A bearing fault diagnosis method and system based on data analysis

Abstract

The present invention discloses a bearing fault diagnosis method and system based on data analysis, specifically relating to the technical field of bearing fault diagnosis. By comparing the preliminary availability coefficient with the preset preliminary availability coefficient threshold, the preliminary availability of the vibration signal data of the target bearing collected by the vibration sensor is judged; then, the final availability coefficient is compared with the preset final availability coefficient threshold. If the final availability coefficient is less than the preset final availability coefficient threshold, the final availability of the data is judged, and for the finally available data, the uploaded vibration signal is preprocessed, and the vibration frequency spectrum atlas of the target bearing is obtained according to the preprocessed vibration signal. According to the fault types corresponding to the preset bearing vibration faults and the vibration frequency spectrum atlas, the fault diagnosis of the target bearing is carried out. In this way, it can be determined that the collected data related to the bearing vibration fault is accurate, making the diagnosis result of the current bearing vibration fault diagnosis system more accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of bearing fault diagnosis, and particularly to a bearing fault diagnosis method and system based on data analysis. Background Art

[0002] Bearing vibration faults refer to abnormal vibrations caused by various reasons during the operation of bearings. Such vibrations can be detected and diagnosed through vibration sensors or other monitoring devices installed on the bearings. Bearing vibration faults will increase the friction and wear of the bearings, shortening their service life. In addition, the vibrations may also cause damage or instability to surrounding equipment or structures, thus affecting the operating stability of the entire production system. In severe cases, vibration faults may even cause the equipment to suddenly stop, resulting in production interruptions and additional maintenance costs. Therefore, it is crucial to diagnose bearing vibration faults in a timely manner and take corresponding treatment measures to ensure the safe operation of the equipment and production efficiency.

[0003] Under normal circumstances, when diagnosing bearing vibration faults, basically the information about bearing vibrations collected by vibration sensors is transmitted to the bearing vibration fault diagnosis system. The bearing vibration fault diagnosis system analyzes the received information to determine whether there is a fault in the bearing vibration, and then takes corresponding measures in a timely manner according to the actual bearing vibration fault situation.

[0004] However, in the above method, when using the bearing vibration fault diagnosis system to diagnose bearing vibrations, the fault diagnosis is often based on the accuracy of the data related to bearing vibration faults collected. If the data related to bearing vibration faults collected has errors and the fault diagnosis is still carried out, it may lead to problems in the diagnosis results of the current bearing vibration fault diagnosis system, resulting in incorrect results for the final bearing vibration fault diagnosis. Summary of the Invention

[0005] The object of the present invention is to solve the problem that when using the bearing vibration fault diagnosis system to diagnose bearing vibrations, the fault diagnosis is often based on the accuracy of the data related to bearing vibration faults collected. If the data related to bearing vibration faults collected has errors and the fault diagnosis is still carried out, it may lead to problems in the diagnosis results of the current bearing vibration fault diagnosis system, resulting in incorrect results for the final bearing vibration fault diagnosis. Thus, a bearing fault diagnosis method and system based on data analysis are proposed.

[0006] In the first aspect of the implementation of the present invention, a bearing fault diagnosis method based on data analysis is first proposed. The method includes:

[0007] Obtain the current sensor position information and electromagnetic interference information of the target bearing, extract the initially available key features regarding the sensor data from the sensor position information and electromagnetic interference information, and analyze the key features to judge the initial availability of the data;

[0008] For the initially available data, obtain the data transmission information of the data transmitted to the bearing vibration fault diagnosis system, extract the finally available key features regarding the sensor data from the data transmission information, and judge the final availability of the data;

[0009] For the finally available data, preprocess the uploaded vibration signal, and obtain the vibration frequency spectrum atlas of the target bearing according to the preprocessed vibration signal;

[0010] Extract the characteristic frequencies corresponding to the preset bearing vibration faults according to the fault types, and perform fault diagnosis on the target bearing according to the corresponding characteristic frequencies and the vibration frequency spectrum atlas.

[0011] Optionally, extracting the initially available key features regarding the sensor data from the sensor position information and electromagnetic interference information, and analyzing the key features to judge the initial availability of the data includes:

[0012] Generate a sensor position deviation index through the sensor position information, generate an electromagnetic interference deviation index through the electromagnetic interference information, and judge the initial availability of the data according to the sensor position deviation index and the electromagnetic interference deviation index;

[0013] The method for obtaining the sensor position deviation index is:

[0014] Obtain the current actual position images of each vibration sensor in the target bearing to obtain an actual position image set;

[0015] Overlay each image in the actual position image set with the corresponding image in the preset position image set, calculate the linear moving distance of the image position of each sensor, and obtain the linear moving distance of the position of the sensor;

[0016] Add up the linear moving distances of the positions of each sensor in the target bearing to obtain the sensor position deviation index.

[0017] Optionally, the method for obtaining the electromagnetic interference deviation index is:

[0018] Obtain the electromagnetic interference signals around the current target bearing during operation, preprocess them to obtain effective electromagnetic interference signals, and mark them as ;

[0019] Use Wavelet to the effective electromagnetic interference signal , perform wavelet transform, and its formula is:

[0020]

[0021] In the formula, is the wavelet coefficient, and are the scale parameter and the translation parameter, which are used to control the stretching and translation of the wavelet function, is the mother wavelet function, is its conjugate complex number;

[0022] Use the wavelet coefficient to calculate the current electromagnetic interference index , and the calculation formula is: , where represents the energy of the wavelet coefficient;

[0023] Calculate the difference between the current electromagnetic interference index and the preset electromagnetic interference index threshold to obtain the current electromagnetic interference deviation index;

[0024] Perform a weighted sum of the sensor position deviation index and the electromagnetic interference deviation index to obtain a preliminary availability coefficient. Compare the preliminary availability coefficient with the preset preliminary availability coefficient threshold. If the preliminary availability coefficient is less than the preset preliminary availability coefficient threshold, it is determined that the data collected by the sensor related to the vibration fault diagnosis of the target bearing is preliminarily available.

[0025] Optionally, extract the final available key features of the sensor data from the data transmission information. Judging the final availability of the data includes:

[0026] Generate a data transmission frequency consistency index and a data transmission integrity index from the data transmission information, and judge the final availability of the data according to the data transmission frequency consistency index and the data transmission integrity index, including:

[0027] The method for obtaining the data transmission frequency consistency index is:

[0028] Obtain the time corresponding to the data uploaded by each vibration sensor in the target bearing to the bearing vibration fault diagnosis system last time to obtain a data upload time series;

[0029] Calculate the absolute difference between all any two data in the upload time series, and aggregate all the calculated absolute differences to obtain an absolute difference set;

[0030] Mark the data in the absolute difference set that is greater than the preset difference threshold as 1, and calculate the ratio of the number of 1s in the absolute difference set to the total number of data to obtain the data transmission frequency consistency index.

[0031] Optionally, the method for obtaining the data transmission integrity index is as follows:

[0032] Mark the data uploaded by each vibration sensor in the target bearing to the bearing vibration fault diagnosis system for the last time, which is denoted as the sent mark.

[0033] Obtain all the marks of the data of the vibration sensors received by the bearing vibration fault diagnosis system, which is denoted as the received mark, and make the sent mark and the received mark correspond one by one, and obtain the number of inconsistent sent marks and received marks, which is denoted as the number of missing marks.

[0034] Calculate the ratio of the number of missing marks to the sent marks to obtain the data transmission integrity index.

[0035] Perform weighted summation on the data transmission frequency consistency index and the data transmission integrity index to obtain the final available coefficient, and compare the final available coefficient with the preset final available coefficient threshold. If the final available coefficient is less than the preset final available coefficient threshold, it is determined that the data obtained by the bearing vibration fault diagnosis system for the vibration fault diagnosis of the target bearing is finally available.

[0036] Optionally, for the finally available data, preprocess the uploaded vibration signals, and obtain the vibration frequency spectrum atlas of the target bearing according to the preprocessed vibration signals, including:

[0037] Preprocess the corresponding vibration signals uploaded by each vibration sensor to obtain the time-domain signals of the vibration sensors. , for the time-domain signals Perform fast Fourier transform to convert them into complex signals in the frequency domain , where represents the frequency;

[0038] Calculate the amplitude spectrum of the vibration signals , represents the amplitude of the frequency-domain signals;

[0039] Plot the amplitudes of the vibration signals corresponding to the frequency as a frequency spectrum diagram. In the frequency spectrum diagram, the horizontal axis represents the frequency and the vertical axis represents the amplitude of the vibration signals, and use this frequency spectrum diagram as the frequency spectrum diagram of the sensor.

[0040] Obtain the frequency spectrum diagrams corresponding to all vibration sensors to obtain the frequency spectrum atlas.

[0041] Optionally, extract the corresponding characteristic frequencies according to the preset fault types corresponding to the bearing vibration faults, and perform fault diagnosis on the target bearing according to the corresponding characteristic frequencies and the vibration frequency spectrum atlas, including:

[0042] The fault types corresponding to the preset bearing vibration faults include inner ring faults, outer ring faults, rolling element faults, and spatial frequency faults;

[0043] The calculation formula for the characteristic frequency corresponding to the inner ring fault is: , where is the characteristic frequency corresponding to the inner ring fault, is the diameter of the inner ring of the bearing; is the diameter of the outer ring of the bearing; is the rotational frequency of the bearing;

[0044] The calculation formula for the characteristic frequency corresponding to the outer ring fault is: , where is the characteristic frequency corresponding to the outer ring fault, is the diameter of the inner ring of the bearing; is the diameter of the outer ring of the bearing; is the rotational frequency of the bearing;

[0045] The calculation formula for the characteristic frequency corresponding to the rolling element fault is: , where is the characteristic frequency corresponding to the rolling element fault, is the number of rolling elements of the bearing, is the rotational frequency of the bearing;

[0046] The calculation formula for the characteristic frequency corresponding to the spatial frequency fault is: , where is the characteristic frequency corresponding to the spatial frequency fault, is the number of rods of the cage, is the rotational frequency of the cage;

[0047] Fault diagnosis of the target bearing is carried out according to the characteristic frequencies corresponding to the inner ring fault, outer ring fault, rolling element fault, and spatial frequency fault and the vibration frequency spectrum atlas.

[0048] Optionally, the fault diagnosis of the target bearing according to the characteristic frequencies corresponding to the inner ring fault, outer ring fault, rolling element fault, and spatial frequency fault and the vibration frequency spectrum atlas includes:

[0049] For each frequency spectrum diagram in the vibration frequency spectrum atlas, respectively obtain the characteristic frequencies corresponding to the inner ring fault, outer ring fault, rolling element fault, and spatial frequency fault and the energy values of their characteristic frequency multiples in this frequency spectrum diagram, and obtain a number of target energy values;

[0050] All the target energy values in each frequency spectrum diagram are removed, the remaining energy values are extracted, and the average value of the remaining energy values is calculated to obtain the average energy value;

[0051] Compare each target energy value with the average energy value. If the target energy value is greater than the average energy value, record the vibration fault type in the vibration fault type of the target bearing as this vibration fault type;

[0052] If the target energy value is not greater than the average energy value, it means that the vibration fault type does not exist in the target bearing;

[0053] Obtain the bearing vibration fault types corresponding to all the spectrograms in the vibration spectrogram set to get all the bearing vibration fault types of the target bearing.

[0054] In the second aspect of the implementation of the present invention, a bearing fault diagnosis system based on data analysis is further proposed. The system includes:

[0055] Preliminary judgment module: Obtain the current sensor position information and electromagnetic interference information of the target bearing, extract the key features that are initially available for the sensor data from the sensor position information and electromagnetic interference information, and analyze the key features to judge the initial availability of the data;

[0056] Final judgment module: For the initially available data, obtain the data transmission information when it is transmitted to the bearing vibration fault diagnosis system, extract the key features that are finally available for the sensor data from the data transmission information, and judge the final availability of the data;

[0057] Spectrum atlas module: For the finally available data, preprocess the uploaded vibration signal, and obtain the vibration spectrum atlas of the target bearing according to the preprocessed vibration signal;

[0058] Vibration fault diagnosis module: Extract the corresponding characteristic frequencies according to the fault types corresponding to the preset bearing vibration faults, and perform fault diagnosis on the target bearing according to the corresponding characteristic frequencies and the vibration spectrum atlas.

[0059] Advantages of the present invention:

[0060] The present invention proposes a bearing fault diagnosis method and system based on data analysis. When using the bearing vibration fault diagnosis system to diagnose the bearing vibration, it can be determined that the collected data related to the bearing vibration fault is accurate, making the diagnosis result of the current bearing vibration fault diagnosis system more accurate, and reducing the probability of errors in the final bearing vibration fault diagnosis result. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The following further describes the present invention with reference to the accompanying drawings.

[0062] Figure 1 It is a flowchart of a bearing fault diagnosis method based on data analysis provided by an embodiment of the present invention;

[0063] Figure 2 This is a framework diagram for bearing fault diagnosis based on data analysis provided by an embodiment of the present invention. Detailed implementation manners

[0064] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of 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.

[0065] Based on the embodiments of 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.

[0066] An embodiment of the present invention provides a bearing fault diagnosis method based on data analysis. Refer to Figure 1 , Figure 1 This is a flowchart of a bearing fault diagnosis method based on data analysis provided by an embodiment of the present invention. The method includes the following steps:

[0067] Obtain the current sensor position information and electromagnetic interference information of the target bearing, extract the initially available key features regarding the sensor data from the sensor position information and electromagnetic interference information, and analyze the key features to judge the initial availability of the data;

[0068] For the initially available data, obtain the data transmission information of the data transmitted to the bearing vibration fault diagnosis system, extract the finally available key features regarding the sensor data from the data transmission information, and judge the final availability of the data;

[0069] For the finally available data, preprocess the uploaded vibration signal, and obtain the vibration frequency spectrum atlas of the target bearing according to the preprocessed vibration signal;

[0070] Extract the corresponding characteristic frequencies according to the fault types corresponding to the preset bearing vibration faults, and perform fault diagnosis on the target bearing according to the corresponding characteristic frequencies and the vibration frequency spectrum atlas.

[0071] Based on the bearing fault diagnosis method based on data analysis provided by the embodiment of the present invention, in the above manner, when using the bearing vibration fault diagnosis system to diagnose the bearing vibration, it can be determined that the collected data related to the bearing vibration fault is accurate, making the diagnosis result of the current bearing vibration fault diagnosis system more accurate and reducing the probability of errors in the final bearing vibration fault diagnosis result.

[0072] It should be noted that the target bearing is the bearing for which vibration fault diagnosis is to be carried out.

[0073] In one embodiment, preliminary available key features regarding sensor data are extracted from the sensor position information and the electromagnetic interference information, and the key features are analyzed to judge the preliminary availability of the data, including:

[0074] A sensor position deviation index is generated through the sensor position information, an electromagnetic interference deviation index is generated through the electromagnetic interference information, and the preliminary availability of the data is judged according to the sensor position deviation index and the electromagnetic interference deviation index;

[0075] The method for obtaining the sensor position deviation index is as follows:

[0076] Obtain the current actual position images of each vibration sensor in the target bearing to obtain an actual position image set;

[0077] Overlay each image in the actual position image set with the corresponding image in the preset position image set, calculate the linear moving distance of the image position of each sensor, and obtain the linear moving distance of the position of this sensor;

[0078] Add up the linear moving distances of the positions of each sensor in the target bearing to obtain the sensor position deviation index.

[0079] In one implementation manner, through the above method, the actual position movement degree of all sensors in the target bearing can be accurately obtained, and the obtained sensor position deviation index is more accurate;

[0080] It should be noted that the preset position image set is an image set presented on the image of the positions of the vibration sensors determined according to the positions of the vibration sensors on the actual target bearing when they can effectively collect data for vibration fault diagnosis of the target bearing, and can be specifically determined by professionals; in addition, the positions of all vibration sensors in the target bearing can be obtained through high-precision imaging equipment or other means;

[0081] It should be noted that the greater the position deviation degree of the vibration sensor, the greater the inaccuracy of the collected data related to bearing vibration fault diagnosis, because the offset of the vibration sensor position will cause changes in the characteristics of the vibration signals it receives and cannot accurately reflect the actual working state of the target bearing. This distortion will directly affect the analysis and interpretation of the data by the vibration fault diagnosis system.

[0082] In one embodiment, the method for obtaining the electromagnetic interference deviation index is as follows:

[0083] Obtain the electromagnetic interference signals around the current target bearing during operation, preprocess them to obtain effective electromagnetic interference signals, and mark them as ;

[0084] Use Wavelet to process the effective electromagnetic interference signal , and perform wavelet transform. The formula is as follows:

[0085]

[0086] In the formula, is the wavelet coefficient, and are the scale parameter and the translation parameter, which are used to control the stretching and translation of the wavelet function, is the mother wavelet function, is its conjugate complex number;

[0087] Use the wavelet coefficient to calculate the current electromagnetic interference index , and the calculation formula is: , where represents the energy of the wavelet coefficient;

[0088] Calculate the difference between the current electromagnetic interference index and the preset electromagnetic interference index threshold to obtain the current electromagnetic interference deviation index.

[0089] It should be noted that the preset electromagnetic interference index refers to the reference value or threshold of electromagnetic interference in the environment around the target bearing under ideal or normal working conditions. This preset value is determined in advance through methods such as historical data, experimental data, or expert experience, and is used to compare the current actual electromagnetic interference situation to determine whether the degree of electromagnetic interference in the current environment is within an acceptable range; in addition, the electromagnetic interference signal around the current target bearing during operation is obtained through a high-precision electromagnetic sensor installed near the target bearing.

[0090] It should be noted that the larger the electromagnetic interference deviation index, the more serious the impact on the signal collected by the vibration sensor, and even the signal may not accurately reflect the actual vibration situation of the target bearing. Even after appropriate preprocessing such as filtering and denoising, the influence of electromagnetic interference may still not be completely eliminated. When the electromagnetic interference deviation index is larger, it means that the data collected by the vibration sensor is no longer available.

[0091] In one embodiment, judging the initial availability of data according to the sensor position deviation index and the electromagnetic interference deviation index includes:

[0092] Normalize the sensor position deviation index and the electromagnetic interference deviation index to obtain the initial availability coefficient. The initial availability coefficient is calculated by the following formula:

[0093]

[0094] In the formula, is the preliminary availability coefficient, and are the sensor position deviation index and the electromagnetic interference deviation index respectively, and are the preset proportionality coefficients of the sensor position deviation index and the electromagnetic interference deviation index respectively, and and are both greater than 0;

[0095] Compare the preliminary availability coefficient with the preset preliminary availability coefficient threshold. If the preliminary availability coefficient is less than the preset preliminary availability coefficient threshold, it is determined that the data collected by the sensor related to the vibration fault diagnosis of the target bearing is preliminarily available;

[0096] If the preliminary availability coefficient is not less than the preset preliminary availability coefficient threshold, it is determined that the data collected by the sensor related to the vibration fault diagnosis of the target bearing is preliminarily unavailable, and a first-level alarm is issued.

[0097] It should be noted that the preset preliminary availability coefficient threshold is set by professional personnel according to the actual situation and is not specifically limited;

[0098] When the preliminary availability coefficient is not less than the preset preliminary availability coefficient threshold, it is determined that the data collected by the sensor related to the vibration fault diagnosis of the target bearing is preliminarily unavailable, and a first-level alarm is issued to remind the staff that the data of the vibration fault diagnosis of the target bearing collected by the vibration sensor is unavailable and needs to be checked in time and corresponding measures should be taken.

[0099] It should be noted that through the above method, the preliminary availability of the data collected by the sensor related to the vibration fault diagnosis of the target bearing can be systematically judged. This method combines the sensor position deviation index and the electromagnetic interference deviation index and conducts a comprehensive evaluation according to the preset proportionality coefficient, effectively improving the accuracy and reliability of data evaluation.

[0100] In one embodiment, extract the key features of the finally available sensor data from the data transmission information. Judging the finally available situation of the data includes:

[0101] Generate a data transmission frequency consistency index and a data transmission integrity index from the data transmission information. Judging the finally available situation of the data according to the data transmission frequency consistency index and the data transmission integrity index includes:

[0102] The method for obtaining the data transmission frequency consistency index is:

[0103] Obtain the time corresponding to the data uploaded by each vibration sensor in the target bearing to the bearing vibration fault diagnosis system for the last time to obtain a data upload time series;

[0104] Calculate the absolute difference between any two data in the uploaded time series, and collect all the calculated absolute differences to obtain an absolute difference set;

[0105] Mark the data in the absolute difference set that is greater than the preset difference threshold as 1, and calculate the ratio of the number of 1s in the absolute difference set to the total number of data to obtain the data transmission frequency consistency index.

[0106] It should be noted that the preset difference threshold is set by professional personnel according to the actual situation and is not specifically limited;

[0107] It should be noted that during the acquisition process of the vibration signal of the target bearing, the upload frequency of each vibration sensor should be consistent when uploading data to the bearing vibration fault diagnosis system each time. If the frequencies are inconsistent, it is very likely that the vibration signal of the target bearing obtained by the bearing vibration fault diagnosis system is inaccurate and cannot represent the true vibration condition of the current target bearing. The reasons are as follows:

[0108] Data loss or duplication: If the upload frequencies of the sensors are inconsistent, it may cause the system to lack data during certain time periods or have duplicate data within the same time period, thus affecting the continuous monitoring of bearing vibration and fault diagnosis.

[0109] Inaccurate data time sequence: The time sequence information of the vibration signal is crucial for fault diagnosis. Inconsistent frequencies will make the time sequence information of the data unreliable and unable to accurately reflect the actual change trend and periodic characteristics of bearing vibration.

[0110] Therefore, maintaining the frequency consistency of the vibration sensor data upload is crucial for ensuring that the bearing vibration fault diagnosis system obtains accurate and reliable vibration signal data.

[0111] In one embodiment, the method for obtaining the data transmission integrity index is as follows:

[0112] Mark the data of each vibration sensor in the target bearing that was last uploaded to the bearing vibration fault diagnosis system respectively, denoted as the issued mark;

[0113] Obtain all the marks of the data of the vibration sensors received by the bearing vibration fault diagnosis system, denoted as the received mark, and make the issued mark and the received mark correspond one by one, and obtain the number of non - matching marks between the issued mark and the received mark, denoted as the missing mark number;

[0114] Calculate the ratio of the missing mark number to the issued mark to obtain the data transmission integrity index.

[0115] It should be noted that when the bearing vibration fault diagnosis system obtains the data transmitted by each vibration sensor, the received data should be consistent with the data transmitted by the sensor. If they are inconsistent, it is very likely that the vibration signals of the target bearing obtained by the bearing vibration fault diagnosis system are inaccurate and cannot represent the true vibration condition of the current target bearing. The reason is that if the vibration signals collected by the sensor cannot be accurately transmitted to the fault diagnosis system, it may lead to data loss or incomplete data. Such data loss may cause the system to fail to obtain complete vibration signal information, thus affecting the accurate assessment of the bearing health status.

[0116] In one embodiment, judging the final availability of data according to the data transmission frequency consistency index and the data transmission integrity index includes:

[0117] Normalize the data transmission frequency consistency index and the data transmission integrity index to obtain the final availability coefficient. The final availability coefficient is calculated by the following formula:

[0118]

[0119] In the formula, is the final availability coefficient, and are the data transmission frequency consistency index and the data transmission integrity index respectively, and are the preset proportionality coefficients of the data transmission frequency consistency index and the data transmission integrity index respectively, and and are both greater than 0;

[0120] Compare the final availability coefficient with the preset final availability coefficient threshold. If the final availability coefficient is less than the preset final availability coefficient threshold, it is determined that the data related to the vibration fault diagnosis of the target bearing obtained by the bearing vibration fault diagnosis system is finally available;

[0121] If the final availability coefficient is not less than the preset final availability coefficient threshold, it is determined that the data related to the vibration fault diagnosis of the target bearing obtained by the bearing vibration fault diagnosis system is finally unavailable, and a secondary alarm is issued.

[0122] It should be noted that the preset final availability coefficient threshold is set by professional personnel according to the actual situation and is not specifically limited;

[0123] When the final available coefficient is not less than the preset final available coefficient threshold, it is determined that the data related to the vibration fault diagnosis of the target bearing obtained by the bearing vibration fault diagnosis system is finally unavailable, and an alarm is issued to remind the staff that the data related to the vibration fault diagnosis of the target bearing obtained by the bearing vibration fault diagnosis system is unavailable and needs to be checked in time and corresponding measures should be taken.

[0124] It should be noted that through the above method, the final availability of the data can be effectively evaluated according to the frequency consistency and integrity of the sensor data, so as to carry out the bearing vibration fault diagnosis and maintenance work in a timely and accurate manner.

[0125] In one embodiment, for the finally available data, the vibration signals uploaded by it are preprocessed, and the vibration frequency spectrum atlas of the target bearing is obtained according to the preprocessed vibration signals, including:

[0126] Preprocess the corresponding vibration signals uploaded by each vibration sensor to obtain the time-domain signal of the vibration sensor , for the time-domain signal Perform a fast Fourier transform to convert it into a complex signal in the frequency domain , where represents the frequency;

[0127] Calculate the amplitude spectrum of the vibration signal , represents the amplitude of the frequency-domain signal;

[0128] Plot the amplitude of the vibration signal corresponding to the frequency as a frequency spectrum diagram. In the frequency spectrum diagram, the horizontal axis represents the frequency and the vertical axis represents the amplitude of the vibration signal. Take this frequency spectrum diagram as the frequency spectrum diagram of the sensor;

[0129] Obtain the frequency spectrum diagrams corresponding to all vibration sensors to obtain a frequency spectrum atlas.

[0130] It should be noted that the vibration signal preprocessing is to optimize the signal for subsequent analysis or diagnosis work. The following are common vibration signal preprocessing steps:

[0131] a. Data cleaning and preprocessing: Remove outliers: Detect and remove outliers that may be caused by sensor errors or abnormal device operations;

[0132] Interpolation processing: Fill in the missing parts caused by intermittent sensors or data loss to ensure the continuity of the time series;

[0133] b. Noise removal and filtering: Time-domain filtering: Use a filter to remove high-frequency noise or low-frequency interference in the vibration signal, for example: Moving average filtering: Smooth the signal and retain the trend of the signal;

[0134] Median filtering: Removes outliers and impulse noise, and retains the central position of the signal;

[0135] Wavelet transform: Extracts signal components at different scales and removes noise;

[0136] Frequency-domain filtering: Selects a suitable filter according to the spectral characteristics, e.g., low-pass filtering: Removes high-frequency components;

[0137] High-pass filtering: Removes low-frequency components;

[0138] Band-pass filtering: Restricts the frequency components of the signal within a specific frequency band;

[0139] c. Feature extraction

[0140] Time-domain features: Extracts statistical features of the vibration signal in the time domain, such as mean, variance, peak value, etc.

[0141] Frequency-domain features: Converts the vibration signal to the frequency domain using methods such as Fourier transform or wavelet transform, and extracts frequency components and spectral energy.

[0142] Time-frequency domain features: Combines time-domain and frequency-domain information, e.g., wavelet packet analysis, to extract the time-varying characteristics of the signal.

[0143] d. Data normalization and standardization

[0144] Normalization: Scales the data proportionally to a unified numerical range, eliminating numerical differences between different sensors or devices.

[0145] Standardization: Adjusts the mean and variance of the data to have unified statistical characteristics, facilitating the application and comparison of subsequent algorithms.

[0146] 3. Data quality assessment

[0147] Data integrity check: Ensures the integrity of the preprocessed data, including data length, continuity, and missing value handling.

[0148] Signal quality assessment: Analyzes the quality of the preprocessed signal to confirm whether it is suitable for subsequent vibration analysis and fault diagnosis.

[0149] Through the above preprocessing steps, the vibration signal can be effectively prepared for subsequent spectral analysis, time-domain analysis, pattern recognition, or fault diagnosis, helping engineers and technicians to more accurately understand the operating state and health condition of the mechanical system. Other preprocessing methods can also be used, which are specifically selected according to the actual situation and are not limited.

[0150] In one embodiment, performing feature extraction to obtain corresponding characteristic frequencies according to the fault types corresponding to preset bearing vibration faults, and performing fault diagnosis on the target bearing according to the corresponding characteristic frequencies and vibration spectrum atlas includes:

[0151] The fault types corresponding to the preset bearing vibration faults include inner ring faults, outer ring faults, rolling element faults, and spatial frequency faults;

[0152] The calculation formula for the characteristic frequency corresponding to the inner ring fault is: , where is the characteristic frequency corresponding to the inner ring fault, is the diameter of the inner ring of the bearing; is the diameter of the outer ring of the bearing; is the rotational frequency of the bearing;

[0153] The calculation formula for the characteristic frequency corresponding to the outer ring fault is: , where is the characteristic frequency corresponding to the outer ring fault, is the diameter of the inner ring of the bearing; is the diameter of the outer ring of the bearing; is the rotational frequency of the bearing;

[0154] The calculation formula for the characteristic frequency corresponding to the rolling element fault is: , where is the characteristic frequency corresponding to the rolling element fault, is the number of rolling elements of the bearing, is the rotational frequency of the bearing;

[0155] The calculation formula for the characteristic frequency corresponding to the spatial frequency fault is: , where is the characteristic frequency corresponding to the spatial frequency fault, is the number of bars of the cage, is the rotational frequency of the cage;

[0156] Performing fault diagnosis on the target bearing according to the characteristic frequencies corresponding to the inner ring fault, outer ring fault, rolling element fault, and spatial frequency fault and the vibration spectrum atlas.

[0157] It should be noted that the inner ring fault usually shows energy peaks at the fundamental frequency (BPFI) of the ball bearing and its multiples in the vibration spectrum. The outer ring fault usually shows energy peaks at the outer ring fundamental frequency (BPFO) of the ball bearing and its multiples in the vibration spectrum. The rolling element fault usually shows the spin frequency of the rolling element between the inner and outer rings of the bearing. The spatial frequency is the vibration frequency caused by the unevenness or fault of the cage.

[0158] It should be noted that the inner ring diameter of the bearing: usually provided by the bearing specification or manufacturer, or obtained by measuring the diameter of the bearing inner ring; the outer ring diameter of the bearing: also provided by the bearing specification or manufacturer, or obtained by measuring the diameter of the bearing outer ring; the bearing rotation frequency: obtained by measuring the rotation speed of the bearing or provided by the operating parameters of the equipment; the number of rolling elements: obtained from the bearing design or specification, usually determined by the bearing model; the number of bars of the cage: obtained from the bearing design or specification, usually determined by the bearing model.

[0159] In one embodiment, the fault diagnosis of the target bearing according to the characteristic frequencies and vibration spectrum atlases corresponding to inner ring faults, outer ring faults, rolling element faults, and spatial frequency faults includes:

[0160] For each spectrogram in the vibration spectrum atlas, respectively obtain the characteristic frequencies corresponding to inner ring faults, outer ring faults, rolling element faults, and spatial frequency faults and the energy values of their characteristic frequency multiples in this spectrogram, to obtain a number of target energy values;

[0161] Exclude all the target energy values in each spectrogram, extract the remaining energy values, and calculate the average value of the remaining energy values to obtain the average energy value;

[0162] Compare each target energy value with the average energy value. If the target energy value is greater than the average energy value, then record it as this vibration fault type in the vibration fault types of the target bearing;

[0163] If the target energy value is not greater than the average energy value, it means that the target bearing does not have this vibration fault type;

[0164] Obtain the bearing vibration fault types corresponding to all the spectrograms in the vibration spectrum atlas to obtain all the bearing vibration fault types of the target bearing.

[0165] It should be noted that by calculating the average energy value and comparing it with the target energy value to judge the bearing vibration fault type, the bearing vibration fault type diagnosed by this method can provide a more comprehensive, robust, and accurate bearing vibration fault diagnosis. This method combines the advantages of overall spectrum analysis and can better support the implementation of predictive maintenance and equipment health management strategies.

[0166] Based on the same inventive concept, the embodiment of the present invention also provides a bearing fault diagnosis system based on data analysis. Refer to Figure 2 , Figure 2 which is a schematic framework diagram of a bearing fault diagnosis system based on data analysis provided by the embodiment of the present invention, including:

[0167] Preliminary judgment module: Obtain the current sensor position information and electromagnetic interference information of the target bearing, extract the initially available key features regarding the sensor data from the sensor position information and electromagnetic interference information, and analyze the key features to judge the initial availability of the data;

[0168] Final judgment module: For the initially available data, obtain the data transmission information when it is transmitted to the bearing vibration fault diagnosis system, extract the finally available key features regarding the sensor data from the data transmission information, and judge the final availability of the data;

[0169] Spectrum atlas module: For the finally available data, preprocess the uploaded vibration signal, and obtain the vibration spectrum atlas of the target bearing based on the preprocessed vibration signal;

[0170] Vibration fault diagnosis module: Extract the corresponding characteristic frequencies according to the preset fault types corresponding to the bearing vibration faults, and perform fault diagnosis on the target bearing based on the corresponding characteristic frequencies and the vibration spectrum atlas.

[0171] Based on the bearing fault diagnosis system based on data analysis provided by the embodiments of the present invention, in the above manner, when using the bearing vibration fault diagnosis system to diagnose the bearing vibration fault, it can be determined that the collected data related to the bearing vibration fault is accurate, making the diagnosis result of the current bearing vibration fault diagnosis system more accurate, and reducing the probability of errors in the final bearing vibration fault diagnosis result.

[0172] The above has described an embodiment of the present invention in detail, but the described content is only the preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the application of the present invention shall still fall within the scope covered by the patent of the present invention.

Claims

1. A bearing fault diagnosis method based on data analysis, characterized in that, Including the following steps: Obtain the current sensor position information and electromagnetic interference information of the target bearing, extract the initially available key features regarding the sensor data from the sensor position information and electromagnetic interference information, and analyze the key features to judge the initial availability of the data; For the initially available data, obtain the data transmission information when it is transmitted to the bearing vibration fault diagnosis system, extract the finally available key features regarding the sensor data from the data transmission information, and judge the final availability of the data; For the finally available data, preprocess the uploaded vibration signal, and obtain the vibration frequency spectrum atlas of the target bearing based on the preprocessed vibration signal; Extract the corresponding characteristic frequencies according to the fault types corresponding to the preset bearing vibrations, and conduct fault diagnosis on the target bearing based on the corresponding characteristic frequencies and the vibration frequency spectrum atlas; Judging the initial availability of the data includes: Generate a sensor position deviation index through the sensor position information, generate an electromagnetic interference deviation index through the electromagnetic interference information, and judge the initial availability of the data according to the sensor position deviation index and the electromagnetic interference deviation index; The method for obtaining the sensor position deviation index is: Obtain the current actual position images of each vibration sensor in the target bearing to obtain an actual position image set; Overlay each image in the actual position image set with the corresponding image in the preset position image set, calculate the linear moving distance of the image position of each sensor, and obtain the linear moving distance of the position of this sensor; Add up the linear moving distances of the positions of each sensor in the target bearing to obtain the sensor position deviation index; The method for obtaining the electromagnetic interference deviation index is: Obtain the electromagnetic interference signals around the current target bearing during operation, preprocess them to obtain effective electromagnetic interference signals, and mark them as B(t); Perform wavelet transform on the effective electromagnetic interference signal B(t) using Morlet wavelet, and its formula is: Wherein, W(a, b) is a wavelet coefficient, a and b are a scale parameter and a translation parameter for controlling the dilation and translation of the wavelet function, ψ is a mother wavelet function, and ψ * is its conjugate complex number; Calculate the current electromagnetic interference index Byx using the wavelet coefficient W(a, b). The calculation formula is: Byx = ∑ a,b |W(a, b)| 2 , where |W(a, b)| 2 represents the energy of the wavelet coefficient; Calculate the difference between the current electromagnetic interference index and the preset electromagnetic interference index threshold to obtain the current electromagnetic interference deviation index; Perform weighted summation on the sensor position deviation index and the electromagnetic interference deviation index to obtain an initially available coefficient. The calculation formula is: Tgf = a1×Gnx + a2×Sfv, where Tgf is the initially available coefficient, Gnx and Sfv are the sensor position deviation index and the electromagnetic interference deviation index respectively, a1 and a2 are the preset proportionality coefficients of the sensor position deviation index and the electromagnetic interference deviation index respectively, and both a1 and a2 are greater than 0; Compare the initially available coefficient with the preset initially available coefficient threshold. If the initially available coefficient is less than the preset initially available coefficient threshold, it is determined that the data collected by the sensor regarding the vibration fault diagnosis of the target bearing is initially available; For the finally available data, preprocessing the uploaded vibration signal and obtaining the vibration frequency spectrum atlas of the target bearing based on the preprocessed vibration signal includes: Preprocess the corresponding vibration signals uploaded by each vibration sensor to obtain the time-domain signal x(t) of the vibration sensor. Perform a fast Fourier transform on the time-domain signal x(t) to convert it into a complex signal X(f) in the frequency domain, where f represents frequency; Calculate the amplitude spectrum |X(f)| of the vibration signal, where |X(f)| represents the amplitude of the frequency-domain signal; Plot the amplitude of the vibration signal corresponding to the frequency f as a spectrogram. In the spectrogram, the horizontal axis represents frequency and the vertical axis represents the amplitude of the vibration signal. Take this spectrogram as the spectrogram of the sensor; Obtain the spectrograms corresponding to all vibration sensors to get a set of spectrograms; Extract the corresponding characteristic frequencies according to the fault types corresponding to the preset bearing vibration faults. The fault diagnosis of the target bearing based on its corresponding characteristic frequencies and the vibration spectrogram set includes: The fault types corresponding to the preset bearing vibration faults include inner race faults, outer race faults, rolling element faults, and spatial frequency faults; The calculation formula for the characteristic frequency corresponding to the inner ring fault is as follows: In the formula, f BPFI is the characteristic frequency corresponding to the inner ring fault, d is the diameter of the inner ring of the bearing; D is the diameter of the outer ring of the bearing; f c is the rotational frequency of the bearing; The calculation formula for the characteristic frequency corresponding to the outer ring fault is as follows: In the formula, f BPFO is the characteristic frequency corresponding to the outer ring fault, d is the diameter of the inner ring of the bearing; D is the diameter of the outer ring of the bearing; f c is the rotational frequency of the bearing; The calculation formula for the characteristic frequency corresponding to the rolling element fault is as follows: In the formula, f BSF is the characteristic frequency corresponding to the rolling element fault, n is the number of rolling elements of the bearing, and f c is the rotational frequency of the bearing; The calculation formula for the characteristic frequency corresponding to the spatial frequency fault is as follows: In the formula, f FT is the characteristic frequency corresponding to the spatial frequency fault, m is the number of rods of the cage, and f r is the rotational frequency of the cage; Perform fault diagnosis on the target bearing according to the characteristic frequencies corresponding to inner race faults, outer race faults, rolling element faults, and spatial frequency faults and the vibration spectrogram set; The fault diagnosis of the target bearing based on the characteristic frequencies corresponding to inner race faults, outer race faults, rolling element faults, and spatial frequency faults and the vibration spectrogram set includes: For each spectrogram in the vibration spectrogram set, respectively obtain the characteristic frequencies corresponding to inner race faults, outer race faults, rolling element faults, and spatial frequency faults and the energy values of their characteristic frequency multiples in this spectrogram to obtain a number of target energy values; Exclude all the target energy values in each spectrogram, extract the remaining energy values, and calculate the average value of the remaining energy values to obtain the average energy value; Compare each target energy value with the average energy value. If the target energy value is greater than the average energy value, record the vibration fault type in the vibration fault type of the target bearing as this vibration fault type; If the target energy value is not greater than the average energy value, it means that the target bearing does not have this vibration fault type; Obtain the bearing vibration fault types corresponding to all spectrograms in the vibration spectrogram set to get all the bearing vibration fault types of the target bearing; Extract the ultimately available key features regarding the sensor data from the data transmission information. Judging the ultimately available situation of the data includes: Generate a data transmission frequency consistency index and a data transmission integrity index from the data transmission information. Judge the ultimately available situation of the data according to the data transmission frequency consistency index and the data transmission integrity index, including: The method for obtaining the data transmission frequency consistency index is: Obtain the time corresponding to the data uploaded by each vibration sensor in the target bearing to the bearing vibration fault diagnosis system for the last time to get a data upload time series; Calculate the absolute differences between all any two data in the upload time series, and aggregate all the calculated absolute differences to get an absolute difference set; Mark the data in the absolute difference set that is greater than the preset difference threshold as 1, and calculate the ratio of the number of 1s in the absolute difference set to the total number of data to get the data transmission frequency consistency index; The method for obtaining the data transmission integrity index is: Mark the data of each vibration sensor in the target bearing that was last uploaded to the bearing vibration fault diagnosis system correspondingly, which is denoted as the issued mark; Obtain all the marks of the data of the vibration sensors received by the bearing vibration fault diagnosis system, which is denoted as the received mark, and correspond the issued mark and the received mark one by one, and obtain the number of inconsistent issued marks and received marks, which is denoted as the number of missing marks; Calculate the ratio of the number of missing marks to the issued mark to obtain the data transmission integrity index; Perform a weighted sum of the data transmission frequency consistency index and the data transmission integrity index to obtain the final available coefficient, and compare the final available coefficient with the preset final available coefficient threshold. If the final available coefficient is less than the preset final available coefficient threshold, it is determined that the data obtained by the bearing vibration fault diagnosis system regarding the vibration fault diagnosis of the target bearing is finally available.

2. A bearing fault diagnosis system based on data analysis, which is used to implement the described bearing fault diagnosis method based on data analysis, and is characterized in that, Including: Preliminary judgment module: Obtain the current sensor position information and electromagnetic interference information of the target bearing, extract the key features that are initially available for the sensor data from the sensor position information and electromagnetic interference information, and analyze the key features to judge the initial availability of the data; Final judgment module: For the initially available data, obtain the data transmission information of the data transmitted to the bearing vibration fault diagnosis system, extract the key features that are finally available for the sensor data from the data transmission information, and judge the final availability of the data; Spectrum atlas module: For the finally available data, preprocess the vibration signal uploaded by it, and obtain the vibration spectrum atlas of the target bearing according to the preprocessed vibration signal; Vibration fault diagnosis module: Extract the corresponding characteristic frequencies according to the fault types corresponding to the preset bearing vibrations, and perform fault diagnosis on the target bearing according to the corresponding characteristic frequencies and the vibration spectrum atlas.

Images