Rolling bearing fault diagnosis method and device, computer equipment, storage medium and program product

Abstract

The invention relates to a rolling bearing fault diagnosis method and device, computer equipment, a storage medium and a program product. The method comprises the steps of obtaining vibration data of a rolling bearing, obtaining fault feature frequency and frequency amplitude of the rolling bearing according to the vibration data, obtaining a confidence rule base according to the frequency amplitude, obtaining feature confidence corresponding to the fault feature frequency according to the frequency amplitude and the confidence rule base, and obtaining fault feature frequency of the rolling bearing according to the confidence rule base and the feature confidence. And fault diagnosis is carried out on the rolling bearing, and the process of fault diagnosis on the rolling bearing comprises at least one of fault diagnosis on an inner ring of the rolling bearing, fault diagnosis on an outer ring of the rolling bearing and fault diagnosis on a rolling body of the rolling bearing. By adopting the method, the fault diagnosis accuracy can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of equipment fault diagnosis, and in particular to a rolling bearing fault diagnosis method, device, computer equipment, storage medium and program product. Background Art

[0002] Currently, fault diagnosis for rolling bearings in blowers primarily relies on physical characteristics such as vibration signals or temperature monitoring. Sensors collect data and use specific algorithms to determine the fault. However, a single physical characteristic, such as vibration or temperature, cannot fully reflect the fault state and is insensitive to early, subtle faults, resulting in low fault diagnosis accuracy. Summary of the Invention

[0003] Based on this, it is necessary to provide a rolling bearing fault diagnosis method, device, computer equipment, storage medium and program product that can improve the accuracy of fault diagnosis in order to solve the above technical problems.

[0004] In a first aspect, the present application provides a rolling bearing fault diagnosis method, comprising:

[0005] Acquiring vibration data of the rolling bearing; the vibration data includes at least one of inner ring vibration data, outer ring vibration data, and rolling element vibration data;

[0006] According to the vibration data, the fault characteristic frequency and frequency amplitude of the rolling bearing are obtained;

[0007] According to the frequency amplitude, a confidence rule base is obtained; the confidence rule base is used to characterize the confidence threshold corresponding to the fault characteristic frequency;

[0008] According to the frequency amplitude and the confidence rule base, the characteristic confidence corresponding to the fault characteristic frequency is obtained, and the rolling bearing fault is diagnosed according to the confidence rule base and the characteristic confidence;

[0009] The process of performing fault diagnosis on the rolling bearing includes at least one of performing fault diagnosis on the inner ring of the rolling bearing, performing fault diagnosis on the outer ring of the rolling bearing, and performing fault diagnosis on the rolling element of the rolling bearing.

[0010] In one embodiment, the step of obtaining the fault characteristic frequency and frequency amplitude of the rolling bearing according to the vibration data includes:

[0011] Obtaining the one-fold frequency of the rotating shaft of the rolling bearing; the one-fold frequency of the rotating shaft is used to represent the rotation frequency of the rotating shaft;

[0012] Obtain the fault characteristic frequency of the rolling bearing based on the rotational frequency and vibration data; the fault characteristic frequency includes the fault frequency, the fault frequency, and the fault frequency. The fault frequency, the fault frequency, and the fault frequency are used to characterize the fault characteristics of the rolling bearing at different fault levels or different fault stages.

[0013] Obtain the frequency amplitude corresponding to the fault characteristic frequency; the frequency amplitude includes the first-time frequency amplitude, the second-time frequency amplitude, and the third-time frequency amplitude.

[0014] In one embodiment, the step of obtaining a confidence rule base according to the frequency amplitude includes:

[0015] Obtaining a first confidence rule based on the one-fold frequency amplitude; the first confidence rule is used to characterize a first initial confidence level when the one-fold frequency amplitude satisfies an amplitude change condition, a first amplitude threshold when the rolling bearing satisfies a valid fault condition, and a first amplitude limit corresponding to the one-fold frequency amplitude;

[0016] Obtaining a second confidence rule based on the double frequency amplitude; the second confidence rule is used to characterize a second initial confidence level when the double frequency amplitude satisfies an amplitude change condition, a second amplitude threshold when the rolling bearing satisfies a valid fault condition, and a second amplitude limit corresponding to the double frequency amplitude;

[0017] A third confidence rule is obtained based on the triple frequency amplitude; the third confidence rule is used to characterize the third initial confidence when the triple frequency amplitude meets the amplitude change condition, the third amplitude threshold when the rolling bearing meets the effective fault condition, and the third amplitude limit corresponding to the triple frequency amplitude.

[0018] In one embodiment, the step of obtaining a characteristic confidence level corresponding to a fault characteristic frequency based on the frequency amplitude and the confidence rule base includes:

[0019] Obtaining a first characteristic confidence level corresponding to the fault frequency doubling according to a first function; the numerator of the first function is the difference between the frequency doubling amplitude and the first amplitude threshold, and the denominator is the difference between the first amplitude limit and the first amplitude threshold;

[0020] Obtaining a second characteristic confidence level corresponding to the fault double frequency according to a second function; the numerator of the second function is the difference between the double frequency amplitude and the second amplitude threshold, and the denominator is the difference between the second amplitude limit and the second amplitude threshold;

[0021] According to the third function, the third characteristic confidence corresponding to the fault triple frequency is obtained; the numerator of the third function is the difference between the triple frequency amplitude and the third amplitude threshold, and the denominator is the difference between the third amplitude limit and the third amplitude threshold.

[0022] In one embodiment, the step of performing fault diagnosis on a rolling bearing according to a confidence rule base and feature confidence includes:

[0023] Obtaining a confidence matching degree according to the first feature confidence degree, the second feature confidence degree, and the third feature confidence degree;

[0024] When the confidence matching degree is less than the matching degree threshold, it is determined that the rolling bearing fails.

[0025] In one embodiment, the method further comprises:

[0026] Obtaining a first confidence difference, a second confidence difference, and a third confidence difference between the target confidence and the first feature confidence, the second feature confidence, and the third feature confidence, respectively;

[0027] The product of the first confidence difference, the second confidence difference, the third confidence difference and the reference confidence is used as the conclusion confidence;

[0028] According to the confidence level of the conclusion, the rolling bearing fault diagnosis is performed.

[0029] In a second aspect, the present application further provides a rolling bearing fault diagnosis device, comprising:

[0030] A data acquisition module, configured to acquire vibration data of the rolling bearing; the vibration data includes at least one of inner ring vibration data, outer ring vibration data, and rolling element vibration data;

[0031] A frequency acquisition module is used to obtain the fault characteristic frequency and frequency amplitude of the rolling bearing based on the vibration data;

[0032] The confidence acquisition module is used to obtain a confidence rule base based on the frequency amplitude; the confidence rule base is used to characterize the confidence threshold corresponding to the fault characteristic frequency;

[0033] A fault diagnosis module is used to obtain the characteristic confidence corresponding to the fault characteristic frequency based on the frequency amplitude and the confidence rule library, and perform fault diagnosis on the rolling bearing based on the confidence rule library and the characteristic confidence; wherein the process of fault diagnosis on the rolling bearing includes at least one of fault diagnosis on the inner ring of the rolling bearing, fault diagnosis on the outer ring of the rolling bearing, and fault diagnosis on the rolling element of the rolling bearing.

[0034] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements any one of the method steps in the first aspect when executing the computer program.

[0035] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements any one of the method steps in the first aspect when the computer program is executed by a processor.

[0036] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which implements any one of the method steps in the first aspect when executed by a processor.

[0037] The above-mentioned rolling bearing fault diagnosis method, device, computer equipment, storage medium and program product obtain the vibration data of the rolling bearing, obtain the fault characteristic frequency and frequency amplitude of the rolling bearing based on the vibration data, obtain the confidence rule base based on the frequency amplitude, obtain the feature confidence corresponding to the fault characteristic frequency based on the frequency amplitude and the confidence rule base, diagnose the rolling bearing fault based on the confidence rule base and the feature confidence, and match the feature confidence corresponding to the fault characteristic frequency with the confidence rule base, thereby improving the accuracy of fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0039] Figure 1 Schematic diagram of an application environment of a rolling bearing fault diagnosis method in one embodiment;

[0040] Figure 2 Schematic diagram of a rolling bearing fault diagnosis method according to an embodiment;

[0041] Figure 3 A schematic flow chart of a rolling bearing fault diagnosis method according to another embodiment;

[0042] Figure 4 is a structural block diagram of a rolling bearing fault diagnosis device in one embodiment;

[0043] Figure 5 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0045] The rolling bearing fault diagnosis method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store data that server 104 needs to process. The data storage system can be integrated with server 104, or located on a cloud or other network server. Terminal 102 is configured to acquire vibration data of a rolling bearing, obtain the rolling bearing's fault characteristic frequency and frequency amplitude based on the vibration data, obtain a confidence rule base based on the frequency amplitude, obtain a feature confidence corresponding to the fault characteristic frequency based on the frequency amplitude and the confidence rule base, and perform a rolling bearing fault diagnosis based on the confidence rule base and the feature confidence. The rolling bearing fault diagnosis process includes at least one of diagnosing the inner race of the rolling bearing, diagnosing the outer race of the rolling bearing, and diagnosing the rolling elements of the rolling bearing. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart car devices, projectors, and the like. Portable wearable devices can include smart watches, smart bracelets, head-mounted devices, and the like. The head-mounted device may be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 may be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0046] In an exemplary embodiment, Figure 2 As shown, a rolling bearing fault diagnosis method is provided, which is applied to Figure 1 The terminal 102 in the example is used as an example to illustrate the process, including the following steps 202 to 208. Among them:

[0047] S202: Acquire vibration data of the rolling bearing; the vibration data includes at least one of inner ring vibration data, outer ring vibration data, and rolling element vibration data.

[0048] Alternatively, vibration data refers to a set of numerical values of physical quantities collected by sensors and other devices, used to describe the vibration state of an object. For rolling bearings, sensors can acquire inner ring vibration data, outer ring vibration data, and rolling element vibration data, which are used to diagnose faults for the inner ring, outer ring, and rolling element of the rolling bearing, respectively. When vibration data is collected by sensors, it is typically represented as a signal.

[0049] S204: Obtain the fault characteristic frequency and frequency amplitude of the rolling bearing according to the vibration data.

[0050] Optionally, by performing signal processing on the vibration data, the time-domain vibration signal is converted into a frequency-domain signal, thereby extracting the characteristic frequency of the rolling bearing fault and the corresponding frequency amplitude. Different fault types will produce characteristic vibrations at specific frequencies, and the amplitude reflects the severity of the fault. By determining these frequencies, it is possible to accurately determine whether components such as the bearing inner ring, outer ring, or rolling element are faulty, as well as the specific location of the fault. In practical applications, the envelope information of the vibration signal can be extracted through envelope spectrum transformation. The signal after envelope demodulation reflects the slow changes in the amplitude of the original vibration signal, and this amplitude change is often closely related to rolling bearing faults.

[0051] S206: Obtain a confidence rule base according to the frequency amplitude; the confidence rule base is used to characterize the confidence threshold corresponding to the fault characteristic frequency.

[0052] Optionally, the confidence rule base stores the judgment criteria for the confidence level of the presence of faults at each fault characteristic frequency under different frequency amplitudes, providing an objective and quantitative judgment basis for fault diagnosis. Usually, the confidence rule base can be determined based on experimental data and actual operating experience.

[0053] S208: According to the frequency amplitude and the confidence rule base, the feature confidence corresponding to the fault feature frequency is obtained, and according to the confidence rule base and the feature confidence, the rolling bearing fault diagnosis is performed; wherein, the process of performing fault diagnosis on the rolling bearing includes at least one of performing fault diagnosis on the inner ring of the rolling bearing, performing fault diagnosis on the outer ring of the rolling bearing, and performing fault diagnosis on the rolling element of the rolling bearing.

[0054] Optionally, the frequency amplitude of the fault characteristic frequency is judged according to the confidence rule base to determine the characteristic confidence corresponding to the fault characteristic frequency, wherein the characteristic confidence is used to characterize the possibility of each possible fault mode. The characteristic confidence is compared with the judgment criteria in the confidence rule base. If the characteristic confidence matches the judgment criteria in the confidence rule base to a high degree of match, it indicates that the possibility of a fault has a high confidence, that is, the fault is more likely to occur. Based on the corresponding vibration data, fault diagnosis can be performed on the inner ring of the rolling bearing, the outer ring of the rolling bearing, and the rolling element of the rolling bearing. It is understandable that, depending on the vibration data, fault diagnosis can be performed on the inner ring of the rolling bearing, the outer ring of the rolling bearing, and at least one of the rolling bearings. The specific selection can be based on actual application requirements.

[0055] In the above-mentioned rolling bearing fault diagnosis method, the vibration data of the rolling bearing is obtained, and the fault characteristic frequency and frequency amplitude of the rolling bearing are obtained based on the vibration data. Based on the frequency amplitude, a confidence rule base is obtained. Based on the frequency amplitude and the confidence rule base, the feature confidence corresponding to the fault characteristic frequency is obtained. According to the confidence rule base and the feature confidence, the rolling bearing fault diagnosis is performed. By matching the feature confidence corresponding to the fault characteristic frequency with the confidence rule base, the accuracy of the fault diagnosis can be improved. Since the vibration data includes at least one of the inner ring vibration data, the outer ring vibration data and the rolling body vibration data, the inner ring of the rolling bearing, the outer ring of the rolling bearing and at least one of the rolling bearing can be diagnosed, thereby improving the comprehensiveness of the fault diagnosis and effectively ensuring the safe operation of the rolling bearing.

[0056] In an exemplary embodiment, the step of obtaining the fault characteristic frequency and frequency amplitude of the rolling bearing based on the vibration data includes: obtaining the single frequency of the rotation frequency of the rotating shaft of the rolling bearing; the single frequency of the rotation frequency is used to characterize the rotation frequency of the rotating shaft; obtaining the fault characteristic frequency of the rolling bearing based on the single frequency of the rotation frequency and the vibration data; the fault characteristic frequency includes the single frequency, the double frequency and the triple frequency, which are respectively used to characterize the fault characteristics of the rolling bearing at different fault degrees or different fault stages; obtaining the frequency amplitude corresponding to the fault characteristic frequency; the frequency amplitude includes the single frequency amplitude, the double frequency amplitude and the triple frequency amplitude.

[0057] Alternatively, the rotational frequency doubles as the shaft's rotational frequency, a fundamental parameter of rolling bearing operation that reflects the overall operating speed of the bearing. This frequency can typically be obtained using a speed sensor mounted near the shaft, or calculated based on information such as the motor's speed and transmission ratio.

[0058] Optionally, when a rolling bearing fails in various components (such as the inner ring, outer ring, and rolling elements) during operation, the interaction between the faulty part and the rotating components generates vibration signals of specific frequencies. These frequencies are related to the rotational frequency of the shaft. Fault frequencies such as the single, double, and triple harmonics are derived based on the failure mechanism and mathematical model of the rolling bearing. For example, when a rolling bearing's inner ring is locally damaged, the periodic impact of the rolling elements and the damaged part produces a characteristic frequency in the vibration signal associated with the inner ring failure. This frequency typically has a specific multiple relationship with the shaft rotational frequency, such as the single, double, or triple harmonics. By performing spectral analysis on the vibration data and combining it with information from the single harmonic of the rotational frequency, these characteristic fault frequencies can be identified. Different harmonics may correspond to different fault severity or stages.

[0059] Furthermore, after determining the characteristic fault frequency through spectrum analysis, the amplitude corresponding to each characteristic frequency can be obtained, namely the amplitude of the first, second, and third harmonics. The amplitude reflects the energy of the frequency component in the vibration signal, that is, the degree of prominence of the fault characteristic. The larger the amplitude, the more significant the corresponding fault characteristic and the more serious the fault may be. By monitoring the changes in the amplitude of different harmonics, the development trend of the fault can be understood.

[0060] For example, for the inner ring of a rolling bearing, the mathematical expression of its fault characteristic frequency is:

[0061] The rotation frequency of the shaft is doubled:

[0062] Rolling bearing inner ring fault frequency:

[0063] Fault double frequency of the inner ring of rolling bearing:

[0064] Fault triple frequency of the inner ring of rolling bearing:

[0065] Where n is the rotation speed of the shaft, is the contact angle, d is the rolling element diameter, N is the number of rolling elements, and D is the diameter of the bearing.

[0066] Similarly, for the outer ring and rolling element of the rolling bearing, the corresponding fault characteristic frequency and frequency amplitude can be obtained in the same manner.

[0067] For example, for the outer ring of a rolling bearing, the mathematical expression of its fault characteristic frequency is:

[0068] The rotation frequency of the shaft is doubled:

[0069] Rolling bearing inner ring fault frequency:

[0070] Fault double frequency of the inner ring of rolling bearing:

[0071] Fault triple frequency of the inner ring of rolling bearing:

[0072] Where n is the rotation speed of the shaft, is the contact angle, d is the rolling element diameter, N is the number of rolling elements, and D is the diameter of the bearing.

[0073] For the outer ring of the rolling bearing, the mathematical expression of its fault characteristic frequency is:

[0074] The rotation frequency of the shaft is doubled:

[0075] Rolling bearing inner ring fault frequency:

[0076] Fault double frequency of the inner ring of rolling bearing:

[0077] Fault triple frequency of the inner ring of rolling bearing:

[0078] Where n is the rotation speed of the shaft, is the contact angle, d is the rolling element diameter, N is the number of rolling elements, and D is the diameter of the bearing.

[0079] In this embodiment, by obtaining the double frequency of the rotation frequency of the rotating shaft of the rolling bearing, the fault characteristic frequency of the rolling bearing is obtained based on the double frequency of the rotation frequency and vibration data, and the frequency amplitude corresponding to the fault characteristic frequency is obtained, which can intuitively reflect the severity of the fault and thus accurately perform fault diagnosis.

[0080] In an exemplary embodiment, the step of obtaining a confidence rule base based on the frequency amplitude includes: obtaining a first confidence rule based on the first-harmonic frequency amplitude; the first confidence rule is used to characterize the first initial confidence when the first-harmonic frequency amplitude meets the amplitude change condition, the first amplitude threshold when the rolling bearing meets the effective fault condition, and the first amplitude limit corresponding to the first-harmonic frequency amplitude; obtaining a second confidence rule based on the double-harmonic frequency amplitude; the second confidence rule is used to characterize the second initial confidence when the double-harmonic frequency amplitude meets the amplitude change condition, the second amplitude threshold when the rolling bearing meets the effective fault condition, and the second amplitude limit corresponding to the double-harmonic frequency amplitude; obtaining a third confidence rule based on the triple-harmonic frequency amplitude; the third confidence rule is used to characterize the third initial confidence when the triple-harmonic frequency amplitude meets the amplitude change condition, the third amplitude threshold when the rolling bearing meets the effective fault condition, and the third amplitude limit corresponding to the triple-harmonic frequency amplitude.

[0081] Optionally, for the single-harmonic amplitude, through analysis and experimental research of a large amount of rolling bearing vibration data, it is determined that when the single-harmonic amplitude meets specific amplitude change conditions, such as the amplitude growth rate within a certain period of time or the degree to which it exceeds a certain reference value, it is assigned a first initial confidence level. The first initial confidence level is the basis for preliminary judgment that there may be a fault in the rolling bearing. At the same time, based on the structural characteristics, operating conditions, and historical fault data of the rolling bearing, the first amplitude threshold when the rolling bearing meets the effective fault condition is determined. When the single-harmonic amplitude reaches or exceeds this threshold, it is more likely to mean that the bearing has an actual fault. In addition, a first amplitude limit corresponding to the single-harmonic amplitude will be set to define the reasonable range of the amplitude. If the single-harmonic amplitude exceeds this limit, it may indicate that the fault is already more serious, or that there are abnormalities in the data that require further analysis.

[0082] Furthermore, since different harmonics may correspond to different fault modes or fault development stages, similar to obtaining the first confidence rule, the double frequency amplitude and the triple frequency amplitude are analyzed separately, and the second initial confidence level when the double frequency amplitude meets the amplitude change condition, the second amplitude threshold when the valid fault condition is met, and the corresponding second amplitude limit are determined respectively, as well as the relevant parameters of the triple frequency amplitude, namely, the third initial confidence level, the third amplitude threshold, and the third amplitude limit.

[0083] For example, taking the inner ring of a rolling bearing as an example, based on its frequency amplitude, the confidence rule base obtained can be expressed as follows: if the amplitude of the first harmonic reaches 0.8 (the corresponding threshold is 0.2, and the limit is 0.8), the amplitude of the second harmonic reaches 0.8 (the corresponding threshold is 0.1, and the limit is 0.6), and the amplitude of the third harmonic reaches 0.9 (the corresponding threshold is 0.1, and the limit is 0.5), and these three prerequisites are met at the same time, then it can be determined that the inner ring of the rolling bearing is faulty, and the confidence level of the fault is 0.9.

[0084] For example, taking the outer ring of a rolling bearing as an example, based on its frequency amplitude, the confidence rule base obtained can be expressed as follows: if the amplitude of the first harmonic reaches 0.8 (the corresponding threshold is 0.2, and the limit is 0.8), the amplitude of the second harmonic reaches 0.8 (the corresponding threshold is 0.2, and the limit is 0.8), and the amplitude of the third harmonic reaches 0.9 (the corresponding threshold is 0.2, and the limit is 0.8), and these three prerequisites are met at the same time, then it can be determined that the inner ring of the rolling bearing has a fault, and the confidence level of the fault is 0.9.

[0085] For example, taking the rolling element of a rolling bearing as an example, based on its frequency amplitude, the confidence rule base obtained can be expressed as follows: if the first harmonic amplitude reaches 0.8 (the corresponding threshold is 0.2, and the limit is 0.8), the second harmonic amplitude reaches 0.8 (the corresponding threshold is 0.1, and the limit is 0.6), and the third harmonic amplitude reaches 0.9 (the corresponding threshold is 0.1, and the limit is 0.5), and these three prerequisites are met at the same time, then it can be determined that the inner ring of the rolling bearing is faulty, and the confidence level of the fault is 0.9.

[0086] In this embodiment, by setting conditions such as thresholds and limits of amplitudes corresponding to different fault characteristic frequencies, it is possible to determine whether there is a fault on the inner ring of the rolling bearing and determine the fault confidence level. This can comprehensively consider various situations of rolling bearing failures and improve the accuracy of fault diagnosis.

[0087] In an exemplary embodiment, the step of obtaining a characteristic confidence corresponding to the fault characteristic frequency based on the frequency amplitude and the confidence rule base includes: obtaining a first characteristic confidence corresponding to the first frequency of the fault based on a first function; the numerator of the first function is the difference between the first frequency amplitude and the first amplitude threshold, and the denominator is the difference between the first amplitude limit and the first amplitude threshold; obtaining a second characteristic confidence corresponding to the second frequency of the fault based on a second function; the numerator of the second function is the difference between the second frequency amplitude and the second amplitude threshold, and the denominator is the difference between the second amplitude limit and the second amplitude threshold; obtaining a third characteristic confidence corresponding to the triple frequency of the fault based on a third function; the numerator of the third function is the difference between the triple frequency amplitude and the third amplitude threshold, and the denominator is the difference between the third amplitude limit and the third amplitude threshold.

[0088] Optionally, the first function is used to calculate the first characteristic confidence corresponding to the fault frequency doubling, wherein the frequency doubling amplitude reflects the energy of the fault frequency doubling in the vibration signal, the first amplitude threshold is the critical value for determining that the rolling bearing may have an effective fault under the frequency doubling related fault, and the first amplitude limit defines the reasonable upper limit of the frequency doubling amplitude. The difference between the frequency doubling amplitude and the first amplitude threshold characterizes the degree to which the current amplitude exceeds the threshold. The larger the difference, the greater the deviation from the normal state. The difference between the first amplitude limit and the first amplitude threshold acts as a normalization function, and the first characteristic confidence is obtained by dividing the two, which quantifies the possibility of judging the existence of the fault based on the frequency doubling amplitude. Similarly, the second function, for the fault frequency doubling, divides the difference between the frequency doubling amplitude and the second amplitude threshold by the difference between the second amplitude limit and the second amplitude threshold to obtain the second characteristic confidence, which is used to measure the possibility of judging the fault based on the frequency doubling amplitude. And according to the difference between the triple frequency amplitude and the third amplitude threshold, and the difference between the third amplitude limit and the third amplitude threshold, a third characteristic confidence is calculated, and the third characteristic confidence reflects the quantitative result of the fault possibility based on the triple frequency amplitude.

[0089] Exemplarily, the first function, the second function, and the third function are all membership functions. Assuming that the amplitudes corresponding to the fault frequency of the inner ring, the fault frequency of the double fault, and the fault frequency of the triple fault are 0.7, 0.5, and 0.4, respectively, the confidence rule base is expressed as follows: if the amplitude of the single frequency reaches 0.8 (the corresponding threshold is 0.2, and the limit is 0.8), the amplitude of the double frequency reaches 0.8 (the corresponding threshold is 0.1, and the limit is 0.6), and the amplitude of the triple frequency reaches 0.9 (the corresponding threshold is 0.1, and the limit is 0.5), and these three prerequisites are met at the same time, then it can be determined that the inner ring of the rolling bearing has a fault, and the confidence of the fault is 0.9. Then, the mathematical expression for calculating the corresponding feature confidence according to the membership function is:

[0090] First feature confidence:

[0091] Second feature confidence:

[0092] Third feature confidence:

[0093] In this embodiment, by obtaining the characteristic confidence corresponding to the fault characteristic frequency based on the frequency amplitude and the confidence rule base, the confidence level of the fault occurrence can be accurately evaluated, thereby improving the accuracy of fault diagnosis.

[0094] In an exemplary embodiment, the step of performing fault diagnosis on a rolling bearing based on a confidence rule base and feature confidence includes: obtaining a confidence matching degree based on a first feature confidence degree, a second feature confidence degree, and a third feature confidence degree; and determining that a rolling bearing fault occurs when the confidence matching degree is less than a matching degree threshold.

[0095] Optionally, the first, second and third characteristic confidence levels are calculated based on the amplitudes of the fault frequency, double frequency and triple frequency respectively, and represent quantitative indicators of the possibility of fault occurrence under different fault characteristic frequencies. These three characteristic confidence levels are integrated to obtain the confidence matching level. Among them, the confidence matching level reflects the degree of compliance of the amplitudes of multiple fault characteristic frequencies with the fault preconditions specified by the confidence rule base. The confidence matching level is compared with the matching level threshold. If the confidence matching level is less than the matching level threshold, it indicates that from the comprehensive analysis of multiple fault characteristic frequencies, the current state of the rolling bearing meets the conditions for the occurrence of the fault, and the possibility of the fault is high. Therefore, it is determined that the rolling bearing has a fault. Among them, the matching level threshold can be determined based on the confidence rule base, and can also be set based on empirical values.

[0096] For example, the inner ring of a rolling bearing is used as an example for illustration. In combination with the above embodiments, the mathematical expression of the confidence matching degree is:

[0097]

[0098] in, are the first feature confidence, the second feature confidence and the third feature confidence respectively, and the calculated Compared with the matching threshold of 0.2, if It means that the actual features match the confidence rule base as a whole, with a high confidence level. If the inner ring surface has a fault, then it is established. Otherwise, the fault is not established.

[0099] For example, in combination with the feature confidence calculated in the above embodiment, the confidence matching degree of the inner ring of the rolling bearing is:

[0100]

[0101] For example, for the outer ring of a rolling bearing, the mathematical expression of its confidence matching is:

[0102]

[0103] in, are the first feature confidence, the second feature confidence and the third feature confidence respectively, and the calculated Compared with the matching threshold of 0.2, if It means that the actual features match the confidence rule base as a whole, with a high confidence level. If the outer ring surface has a fault, then it is established. Otherwise, the fault is not established.

[0104] For example, for rolling elements of rolling bearings, the mathematical expression of the confidence matching degree is:

[0105]

[0106] in, are the first feature confidence, the second feature confidence and the third feature confidence respectively, and the calculated Compared with the matching threshold of 0.2, if It means that the actual features match the confidence rule base as a whole, with a high confidence level. If the outer ring surface has a fault, then it is established. Otherwise, the fault is not established.

[0107] In this embodiment, by obtaining the confidence matching degree based on the first feature confidence degree, the second feature confidence degree and the third feature confidence degree, when the confidence matching degree is less than the matching degree threshold, it is determined that the rolling bearing has a fault, which can improve the accuracy of fault diagnosis.

[0108] In an exemplary embodiment, the method further includes: respectively obtaining a first confidence difference, a second confidence difference, and a third confidence difference between the target confidence and the first feature confidence, the second feature confidence, and the third feature confidence; taking the product of the first confidence difference, the second confidence difference, the third confidence difference, and the reference confidence as a conclusion confidence; and performing fault diagnosis on the rolling bearing based on the conclusion confidence.

[0109] Optionally, the target confidence is a numerical value representing an ideal or standard fault probability, usually 1. The first confidence difference reflects the degree of difference between the fault probability reflected by the single-frequency amplitude and the target situation. Similarly, the second confidence difference reflects the degree of difference between the fault probability reflected by the double-frequency amplitude and the target situation. The third confidence difference reflects the degree of difference between the fault probability reflected by the triple-frequency amplitude and the target situation. The reference confidence is a pre-set value used to adjust and calibrate the calculation results. The three calculated confidence differences are multiplied by the reference confidence to obtain the conclusion confidence, which integrates the differences between the fault probability and the target value under multiple fault characteristic frequencies, as well as reference factors, to obtain a quantitative indicator that comprehensively reflects the possibility of rolling bearing failure.

[0110] For example, still taking the inner ring of a rolling bearing as an example, combined with the above embodiment, the data expression of the conclusion confidence is expressed as:

[0111]

[0112] in, are the first feature confidence, the second feature confidence and the third feature confidence respectively, is the reference confidence level, where The larger the value is, the higher the credibility of the conclusion that there is a fault on the surface of the inner ring of the rolling bearing is, and vice versa.

[0113] For example, in combination with the feature confidence calculated in the above embodiment, the conclusion confidence of the inner ring of the rolling bearing is:

[0114]

[0115] For example, for the outer ring of a rolling bearing, the data expression of the confidence level of the conclusion is expressed as:

[0116]

[0117] in, are the first feature confidence, the second feature confidence and the third feature confidence respectively, is the reference confidence level, where The larger the value is, the higher the credibility of the conclusion that there is a fault on the surface of the inner ring of the rolling bearing is, and vice versa.

[0118] For example, for the outer ring of a rolling bearing, the data expression of the confidence level of the conclusion is expressed as:

[0119]

[0120] in, are the first feature confidence, the second feature confidence and the third feature confidence respectively, is the reference confidence level, where The larger the value is, the higher the credibility of the conclusion that there is a fault on the surface of the inner ring of the rolling bearing is, and vice versa.

[0121] In this embodiment, by obtaining the conclusion confidence and performing fault diagnosis on the rolling bearing according to the conclusion confidence, the difference between the fault probability and the target value under multiple fault characteristic frequencies can be comprehensively considered, thereby further improving the accuracy of fault diagnosis.

[0122] In an exemplary embodiment, Figure 3 As shown, a rolling bearing fault diagnosis method is provided, which includes the following steps:

[0123] Vibration data of the rolling bearing is acquired; the vibration data includes at least one of inner ring vibration data, outer ring vibration data, and rolling element vibration data.

[0124] Obtain the single-octave frequency of the rotational frequency of the rotating shaft of the rolling bearing; the single-octave frequency of the rotational frequency is used to characterize the rotational frequency of the rotating shaft; obtain the fault characteristic frequency of the rolling bearing based on the single-octave frequency of the rotational frequency and the vibration data; the fault characteristic frequency includes the single-octave frequency, the double-octave frequency and the triple-octave frequency, which are respectively used to characterize the fault characteristics of the rolling bearing at different fault degrees or different fault stages; obtain the frequency amplitude corresponding to the fault characteristic frequency; the frequency amplitude includes the single-octave frequency amplitude, the double-octave frequency amplitude and the triple-octave frequency amplitude.

[0125] According to the first-harmonic frequency amplitude, a first confidence rule is obtained; the first confidence rule is used to characterize the first initial confidence when the first-harmonic frequency amplitude meets the amplitude change condition, the first amplitude threshold when the rolling bearing meets the effective fault condition, and the first amplitude limit corresponding to the first-harmonic frequency amplitude; according to the double-harmonic frequency amplitude, a second confidence rule is obtained; the second confidence rule is used to characterize the second initial confidence when the double-harmonic frequency amplitude meets the amplitude change condition, the second amplitude threshold when the rolling bearing meets the effective fault condition, and the second amplitude limit corresponding to the double-harmonic frequency amplitude; according to the triple-harmonic frequency amplitude, a third confidence rule is obtained; the third confidence rule is used to characterize the third initial confidence when the triple-harmonic frequency amplitude meets the amplitude change condition, the third amplitude threshold when the rolling bearing meets the effective fault condition, and the third amplitude limit corresponding to the triple-harmonic frequency amplitude.

[0126] According to the first function, the first characteristic confidence corresponding to the fault frequency doubling is obtained; the numerator of the first function is the difference between the frequency doubling amplitude and the first amplitude threshold, and the denominator is the difference between the first amplitude limit and the first amplitude threshold; according to the second function, the second characteristic confidence corresponding to the fault frequency doubling is obtained; the numerator of the second function is the difference between the frequency doubling amplitude and the second amplitude threshold, and the denominator is the difference between the second amplitude limit and the second amplitude threshold; according to the third function, the third characteristic confidence corresponding to the fault frequency doubling is obtained; the numerator of the third function is the difference between the frequency doubling amplitude and the third amplitude threshold, and the denominator is the difference between the third amplitude limit and the third amplitude threshold.

[0127] A confidence matching degree is obtained according to the first feature confidence degree, the second feature confidence degree, and the third feature confidence degree; and when the confidence matching degree is less than a matching degree threshold, it is determined that a rolling bearing fault occurs.

[0128] The first confidence difference, the second confidence difference and the third confidence difference between the target confidence and the first feature confidence, the second feature confidence and the third feature confidence are respectively obtained; the product of the first confidence difference, the second confidence difference, the third confidence difference and the reference confidence is used as the conclusion confidence; and the rolling bearing fault is diagnosed based on the conclusion confidence.

[0129] The process of performing fault diagnosis on the rolling bearing includes at least one of performing fault diagnosis on the inner ring of the rolling bearing, performing fault diagnosis on the outer ring of the rolling bearing, and performing fault diagnosis on the rolling element of the rolling bearing.

[0130] In this embodiment, the vibration data of the rolling bearing is obtained, and the fault characteristic frequency and frequency amplitude of the rolling bearing are obtained based on the vibration data. The confidence rule base is obtained based on the frequency amplitude. The feature confidence corresponding to the fault characteristic frequency is obtained based on the frequency amplitude and the confidence rule base. The rolling bearing is fault diagnosed based on the confidence rule base and the feature confidence. By matching the feature confidence corresponding to the fault characteristic frequency with the confidence rule base, the accuracy of the fault diagnosis can be improved. Since the vibration data includes at least one of the inner ring vibration data, the outer ring vibration data and the rolling body vibration data, the inner ring of the rolling bearing, the outer ring of the rolling bearing and at least one of the rolling bearing can be diagnosed, thereby improving the comprehensiveness of the fault diagnosis and effectively ensuring the safe operation of the rolling bearing.

[0131] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0132] Based on the same inventive concept, embodiments of the present application further provide a rolling bearing fault diagnosis device for implementing the aforementioned rolling bearing fault diagnosis method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations in one or more embodiments of the rolling bearing fault diagnosis device provided below can be found in the aforementioned limitations on the rolling bearing fault diagnosis method and will not be further elaborated here.

[0133] In an exemplary embodiment, Figure 4 As shown, a rolling bearing fault diagnosis device is provided, comprising: a data acquisition module 10, a frequency acquisition module 20, a confidence acquisition module 30 and a fault diagnosis module 40, wherein:

[0134] The data acquisition module 10 is used to acquire vibration data of the rolling bearing; the vibration data includes at least one of inner ring vibration data, outer ring vibration data and rolling element vibration data.

[0135] The frequency acquisition module 20 is used to acquire the fault characteristic frequency and frequency amplitude of the rolling bearing according to the vibration data.

[0136] The confidence acquisition module 30 is used to acquire a confidence rule base according to the frequency amplitude; the confidence rule base is used to characterize the confidence threshold corresponding to the fault characteristic frequency.

[0137] The fault diagnosis module 40 is used to obtain the characteristic confidence corresponding to the fault characteristic frequency based on the frequency amplitude and the confidence rule base, and perform fault diagnosis on the rolling bearing based on the confidence rule base and the characteristic confidence; wherein, the process of fault diagnosis on the rolling bearing includes at least one of fault diagnosis on the inner ring of the rolling bearing, fault diagnosis on the outer ring of the rolling bearing, and fault diagnosis on the rolling element of the rolling bearing.

[0138] In an exemplary embodiment, the frequency acquisition module 20 is also used to obtain the single-octave frequency of the rotational frequency of the rotating shaft of the rolling bearing; the single-octave frequency of the rotational frequency is used to characterize the rotational frequency of the rotating shaft; based on the single-octave frequency of the rotational frequency and the vibration data, the fault characteristic frequency of the rolling bearing is obtained; the fault characteristic frequency includes the single-octave frequency, the double-octave frequency and the triple-octave frequency of the fault, and the single-octave frequency, the double-octave frequency and the triple-octave frequency of the fault are respectively used to characterize the fault characteristics of the rolling bearing at different fault degrees or different fault stages; the frequency amplitude corresponding to the fault characteristic frequency is obtained; the frequency amplitude includes the single-octave amplitude, the double-octave amplitude and the triple-octave amplitude.

[0139] In an exemplary embodiment, the confidence acquisition module 30 is also used to obtain a first confidence rule based on the first-harmonic frequency amplitude; the first confidence rule is used to characterize the first initial confidence when the first-harmonic frequency amplitude meets the amplitude change condition, the first amplitude threshold when the rolling bearing meets the effective fault condition, and the first amplitude limit corresponding to the first-harmonic frequency amplitude; the second confidence rule is obtained based on the double-harmonic frequency amplitude; the second confidence rule is used to characterize the second initial confidence when the double-harmonic frequency amplitude meets the amplitude change condition, the second amplitude threshold when the rolling bearing meets the effective fault condition, and the second amplitude limit corresponding to the double-harmonic frequency amplitude; the third confidence rule is obtained based on the triple-harmonic frequency amplitude; the third confidence rule is used to characterize the third initial confidence when the triple-harmonic frequency amplitude meets the amplitude change condition, the third amplitude threshold when the rolling bearing meets the effective fault condition, and the third amplitude limit corresponding to the triple-harmonic frequency amplitude.

[0140] In an exemplary embodiment, the fault diagnosis module 40 is also used to obtain a first characteristic confidence corresponding to the first frequency harmonic of the fault according to a first function; the numerator of the first function is the difference between the first frequency harmonic amplitude and the first amplitude threshold, and the denominator is the difference between the first amplitude limit and the first amplitude threshold; according to a second function, obtain a second characteristic confidence corresponding to the second frequency harmonic of the fault; the numerator of the second function is the difference between the second frequency harmonic amplitude and the second amplitude threshold, and the denominator is the difference between the second amplitude limit and the second amplitude threshold; according to a third function, obtain a third characteristic confidence corresponding to the third frequency harmonic of the fault; the numerator of the third function is the difference between the triple frequency harmonic amplitude and the third amplitude threshold, and the denominator is the difference between the third amplitude limit and the third amplitude threshold.

[0141] In an exemplary embodiment, the fault diagnosis module 40 is further configured to obtain a confidence matching degree based on the first feature confidence degree, the second feature confidence degree, and the third feature confidence degree; and determine that a rolling bearing fault occurs when the confidence matching degree is less than a matching degree threshold.

[0142] In an exemplary embodiment, the fault diagnosis module 40 is also used to obtain the first confidence difference, the second confidence difference and the third confidence difference between the target confidence and the first feature confidence, the second feature confidence and the third feature confidence, respectively; take the product of the first confidence difference, the second confidence difference, the third confidence difference and the reference confidence as the conclusion confidence; and perform fault diagnosis on the rolling bearing based on the conclusion confidence.

[0143] Each module in the rolling bearing fault diagnosis device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0144] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via wired or wireless communication, and the wireless communication can be achieved via Wi-Fi, a mobile cellular network, near field communication (NFC), or other technologies. When the computer program is executed by the processor, a rolling bearing fault diagnosis method is implemented. The display unit of the computer device is used to form a visually visible image, and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0145] Those skilled in the art will understand that Figure 5The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0146] In an exemplary embodiment, a computer device is provided, comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: obtaining vibration data of a rolling bearing; the vibration data includes at least one of inner ring vibration data, outer ring vibration data and rolling body vibration data; obtaining the fault characteristic frequency and frequency amplitude of the rolling bearing based on the vibration data; obtaining a confidence rule base based on the frequency amplitude; the confidence rule base is used to characterize the confidence threshold corresponding to the fault characteristic frequency; obtaining the feature confidence corresponding to the fault characteristic frequency based on the frequency amplitude and the confidence rule base, and performing fault diagnosis on the rolling bearing based on the confidence rule base and the feature confidence; wherein the process of performing fault diagnosis on the rolling bearing includes at least one of performing fault diagnosis on the inner ring of the rolling bearing, performing fault diagnosis on the outer ring of the rolling bearing, and performing fault diagnosis on the rolling body of the rolling bearing.

[0147] In one embodiment, when a processor executes a computer program, the processor obtains the fault characteristic frequency and frequency amplitude of the rolling bearing based on vibration data, including: obtaining the single frequency of the rotation frequency of the rotating shaft of the rolling bearing; the single frequency of the rotation frequency is used to characterize the rotation frequency of the rotating shaft; according to the single frequency of the rotation frequency and the vibration data, the fault characteristic frequency of the rolling bearing is obtained; the fault characteristic frequency includes the single frequency, the double frequency and the triple frequency, which are respectively used to characterize the fault characteristics of the rolling bearing at different fault degrees or different fault stages; obtaining the frequency amplitude corresponding to the fault characteristic frequency; the frequency amplitude includes the single frequency amplitude, the double frequency amplitude and the triple frequency amplitude.

[0148] In one embodiment, when a processor executes a computer program, the process involved in obtaining a confidence rule base based on frequency amplitude includes: obtaining a first confidence rule based on the first-harmonic frequency amplitude; the first confidence rule is used to characterize a first initial confidence level when the first-harmonic frequency amplitude satisfies an amplitude change condition, a first amplitude threshold value when the rolling bearing satisfies an effective fault condition, and a first amplitude limit value corresponding to the first-harmonic frequency amplitude; obtaining a second confidence rule based on the second-harmonic frequency amplitude; the second confidence rule is used to characterize a second initial confidence level when the second-harmonic frequency amplitude satisfies an amplitude change condition, a second amplitude threshold value when the rolling bearing satisfies an effective fault condition, and a second amplitude limit value corresponding to the second-harmonic frequency amplitude; obtaining a third confidence rule based on the tripled frequency amplitude; the third confidence rule is used to characterize a third initial confidence level when the tripled frequency amplitude satisfies an amplitude change condition, a third amplitude threshold value when the rolling bearing satisfies an effective fault condition, and a third amplitude limit value corresponding to the tripled frequency amplitude.

[0149] In one embodiment, when a processor executes a computer program, the process involves obtaining a characteristic confidence corresponding to a fault characteristic frequency based on the frequency amplitude and a confidence rule base, including: obtaining a first characteristic confidence corresponding to a single frequency of the fault based on a first function; the numerator of the first function is the difference between the single frequency amplitude and the first amplitude threshold, and the denominator is the difference between the first amplitude limit and the first amplitude threshold; obtaining a second characteristic confidence corresponding to a double frequency of the fault based on a second function; the numerator of the second function is the difference between the double frequency amplitude and the second amplitude threshold, and the denominator is the difference between the second amplitude limit and the second amplitude threshold; obtaining a third characteristic confidence corresponding to a triple frequency of the fault based on a third function; the numerator of the third function is the difference between the triple frequency amplitude and the third amplitude threshold, and the denominator is the difference between the third amplitude limit and the third amplitude threshold.

[0150] In one embodiment, when a processor executes a computer program, fault diagnosis of a rolling bearing is performed based on a confidence rule base and a feature confidence, including: obtaining a confidence matching degree based on a first feature confidence degree, a second feature confidence degree, and a third feature confidence degree; and determining that a rolling bearing fault occurs when the confidence matching degree is less than a matching degree threshold.

[0151] In one embodiment, when the processor executes the computer program, the following steps are also implemented: respectively obtaining the first confidence difference, the second confidence difference and the third confidence difference between the target confidence and the first feature confidence, the second feature confidence and the third feature confidence; taking the product of the first confidence difference, the second confidence difference, the third confidence difference and the reference confidence as the conclusion confidence; and performing fault diagnosis on the rolling bearing based on the conclusion confidence.

[0152] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: obtaining vibration data of a rolling bearing; the vibration data includes at least one of inner ring vibration data, outer ring vibration data and rolling body vibration data; according to the vibration data, obtaining the fault characteristic frequency and frequency amplitude of the rolling bearing; according to the frequency amplitude, obtaining a confidence rule base; the confidence rule base is used to characterize the confidence threshold corresponding to the fault characteristic frequency; according to the frequency amplitude and the confidence rule base, obtaining the feature confidence corresponding to the fault characteristic frequency, and performing fault diagnosis on the rolling bearing according to the confidence rule base and the feature confidence; wherein the process of performing fault diagnosis on the rolling bearing includes at least one of performing fault diagnosis on the inner ring of the rolling bearing, performing fault diagnosis on the outer ring of the rolling bearing, and performing fault diagnosis on the rolling body of the rolling bearing.

[0153] In one embodiment, when a computer program is executed by a processor, it involves obtaining the fault characteristic frequency and frequency amplitude of the rolling bearing based on vibration data, including: obtaining the single frequency of the rotation frequency of the rotating shaft of the rolling bearing; the single frequency of the rotation frequency is used to characterize the rotation frequency of the rotating shaft; obtaining the fault characteristic frequency of the rolling bearing based on the single frequency of the rotation frequency and the vibration data; the fault characteristic frequency includes the single frequency, the double frequency and the triple frequency, which are respectively used to characterize the fault characteristics of the rolling bearing at different fault degrees or different fault stages; obtaining the frequency amplitude corresponding to the fault characteristic frequency; the frequency amplitude includes the single frequency amplitude, the double frequency amplitude and the triple frequency amplitude.

[0154] In one embodiment, when a computer program is executed by a processor, the process involved in obtaining a confidence rule base based on frequency amplitude includes: obtaining a first confidence rule based on the first-harmonic frequency amplitude; the first confidence rule is used to characterize a first initial confidence level when the first-harmonic frequency amplitude satisfies an amplitude change condition, a first amplitude threshold value when the rolling bearing satisfies an effective fault condition, and a first amplitude limit value corresponding to the first-harmonic frequency amplitude; obtaining a second confidence rule based on the double-harmonic frequency amplitude; the second confidence rule is used to characterize a second initial confidence level when the double-harmonic frequency amplitude satisfies an amplitude change condition, a second amplitude threshold value when the rolling bearing satisfies an effective fault condition, and a second amplitude limit value corresponding to the double-harmonic frequency amplitude; obtaining a third confidence rule based on the triple-harmonic frequency amplitude; the third confidence rule is used to characterize a third initial confidence level when the triple-harmonic frequency amplitude satisfies an amplitude change condition, a third amplitude threshold value when the rolling bearing satisfies an effective fault condition, and a third amplitude limit value corresponding to the triple-harmonic frequency amplitude.

[0155] In one embodiment, when a computer program is executed by a processor, the computer program involves obtaining a characteristic confidence corresponding to the fault characteristic frequency based on the frequency amplitude and the confidence rule base, including: obtaining a first characteristic confidence corresponding to the first frequency of the fault according to a first function; the numerator of the first function is the difference between the first frequency amplitude and the first amplitude threshold, and the denominator is the difference between the first amplitude limit and the first amplitude threshold; obtaining a second characteristic confidence corresponding to the second frequency of the fault according to a second function; the numerator of the second function is the difference between the second frequency amplitude and the second amplitude threshold, and the denominator is the difference between the second amplitude limit and the second amplitude threshold; obtaining a third characteristic confidence corresponding to the third frequency of the fault according to a third function; the numerator of the third function is the difference between the triple frequency amplitude and the third amplitude threshold, and the denominator is the difference between the third amplitude limit and the third amplitude threshold.

[0156] In one embodiment, when a computer program is executed by a processor, fault diagnosis of a rolling bearing is performed based on a confidence rule base and feature confidence, including: obtaining a confidence matching degree based on a first feature confidence degree, a second feature confidence degree, and a third feature confidence degree; and determining that a rolling bearing fault occurs when the confidence matching degree is less than a matching degree threshold.

[0157] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: respectively obtaining the first confidence difference, the second confidence difference and the third confidence difference between the target confidence and the first feature confidence, the second feature confidence and the third feature confidence; taking the product of the first confidence difference, the second confidence difference, the third confidence difference and the reference confidence as the conclusion confidence; and performing fault diagnosis on the rolling bearing based on the conclusion confidence.

[0158] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps: obtaining vibration data of a rolling bearing; the vibration data comprising at least one of inner ring vibration data, outer ring vibration data, and rolling body vibration data; obtaining a fault characteristic frequency and frequency amplitude of the rolling bearing based on the vibration data; obtaining a confidence rule base based on the frequency amplitude; the confidence rule base is used to characterize a confidence threshold corresponding to the fault characteristic frequency; obtaining a feature confidence corresponding to the fault characteristic frequency based on the frequency amplitude and the confidence rule base, and performing fault diagnosis on the rolling bearing based on the confidence rule base and the feature confidence; wherein the process of performing fault diagnosis on the rolling bearing comprises at least one of performing fault diagnosis on the inner ring of the rolling bearing, performing fault diagnosis on the outer ring of the rolling bearing, and performing fault diagnosis on the rolling body of the rolling bearing.

[0159] In one embodiment, when a computer program is executed by a processor, it involves obtaining the fault characteristic frequency and frequency amplitude of the rolling bearing based on vibration data, including: obtaining the single frequency of the rotation frequency of the rotating shaft of the rolling bearing; the single frequency of the rotation frequency is used to characterize the rotation frequency of the rotating shaft; obtaining the fault characteristic frequency of the rolling bearing based on the single frequency of the rotation frequency and the vibration data; the fault characteristic frequency includes the single frequency, the double frequency and the triple frequency, which are respectively used to characterize the fault characteristics of the rolling bearing at different fault degrees or different fault stages; obtaining the frequency amplitude corresponding to the fault characteristic frequency; the frequency amplitude includes the single frequency amplitude, the double frequency amplitude and the triple frequency amplitude.

[0160] In one embodiment, when a computer program is executed by a processor, the process involved in obtaining a confidence rule base based on frequency amplitude includes: obtaining a first confidence rule based on the first-harmonic frequency amplitude; the first confidence rule is used to characterize a first initial confidence level when the first-harmonic frequency amplitude satisfies an amplitude change condition, a first amplitude threshold value when the rolling bearing satisfies an effective fault condition, and a first amplitude limit value corresponding to the first-harmonic frequency amplitude; obtaining a second confidence rule based on the double-harmonic frequency amplitude; the second confidence rule is used to characterize a second initial confidence level when the double-harmonic frequency amplitude satisfies an amplitude change condition, a second amplitude threshold value when the rolling bearing satisfies an effective fault condition, and a second amplitude limit value corresponding to the double-harmonic frequency amplitude; obtaining a third confidence rule based on the triple-harmonic frequency amplitude; the third confidence rule is used to characterize a third initial confidence level when the triple-harmonic frequency amplitude satisfies an amplitude change condition, a third amplitude threshold value when the rolling bearing satisfies an effective fault condition, and a third amplitude limit value corresponding to the triple-harmonic frequency amplitude.

[0161] In one embodiment, when a computer program is executed by a processor, the computer program involves obtaining a characteristic confidence corresponding to the fault characteristic frequency based on the frequency amplitude and the confidence rule base, including: obtaining a first characteristic confidence corresponding to the first frequency of the fault according to a first function; the numerator of the first function is the difference between the first frequency amplitude and the first amplitude threshold, and the denominator is the difference between the first amplitude limit and the first amplitude threshold; obtaining a second characteristic confidence corresponding to the second frequency of the fault according to a second function; the numerator of the second function is the difference between the second frequency amplitude and the second amplitude threshold, and the denominator is the difference between the second amplitude limit and the second amplitude threshold; obtaining a third characteristic confidence corresponding to the third frequency of the fault according to a third function; the numerator of the third function is the difference between the triple frequency amplitude and the third amplitude threshold, and the denominator is the difference between the third amplitude limit and the third amplitude threshold.

[0162] In one embodiment, when a computer program is executed by a processor, fault diagnosis of a rolling bearing is performed based on a confidence rule base and feature confidence, including: obtaining a confidence matching degree based on a first feature confidence degree, a second feature confidence degree, and a third feature confidence degree; and determining that a rolling bearing fault occurs when the confidence matching degree is less than a matching degree threshold.

[0163] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: respectively obtaining the first confidence difference, the second confidence difference and the third confidence difference between the target confidence and the first feature confidence, the second feature confidence and the third feature confidence; taking the product of the first confidence difference, the second confidence difference, the third confidence difference and the reference confidence as the conclusion confidence; and performing fault diagnosis on the rolling bearing based on the conclusion confidence.

[0164] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0165] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0166] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A rolling bearing fault diagnosis method, characterized in that: The method comprises: Acquiring vibration data of the rolling bearing; the vibration data includes at least one of inner ring vibration data, outer ring vibration data, and rolling element vibration data; Acquiring the fault characteristic frequency and frequency amplitude of the rolling bearing according to the vibration data; According to the frequency amplitude, a confidence rule base is obtained; the confidence rule base is used to characterize the confidence threshold corresponding to the fault characteristic frequency; Acquire a characteristic confidence level corresponding to the fault characteristic frequency according to the frequency amplitude and the confidence rule base, and perform fault diagnosis on the rolling bearing according to the confidence rule base and the characteristic confidence level; The process of diagnosing the rolling bearing fault includes at least one of diagnosing the inner ring of the rolling bearing fault, diagnosing the outer ring of the rolling bearing fault, and diagnosing the rolling element of the rolling bearing fault.

2. The method according to claim 1, characterized in that The step of obtaining the fault characteristic frequency and frequency amplitude of the rolling bearing according to the vibration data includes: Obtaining a frequency multiplication of the rotation frequency of the rotating shaft of the rolling bearing; the frequency multiplication of the rotation frequency is used to represent the rotation frequency of the rotating shaft; Obtaining a fault characteristic frequency of the rolling bearing according to the rotation frequency harmonics and the vibration data; the fault characteristic frequency includes a fault harmonics ... Obtain a frequency amplitude corresponding to the fault characteristic frequency; the frequency amplitude includes a single-frequency amplitude, a double-frequency amplitude, and a triple-frequency amplitude.

3. The method according to claim 2, characterized in that The obtaining of a confidence rule base according to the frequency amplitude includes: Obtaining a first confidence rule based on the first-harmonic frequency amplitude; the first confidence rule is used to characterize a first initial confidence level when the first-harmonic frequency amplitude satisfies an amplitude change condition, a first amplitude threshold when the rolling bearing satisfies a valid fault condition, and a first amplitude limit corresponding to the first-harmonic frequency amplitude; Obtaining a second confidence rule based on the double frequency amplitude; the second confidence rule is used to characterize a second initial confidence level when the double frequency amplitude satisfies the amplitude change condition, a second amplitude threshold when the rolling bearing satisfies the effective fault condition, and a second amplitude limit corresponding to the double frequency amplitude; A third confidence rule is obtained based on the tripled frequency amplitude; the third confidence rule is used to characterize a third initial confidence level when the tripled frequency amplitude meets the amplitude change condition, a third amplitude threshold when the rolling bearing meets the effective fault condition, and a third amplitude limit corresponding to the tripled frequency amplitude.

4. The method according to claim 3, characterized in that The acquiring, based on the frequency amplitude and the confidence rule base, a characteristic confidence level corresponding to the fault characteristic frequency includes: Obtaining a first characteristic confidence level corresponding to the fault frequency doubling according to a first function, wherein the numerator of the first function is the difference between the frequency doubling amplitude and the first amplitude threshold, and the denominator is the difference between the first amplitude limit and the first amplitude threshold; Obtaining a second characteristic confidence level corresponding to the fault double frequency according to a second function, wherein the numerator of the second function is the difference between the double frequency amplitude and the second amplitude threshold, and the denominator is the difference between the second amplitude limit and the second amplitude threshold; According to a third function, a third characteristic confidence corresponding to the fault triple frequency is obtained; the numerator of the third function is the difference between the triple frequency amplitude and the third amplitude threshold, and the denominator is the difference between the third amplitude limit and the third amplitude threshold.

5. The method according to claim 4, characterized in that The performing fault diagnosis on the rolling bearing according to the confidence rule base and the feature confidence level includes: Obtaining a confidence matching degree according to the first feature confidence degree, the second feature confidence degree, and the third feature confidence degree; When the confidence matching degree is less than the matching degree threshold, it is determined that a fault occurs in the rolling bearing.

6. The method according to claim 5, characterized in that The method further comprises: Respectively obtaining a first confidence difference, a second confidence difference, and a third confidence difference between the target confidence and the first feature confidence, the second feature confidence, and the third feature confidence; Taking the product of the first confidence difference, the second confidence difference, the third confidence difference and the reference confidence as the conclusion confidence; Perform fault diagnosis on the rolling bearing according to the conclusion confidence.

7. A rolling bearing fault diagnosis device, characterized in that: The device comprises: A data acquisition module, configured to acquire vibration data of the rolling bearing; the vibration data comprising at least one of inner ring vibration data, outer ring vibration data, and rolling element vibration data; A frequency acquisition module, configured to acquire the fault characteristic frequency and frequency amplitude of the rolling bearing according to the vibration data; A confidence acquisition module, configured to acquire a confidence rule base according to the frequency amplitude; the confidence rule base is configured to characterize a confidence threshold corresponding to the fault characteristic frequency; A fault diagnosis module is used to obtain the characteristic confidence corresponding to the fault characteristic frequency based on the frequency amplitude and the confidence rule base, and perform fault diagnosis on the rolling bearing based on the confidence rule base and the characteristic confidence; wherein the process of performing fault diagnosis on the rolling bearing includes at least one of performing fault diagnosis on the inner ring of the rolling bearing, performing fault diagnosis on the outer ring of the rolling bearing, and performing fault diagnosis on the rolling element of the rolling bearing.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images