Method and device for diagnosing equipment bearing fault, equipment and readable storage medium

Abstract

The invention provides a method, device and equipment for diagnosing equipment bearing faults and a readable storage medium, and the method comprises the steps: carrying out the noise reduction processing of conventional data and real-time monitoring data of a to-be-diagnosed equipment bearing, and obtaining the processed conventional data and monitoring data, obtaining vibration data and current data under a standard working condition, wherein the real-time monitoring data comprises real-time vibration data and real-time current data; extracting time domain features and frequency domain features of the processed conventional data and the real-time monitoring data; and the to-be-diagnosed equipment bearing is diagnosed by combining the time domain feature, the frequency domain feature and the change condition of the real-time current data. Through the method, the effect of accurately diagnosing the equipment bearing fault can be achieved.

Description

Technical Field

[0001] The present application relates to the field of bearing equipment detection, and in particular, to a method, apparatus, device and readable storage medium for diagnosing equipment bearing faults. Background Art

[0002] At present, the vibration data of bearings monitored during the operation of rotating mechanical equipment is mainly used to diagnose and analyze the possible fault locations and fault types of bearings. By establishing intelligent algorithms (including but not limited to neural networks, support vector machines, fuzzy logic, long short-term memory networks, transfer learning algorithms, etc.), the intelligent algorithms are trained with a certain amount of fault data samples to achieve the diagnosis of equipment faults. Alternatively, signal analysis methods are used to transform the collected vibration signals (including but not limited to frequency domain analysis, envelope analysis, wavelet analysis, etc.), and these are presented to users in the form of graphics. Users analyze the health of the equipment based on basic equipment information and professional knowledge in the field of signal analysis.

[0003] However, equipment fault diagnosis algorithm models are divided into data-based modeling and mechanism-based modeling. Data-based modeling lacks relevant data on site, and the model has poor reusability. For different scenarios and equipment, the model needs to be retrained. The software based on mechanism knowledge analysis does not really realize fault diagnosis and analysis. It requires users to have strong professional knowledge to diagnose and analyze the equipment. In addition, the operating conditions of the equipment are changeable, and the vibration benchmark will also change, which makes it difficult for even personnel with rich professional knowledge to make more accurate analysis and judgment.

[0004] Therefore, how to accurately diagnose equipment bearing failure is a technical problem that needs to be solved. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a method for diagnosing equipment bearing faults. The technical solution of the embodiments of the present application can achieve the effect of accurately diagnosing equipment bearing faults.

[0006] In a first aspect, an embodiment of the present application provides a method for diagnosing equipment bearing faults, comprising: performing noise reduction processing on conventional data and real-time monitoring data of the bearing of the equipment to be diagnosed to obtain processed conventional data and monitoring data, wherein the conventional data includes vibration data and current data obtained under standard operating conditions when the equipment is normal, and the real-time monitoring data includes real-time vibration data and real-time current data; extracting time domain characteristics and frequency domain characteristics of the processed conventional data and real-time monitoring data; and diagnosing the bearing of the equipment to be diagnosed in combination with changes in time domain characteristics, frequency domain characteristics and real-time current data.

[0007] In the above embodiments of the present application, data noise reduction can improve data quality, thereby improving the accuracy of data analysis and diagnosis of equipment bearings. By using time domain features and frequency domain features, combined with current data, the fault location and type of bearing faults can be diagnosed, overcoming the problems of lack of field sample data in data modeling, resulting in difficult modeling and inaccurate modeling, and achieving the effect of accurately diagnosing equipment bearing faults.

[0008] In some embodiments, the bearing of the equipment to be diagnosed is diagnosed in combination with the changes in time domain characteristics, frequency domain characteristics and real-time current data, including: determining the time domain characteristic difference and frequency domain characteristic difference corresponding to the real-time monitoring data and conventional data of the bearing of the equipment to be diagnosed; matching the bearing fault type probability and the bearing fault location probability corresponding to the time domain characteristic difference and the frequency domain characteristic difference respectively through a preset bearing fault type probability distribution table and a bearing fault location probability distribution table; determining the fault condition of the bearing of the equipment to be diagnosed in combination with the changes in real-time current data, the bearing fault type probability and the bearing fault location probability.

[0009] In the above embodiments, the present application utilizes time domain features and frequency domain features and a probability fusion method to realize the diagnosis of the fault location and bearing fault type of the bearing, and adopts a matching mechanism to determine the most likely fault type and fault location through a preset bearing fault type probability distribution table and a bearing fault location probability distribution table.

[0010] In some embodiments, the conventional data and real-time monitoring data of the bearing of the equipment to be diagnosed are subjected to noise reduction processing to obtain processed conventional data and monitoring data, including: summing the conventional data and real-time monitoring data in segments according to the period of the signal, then taking the average value of the summed data, and removing useless information in the conventional data and real-time monitoring data to obtain the processed conventional data and monitoring data.

[0011] In the above-mentioned embodiments of the present application, by processing conventional data, monitoring data and useless information, the quality of conventional data and real-time monitoring data can be improved, thereby improving the quality of equipment bearing diagnosis.

[0012] In some embodiments, time domain features and frequency domain features of processed conventional data and real-time monitoring data are extracted, including: extracting time domain features of conventional data and real-time monitoring data according to the relationship between signal time and signal amplitude of conventional data and real-time monitoring data; extracting frequency domain features of conventional data and real-time monitoring data according to the relationship between signal frequency and signal amplitude of conventional data and real-time monitoring data.

[0013] In the above embodiments of the present application, the time domain features and frequency domain features can be accurately extracted through the signal time and signal amplitude relationship, signal frequency and signal amplitude relationship of conventional data and real-time monitoring data, and through the signal analysis formula.

[0014] In some embodiments, the bearing of the equipment to be diagnosed is diagnosed in combination with the time domain characteristics, frequency domain characteristics and changes in real-time current data, including: converting the time domain signals corresponding to the processed conventional data and the real-time monitoring data into frequency domain signals; converting the time domain signal characteristics corresponding to the processed conventional data and the real-time monitoring data into frequency domain signal characteristics; determining the probability of various types of faults occurring in the bearing of the equipment to be diagnosed based on the time domain signal characteristics; determining the probability of the bearing fault of the equipment to be diagnosed occurring in various parts based on the frequency domain signal characteristics; and diagnosing the bearing of the equipment to be diagnosed in combination with the changes in the real-time current data, the probability of various types of faults occurring in the bearing of the equipment to be diagnosed and the probability of the bearing fault of the equipment to be diagnosed occurring in various parts.

[0015] In the above embodiments, the present application utilizes time domain characteristics and frequency domain characteristics in combination with current data to realize the diagnosis of the fault location and bearing fault type of the bearing, thereby overcoming the problems of lack of field sample data in data modeling, resulting in difficult modeling and inaccurate modeling.

[0016] In some embodiments, the bearing of the equipment to be diagnosed is diagnosed by combining the changes in time domain characteristics, frequency domain characteristics and real-time current data, including: combining the knowledge of bearing mechanism, performing a probability fusion analysis on the changes in time domain characteristics, frequency domain characteristics and real-time current data, and obtaining the location and type of the bearing fault.

[0017] In the above-mentioned embodiments, the present application combines the knowledge of bearing mechanism and utilizes the probability fusion method to realize the diagnosis of the fault location and the bearing fault type of the bearing.

[0018] In some embodiments, the bearings of the equipment to be diagnosed are diagnosed in combination with the changes in time domain characteristics, frequency domain characteristics and real-time current data, including: selecting different types of values ​​in time domain characteristics and frequency domain characteristics as diagnostic basis; and diagnosing the bearings of the equipment to be diagnosed through the changes in diagnostic basis, time domain characteristics, frequency domain characteristics and real-time current data.

[0019] In the above embodiments of the present application, by selecting different types of values ​​in the time domain characteristics and the frequency domain characteristics as the diagnosis basis, the equipment bearing can be accurately diagnosed according to the diagnosis basis.

[0020] In a second aspect, an embodiment of the present application provides a device for diagnosing a bearing failure of an equipment, comprising:

[0021] A preprocessing module is used to perform noise reduction processing on the conventional data and real-time monitoring data of the bearing of the equipment to be diagnosed, so as to obtain processed conventional data and monitoring data, wherein the conventional data includes vibration data and current data obtained under standard working conditions when the equipment is normal, and the real-time monitoring data includes real-time vibration data and real-time current data;

[0022] Feature extraction module, used to extract time domain features and frequency domain features of processed conventional data and real-time monitoring data;

[0023] The diagnosis module is used to diagnose the bearing of the equipment to be diagnosed by combining the time domain characteristics, frequency domain characteristics and the changes of real-time current data.

[0024] Optionally, the diagnostic module is specifically used for:

[0025] Determine the time domain characteristic difference and frequency domain characteristic difference corresponding to the real-time monitoring data and conventional data of the bearing of the equipment to be diagnosed;

[0026] Match the bearing fault type probability and the bearing fault location probability corresponding to the time domain feature difference and the frequency domain feature difference respectively through the preset bearing fault type probability distribution table and the bearing fault location probability distribution table;

[0027] The fault condition of the bearing of the equipment to be diagnosed is determined by combining the changes in real-time current data, the probability of the bearing fault type and the probability of the bearing fault location.

[0028] Optionally, the preprocessing module is specifically used for:

[0029] The processed conventional data and real-time monitoring data are obtained by summing the conventional data and the real-time monitoring data in sections according to the signal period, taking the average value of the summed data, and removing useless information in the conventional data and the real-time monitoring data.

[0030] Optionally, the feature extraction module is specifically used for:

[0031] According to the signal time and signal amplitude relationship between the conventional data and the real-time monitoring data, the time domain characteristics of the conventional data and the real-time monitoring data are extracted;

[0032] According to the relationship between the signal frequency and signal amplitude of the conventional data and the real-time monitoring data, the frequency domain characteristics of the conventional data and the real-time monitoring data are extracted.

[0033] Optionally, the diagnostic module is specifically used for:

[0034] Convert the time domain signal features corresponding to the processed conventional data and real-time monitoring data into frequency domain signal features;

[0035] According to the time domain signal characteristics, determine the probability of various types of faults occurring in the bearing of the equipment to be diagnosed;

[0036] According to the frequency domain signal characteristics, determine the probability of the bearing fault of the equipment to be diagnosed occurring in various parts;

[0037] The bearing of the equipment to be diagnosed is diagnosed based on the changes in real-time current data, the probability of various types of failures occurring in the bearing of the equipment to be diagnosed, and the probability of failures occurring in various parts of the bearing of the equipment to be diagnosed.

[0038] Optionally, the diagnostic module is specifically used for:

[0039] Combined with the knowledge of bearing mechanism, a probability fusion analysis is performed on the changes in time domain characteristics, frequency domain characteristics and real-time current data to obtain the location and type of bearing faults.

[0040] Optionally, the diagnostic module is specifically used for:

[0041] Select different types of values ​​in time domain features and frequency domain features as the basis for diagnosis;

[0042] The bearings of the equipment to be diagnosed are diagnosed through the changes in diagnostic basis, time domain characteristics, frequency domain characteristics and real-time current data.

[0043] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the method provided in the first aspect are performed.

[0044] In a fourth aspect, an embodiment of the present application provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the method provided in the first aspect are performed.

[0045] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by practicing the embodiments of the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 A flow chart of a method for diagnosing equipment bearing failure provided in an embodiment of the present application;

[0048] Figure 2 A flowchart of an implementation method for diagnosing a bearing fault of an equipment provided in an embodiment of the present application;

[0049] Figure 3 A schematic block diagram of a device for diagnosing equipment bearing failure provided in an embodiment of the present application;

[0050] Figure 4 A schematic diagram of the structure of a device for diagnosing equipment bearing failure provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0052] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0053] This application is applied to the scenario of bearing equipment detection. The specific scenario is to perform noise reduction processing on the vibration data and current data of the equipment bearing, and then use time domain characteristics, frequency domain characteristics and current data, combined with bearing mechanism knowledge, and use probabilistic fusion methods to realize the diagnosis of the bearing fault location and bearing fault type.

[0054] At present, the current of rotating mechanical equipment during operation and the vibration data of monitoring bearings are mainly used to diagnose and analyze the possible fault locations and fault types of bearings. By establishing intelligent algorithms (including but not limited to neural networks, support vector machines, fuzzy logic, long short-term memory networks, transfer learning algorithms, etc.), the intelligent algorithms are trained with a certain amount of fault data samples to achieve the diagnosis of equipment faults. Alternatively, signal analysis methods are used to transform the collected vibration signals (including but not limited to frequency domain analysis, envelope analysis, wavelet analysis, etc.), and these are presented to users in the form of graphics. Users analyze the health of the equipment based on the basic information of the equipment and professional knowledge in the field of signal analysis. However, the equipment fault diagnosis algorithm models are divided into data-based modeling and mechanism-based modeling. The data-based modeling lacks relevant data on site, and the model has poor reusability. For different scenarios and equipment, the model needs to be retrained. The software based on mechanism knowledge analysis does not really realize fault diagnosis and analysis. Users need to have strong professional knowledge to diagnose and analyze the equipment. In addition, the operating conditions of the equipment are changeable, and the vibration benchmark will also change, which makes it difficult for even personnel with rich professional knowledge to make more accurate analysis and judgment.

[0055] To this end, this application performs noise reduction processing on the conventional data and real-time monitoring data of the bearing of the equipment to be diagnosed, and obtains the processed conventional data and monitoring data, wherein the conventional data includes vibration data and current data obtained under standard working conditions when the equipment is normal, and the real-time monitoring data includes real-time vibration data and real-time current data; extracts the time domain characteristics and frequency domain characteristics of the processed conventional data and real-time monitoring data; and diagnoses the bearing of the equipment to be diagnosed in combination with the changes in the time domain characteristics, frequency domain characteristics and real-time current data. Data noise reduction can improve data quality, thereby improving the accuracy of data analysis and diagnosis of equipment bearings. By using time domain characteristics and frequency domain characteristics, combined with current data, the fault location and type of the bearing can be diagnosed, overcoming the problems of lack of field sample data in data modeling, resulting in difficult modeling and inaccurate modeling, and achieving the effect of accurately diagnosing equipment bearing faults.

[0056] In the embodiment of the present application, the executing entity may be a diagnostic equipment bearing fault device in a diagnostic equipment bearing fault system. In actual applications, the diagnostic equipment bearing fault device may be an electronic device such as a terminal device and a server, which is not limited here.

[0057] Combine the following Figure 1 The method for diagnosing equipment bearing faults in an embodiment of the present application is described in detail.

[0058] Please see Figure 1 , Figure 1 A flow chart of a method for diagnosing a bearing fault of an equipment provided in an embodiment of the present application is shown in FIG. Figure 1 The method shown for diagnosing equipment bearing failures includes:

[0059] Step 110: performing noise reduction processing on the conventional data and real-time monitoring data of the bearing of the equipment to be diagnosed to obtain processed conventional data and monitoring data.

[0060] Among them, conventional data includes vibration data and current data obtained under standard operating conditions when the equipment is normal, and real-time monitoring data includes real-time vibration data and real-time current data.

[0061] In some embodiments of the present application, noise reduction processing is performed on the conventional data and real-time monitoring data of the bearing of the diagnostic equipment, including: summing the conventional data and the real-time monitoring data in segments according to the signal period, taking the average value of the summed data, and removing useless information in the conventional data and the real-time monitoring data to obtain processed conventional data and monitoring data.

[0062] In the above process, the present application can improve the quality of conventional data and real-time monitoring data by processing conventional data, monitoring data and useless information, thereby improving the quality of equipment bearing diagnosis.

[0063] Among them, useless information can be interference noise contained in some data and abnormal discrete data points.

[0064] Step 120: extracting time domain features and frequency domain features of the processed conventional data and real-time monitoring data.

[0065] In some embodiments of the present application, time domain features and frequency domain features of processed conventional data and real-time monitoring data are extracted, including: extracting time domain features of conventional data and real-time monitoring data according to the relationship between signal time and signal amplitude of conventional data and real-time monitoring data; extracting frequency domain features of conventional data and real-time monitoring data according to the relationship between signal frequency and signal amplitude of conventional data and real-time monitoring data.

[0066] In the above process, the present application can accurately extract time domain features and frequency domain features through the signal time and signal amplitude relationship, signal frequency and signal amplitude relationship of conventional data and real-time monitoring data, and through signal analysis formulas.

[0067] Among them, the time domain features and frequency domain features include relevant numerical values ​​of time domain signals and frequency domain signals. For example, the characteristic values ​​include maximum value, maximum absolute value, minimum value, mean value, peak-to-peak value, absolute mean value, root mean square value, root amplitude, standard deviation, sheath, skewness, margin index, waveform index, pulse index and peak index, etc.

[0068] Specifically, the calculation method of the time domain feature related information can be implemented by the method in Table 1:

[0069] Table 1

[0070]

[0071]

[0072] Among them, x(n) is the time domain sequence of the signal, n=1,2…N, and N is the number of sample points.

[0073] Optionally, the frequency domain feature is used to extract faults based on the relationship between the frequency and amplitude of the signal. The frequency domain feature can be used to diagnose the fault location of the bearing. The conversion can be achieved by the following methods:

[0074] First, the collected time domain signal is converted into a frequency domain signal. The continuous Fourier transform formula of the discrete time signal x(t) is:

[0075]

[0076] Among them, x(ω) is the frequency domain sequence of the signal, ω represents the frequency domain sequence number, n=1,2…N, t and T represent time, and α and b are constants.

[0077] Secondly, the frequency domain characteristics of conventional data and real-time monitoring data can be extracted by determining the frequency of faults occurring in different fault locations of the bearing of the equipment to be diagnosed, which can be obtained by the following formula:

[0078]

[0079]

[0080] Among them, d is the rolling element diameter; D is the average diameter of the rolling bearing; θ is the radial contact angle; n is the number of rolling elements; N is the shaft speed, FFTF is the cage failure frequency; FBSF is the bearing rolling element failure frequency; FBPFO is the bearing outer ring failure frequency; FBPFI is the bearing inner ring failure frequency.

[0081] Finally, the theoretical calculated values ​​of the frequencies generated by different parts of the bearing may often deviate from the actual values. Therefore, it is not possible to simply determine whether there is a fault in the part based on the amplitude change in the theoretically calculated frequency. Therefore, this application selects the theoretically calculated frequency, selects a frequency interval within a certain range near it, and calculates the energy change in the frequency interval to determine whether there is a fault in the part. The specific calculation method is as follows:

[0082] Cage fault band energy calculation:

[0083]

[0084] Rolling element fault band energy calculation:

[0085]

[0086] Outer ring fault band energy calculation:

[0087]

[0088] Inner ring fault band energy calculation:

[0089]

[0090] Among them, k is half of the bandwidth of the frequency band, and the bandwidth of the frequency band can be set according to the specific parameters of the bearing. X is the frequency domain sequence of the signal, and i is a positive integer. The energy values ​​of the cage fault band, the rolling element fault band, the outer ring fault band, and the inner ring fault band can be compared with the changes in their corresponding initial values ​​and the preset threshold to determine whether a fault has occurred. For example, when the change value of the outer ring fault band energy is greater than or equal to the preset threshold, it is considered that a fault has occurred in the outer ring of the equipment bearing.

[0091] Step 130: diagnose the bearing of the equipment to be diagnosed by combining the time domain characteristics, frequency domain characteristics and changes in real-time current data.

[0092] The change of the current data indicates the change of the real-time current data relative to the rated current.

[0093] In some embodiments of the present application, the bearings of the equipment to be diagnosed are diagnosed in combination with the changes in time domain characteristics, frequency domain characteristics and real-time current data, including: selecting different types of values ​​in time domain characteristics and frequency domain characteristics as diagnostic basis; and diagnosing the bearings of the equipment to be diagnosed through the changes in the diagnostic basis, time domain characteristics, frequency domain characteristics and real-time current data.

[0094] In the above process, the present application selects different types of values ​​in the time domain characteristics and the frequency domain characteristics as the diagnosis basis, so that the equipment bearing can be accurately diagnosed according to the diagnosis basis.

[0095] Among them, the diagnosis basis includes peak value, effective value, peak index, kurtosis, waveform index and margin index, etc., which can realize the diagnosis of bearing fault type. The diagnosis basis can realize the diagnosis of equipment bearing fault type.

[0096] Specifically: The relationship between the diagnosis of the equipment bearing fault type can be realized through the diagnosis basis as follows:

[0097] Peak value: Peak value is very suitable for impact detection such as peeling or scratching. For instantaneous impact phenomena, the greater the impact force, the higher the peak value. Therefore, when detecting impact vibration caused by peeling and scratching on the bearing surface, to reflect the fault state of the bearing operation, the peak value is more effective than the effective value. In addition, peak value diagnosis is also often used in low speed conditions.

[0098] Effective value: The effective value reflects the wear of the bearing. The greater the bearing wear, the greater the effective value. A slight impact has little effect on the effective value of the fault, but as the impact energy continues to increase, the effective value will gradually increase, but relatively lagging. The effective value is not very sensitive to the fault, but has good stability and increases monotonically as the fault develops.

[0099] Peak index: Peak index is used to detect instantaneous impact vibration caused by discrete defects such as peeling and scratches on the bearing surface. Peak index is more sensitive than effective value. When the peak index increases, it is easier to judge whether the bearing is faulty. However, when the fault continues to expand and the peak value gradually reaches the extreme value, the effective value also continues to increase, and the peak index also begins to gradually decrease. By monitoring the peak index, rolling bearings can be effectively predicted early and the development trend of faults can be reflected. It has a good monitoring effect on impacts such as pitting and scratches.

[0100] Kurtosis index: Kurtosis index can reflect the impact characteristics of the equipment, indicating the possibility of surface damage faults. The kurtosis index of a normal bearing vibration signal is close to 3. In the early stage of the fault, the index increases continuously and decreases in the late stage.

[0101] Waveform index: The larger the waveform index, the more likely the rolling bearing is to have pitting, and the smaller the waveform index, the more likely it is to have wear.

[0102] Margin index: Margin can reflect the wear condition of equipment. Margin factor is often used to detect the wear condition of mechanical equipment.

[0103] In some embodiments of the present application, the bearing of the equipment to be diagnosed is diagnosed in combination with the time domain characteristics, frequency domain characteristics and changes in real-time current data, including: converting the time domain signals corresponding to the processed conventional data and real-time monitoring data into frequency domain signals; respectively calculating the time domain signal characteristics and frequency domain signal characteristics; determining the probabilities of various types of faults occurring in the bearing of the equipment to be diagnosed based on the time domain signal characteristics; determining the probabilities of the bearing faults of the equipment to be diagnosed occurring in various locations based on the frequency domain signal characteristics; and diagnosing the bearing of the equipment to be diagnosed in combination with the changes in real-time current data, the probabilities of various types of faults occurring in the bearing of the equipment to be diagnosed and the probabilities of the bearing faults of the equipment to be diagnosed occurring in various locations.

[0104] In the above process, the present application utilizes time domain characteristics and frequency domain characteristics, combined with current data, to realize the diagnosis of the fault location and bearing fault type of the bearing, thereby overcoming the problems of lack of field sample data in data model building, resulting in difficult modeling and inaccurate modeling.

[0105] In some embodiments of the present application, the bearing of the equipment to be diagnosed is diagnosed in combination with the changes in time domain characteristics, frequency domain characteristics and real-time current data, including: determining the time domain characteristic difference and frequency domain characteristic difference corresponding to the real-time monitoring data and conventional data of the bearing of the equipment to be diagnosed; matching the bearing fault type probability and the bearing fault location probability corresponding to the time domain characteristic difference and the frequency domain characteristic difference respectively through a preset bearing fault type probability distribution table and a bearing fault location probability distribution table; determining the fault condition of the bearing of the equipment to be diagnosed in combination with the changes in real-time current data, the bearing fault type probability and the bearing fault location probability.

[0106] In the above process, the present application utilizes time domain features and frequency domain features, and utilizes a probability fusion method to realize the diagnosis of the fault location and bearing fault type of the bearing, and adopts a matching mechanism. Through a preset bearing fault type probability distribution table and a bearing fault location probability distribution table, the probability values ​​under each time domain feature and each frequency domain feature are integrated to determine the most likely fault type and fault location.

[0107] Among them, a fault type probability table can be established based on different values ​​of time domain characteristics (peak value T1, effective value T2, peak factor T3, kurtosis factor T4, waveform factor T5, margin factor T6). Specifically, the relationship between different values ​​and fault types can be used to establish a fault type probability distribution table under the standard load of the bearing according to the change of the time domain characteristic value of the bearing vibration signal. The fault type probability Pn should avoid being 0. See Table 2 for details:

[0108] Table 2

[0109]

[0110] Among them, X is set to the feature value extracted after obtaining the current bearing status data, X 标准 These are the eigenvalues ​​extracted when the bearing is in a healthy state.

[0111] The following are the standards for fault diagnosis: Below normal range: X<0.8X 标准 ; Normal range: X ≥ 0.8X 标准 and X≤1.2X 标准 ; Above normal range: X>1.2X 标准 .

[0112] Optionally, according to the changes in various energy values ​​(bearing cage fault band energy, rolling element fault band energy, outer ring fault band energy, inner ring fault band energy), a fault position probability distribution table under the standard load of the bearing can be established, and the fault type probability Pn should be avoided to be 0. See Table 3 for details:

[0113] Table 3

[0114]

[0115] Among them, X is set to the feature value extracted after obtaining the current bearing status data, X 标准 It is the characteristic value extracted when the bearing is in a healthy state. Each energy value corresponds to the energy value of the cage fault band T7, the rolling element fault band energy T8, the outer ring fault band energy T9 and the inner ring fault band energy T10.

[0116] The following are the standards for fault diagnosis: Below normal range: X<0.8X 标准 ; Normal range: X ≥ 0.8X 标准 and X≤1.2X 标准 ; Above normal range: X>1.2X 标准 .

[0117] Optionally, after obtaining the above probability distribution table, the probability distribution table needs to be adjusted, including: the characteristic value of the bearing time domain signal will be affected by the size of the load it carries, the current reflects the load of the equipment, the larger the current, the larger the load, and the corresponding vibration characteristic value, so it is necessary to adjust the level according to the current adjustment strategy (the specific adjustment setting value can be set according to the needs). For example, the current adjustment strategy is as follows: the current increases, the load increases, and different characteristic values ​​increase or decrease. The specific changes are as follows: the peak value shows an increasing trend, the effective value shows an increasing trend, the cage fault band energy shows an increasing trend, the rolling element fault band energy shows an increasing trend, the outer ring fault band energy shows an increasing trend, and the inner ring fault band energy shows an increasing trend, while the peak factor, kurtosis factor, waveform factor, and margin factor have little change trend.

[0118] For example, when the current increases, the equipment load increases, and the reference benchmark of the vibration characteristic value also changes. Compared with the probability distribution table under the standard load, adjustments need to be made. The peak range is adjusted down by one level, the effective value range is adjusted down by one level, the cage frequency band energy range is adjusted down by one level, the ball frequency band energy range is adjusted down by one level, the outer ring frequency band energy range is adjusted down by one level, and the inner ring frequency band energy range is adjusted down by one level. The peak factor, kurtosis factor, waveform factor, and margin factor are not adjusted. When the current decreases, the equipment load decreases, and the characteristic value range adjustment is opposite to the above. Then, the probability distribution table is compared to perform probability calculations. Finally, the bearing fault type diagnosis is realized based on the equipment current data and vibration data.

[0119] In some embodiments of the present application, the bearings of the equipment to be diagnosed are diagnosed by combining the time domain characteristics, frequency domain characteristics and changes in real-time current data, including: combining the knowledge of bearing mechanism, performing a probability fusion analysis on the changes in time domain characteristics, frequency domain characteristics and real-time current data, and obtaining the location and type of the bearing fault.

[0120] In the above process, the present application combines the knowledge of bearing mechanism and utilizes the probability fusion method to realize the diagnosis of the fault location and type of bearing.

[0121] Optionally, the bearing fault type probability and the bearing fault location probability corresponding to the time domain feature difference and the frequency domain feature difference are matched; the fault condition of the bearing of the equipment to be diagnosed is determined by combining the change of the real-time current data, the bearing fault type probability and the bearing fault location probability, including:

[0122] Bearing fault type diagnosis:

[0123] According to the difference between the time domain characteristics calculated from the monitored vibration signal and the time domain characteristic values ​​calculated when the equipment is operating normally, the range x of each monitored time domain characteristic value is determined, and the probability of each type of fault is calculated to identify the fault type. The fault type with the highest probability is the possible fault type of the bearing:

[0124] (1) Probability of normal bearing:

[0125] P(a)=T1(x:a)*T2(x:a)*T3(x:a)*T4(x:a)*T5(x:a)*T6(x:a)

[0126] (2) Probability of bearing scratches:

[0127] P(b)=T1(x:b)*T2(x:b)*T3(x:b)*T4(x:b)*T5(x:b)*T6(x:b)

[0128] (3) Probability of bearing pitting:

[0129] P(c)=T1(x:c)*T2(x:c)*T3(x:c)*T4(x:c)*T5(x:c)*T6(x:c)

[0130] (4) Probability of bearing surface peeling:

[0131] P(d)=T1(x:d)*T2(x:d)*T3(x:d)*T4(x:d)*T5(x:d)*T6(x:d)

[0132] (5) Probability of bearing wear:

[0133] P(e)=T1(x:e)*T2(x:e)*T3(x:e)*T4(x:e)*T5(x:e)*T6(x:e)

[0134] Among them, P(a), P(b), P(c), P(d) and P(e) represent the probability of the type of fault, x represents the range of each time domain characteristic value, a, b, c, d and e represent the fault type of the bearing, T1, T2, T3, T4, T5 and T6 represent the time domain characteristic signals of the equipment bearing, corresponding to the time domain features in Table 2, and each time domain feature corresponds to a probability distribution table.

[0135] Bearing fault location diagnosis:

[0136] According to the difference between the frequency domain characteristics calculated from the monitored vibration signal and the frequency domain characteristic values ​​calculated when the equipment is operating normally, the range x of each frequency domain characteristic value monitored is determined, and the probability of failure of each part is calculated to identify the faulty part. The part with the highest probability is the possible faulty part of the bearing:

[0137] (1) Probability of normal bearing:

[0138] P(f)=T7(x:f)*T8(x:f)*T9(x:f)*T10(x:f)

[0139] (2) Probability of bearing cage failure:

[0140] P(g)=T7(x:g)*T8(x:g)*T9(x:g)*T10(x:g)

[0141] (3) Probability of bearing rolling element failure:

[0142] P(h)=T7(x:h)*T8(x:h)*T9(x:h)*T10(x:h)

[0143] (4) Probability of bearing outer ring failure:

[0144] P(i)=T7(x:i)*T8(x:i)*T9(x:i)*T10(x:i)

[0145] (5) Probability of bearing inner ring failure:

[0146] P(j)=T7(x:j)*T8(x:j)*T9(x:j)*T10(x:j)

[0147] Among them, P(f), P(g), P(h), P(i) and P(j) represent the probability of the fault location, x represents the range of each frequency domain characteristic value, f, g, h, i and j represent the location of the bearing fault, T7, T8, T9 and T10 represent the energy values ​​of the cage fault frequency band, rolling element fault frequency band, outer ring fault frequency band and inner ring fault frequency band of the equipment bearing respectively. Corresponding to the frequency domain features in Table 3, each frequency domain feature corresponds to a probability distribution table.

[0148] In the above Figure 1 In the process shown, the present application performs noise reduction processing on the conventional data and real-time monitoring data of the bearing of the equipment to be diagnosed, thereby obtaining processed conventional data and monitoring data, wherein the conventional data includes normal vibration data and rated current, and the real-time monitoring data includes real-time vibration data and real-time current data; extracts the time domain characteristics and frequency domain characteristics of the processed conventional data and real-time monitoring data; and diagnoses the bearing of the equipment to be diagnosed in combination with the changes in the time domain characteristics, frequency domain characteristics and real-time current data. Data noise reduction can improve data quality, thereby improving the accuracy of data analysis and diagnosis of equipment bearings. By utilizing time domain characteristics and frequency domain characteristics, combined with current data, the fault location and type of the bearing can be diagnosed, overcoming the problems of lack of field sample data in data modeling, resulting in difficult and inaccurate modeling, and achieving the effect of accurately diagnosing equipment bearing faults.

[0149] Combine the following Figure 2 The implementation method of diagnosing equipment bearing faults in an embodiment of the present application is described in detail.

[0150] Please see Figure 2 , Figure 2 A flowchart of an implementation method for diagnosing a bearing fault of an equipment provided in an embodiment of the present application is shown as follows: Figure 2 The implementation method shown for diagnosing equipment bearing failures includes:

[0151] Normal bearing vibration data, real-time monitoring data and equipment rated current under rated power of the equipment are collected. The vibration data and normal bearing vibration data in the real-time monitoring data are processed by data noise reduction to extract the time domain characteristics and frequency domain characteristics of the data, and are used as the judgment benchmark and judgment basis respectively. The current data and equipment rated current in the real-time monitoring data are used as the implementation current change situation. Finally, combined with the bearing mechanism knowledge, the bearing fault type probability and bearing fault location probability corresponding to the time domain feature difference and frequency domain feature difference are matched through the preset bearing fault type probability distribution table and bearing fault location probability distribution table; combined with the changes in real-time current data, the bearing fault type probability and the bearing fault location probability, determine whether the bearing of the equipment to be diagnosed is faulty and the corresponding fault location and fault type.

[0152] also, Figure 2 The specific methods and steps shown can be found in Figure 1 The method shown will not be described in detail here.

[0153] Previous article Figure 1-Figure 2 Describes the method of diagnosing equipment bearing failure. Figure 3-Figure 4 Describe an apparatus for diagnosing bearing failures in equipment.

[0154] Please refer to Figure 3 , is a schematic block diagram of a device 300 for diagnosing a bearing fault of an equipment provided in an embodiment of the present application. The device 300 may be a module, a program segment or a code on an electronic device. The device 300 is similar to the above Figure 1 The method embodiment corresponds to and can be executed Figure 1 The various steps involved in the method embodiment and the specific functions of the device 300 can be found in the description below. To avoid repetition, the detailed description is appropriately omitted here.

[0155] Optionally, the device 300 includes:

[0156] The preprocessing module 310 is used to perform noise reduction processing on the conventional data and real-time monitoring data of the bearing of the equipment to be diagnosed, so as to obtain processed conventional data and monitoring data, wherein the conventional data includes vibration data and current data obtained under standard working conditions when the equipment is normal, and the real-time monitoring data includes real-time vibration data and real-time current data;

[0157] Feature extraction module 320, used to extract time domain features and frequency domain features of processed conventional data and real-time monitoring data;

[0158] The diagnosis module 330 is used to diagnose the bearing of the equipment to be diagnosed by combining the time domain characteristics, frequency domain characteristics and the changes in the real-time current data.

[0159] Optionally, the diagnostic module is specifically used for:

[0160] Determine the time domain feature difference and frequency domain feature difference corresponding to the real-time monitoring data and conventional data of the bearing of the equipment to be diagnosed; match the bearing fault type probability and bearing fault location probability corresponding to the time domain feature difference and frequency domain feature difference respectively through the preset bearing fault type probability distribution table and bearing fault location probability distribution table; combine the changes in real-time current data, the bearing fault type probability and the bearing fault location probability to determine the fault condition of the bearing of the equipment to be diagnosed.

[0161] Optionally, the preprocessing module is specifically used for:

[0162] The processed conventional data and monitoring data are obtained by summing the conventional data and the real-time monitoring data in sections, taking the average value of the summed data, and removing useless information in the conventional data and the real-time monitoring data.

[0163] Optionally, the feature extraction module is specifically used for:

[0164] According to the relationship between the signal time and signal amplitude of conventional data and real-time monitoring data, the time domain characteristics of conventional data and real-time monitoring data are extracted. According to the relationship between the signal frequency and signal amplitude of conventional data and real-time monitoring data, the frequency domain characteristics of conventional data and real-time monitoring data are extracted.

[0165] Optionally, the diagnostic module is specifically used for:

[0166] The time domain signal characteristics corresponding to the processed routine data and real-time monitoring data are converted into frequency domain signal characteristics; the probability of various types of bearing failures of the equipment to be diagnosed is determined based on the time domain signal characteristics; the probability of bearing failures of the equipment to be diagnosed occurring in various locations is determined based on the frequency domain signal characteristics; the bearing of the equipment to be diagnosed is diagnosed based on the changes in real-time current data, the probability of various types of bearing failures of the equipment to be diagnosed occurring in various locations.

[0167] Optionally, the diagnostic module is specifically used for:

[0168] Combined with the knowledge of bearing mechanism, a probability fusion analysis is performed on the changes in time domain characteristics, frequency domain characteristics and real-time current data to obtain the location and type of bearing faults.

[0169] Optionally, the diagnostic module is specifically used for:

[0170] Different types of values ​​in time domain characteristics and frequency domain characteristics are selected as diagnostic basis; the bearing of the equipment to be diagnosed is diagnosed through the changes in the diagnostic basis, time domain characteristics, frequency domain characteristics and real-time current data.

[0171] Please refer to Figure 4 The structure schematic block diagram of a device for diagnosing bearing faults of equipment provided in an embodiment of the present application is shown in FIG. 4 . The device may include a memory 410 and a processor 420. Optionally, the device may also include: a communication interface 430 and a communication bus 440. The device is similar to the above Figure 1 The method embodiment corresponds to and can be executed Figure 1 The various steps involved in the method embodiment and the specific functions of the device can be found in the description below.

[0172] Specifically, the memory 410 is used to store computer-readable instructions.

[0173] Processor 420 is used to process the readable instructions stored in the memory and can execute Figure 1 The steps in the method.

[0174] The communication interface 430 is used for signaling or data communication with other node devices, for example, for communication with a server or a terminal, or for communication with other device nodes, but the embodiments of the present application are not limited thereto.

[0175] The communication bus 440 is used to realize direct connection and communication among the above components.

[0176] The communication interface 430 of the device in the embodiment of the present application is used to communicate signals or data with other node devices. The memory 410 can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The memory 410 can also be at least one storage device located away from the aforementioned processor. The memory 410 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 420, the electronic device executes the aforementioned Figure 1 The method process shown. The processor 420 can be used on the device 300 and is used to perform the functions in the present application. Exemplarily, the above-mentioned processor 420 can be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, and the embodiments of the present application are not limited thereto.

[0177] The embodiment of the present application also provides a readable storage medium, when the computer program is executed by a processor, Figure 1 The method process in the method embodiment shown is executed by the electronic device.

[0178] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method, and will not be described in detail here.

[0179] In summary, the embodiments of the present application provide a method, apparatus, device and readable storage medium for diagnosing equipment bearing faults, the method comprising: performing noise reduction processing on conventional data and real-time monitoring data of the equipment bearing to be diagnosed, obtaining processed conventional data and monitoring data, wherein the conventional data includes vibration data and current data obtained under standard working conditions when the equipment is normal, and the real-time monitoring data includes real-time vibration data and real-time current data; extracting time domain characteristics and frequency domain characteristics of the processed conventional data and real-time monitoring data; combining the changes in time domain characteristics, frequency domain characteristics and real-time current data to diagnose the equipment bearing to be diagnosed. This method can achieve the effect of accurately diagnosing equipment bearing faults.

[0180] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0181] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0182] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0183] The above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0184] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0185] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A method for diagnosing equipment bearing failure, characterized in that: include: Performing noise reduction processing on the conventional data and real-time monitoring data of the bearing of the equipment to be diagnosed to obtain processed conventional data and monitoring data, wherein the conventional data includes vibration data and current data obtained under standard working conditions when the equipment is normal, and the real-time monitoring data includes real-time vibration data and real-time current data; Extracting time domain features and frequency domain features of the processed conventional data and real-time monitoring data; The bearing of the equipment to be diagnosed is diagnosed by combining the time domain characteristics, the frequency domain characteristics and the changes in the real-time current data.

2. The method according to claim 1, characterized in that The step of diagnosing the bearing of the equipment to be diagnosed by combining the time domain features, the frequency domain features and the change of the real-time current data includes: Determine the time domain characteristic difference and the frequency domain characteristic difference corresponding to the real-time monitoring data and the conventional data of the bearing of the equipment to be diagnosed; Match the bearing fault type probability and the bearing fault location probability corresponding to the time domain feature difference and the frequency domain feature difference respectively through a preset bearing fault type probability distribution table and a bearing fault location probability distribution table; The fault condition of the bearing of the equipment to be diagnosed is determined based on the change of the real-time current data, the probability of the bearing fault type and the probability of the bearing fault location.

3. The method according to claim 1 or 2, characterized in that: The noise reduction process is performed on the conventional data and real-time monitoring data of the bearing of the equipment to be diagnosed to obtain the processed conventional data and monitoring data, including: The processed conventional data and monitoring data are obtained by summing the conventional data and the real-time monitoring data in sections, taking the average value of the summed data, and removing useless information in the conventional data and the real-time monitoring data.

4. The method according to claim 1 or 2, characterized in that: The extracting of time domain features and frequency domain features of the processed conventional data and real-time monitoring data includes: Extracting the time domain features of the conventional data and the real-time monitoring data according to the signal time and signal amplitude relationship between the conventional data and the real-time monitoring data; The frequency domain features of the conventional data and the real-time monitoring data are extracted according to the relationship between the signal frequency and the signal amplitude of the conventional data and the real-time monitoring data.

5. The method according to claim 1 or 2, characterized in that: The step of diagnosing the bearing of the equipment to be diagnosed by combining the time domain features, the frequency domain features and the change of the real-time current data includes: Converting the time domain signal features corresponding to the processed conventional data and real-time monitoring data into frequency domain signal features; Determining the probability of various types of faults occurring in the bearing of the equipment to be diagnosed according to the time domain signal characteristics; Determining the probability of the bearing fault of the equipment to be diagnosed occurring at various locations according to the frequency domain signal characteristics; The bearing of the equipment to be diagnosed is diagnosed based on the change of the real-time current data, the probability of various types of faults occurring in the bearing of the equipment to be diagnosed, and the probability of the fault of the bearing of the equipment to be diagnosed occurring in various locations.

6. The method according to claim 1 or 2, characterized in that: The step of combining the time domain features, the frequency domain features and the changes in the real-time current data to diagnose the bearing of the equipment to be diagnosed includes: Combined with the knowledge of bearing mechanism, a probability fusion analysis is performed on the changes in the time domain characteristics, the frequency domain characteristics and the real-time current data to obtain the location and type of bearing faults.

7. The method according to claim 1 or 2, characterized in that: The combining the time domain features, the frequency domain features and the changes in the real-time current data to diagnose the bearing of the equipment to be diagnosed includes: Selecting different types of values ​​in the time domain features and the frequency domain features as diagnosis basis; The bearing of the equipment to be diagnosed is diagnosed based on the diagnosis basis, the time domain characteristics, the frequency domain characteristics and the changes in the real-time current data.

8. A device for diagnosing equipment bearing failure, characterized in that: include: A preprocessing module, used for performing noise reduction processing on conventional data and real-time monitoring data of the bearing of the equipment to be diagnosed, to obtain processed conventional data and monitoring data, wherein the conventional data includes vibration data and current data obtained under standard working conditions when the equipment is normal, and the real-time monitoring data includes real-time vibration data and real-time current data; A feature extraction module, used to extract time domain features and frequency domain features of the processed conventional data and real-time monitoring data; The diagnosis module is used to diagnose the bearing of the equipment to be diagnosed by combining the time domain characteristics, the frequency domain characteristics and the changes in the real-time current data.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the method according to any one of claims 1 to 7 are executed.

10. A computer-readable storage medium, characterized in that: include: A computer program, when the computer program is run on a computer, causes the computer to execute the method according to any one of claims 1 to 7.

Images