Main bearing fault diagnosis method and related device

Abstract

The invention belongs to the field of wind generating set fault diagnosis, and discloses a main bearing fault diagnosis method and a related device, the state of a main bearing can be preliminarily judged by equally dividing the vibration waveform of the main bearing and obtaining a first index according to a sub-vibration waveform impact factor, and when the first index exceeds the standard, an envelope spectrum is further obtained to obtain a fault index; meanwhile, Fourier transform and normalization processing are carried out on the vibration waveform to obtain a normalized frequency spectrum, and a second index and a third index are obtained by analyzing the exceeding energy proportion and the exceeding energy distribution condition according to the normalized frequency spectrum; according to the method, due to the application of spectrum signal normalization, the method is not limited by the models of the main bearings, the problems of false alarm and missing alarm caused by large difference of vibration effective values of the main bearings of different models are effectively avoided, and the universality and accuracy of diagnosis are greatly improved. In the diagnosis process, the accuracy and efficiency of main bearing fault diagnosis are effectively improved by analyzing the proportion of the excessive energy and analyzing the distribution condition of the excessive energy.

Description

Technical Field

[0001] The invention belongs to the field of wind turbine generator fault diagnosis and relates to a main bearing fault diagnosis method and related devices. Background Art

[0002] Wind power generation, as a clean, renewable energy source, is playing an increasingly important role. As the core equipment of wind power generation systems, the stable operation of wind turbines is directly related to power generation efficiency and energy supply reliability. As a key component of wind turbines, the main bearing bears the important tasks of supporting the rotor weight and transmitting torque. Exposure to complex alternating loads and harsh environmental conditions over long periods of time makes it highly susceptible to failure. A main bearing failure not only causes the unit to shut down for maintenance, resulting in power generation losses, but can also cause more serious equipment damage and even jeopardize the safe operation of the entire wind farm. Therefore, timely and accurate fault diagnosis of wind turbine main bearings is of great practical significance.

[0003] While various technical approaches exist for wind turbine main bearing fault diagnosis, they all have varying degrees of limitations. Some traditional methods rely on manual inspections and empirical judgment. This approach is not only inefficient but also requires a high level of professional expertise and experience from inspectors. This makes it difficult to detect potential early-stage faults and fails to meet the real-time and accuracy requirements of large-scale wind farms for main bearing fault diagnosis.

[0004] With the development of sensor technology and signal processing technology, some fault diagnosis methods based on vibration signal analysis have gradually been applied. However, these methods also face many challenges in practical applications. On the one hand, different types of wind turbine main bearings have different structural characteristics and operating parameters. Existing fault diagnosis methods often lack universality and are difficult to apply to various types of main bearings, resulting in the need for a lot of adjustment and optimization work in practical applications. On the other hand, due to the complex operating environment of wind turbines, vibration signals are easily affected by various interference factors. Existing fault diagnosis methods have deficiencies in fault feature extraction and identification, and cannot effectively avoid false alarms and missed alarms. In addition, accurately distinguishing the severity of the fault is also a difficult problem in existing technologies. It is currently difficult to effectively identify the severity of the fault, resulting in the inability to formulate a maintenance strategy that adapts to the severity of the fault, thereby affecting maintenance efficiency and cost. Summary of the Invention

[0005] The purpose of the present invention is to overcome the above-mentioned shortcomings of the prior art and provide a main bearing fault diagnosis method and related devices.

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

[0007] In a first aspect, the present invention provides a main bearing fault diagnosis method, comprising: obtaining a vibration waveform of the main bearing; equally dividing the vibration waveform of the main bearing to obtain a plurality of sub-vibration waveforms, obtaining and obtaining a first indicator based on the impact factor of each sub-vibration waveform; when the first indicator is within the standard, the diagnosis result is no fault; when the first indicator is exceeded, obtaining an envelope spectrum of the vibration waveform of the main bearing, and obtaining and obtaining a fault indicator based on the frequencies of the top three frequency points of the amplitude of the envelope spectrum; and performing Fourier transform and normalization on the vibration waveform of the main bearing to obtain a normalized spectrum, obtaining and obtaining a fault indicator based on the amplitude of the envelope spectrum. The second indicator is obtained by the percentage of energy exceeding the standard in the normalized spectrum; when the second indicator is within the standard: when the fault indicator is exceeded, the diagnosis result is a third-level fault; otherwise, the diagnosis result is a third-level poor lubrication; when the second indicator is exceeded, the third indicator is obtained based on the proportion of energy exceeding the standard in the first half of the normalized spectrum; when the third indicator is within the standard: when the fault indicator is exceeded, the diagnosis result is a second-level fault; otherwise, the diagnosis result is a second-level poor lubrication; when the third indicator is exceeded: when the fault indicator is exceeded, the diagnosis result is a first-level fault; otherwise, the diagnosis result is a first-level poor lubrication.

[0008] Optionally, before obtaining the vibration waveform of the main bearing, the method further includes: obtaining the actual speed and rated speed of the main bearing; when the actual speed is greater than n times the rated speed, obtaining the vibration waveform of the main bearing; when the actual speed is not greater than n times the rated speed, ending the main bearing fault diagnosis; wherein n is a preset constant.

[0009] Optionally, the method further includes: performing band-pass filtering on the vibration waveform of the main bearing before processing the vibration waveform of the main bearing; wherein, when the vibration waveform of the main bearing is band-pass filtered, the filtering low point flow is:

[0010] flow=(rpm / 60)*FTF*5

[0011] Among them, rpm is the actual speed of the main bearing; FTF is the cage failure frequency of the main bearing.

[0012] The filtering high point fhigh is:

[0013] fhigh=(rpm / 60)*BPFI*25

[0014] Among them, BPFI is the failure frequency of the inner ring of the main bearing.

[0015] Optionally, the fault index obtained according to the frequencies of the top three frequency points of the envelope spectrum amplitude includes: when the frequencies of the top three frequency points of the envelope spectrum amplitude are all between 0.9*FTF and 1.1*BPFI, the fault index exceeds the standard; otherwise, the fault index does not exceed the standard; among them, FTF is the retainer fault frequency of the main bearing; BPFI is the inner ring fault frequency of the main bearing.

[0016] Optionally, the obtaining and obtaining of the first indicator based on the impact factor of each sub-vibration waveform includes: dividing the peak value of each sub-vibration waveform by the effective value of the vibration waveform of the main bearing to obtain the impact factor of each sub-vibration waveform; when at least half of the impact factors of each sub-vibration waveform exceed a preset impact factor threshold, the first indicator exceeds the standard; otherwise, the first indicator does not exceed the standard.

[0017] Optionally, the obtaining and obtaining of the second indicator based on the percentage of energy exceeding the standard in the normalized spectrum includes: obtaining the proportion of amplitudes greater than 1.5*std in the amplitude sequence of the normalized spectrum, and obtaining the percentage of energy exceeding the standard in the normalized spectrum; wherein std is the standard deviation of the normalized spectrum; when the percentage of energy exceeding the standard in the normalized spectrum is greater than a preset threshold value of the percentage of energy exceeding the standard, the second indicator is exceeded; otherwise, the second indicator is not exceeded.

[0018] Optionally, the acquiring and obtaining of the third indicator based on the proportion of energy exceeding the standard in the first half of the normalized spectrum includes: acquiring the ratio of the sum of the effective values ​​of each amplitude in the first half of the normalized spectrum to the sum of the effective values ​​of all amplitudes of the normalized spectrum to obtain the proportion of energy exceeding the standard in the first half of the normalized spectrum; when the proportion of energy exceeding the standard in the first half of the normalized spectrum is greater than a preset threshold value of the proportion of energy exceeding the standard in the first half, the third indicator is exceeded; otherwise, the third indicator is not exceeded.

[0019] In a second aspect, the present invention provides a main bearing fault diagnosis system, comprising: a data acquisition module for acquiring a vibration waveform of the main bearing; a first discrimination module for equally dividing the vibration waveform of the main bearing into a plurality of sub-vibration waveforms, acquiring and obtaining a first indicator based on the impact factor of each sub-vibration waveform; when the first indicator is within the standard, the diagnosis result is no fault; a second discrimination module for acquiring an envelope spectrum of the vibration waveform of the main bearing when the first indicator is exceeded, and acquiring and obtaining a fault indicator based on the frequencies of the top three frequency points of the amplitude of the envelope spectrum; and performing Fourier transform and normalization on the vibration waveform of the main bearing to obtain a normalized a spectrum, obtains and obtains a second indicator based on the percentage of energy exceeding the standard in the normalized spectrum; when the second indicator is within the standard: when the fault indicator is exceeded, the diagnosis result is a third-level fault; otherwise, the diagnosis result is a third-level poor lubrication; a third discrimination module is used to obtain and obtain a third indicator based on the proportion of energy exceeding the standard in the first half of the normalized spectrum when the second indicator is exceeded; when the third indicator is within the standard: when the fault indicator is exceeded, the diagnosis result is a second-level fault; otherwise, the diagnosis result is a second-level poor lubrication; when the third indicator is exceeded: when the fault indicator is exceeded, the diagnosis result is a first-level fault; otherwise, the diagnosis result is a first-level poor lubrication.

[0020] According to a third aspect of the present invention, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned main bearing fault diagnosis method when executing the computer program.

[0021] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the main bearing fault diagnosis method are implemented.

[0022] Compared with the prior art, the present invention has the following beneficial effects:

[0023] The main bearing fault diagnosis method of the present invention can preliminarily judge the main bearing status by dividing the vibration waveform of the main bearing into equal parts and obtaining a first indicator based on the impact factor of the sub-vibration waveform. When the first indicator exceeds the standard, the envelope spectrum is further obtained to obtain the fault indicator. At the same time, the vibration waveform is Fourier transformed and normalized to obtain a normalized spectrum. Based on this, the second and third indicators are obtained by analyzing the proportion of energy exceeding the standard and the distribution of energy exceeding the standard. Among them, the application of spectrum signal normalization makes the method not limited by the main bearing model, effectively avoiding the false alarm and missed alarm problems caused by the large difference in the effective vibration values ​​of main bearings of different models, and greatly improving the universality and accuracy of the diagnosis. During the diagnosis process, by analyzing the proportion of energy exceeding the standard and the distribution of energy exceeding the standard, it is possible to carefully and accurately determine whether the main bearing has a fault and the severity of the fault, effectively improving the accuracy and efficiency of the diagnosis. In particular, for main bearings under low-speed and heavy-load conditions, it is possible to successfully identify those fault features that are not easy to detect in the vibration signal waveform and spectrum, and achieve accurate diagnosis. In summary, the main bearing fault diagnosis method of the present invention can not only accurately diagnose the main bearing fault, but also give the severity of the main bearing fault, thereby providing solid and effective support for subsequent maintenance decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a flow chart of a main bearing fault diagnosis method according to an embodiment of the present invention.

[0025] Figure 2 Detailed flow chart of the main bearing fault diagnosis method according to an embodiment of the present invention.

[0026] Figure 3 This is a normalized frequency spectrum diagram of a main bearing with a certain fault according to an embodiment of the present invention.

[0027] Figure 4 This is a normalized frequency spectrum diagram of a normal main bearing according to an embodiment of the present invention.

[0028] Figure 5 This is a structural block diagram of a main bearing fault diagnosis system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] The present invention is described in further detail below with reference to the accompanying drawings:

[0032] See also Figure 1 In one embodiment of the present invention, a main bearing fault diagnosis method is provided, specifically a main bearing fault diagnosis method based on the proportion of excessive energy and the distribution of excessive energy, which overcomes the problems existing in the existing main bearing fault diagnosis method, such as being difficult to apply to various types of main bearings, being unable to effectively avoid false alarms and missed alarms, and being unable to accurately distinguish the severity of the fault.

[0033] Specifically, the main bearing fault diagnosis method of the present invention includes the following steps:

[0034] S1: Obtain the vibration waveform of the main bearing.

[0035] S2: Divide the vibration waveform of the main bearing into several sub-vibration waveforms, obtain and obtain a first indicator based on the impact factor of each sub-vibration waveform; when the first indicator does not exceed the standard, the diagnosis result is no fault.

[0036] S3: When the first indicator exceeds the standard, the envelope spectrum of the vibration waveform of the main bearing is obtained, and the frequencies of the top three frequency points of the envelope spectrum are obtained and the fault indicator is obtained according to the amplitude; and the vibration waveform of the main bearing is Fourier transformed and normalized to obtain a normalized spectrum, and the second indicator is obtained according to the percentage of energy exceeding the standard of the normalized spectrum; when the second indicator does not exceed the standard: when the fault indicator exceeds the standard, the diagnosis result is a third-level fault; otherwise, the diagnosis result is a third-level poor lubrication.

[0037] S4: When the second indicator exceeds the standard, obtain and obtain the third indicator based on the proportion of the energy exceeding the standard in the first half of the normalized spectrum; when the third indicator does not exceed the standard: when the fault indicator exceeds the standard, the diagnosis result is a secondary fault; otherwise, the diagnosis result is a secondary poor lubrication; when the third indicator exceeds the standard: when the fault indicator exceeds the standard, the diagnosis result is a primary fault; otherwise, the diagnosis result is a primary poor lubrication.

[0038] The main bearing fault diagnosis method of the present invention can preliminarily judge the main bearing status by dividing the vibration waveform of the main bearing into equal parts and obtaining a first indicator based on the impact factor of the sub-vibration waveform. When the first indicator exceeds the standard, the envelope spectrum is further obtained to obtain the fault indicator. At the same time, the vibration waveform is Fourier transformed and normalized to obtain a normalized spectrum. Based on this, the second and third indicators are obtained by analyzing the proportion of energy exceeding the standard and the distribution of energy exceeding the standard. Among them, the application of spectrum signal normalization makes the method not limited by the main bearing model, effectively avoiding the false alarm and missed alarm problems caused by the large difference in the effective vibration values ​​of main bearings of different models, and greatly improving the universality and accuracy of the diagnosis. During the diagnosis process, by analyzing the proportion of energy exceeding the standard and the distribution of energy exceeding the standard, it is possible to carefully and accurately determine whether the main bearing has a fault and the severity of the fault, effectively improving the accuracy and efficiency of the diagnosis. In particular, for main bearings under low-speed and heavy-load conditions, it is possible to successfully identify those fault features that are not easy to detect in the vibration signal waveform and spectrum, and achieve accurate diagnosis. In summary, the main bearing fault diagnosis method of the present invention can not only accurately diagnose the main bearing fault, but also give the severity of the main bearing fault, thereby providing solid and effective support for subsequent maintenance decisions.

[0039] In one possible implementation, see Figure 2 Before obtaining the vibration waveform of the main bearing, the method further includes: obtaining the actual speed and rated speed of the main bearing; when the actual speed is greater than n times the rated speed, obtaining the vibration waveform of the main bearing; when the actual speed is not greater than n times the rated speed, ending the main bearing fault diagnosis; wherein n is a preset constant.

[0040] For example, the preset constant n can be set to 0.6. Explanatoryally, by adding a step to compare the actual speed with the multiple of the rated speed before acquiring the main bearing vibration waveform, it is possible to effectively avoid collecting invalid vibration data when the equipment is running at low speed or has not reached a stable operating condition. This not only reduces the unnecessary data processing burden, but also improves the accuracy and reliability of fault diagnosis, while also reducing the risk of misdiagnosis.

[0041] In one possible implementation, see again Figure 2 The main bearing fault diagnosis method further includes: before processing the vibration waveform of the main bearing, performing band-pass filtering on the vibration waveform of the main bearing.

[0042] Among them, when the vibration waveform of the main bearing is band-pass filtered, the filtering low point flow is:

[0043] flow=(rpm / 60)*FTF*5

[0044] Among them, rpm is the actual speed of the main bearing; FTF is the cage failure frequency of the main bearing.

[0045] The filtering high point fhigh is:

[0046] fhigh=(rpm / 60)*BPFI*25

[0047] Among them, BPFI is the failure frequency of the inner ring of the main bearing.

[0048] Explanatory note: The main bearing inner ring fault frequency (BPFI) and the main bearing cage fault frequency (FTF) corresponding to the main bearing model are obtained. For example, if the BPFI cannot be obtained, default parameters are used, with the default BPFI being between 3 and 7 times the main bearing rotational frequency.

[0049] Explanatory, by adopting the bandpass filter parameters dynamically calculated based on the actual speed rpm of the main bearing, where the filter low point flow is associated with the cage fault frequency FTF, and the filter high point fhigh is associated with the inner ring fault frequency BPFI, the background noise and high-frequency interference irrelevant to the fault can be accurately filtered out, while the effective vibration signal of the fault characteristic frequency band is completely retained, thereby significantly improving the sensitivity and signal-to-noise ratio of fault diagnosis and avoiding missed detection or misjudgment.

[0050] In one possible implementation, see again Figure 2 The fault index obtained according to the frequencies of the top three frequency points of the envelope spectrum amplitude includes: when the frequencies of the top three frequency points of the envelope spectrum amplitude are all between 0.9*FTF and 1.1*BPFI, the fault index exceeds the standard; otherwise, the fault index does not exceed the standard; among them, FTF is the retainer fault frequency of the main bearing; BPFI is the inner ring fault frequency of the main bearing.

[0051] Explanatory, when the frequencies of the first three frequency points of the envelope spectrum amplitude are all between 0.9*FTF and 1.1*BPFI, it indicates that the bearing fault frequency exists in the main energy, indicating that the main bearing has fault damage.

[0052] In one possible implementation, see again Figure 2 The obtaining and obtaining the first indicator based on the impact factor of each sub-vibration waveform includes: dividing the peak value of each sub-vibration waveform by the effective value of the vibration waveform of the main bearing to obtain the impact factor of each sub-vibration waveform; when at least half of the impact factors of each sub-vibration waveform exceed the preset impact factor threshold, the first indicator exceeds the standard; otherwise, the first indicator does not exceed the standard.

[0053] For example, the preset impact factor threshold can be set to 6. The vibration waveform of the main bearing can be divided into 6 equal parts to obtain 6 sub-vibration waveforms, and then 6 impact factors are obtained. If 3 or more impact factors are greater than 6, it indicates that the impact in the waveform is obvious. If 3 or more impact factors are not greater than 6, it indicates that the impact in the waveform is not obvious, thereby achieving accurate determination of the first indicator.

[0054] In one possible implementation, see again Figure 2 The obtaining and obtaining of the second indicator based on the percentage of energy exceeding the standard in the normalized spectrum includes: obtaining the proportion of amplitudes greater than 1.5*std in the amplitude sequence of the normalized spectrum to obtain the percentage of energy exceeding the standard in the normalized spectrum; wherein std is the standard deviation of the normalized spectrum; when the percentage of energy exceeding the standard in the normalized spectrum is greater than a preset threshold value of the percentage of energy exceeding the standard, the second indicator is exceeded; otherwise, the second indicator is not exceeded.

[0055] Explanatory, the vibration waveform of the main bearing is Fourier transformed to obtain a spectrum, and the spectrum is normalized to obtain a normalized spectrum. The standard deviation std of the normalized spectrum is calculated, and then the proportion of amplitudes greater than 1.5*std in the amplitude series of the normalized spectrum is calculated to obtain the percentage of excess energy. If the excess energy percentage is greater than a specified excess energy percentage threshold (such as 30%, which can be configured according to the model of the main bearing), it means that there are a large number of spectral sidebands in the low frequency band, and the degree of fault or defect is high.

[0056] In one possible implementation, see again Figure 2The obtaining and obtaining of the third indicator based on the proportion of energy exceeding the standard in the first half of the normalized spectrum includes: obtaining the ratio of the sum of the effective values ​​of each amplitude in the first half of the normalized spectrum to the sum of the effective values ​​of all amplitudes of the normalized spectrum to obtain the proportion of energy exceeding the standard in the first half of the normalized spectrum; when the proportion of energy exceeding the standard in the first half of the normalized spectrum is greater than a preset threshold value of the proportion of energy exceeding the standard in the first half, the third indicator is exceeded; otherwise, the third indicator is not exceeded.

[0057] Explanatory, calculate the ratio of the sum rms1 of the effective values ​​of each amplitude in the first half of the normalized spectrum to the sum rms of the effective values ​​of all amplitudes in the normalized spectrum. If rms1 / rms> the preset threshold of the proportion of excessive energy in the first half (such as 50%, which can be configured according to the model of the main bearing), it means that the fault characteristics are concentrated in the first half, and the damage or defective condition of the main bearing is relatively serious.

[0058] In a possible implementation, the main bearing fault diagnosis method further includes: pushing the diagnosis result. Exemplarily, the diagnosis result can be pushed to an operation and maintenance terminal or a monitoring platform in real time.

[0059] For example, by pushing the main bearing fault diagnosis results in real time, relevant personnel can obtain equipment health status information in the first time, achieve rapid response and disposal of faults, and provide data support for preventive maintenance, effectively reducing the risk of unplanned downtime and improving the reliability and safety of overall equipment operation.

[0060] See also Figure 3 , shows the normalized spectrum obtained after filtering, Fourier transform, spectrum normalization, and standard deviation calculation of the vibration waveform signal of a faulty main bearing. The orange line is the 1.5 times standard deviation line. It can be seen that a large number of sidebands exceed the orange line, indicating that there is a fault in the main bearing. Figure 4 Figure 2 shows the normalized spectrum of a healthy main bearing vibration waveform signal after filtering, Fourier transform, spectrum normalization, and standard deviation calculation. The orange line represents the 1.5 times standard deviation line. This shows that, with the exception of the meshing frequency transmitted from the gearbox, the other sidebands do not exceed the orange line, indicating a healthy main bearing.

[0061] The following are device embodiments of the present invention, which can be used to perform the method embodiments of the present invention. For details not disclosed in the device embodiments, please refer to the method embodiments of the present invention.

[0062] See also Figure 5In another embodiment of the present invention, a main bearing fault diagnosis system is provided, which can be used to implement the above-mentioned main bearing fault diagnosis method. Specifically, the main bearing fault diagnosis system includes a data acquisition module, a first discrimination module, a second discrimination module and a third discrimination module. The data acquisition module is used to obtain the vibration waveform of the main bearing; the first discrimination module is used to divide the vibration waveform of the main bearing into several sub-vibration waveforms, obtain and obtain a first indicator based on the impact factor of each sub-vibration waveform; when the first indicator does not exceed the standard, the diagnosis result is no fault; the second discrimination module is used to obtain the envelope spectrum of the vibration waveform of the main bearing when the first indicator exceeds the standard, and obtain and obtain a fault indicator based on the frequency of the first three frequency points of the amplitude of the envelope spectrum; and perform Fourier transform and normalization on the vibration waveform of the main bearing to obtain a normalized spectrum, obtain and obtain a fault indicator based on the normalized spectrum. The second indicator is obtained by the percentage of energy exceeding the standard of the spectrum; when the second indicator is within the standard: when the fault indicator is exceeded, the diagnosis result is a third-level fault; otherwise, the diagnosis result is a third-level poor lubrication; the third discrimination module is used to obtain and obtain the third indicator based on the proportion of energy exceeding the standard in the first half of the normalized spectrum when the second indicator is exceeded; when the third indicator is within the standard: when the fault indicator is exceeded, the diagnosis result is a second-level fault; otherwise, the diagnosis result is a second-level poor lubrication; when the third indicator is exceeded: when the fault indicator is exceeded, the diagnosis result is a first-level fault; otherwise, the diagnosis result is a first-level poor lubrication.

[0063] All relevant contents of each step involved in the embodiment of the aforementioned main bearing fault diagnosis method can be referred to the functional description of the functional modules corresponding to the main bearing fault diagnosis system in the embodiment of the present invention, and will not be repeated here.

[0064] The module division in the embodiments of the present invention is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in various embodiments of the present invention may be integrated into a single processor, exist physically as separate modules, or two or more modules may be integrated into a single module. The integrated modules may be implemented in either hardware or software functional modules.

[0065] In another embodiment of the present invention, a computer device is provided, which includes a processor and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of the main bearing fault diagnosis method.

[0066] In another embodiment of the present invention, the present invention further provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It can be understood that the computer-readable storage medium here can include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space. These instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the main bearing fault diagnosis method in the above embodiment.

[0067] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0068] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0069] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0070] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0071] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A main bearing fault diagnosis method, characterized in that: include: Obtain the vibration waveform of the main bearing; The vibration waveform of the main bearing is equally divided into a plurality of sub-vibration waveforms, and a first index is obtained based on the impact factor of each sub-vibration waveform; when the first index does not exceed the standard, the diagnosis result is no fault; When the first indicator exceeds the standard, the envelope spectrum of the vibration waveform of the main bearing is obtained, and the frequencies of the first three frequency points of the envelope spectrum are obtained and the fault indicator is obtained based on the amplitude; the vibration waveform of the main bearing is Fourier transformed and normalized to obtain a normalized spectrum, and the second indicator is obtained based on the energy percentage exceeding the standard of the normalized spectrum; when the second indicator does not exceed the standard: when the fault indicator exceeds the standard, the diagnosis result is a third-level fault; otherwise, the diagnosis result is a third-level lubrication failure; When the second indicator exceeds the standard, the third indicator is obtained and based on the proportion of the energy exceeding the standard in the first half of the normalized spectrum; when the third indicator does not exceed the standard: when the fault indicator exceeds the standard, the diagnosis result is a secondary fault; otherwise, the diagnosis result is secondary poor lubrication; when the third indicator exceeds the standard: when the fault indicator exceeds the standard, the diagnosis result is a primary fault; otherwise, the diagnosis result is a primary poor lubrication.

2. The main bearing fault diagnosis method according to claim 1, characterized in that: Before obtaining the vibration waveform of the main bearing, the method further includes: Obtain the actual speed and rated speed of the main bearing; When the actual speed is greater than n times the rated speed, the vibration waveform of the main bearing is obtained; when the actual speed is not greater than n times the rated speed, the main bearing fault diagnosis is ended; where n is a preset constant.

3. The main bearing fault diagnosis method according to claim 1, characterized in that: Also includes: Before processing the vibration waveform of the main bearing, the vibration waveform of the main bearing is subjected to band-pass filtering; Among them, when the vibration waveform of the main bearing is band-pass filtered, the filtering low point flow is: flow=(rpm / 60)*FTF*5 Among them, rpm is the actual speed of the main bearing; FTF is the cage failure frequency of the main bearing; The filtering high point fhigh is: fhigh=(rpm / 60)*BPFI*25 Among them, BPFI is the failure frequency of the inner ring of the main bearing.

4. The main bearing fault diagnosis method according to claim 1, characterized in that: Obtaining the fault indicator based on the frequencies of the top three frequency points of the envelope spectrum amplitude includes: When the frequencies of the first three frequency points of the envelope spectrum amplitude are all between 0.9*FTF and 1.1*BPFI, the fault indicator is exceeded; otherwise, the fault indicator is within the standard; Among them, FTF is the cage failure frequency of the main bearing; BPFI is the inner ring failure frequency of the main bearing.

5. The main bearing fault diagnosis method according to claim 1, characterized in that: The obtaining and obtaining the first indicator according to the impact factor of each sub-vibration waveform includes: The peak value of each sub-vibration waveform is divided by the effective value of the vibration waveform of the main bearing to obtain the impact factor of each sub-vibration waveform; when at least half of the impact factors of each sub-vibration waveform exceed the preset impact factor threshold, the first indicator is exceeded; otherwise, the first indicator is within the standard.

6. The main bearing fault diagnosis method according to claim 1, characterized in that: The obtaining and obtaining the second indicator according to the excess energy percentage of the normalized spectrum includes: Obtain the percentage of amplitudes greater than 1.5*std in the amplitude sequence of the normalized spectrum to obtain the percentage of energy exceeding the standard in the normalized spectrum; where std is the standard deviation of the normalized spectrum; When the excess energy percentage of the normalized spectrum is greater than a preset excess energy percentage threshold, the second indicator is exceeded; otherwise, the second indicator is not exceeded.

7. The main bearing fault diagnosis method according to claim 1, characterized in that: The obtaining and obtaining the third indicator according to the proportion of energy exceeding the standard in the first half of the normalized spectrum includes: Obtaining the ratio of the sum of the effective values ​​of each amplitude in the first half of the normalized spectrum to the sum of the effective values ​​of all amplitudes in the normalized spectrum, to obtain the excess energy ratio in the first half of the normalized spectrum; When the proportion of energy exceeding the standard in the first half of the normalized spectrum is greater than a preset threshold of energy exceeding the standard in the first half, the third indicator exceeds the standard; otherwise, the third indicator does not exceed the standard.

8. A main bearing fault diagnosis system, characterized in that: include: A data acquisition module, used to obtain the vibration waveform of the main bearing; A first discrimination module is configured to equally divide the vibration waveform of the main bearing into a plurality of sub-vibration waveforms, obtain and derive a first index based on the impact factor of each sub-vibration waveform; and when the first index does not exceed the standard, the diagnosis result is that there is no fault; The second discrimination module is configured to, when the first indicator exceeds the standard, obtain an envelope spectrum of the vibration waveform of the main bearing, obtain and obtain a fault indicator based on the frequencies of the top three frequency points of the envelope spectrum; perform Fourier transform and normalization on the vibration waveform of the main bearing to obtain a normalized spectrum, obtain and obtain a second indicator based on the percentage of energy exceeding the standard in the normalized spectrum; and when the second indicator does not exceed the standard: if the fault indicator exceeds the standard, the diagnosis result is a third-level fault; otherwise, the diagnosis result is a third-level lubrication failure; The third discrimination module is used to obtain and obtain the third indicator based on the proportion of the energy exceeding the standard in the first half of the normalized spectrum when the second indicator exceeds the standard; when the third indicator does not exceed the standard: when the fault indicator exceeds the standard, the diagnosis result is a secondary fault; otherwise, the diagnosis result is secondary poor lubrication; when the third indicator exceeds the standard: when the fault indicator exceeds the standard, the diagnosis result is a primary fault; otherwise, the diagnosis result is a primary poor lubrication.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the main bearing fault diagnosis method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the main bearing fault diagnosis method according to any one of claims 1 to 7 are implemented.

Images