Sliding data dilution method and system based on SSA optimized SVMD denoising and fusion of multiple principles

Abstract

The present invention discloses a sliding data dilution method and system based on SSA-optimized SVMD noise reduction and the integration of multiple principles. The method collects vibration signals and current, voltage, and speed parameter signals. Based on SSA, a composite index combining mutual information entropy and energy difference is used as a fitness function to optimize the SVMD parameter maxAlpha. The optimized SVMD algorithm is used to decompose the original vibration signal to obtain several modal components (IMFs). Noisy IMF components are discarded, and the signal is reconstructed to obtain a denoised signal. The eigenvalues ​​of the denoised signal Y are calculated, including the effective value of the full-frequency speed and the vibration impact value. Transient and steady-state operating conditions are identified for each IMF component and eigenvalue data. All transient operating condition data with changes in operating conditions is retained, while steady-state operating condition data is diluted. The overall data outside the retained data is diluted and retained according to time rules. This reduces the burden of data storage and processing, ensuring the efficiency and accuracy of data processing and analysis.

Description

Technical Field

[0001] The present invention relates to a vibration data processing and analysis technology for industrial equipment, and in particular to a sliding data dilution method and system for alleviating the burden of data storage and processing. Background Art

[0002] In modern industrial environments, with increasing automation and the rapid development of sensor technology, vibration data acquisition has become a vital tool for equipment monitoring and maintenance management. During operation, vibration signals from industrial equipment provide valuable operational status information, crucial for fault detection, health monitoring, and performance optimization. However, in practice, data acquisition and processing are often subject to noise and other interference signals. These interference can originate from the external environment, mechanical vibrations within the equipment itself, and electromagnetic interference. The effects of noise and interference complicate the raw vibration data, reducing the ratio of valid information to noise in the signal (i.e., the signal-to-noise ratio), thereby impacting the accuracy of data analysis and fault diagnosis. Data with a low signal-to-noise ratio can lead to misjudgments, preventing maintenance personnel from promptly identifying potential equipment failures, which in turn impacts production stability and safety. Therefore, effectively removing noise and improving the signal-to-noise ratio (SNR) are key issues in improving data analysis reliability.

[0003] In addition to noise, industrial systems generate a large amount of redundant data as data is continuously collected and stored. This redundant data consumes significant storage space, putting pressure on servers and impacting the efficiency of data processing and analysis. Traditionally, some companies have resorted to purging old data. While this approach is simple and straightforward, it can result in the loss of important historical data. This historical data is crucial for tracking equipment performance changes, analyzing failure trends, and developing maintenance plans.

[0004] Therefore, the current challenge lies in how to effectively remove noise during the data acquisition process and improve the signal-to-noise ratio of the data. At the same time, adopt a reasonable data dilution method to reduce the amount of data and alleviate storage pressure while ensuring data quality, so as to avoid the subsequent data processing and analysis stages leading to reduced efficiency. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a sliding data dilution method and system based on the sparrow optimization algorithm (SSA) optimization of successive variational mode decomposition (SVMD) denoising and the integration of multiple principles, so as to reduce the burden of data storage and processing and ensure the efficiency and accuracy of data processing and analysis.

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

[0007] A sliding data dilution method based on SSA optimization SVMD noise reduction and fusion of multiple principles, characterized by comprising the following steps:

[0008] S1 collects vibration signal X and current, voltage, and speed parameter signals;

[0009] S2 optimizes the SVMD parameter maxAlpha based on SSA combined with a composite indicator of mutual information entropy and energy difference as the fitness function;

[0010] S3 uses the optimized SVMD algorithm to decompose the original vibration signal X to obtain several modal components (IMFs), discards the IMF components containing noise, and reconstructs the signal to obtain the denoised signal Y;

[0011] S4 calculates the characteristic values ​​of the denoised signal Y: effective value of the full-frequency speed and vibration impact value;

[0012] S5 identifies the transient and steady-state conditions for each IMF component and eigenvalue data, retains all transient condition data with changed conditions, and dilutes the steady-state condition data;

[0013] S6 dilutes and retains the overall data other than the retained data according to the time rule.

[0014] In the above technical solution, step S2 uses mutual information entropy and energy difference as fitness functions, and the sparrow search algorithm SSA is set to adjust the SVMD parameter maxAlpha according to the value of the function. The optimization goal is to minimize mutual information entropy and energy difference.

[0015] The optimization algorithm adjusts the SVMD parameter maxAlpha to minimize the mutual information entropy and energy difference. A smaller mutual information entropy indicates less information redundancy between the modal components and the original signal, while a smaller energy difference indicates that the decomposed modal components are able to better reconstruct the original signal and preserve the signal's key energy characteristics. By optimizing this composite metric, a more optimal SVMD parameter maxAlpha can be obtained, thereby improving the quality of signal decomposition and denoising. This ensures that the decomposed modal components have both low information redundancy with the original signal and better preserve the signal's energy characteristics.

[0016] In the above technical solution, step S3 calculates the Pearson correlation coefficient of each IMF component, and selects the IMF component with a Pearson correlation coefficient greater than a set threshold for denoising and reconstruction.

[0017] The present invention selects IMF components with a Pearson correlation coefficient greater than 0.5, discards IMF components containing noise, and reconstructs the signal to obtain a denoised signal Y.

[0018] In the above technical solution, step S5 further includes at least one of the following steps:

[0019] S51 For the first type of steady-state operating condition data that meets the steady-state operating condition, when the frequency-pass speed effective value and vibration impact value parameters have an over-threshold alarm, at least the full amount of data for the alarm period shall be retained;

[0020] S52: For the second type of steady-state operating condition data that meets the steady-state operating conditions and excludes the threshold crossing alarm, for rare data in the current, voltage, and speed parameters, the data of the set number of points before and after the current value of the parameter is retained. The remaining parameters are retained synchronously according to the timestamp of the retained data of the parameter to ensure the consistency of the timestamp.

[0021] Therefore, when the amount of steady-state data storage is very large, the data dilution method based on multi-principle fusion can effectively dilute a large amount of historical data, retain important historical data, and reduce storage pressure.

[0022] In the above technical solution, step S5 calculates the absolute error between the current value and the previous value of each parameter for the effective value of the through-frequency speed, vibration impact value, current, voltage, and speed parameter change rate parameters. If and only if the absolute errors of all parameters fall within the set range, it is a steady-state operating condition; otherwise, it is a transient operating condition.

[0023] In the above technical solution, in step S5, the dilution data is grouped and retained according to the time period of year, month, and week.

[0024] For example, weekly data is retained for 5 minutes, monthly data is retained for 30 minutes, and annual data is retained for 6 hours. The time can be set according to actual needs.

[0025] In the above technical solution, in step S51, all data of the alarm time period, the set time before the alarm triggering moment, and the set time after the alarm ending moment are retained.

[0026] In the above technical solution, in step S51, the data between 15 seconds before the alarm triggering time and the data between 15 seconds after the alarm ending time are retained.

[0027] In the above technical solution, step S52 uses a gradient ratio detection method to determine whether the current, voltage, and speed parameters are rare data.

[0028] In the above technical solution, the gradient ratio detection method in step S52 is as follows: assuming that the data has 2N points, if the ratio of the Nth point to the N-1th point, the ratio of the N+1th point to the N-2th point, the ratio of the N+2th point to the N-3th point, the ratio of the N+3th point to the N-4th point,... are all greater than the set threshold for ten consecutive times, they are regarded as rare data.

[0029] In the above technical solution, in step S52, if any of these key parameters is rare data, the data of 10 points before and after the current value of the parameter is retained, and the remaining parameters are retained synchronously according to the timestamp of the parameter retention data to ensure the consistency of the timestamp.

[0030] A sliding data dilution system based on SSA optimization SVMD noise reduction and fusion of multiple principles, characterized by including:

[0031] Signal acquisition module, used to collect vibration signal X and current, voltage, and speed parameter signals;

[0032] The signal denoising and reconstruction module is used to optimize the SVMD parameter maxAlpha based on the fitness function using a composite indicator combining SSA with mutual information entropy and energy difference. The optimized SVMD algorithm is used to decompose the original vibration signal X to obtain several modal components (IMFs). The noisy IMF components are discarded, and the signal is reconstructed to obtain the denoised signal Y.

[0033] The operating condition identification and data dilution module is used to calculate the eigenvalues ​​of the denoised signal Y: the effective value of the full-frequency speed and the vibration impact value; it identifies the transient and steady-state operating conditions of each IMF component and eigenvalue data, retains all transient operating condition data with changes in the operating conditions, dilutes the steady-state operating condition data, and then dilutes the overall data according to the time series and retains them in groups.

[0034] In the above technical solution, a first-type steady-state working condition data storage unit is set in the working condition identification and data dilution module. For the full data that meets the steady-state working condition, when the effective value of the through-frequency speed and the vibration impact value parameters exceed the threshold alarm, at least the full data of the alarm time period is retained.

[0035] In the above technical solution, a second type of steady-state operating condition data storage unit is set in the operating condition identification and data dilution module. For the full amount of data that meets the steady-state operating condition and eliminates the threshold crossing alarm, for the rare data in the current, voltage, and speed parameters, the data of a set number of points before and after the current value of the parameter is retained. The remaining parameters are retained synchronously according to the timestamp of the retained data of the parameter to ensure the consistency of the timestamp.

[0036] In addition, the present invention also provides a computer-readable storage medium, in which a computer program is stored. When the program is executed, it is used to implement the above-mentioned sliding data dilution method based on SSA optimization SVMD noise reduction and fusion of multiple principles.

[0037] Therefore, the present invention optimizes the successive variational mode decomposition (SVMD) algorithm based on the sparrow optimization algorithm (SSA), and uses the composite indicator of the fusion of mutual information entropy and energy difference as the fitness function to optimize the parameter maxAlpha, so as to perform noise reduction on the signal to improve the signal-to-noise ratio of the data. At the same time, it proposes a sliding dilution method with multi-principle fusion to dilute the stored historical data, so as to retain valid data, eliminate invalid data, and reduce the burden of data storage and processing.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] The successive variational mode decomposition (SVMD) algorithm is optimized based on the sparrow optimization algorithm (SSA) combined with a composite indicator that combines mutual information entropy and energy difference as the fitness function to achieve signal noise reduction processing and improve the signal-to-noise ratio of the data. When the collected data contains a lot of noise and interference signals, the noise reduction performance of the algorithm can be improved, the noise in the vibration signal can be effectively removed, and the signal-to-noise ratio of the signal can be improved.

[0040] A method based on the accumulation of absolute errors is proposed to identify transient and steady-state operating conditions. All transient operating condition data is retained, and only the steady-state operating condition data is processed. When the operating state changes, the transient and steady-state operating conditions can be effectively identified, and the transient operating condition data is retained, while the steady-state operating condition data is diluted, thus ensuring data quality.

[0041] This paper proposes a sliding data dilution method for steady-state operating condition data, using a multi-principle approach that integrates alarm, dilution, and time principles. When the amount of steady-state data stored is very large, this multi-principle data dilution method effectively dilutes large amounts of historical data, retaining valid data while eliminating invalid data, thus reducing the burden of data storage and processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0043] Figure 1 Flowchart of a sliding data dilution method based on SSA optimization of SVMD noise reduction and integration of multiple principles according to an embodiment of the present invention. The left half is data noise reduction, and the right half is data dilution.

[0044] Figure 2 is the original vibration acceleration data X collected in one embodiment of the present invention.

[0045] Figure 3 yes Figure 2 The signal Y after denoising. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0047] like Figure 1 As shown, in order to make the purpose, technical solutions and advantages of the present invention more clear, the sliding data dilution method based on SSA optimization SVMD noise reduction and fusion of multiple principles of the embodiment of the present invention will be described in detail with reference to the accompanying drawings.

[0048] In this embodiment, the sliding data dilution method based on SSA optimization SVMD noise reduction and integration of multiple principles includes the following steps:

[0049] Collect vibration signal X and current, voltage and speed parameter signals of rotating equipment;

[0050] Based on the Sparrow Optimization Algorithm (SSA) combined with the composite index of mutual information entropy and energy difference as the fitness function, the parameter maxAlpha of the Successive Variational Mode Decomposition (SVMD) is optimized;

[0051] The optimized SVMD algorithm is used to decompose the original vibration signal X to obtain several modal components (IMFs). The Pearson correlation coefficient of each IMF is calculated. The IMF components with a Pearson correlation coefficient greater than 0.5 are selected, and the IMF components containing noise are discarded. The signal is then reconstructed to obtain the denoised signal Y.

[0052] Calculate the characteristic values ​​of signal Y: effective value of full-frequency speed, vibration impact value;

[0053] Formula for effective value of frequency speed:

[0054] Step 1: Integrate the signal Y to obtain the speed signal Y(n);

[0055] Step 2: Filter the speed signal Y(n) in the range of [3,1000 Hz] to obtain the filtered signal y(n);

[0056] Step 3: Calculate the effective value of the pass frequency speed:

[0057] Vibration shock value calculation steps:

[0058] Step 1: Band-pass filter the signal Y in the filtering range of [5k, 10kHz] to obtain the filtered signal y1;

[0059] Step 2: Perform Hilbert envelope transform on the filtered signal y1 to obtain the envelope signal y2;

[0060] Step 3: Band-pass filter the envelope signal y2 again in the filtering range of [5, 1000 Hz] to obtain the filtered signal y3;

[0061] Step 4: Calculate the vibration impact value;

[0062] In order to distinguish the steady-state and transient operating conditions of the equipment and to reasonably process the data under different operating conditions, a steady-state operating model is created based on the logical "AND" relationship between the effective value of the through-frequency speed, vibration impact value, current, voltage, and speed parameter change rate.

[0063] The following are the steps to build a steady-state model:

[0064] (1) Data collection and preprocessing:

[0065] Collect parameter data such as effective value of frequency speed, vibration impact value, current, voltage, speed, etc.

[0066] The collected data is preprocessed, including filtering, denoising, normalization and other operations, to improve data quality and consistency.

[0067] (2) Calculation of rate of change:

[0068] For each parameter, calculate the absolute error between its current value and the previous value , Indicates the i-th parameter (such as the effective value of the through-frequency speed, vibration impact value, etc.).

[0069] (3) Construction of steady-state judgment logic:

[0070] Based on the set error range (e.g., [0, 0.5]), the change rate of each parameter is judged to meet the steady-state condition. Specifically, the current working condition is considered to meet the steady-state condition if and only if the absolute error of all parameters falls within this range.

[0071] The logical "and" relationship is adopted, that is, when all parameters meet the conditions, it is determined to be a steady-state condition.

[0072] (4) Absolute error accumulation verification:

[0073] Continuously monitor the changes in parameters and accumulate the number of times the steady-state condition is met. If the cumulative number reaches 5, it is finally determined to be a steady-state condition; otherwise, it is determined to be a transient condition.

[0074] This method can effectively avoid misjudgment caused by accidental factors and improve the reliability of steady-state working condition judgment.

[0075] (5) Data processing and model building:

[0076] All data determined to be transient conditions are retained for further analysis.

[0077] For steady-state data, dilution processing is performed to reduce the data volume and improve data processing efficiency.

[0078] Through the above steps, a model that can accurately distinguish between steady-state and transient operating conditions is constructed, providing a basis for subsequent equipment status monitoring and fault diagnosis.

[0079] For the five parameters of frequency-pass speed effective value (V), vibration impact value (A), current (I), voltage (U), and speed parameter change rate (Ra), the steady-state operating model can be expressed as follows:

[0080] Steady-state condition = ;

[0081] By monitoring the rate of change of each parameter and combining it with the absolute error accumulation verification method, the model can accurately identify the operating status of the equipment, providing strong support for equipment operation status assessment and fault warning.

[0082] A verification method based on cumulative absolute error is used to identify transient and steady-state operating conditions. Specifically, if the absolute error between the current and previous values ​​of each operating parameter falls within the range [0, 0.5] (the error range can be set based on the actual equipment conditions), and if this condition is met for five consecutive times, the condition is considered steady-state; otherwise, it is transient. All transient operating condition data for which the operating condition has changed is retained, while the steady-state data is diluted.

[0083] For the full data that meets the steady-state working conditions, when the effective value of the through-frequency speed and the vibration impact value parameters exceed the threshold alarm, the full data of the alarm time period is retained, and the data between 15 seconds before the alarm trigger time and 15 seconds after the alarm end time is retained.

[0084] For all data that meets steady-state operating conditions and excludes threshold-crossing alarms, a gradient ratio detection method is used to determine whether key parameters such as current, voltage, and speed are rare data. If any of these key parameters are rare, the data for 10 points before and after the current value of the parameter is retained (the number of points can be set according to actual needs). The remaining parameters are retained synchronously with the timestamp of the retained data for the parameter to ensure timestamp consistency.

[0085] Gradient ratio detection method:

[0086] Assume that the data consists of 2N points. If the ratios of the Nth point to the N-1th point, the ratios of the N+1th point to the N-2th point, the ratios of the N+2th point to the N-3th point, and the ratios of the N+3th point to the N-4th point, etc., are all greater than 1.5 ten times in a row (the threshold can be set based on the actual device situation), the data is considered rare.

[0087] The overall data is diluted and retained according to the time series. Weekly data is retained in a group of 5 minutes, monthly data is retained in a group of 30 minutes, and annual data is retained in a group of 6 hours (the time can be set according to actual needs). The time principle dilution method is as follows:

[0088] 1) Weekly data dilution: When the full set of key parameter data contains any of transient data, alarm data, and rare data within a 5-minute time segment, the data is retained according to steps S5, S6, and S7, and the remaining data is deleted. If none of the data are included, a set of data is retained for 5 minutes.

[0089] 2) Monthly data dilution: When the full set of key parameter data contains any of transient data, alarm data, and rare data within a 30-minute time segment, the data is retained according to steps S5, S6, and S7, and the remaining data is deleted. If none of the data are included, a set of data is retained for 30 minutes.

[0090] 3) Annual data dilution: When the full key parameter data contains any of transient data, alarm data, and rare data within a 6-hour time segment, the data is retained according to steps S5, S6, and S7, and the remaining data is deleted. If none of the data are included, a set of data is retained for 6 hours.

[0091] Complete data dilution.

[0092] Example 2:

[0093] According to Figure 1 Process, select the original vibration acceleration data X of 1s as Figure 2 As shown; and simulate the current, voltage, and speed parameter values.

[0094] The 1-second data is denoised, and the Pearson correlation coefficient values ​​of the decomposed IMF components are shown in Table 1. The IMF components greater than 0.5 are selected to reconstruct the signal and obtain the denoised signal Y, as shown in Figure 3 shown.

[0095] Calculate the characteristic values ​​of signal Y: effective value of full-frequency speed and vibration impact value.

[0096] Table 1

[0097]

[0098] Determine transient and steady-state operating conditions, and retain transient operating condition data;

[0099] Determine whether the characteristic value exceeds the alarm line and retain the alarm data;

[0100] Determine the scarcity of data and retain rare data;

[0101] According to the time rules, the overall data other than the retained data is diluted and retained. Weekly data is retained in a group of 5 minutes, monthly data is retained in a group of 30 minutes, and annual data is retained in a group of 6 hours.

[0102] At this point, data dilution is complete.

[0103] Example 3

[0104] The sliding data dilution system based on SSA optimization SVMD noise reduction and fusion of multiple principles implemented in the present invention includes:

[0105] Signal acquisition module, used to collect vibration signal X and current, voltage, and speed parameter signals;

[0106] The signal denoising and reconstruction module is used to optimize the SVMD parameter maxAlpha based on the fitness function using a composite indicator combining SSA with mutual information entropy and energy difference. The optimized SVMD algorithm is used to decompose the original vibration signal X to obtain several modal components (IMFs). The noisy IMF components are discarded, and the signal is reconstructed to obtain the denoised signal Y.

[0107] The operating condition identification and data dilution module is used to calculate the eigenvalues ​​of the denoised signal Y: the effective value of the full-frequency speed and the vibration impact value; it identifies the transient and steady-state operating conditions of each IMF component and eigenvalue data, retains all transient operating condition data with changes in the operating conditions, dilutes the steady-state operating condition data, and then dilutes the overall data according to the time series and retains them in groups.

[0108] In the working condition identification and data dilution module, a first type of steady-state working condition data storage unit is set to retain the full amount of data that meets the steady-state working condition at least for the alarm period when the effective value of the through-frequency speed and the vibration impact value parameters exceed the threshold alarm;

[0109] A second type of steady-state operating condition data storage unit is set up to store all data that meets steady-state operating conditions and excludes threshold crossing alarms. For rare data in current, voltage, and speed parameters, the data of a set number of points before and after the current value of the parameter is retained; the remaining parameters are retained synchronously with the timestamp of the parameter's retained data to ensure timestamp consistency;

[0110] All transient operating condition data of the changed operating condition are retained in the third storage unit.

[0111] It should be understood that those skilled in the art can make improvements or changes based on the above description, and all such improvements and changes should fall within the scope of protection of the appended claims of the present invention.

Claims

1. A sliding data dilution method based on SSA optimization SVMD noise reduction and fusion of multiple principles, characterized by For vibration data processing, including the following steps: S1 collects vibration signal X and current, voltage, and speed parameter signals; S2 optimizes the SVMD parameter maxAlpha based on SSA combined with a composite indicator of mutual information entropy and energy difference as the fitness function; S3 uses the optimized SVMD algorithm to decompose the original vibration signal X to obtain several modal components (IMFs), discards the IMF components containing noise, and reconstructs the signal to obtain the denoised signal Y; S4 calculates the characteristic values ​​of the denoised signal Y: effective value of the full-frequency speed and vibration impact value; S5 identifies the transient and steady-state conditions for each IMF component and eigenvalue data, retains all transient condition data with changed conditions, and dilutes the steady-state condition data; S6 dilutes and retains the overall data other than the retained data according to the time rule.

2. The sliding data dilution method based on SSA optimization SVMD noise reduction and fusion of multiple principles according to claim 1 is characterized in that Step S2: Mutual information entropy and energy difference are used as fitness functions. The sparrow search algorithm SSA is set to adjust the parameter maxAlpha of SVMD according to the value of the function. The optimization goal is to minimize mutual information entropy and energy difference.

3. The sliding data dilution method based on SSA optimization SVMD noise reduction and fusion of multiple principles according to claim 1 is characterized in that Step S3: Calculate the Pearson correlation coefficient of each IMF component, and select the IMF component with a Pearson correlation coefficient greater than a set threshold for denoising and reconstruction.

4. The sliding data dilution method based on SSA optimization SVMD noise reduction and fusion of multiple principles according to claim 1 is characterized in that Step S5 further includes at least one of the following steps: S51 For the first type of steady-state operating condition data that meets the steady-state operating condition, when the frequency-pass speed effective value and vibration impact value parameters have an over-threshold alarm, at least the full amount of data for the alarm period shall be retained; S52: For the second type of steady-state operating condition data that meets the steady-state operating conditions and excludes the threshold crossing alarm, for rare data in the current, voltage, and speed parameters, the data of the set number of points before and after the current value of the parameter is retained. The remaining parameters are retained synchronously according to the timestamp of the retained data of the parameter to ensure the consistency of the timestamp.

5. The sliding data dilution method based on SSA optimization SVMD noise reduction and fusion of multiple principles according to claim 4 is characterized in that In step S51, all data of the alarm time period, the set time before the alarm triggering time, and the set time after the alarm ending time are retained.

6. The sliding data dilution method based on SSA optimization SVMD noise reduction and fusion of multiple principles according to claim 4 is characterized in that Step S52 uses a gradient ratio detection method to determine whether the current, voltage, and speed parameters are rare data.

7. The sliding data dilution method based on SSA optimization SVMD noise reduction and fusion of multiple principles according to claim 1 is characterized in that Step S5: Calculate the absolute error between the current value and the previous value of each parameter for the effective value of the through-frequency speed, vibration impact value, current, voltage, and speed parameter change rate. If and only if the absolute errors of all parameters fall within the set range, it is a steady-state operating condition; otherwise, it is a transient operating condition.

8. The sliding data dilution method based on SSA optimization SVMD noise reduction and fusion of multiple principles according to claim 1 is characterized in that In step S6, the dilution data is grouped and retained according to the time period of year, month, and week.

9. A sliding data dilution system based on SSA optimization SVMD noise reduction and fusion of multiple principles, characterized by include: Signal acquisition module, used to collect vibration signal X and current, voltage, and speed parameter signals; The signal denoising and reconstruction module is used to optimize the SVMD parameter maxAlpha based on the composite index of SSA combined with mutual information entropy and energy difference as the fitness function; The optimized SVMD algorithm is used to decompose the original vibration signal X to obtain several modal components (IMFs). The IMF components containing noise are discarded, and the signal is reconstructed to obtain the denoised signal Y. The operating condition identification and data dilution module is used to calculate the eigenvalues ​​of the denoised signal Y: the effective value of the full-frequency speed and the vibration impact value; it identifies the transient and steady-state operating conditions of each IMF component and eigenvalue data, retains all transient operating condition data with changes in the operating conditions, dilutes the steady-state operating condition data, and then dilutes the overall data according to the time series and retains them in groups.

10. The sliding data dilution system based on SSA optimization SVMD noise reduction and fusion of multiple principles according to claim 9 is characterized in that include: In the working condition identification and data dilution module, a first type of steady-state working condition data storage unit is set to retain the full amount of data that meets the steady-state working condition at least for the alarm period when the effective value of the through-frequency speed and the vibration impact value parameters exceed the threshold alarm; A second type of steady-state operating condition data storage unit is set up to store all data that meets the steady-state operating conditions and excludes threshold crossing alarms. For rare data in current, voltage, and speed parameters, a set number of points of data before and after the current value of the parameter are retained; the remaining parameters are retained synchronously according to the timestamp of the parameter's retained data to ensure the consistency of the timestamp.

Images