hierarchical component at each layer node e by multiplying the matrix form of the corresponding operator for each layer by the time series; the entropy value calculation module is used to calculate the CBE value of each layer based on the hierarchical component at each layer node e and define the set of CBE values of all components as the improved hierarchical conditional bubble entropy value (HCBE); the feature extraction module is used to use the multi-strategy fusion Harris hawk optimization algorithm to find the optimal parameters of HCBE, and when the non-negative integer e is less than the threshold, output the final improved hierarchical conditional bubble entropy value (IHCBE) as the feature for characterizing faults in different states of the hydroelectric generating unit.

[0122] The above content is a further detailed description of the present invention in combination with specific preferred embodiments. For those skilled in the technical field to which the present invention belongs, without departing from the concept of the present invention, several simple deductions or substitutions can still be made, and all should be regarded as belonging to the protection scope of the present invention.

Claims

1. A method for extracting vibration signal characteristics of a hydroelectric generating unit, characterized in that Including: Obtain the vibration signal of the hydropower unit; Based on the conditional bubble entropy CBE, use the methods of moving average and moving difference to hierarchically decompose the time series of the vibration signal, and obtain the matrix form of the operator corresponding to each layer; the operator includes the low-frequency component and the high-frequency component of the time series; Construct a vector representing a non - negative integer e and obtain the matrix form of the corresponding operator for each layer of the vector. Obtain the hierarchical component at each layer node e by multiplying the matrix form of the corresponding operator for each layer by the time series; Based on the hierarchical components at each layer of nodes e calculate the conditional bubble entropy CBE value for each layer, and define the set of conditional bubble entropy CBE values of all components as the improved hierarchical conditional bubble entropy value HCBE; Use the multi-strategy fusion Harris hawk optimization algorithm to find the optimal parameters of HCBE, and when the non-negative integer e is less than the threshold, output the final improved hierarchical conditional bubble entropy value IHCBE as the feature for characterizing faults in different states of the hydropower unit. The specific process of obtaining the conditional bubble entropy CBE is as follows: Based on the bubble entropy BE, use conditional entropy to replace the Rényi entropy to calculate the vector sorting distribution, and obtain the conditional bubble entropy CBE; Among them, the conditional entropy replacing the Rényi entropy has the following expression: ； Where the specific expression of the conditional bubble entropy CBE is: ； Among them, is the embedding dimension set for the conditional bubble entropy, is the conditional probability of the i row vector occurring, n is the time series the maximum number of rows, i is a natural number of represents the conditional entropy with a conditional coefficient of 2 and an embedding dimension of ; represents the conditional entropy with a conditional coefficient of 2 and an embedding dimension of ; The Harris hawk optimization algorithm using multi-strategy fusion is used to find the optimal parameters of HCBE, and when the non-negative integer e is less than the threshold, the final improved hierarchical conditional bubble entropy value IHCBE is output, specifically: Setting Hierarchical Conditional Bubble Entropy Using a Multi-Strategy Fusion Harris Hawk Optimization Algorithm When the entropy value of HCBE is input into a kernel extreme learning machine for classification, the classification accuracy of the test set is obtained ; Using the multi-strategy fusion Harris hawk optimization algorithm to make the hierarchical conditional bubble entropy be , and input the obtained entropy value into the kernel extreme learning machine for classification to obtain the classification accuracy of the test set , if , then output the current value. At this time the value is the optimal number of levels, and the final improved hierarchical conditional bubble entropy value IHCBE is obtained.

2. The method for extracting the vibration signal characteristics of a hydropower unit according to claim 1, wherein, The method of using moving average and moving difference to hierarchically decompose the time series of the vibration signal and obtain the matrix form of the operator corresponding to each layer is specifically as follows: For a time series define the operators and The specific expressions are as follows: ； Among them, is the length of the time series; and represent the low-frequency component and the high-frequency component of the time series respectively, is the th time point, is the th time point; Use the methods of moving average and moving difference to hierarchically decompose the time series of the vibration signal, and obtain the matrix form of the operator corresponding to each layer. The specific expression is: ； Among them, is the number of decomposition layers, is the operator corresponding to the -th layer, .

3. A method for extracting vibration signal characteristics of a hydropower unit according to claim 1, characterized in that, The construction of the vector representing the non-negative integer e, the specific expression is: ； Among them, when a given integer e exists, there is a unique vector , where , represents the th vector value.

4. A method for extracting vibration signal characteristics of a hydropower unit according to claim 1, characterized in that, Obtaining the hierarchical component at each layer node by multiplying the matrix form of the corresponding operator of each layer by the time series, and the specific expression is as follows: e ​ ； Among them, is the hierarchical component at the layer node, and is the matrix form of the vector corresponding to the operator at each layer.

5. The method for extracting the vibration signal characteristics of a hydropower unit according to claim 1, wherein Calculate the conditional bubble entropy CBE value of each layer, and define the set of conditional bubble entropy CBE values of all components as the improved hierarchical conditional bubble entropy value HCBE. Specifically: ； Among them, h represents the level, k represents the number of decomposition levels, and e represents a non-negative integer. The embedding dimension set for the conditional bubble entropy A vector of non-negative integers e representing the number of levels of conditional bubble entropy calculation at the embedding dimension when it is k.

6. A vibration signal feature extraction system for a hydropower unit, which is used to execute the feature extraction method described in any one of claims 1-5, and is characterized in that Including: A data acquisition module for obtaining the vibration signal of the hydropower unit; A matrix acquisition module for hierarchically decomposing the time series of the vibration signal based on the conditional bubble entropy CBE by using the methods of moving average and moving difference, and obtaining the matrix form of the operator corresponding to each layer; the operator includes the low-frequency component and the high-frequency component of the time series; Hierarchical component module, used to construct a vector representing a non-negative integer e and obtain the matrix form of the corresponding operator of the vector at each layer, and obtain the hierarchical component at each layer node e by multiplying the matrix form of the corresponding operator of each layer by the time series; An entropy value calculation module, which is used to calculate the conditional bubble entropy CBE value of each layer based on the hierarchical components at each layer node e and define the set of conditional bubble entropy CBE values of all components as the improved hierarchical conditional bubble entropy value HCBE; A feature extraction module, which is used to find the optimal parameters of HCBE by using a multi-strategy fusion Harris hawks optimization algorithm, and when the non-negative integer e is less than the threshold, output the final improved hierarchical conditional bubble entropy value IHCBE as the feature representing the fault.

7. A computer device, characterized in that, Including a memory and a processor. When the program stored in the memory is executed by the processor, the processor executes the steps of a method for extracting the characteristics of the vibration signal of a hydropower unit as described in any one of claims 1 to 5.

Images