Rolling bearing state evaluation method and related equipment

Abstract

The invention provides a rolling bearing state evaluation method and related equipment, and the method comprises the steps: carrying out the Fourier transform processing of a first-order time domain signal, obtaining a frequency domain signal, and obtaining a noise index of a rolling bearing based on the frequency domain signal; performing envelope demodulation processing on the first-order time domain signal to obtain an envelope spectrum, and obtaining a sideband index of the rolling bearing based on the envelope spectrum; performing band-pass filtering processing on the first-order time-domain signal to obtain a filtered time-domain signal, and obtaining an impact index of the rolling bearing based on the filtered time-domain signal; and according to the noise index, the sideband index and the impact index, carrying out multi-modal feature weighted fusion to obtain a bearing health index reflecting the health state of the rolling bearing. According to the noise index, the sideband index and the impact index, multi-modal feature weighted fusion is carried out, the defects of single evaluation dimension, deterioration reason information loss, insensitivity to early failure and the like are overcome, and early, accurate and continuous quantitative evaluation and trend prediction of the health state of the rolling bearing are realized.

Description

Technical Field

[0001] This invention relates to the field of condition monitoring, and more specifically, to a method and related equipment for assessing the condition of rolling bearings. Background Technology

[0002] In the field of industrial transmission, rolling bearings, as the joints of rotating machinery, are the cornerstone of stable equipment operation. If even minor damage to bearings is not detected in time, it can easily propagate under continuous load, ultimately leading to transmission failure, cascading equipment damage, and other serious consequences, resulting in unplanned downtime and huge maintenance costs. Therefore, accurate diagnosis and trend prediction of bearing conditions have become a core aspect of intelligent industrial operation and maintenance. Vibration analysis, due to its rich information, mature technology, and ability to achieve online monitoring, presents a significant challenge for those skilled in the art in applying it to rolling bearing fault diagnosis. Summary of the Invention

[0003] The purpose of this invention is to provide a method and related equipment for assessing the condition of rolling bearings, so as to improve the above-mentioned problems.

[0004] To achieve the above objectives, the technical solutions adopted in the embodiments of the present invention are as follows: In a first aspect, embodiments of the present invention provide a method for evaluating the condition of a rolling bearing, the method comprising: The vibration signal of the rolling bearing is subjected to mean-removal processing to obtain the first-order time-domain signal; The initial time-domain signal is subjected to Fourier transform processing to obtain its corresponding frequency-domain signal, and the noise index of the rolling bearing is obtained based on the frequency-domain signal. The initial time-domain signal is subjected to envelope demodulation to obtain its corresponding envelope spectrum, and the sideband index of the rolling bearing is obtained based on the envelope spectrum. The initial time-domain signal is subjected to bandpass filtering to obtain its corresponding filtered time-domain signal, and the impact index of the rolling bearing is obtained based on the filtered time-domain signal. Multimodal feature weighted fusion is performed based on the noise index, the sideband index, and the impact index to obtain a bearing health index that reflects the health status of the rolling bearing.

[0005] Secondly, embodiments of the present invention provide a rolling bearing condition assessment device, the device comprising: The first processing unit is used to perform mean-removal processing on the vibration signal of the rolling bearing to obtain the first-order time-domain signal. The first processing unit is further configured to perform Fourier transform processing on the initial time domain signal to obtain its corresponding frequency domain signal, and obtain the noise index of the rolling bearing based on the frequency domain signal. The first processing unit is further configured to perform envelope demodulation processing on the initial time-domain signal to obtain its corresponding envelope spectrum, and obtain the sideband index of the rolling bearing based on the envelope spectrum; The first processing unit is further configured to perform bandpass filtering on the initial time-domain signal to obtain its corresponding filtered time-domain signal, and obtain the impact index of the rolling bearing based on the filtered time-domain signal; The second processing unit is used to perform multimodal feature weighted fusion based on the noise index, the sideband index, and the impact index to obtain a bearing health index that reflects the health status of the rolling bearing.

[0006] Thirdly, embodiments of the present invention provide a storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method.

[0007] Fourthly, embodiments of the present invention provide an electronic device, the electronic device comprising: a processor and a memory, the memory being used to store one or more programs; when the one or more programs are executed by the processor, the above-described method is implemented.

[0008] Compared to existing technologies, the rolling bearing condition assessment method and related equipment provided in this invention perform mean-removal processing on the vibration signal of the rolling bearing to obtain an initial time-domain signal; perform Fourier transform processing on the initial time-domain signal to obtain its corresponding frequency-domain signal, and obtain the noise index of the rolling bearing based on the frequency-domain signal; perform envelope demodulation processing on the initial time-domain signal to obtain its corresponding envelope spectrum, and obtain the sideband index of the rolling bearing based on the envelope spectrum; perform bandpass filtering processing on the initial time-domain signal to obtain its corresponding filtered time-domain signal, and obtain the impact index of the rolling bearing based on the filtered time-domain signal; and perform multi-modal feature weighted fusion based on the noise index, sideband index, and impact index to obtain a bearing health index reflecting the health status of the rolling bearing. This multi-modal feature weighted fusion based on the noise index, sideband index, and impact index overcomes the shortcomings of single assessment dimensions, lack of information on deterioration causes, and insensitivity to early faults, achieving early, accurate, and continuous quantitative assessment and trend prediction of the rolling bearing health status.

[0009] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0010] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0012] Figure 2 This is one of the flowcharts illustrating the rolling bearing condition assessment method provided in this embodiment of the invention.

[0013] Figure 3 This is the second flowchart illustrating the rolling bearing condition assessment method provided in this embodiment of the invention.

[0014] Figure 4 This is a schematic diagram of a rolling bearing condition assessment device provided in an embodiment of the present invention.

[0015] In the diagram: 10-Processor; 11-Memory; 12-Bus; 13-Communication interface; 701-First processing unit; 702-Second processing unit. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0017] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0018] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0019] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0020] In the description of this invention, it should be noted that the terms "upper," "lower," "inner," "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship in which the product of this invention is usually placed when in use. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limiting this invention.

[0021] In the description of this invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set" and "connection" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0022] The following detailed description of some embodiments of the present invention is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0023] This invention provides an electronic device, which may be a mobile phone, a computer, or a server. Please refer to... Figure 1 This is a schematic diagram of the structure of an electronic device. The electronic device includes a processor 10, a memory 11, and a bus 12. The processor 10 and the memory 11 are connected via the bus 12. The processor 10 is used to execute executable modules, such as computer programs, stored in the memory 11.

[0024] Processor 10 can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the rolling bearing condition assessment method can be completed through integrated logic circuits in the hardware or software instructions within processor 10. Processor 10 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0025] The memory 11 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage.

[0026] Bus 12 can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. Figure 1 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus 12 or one type of bus 12.

[0027] The memory 11 is used to store programs, such as programs corresponding to a rolling bearing condition assessment device. The rolling bearing condition assessment device includes at least one software functional module that can be stored in the memory 11 in the form of software or firmware, or embedded in the operating system (OS) of the electronic device. Upon receiving an execution instruction, the processor 10 executes the program to implement the rolling bearing condition assessment method.

[0028] The electronic device provided in this embodiment of the invention may further include a communication interface 13. The communication interface 13 is connected to the processor 10 via a bus.

[0029] It should be understood that, Figure 1 The structure shown is only a partial schematic diagram of the electronic device; the electronic device may also include components that are larger than... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown. Figure 1 The components shown can be implemented using hardware, software, or a combination thereof.

[0030] The rolling bearing condition assessment method provided in this embodiment of the invention can be applied to, but is not limited to, applications in... Figure 1 For the specific process of the electronic devices shown, please refer to [link / reference]. Figure 2 The rolling bearing condition assessment methods include: S10, S20, S30, S40 and S50, which are described in detail below.

[0031] S10 performs mean-removal processing on the vibration signal of the rolling bearing to obtain the initial time-domain signal.

[0032] The initial time-domain signal is the vibration signal after removing the mean.

[0033] S20 performs Fourier transform on the initial time-domain signal to obtain its corresponding frequency-domain signal, and obtains the noise index of the rolling bearing based on the frequency-domain signal.

[0034] The frequency domain signal includes the frequency and the amplitude corresponding to the frequency.

[0035] S30 performs envelope demodulation on the initial time-domain signal to obtain its corresponding envelope spectrum, and obtains the sideband index of the rolling bearing based on the envelope spectrum.

[0036] S40 performs bandpass filtering on the initial time-domain signal to obtain its corresponding filtered time-domain signal, and obtains the impact index of the rolling bearing based on the filtered time-domain signal.

[0037] The upper and lower limits of the bandpass filter can be set to 600Hz-10kHz, but are not limited to this range. This range can be adjusted as needed.

[0038] S50 performs multimodal feature weighted fusion based on noise index, sideband index and impact index to obtain a bearing health index that reflects the health status of rolling bearings.

[0039] In the rolling bearing condition assessment method provided in this embodiment of the invention, multimodal feature weighted fusion is performed based on noise index, sideband index and impact index to overcome the defects such as single assessment dimension, lack of information on deterioration causes and insensitivity to early faults, and to achieve early, accurate and continuous quantitative assessment and trend prediction of rolling bearing health status.

[0040] Based on the foregoing, this embodiment of the invention also provides an optional implementation method for the vibration signal acquisition process, which is described below.

[0041] The vibration signal acquisition unit is deployed in the detection area of ​​the rolling bearing. Under stable operating conditions, the vibration signal of the rolling bearing is acquired according to a preset spectral resolution. The vibration signal acquisition unit can be an accelerometer or a velocity sensor. The spectral resolution requirement is a sampling frequency greater than 1 Hz, and the sampling duration is a set duration corresponding to the sampling frequency. A higher sampling frequency results in a shorter sampling duration; for example, a 1.28-second sampling duration for an acceleration vibration signal at a sampling frequency of 51200 Hz. Stable operating conditions refer to a preset time period after startup.

[0042] Building upon the preceding text, this embodiment of the invention also provides an optional implementation method for obtaining the noise index of the rolling bearing in step S20, as detailed below. Obtaining the noise index of the rolling bearing based on a frequency domain signal includes steps S210 to S250, which are specifically described below.

[0043] S210, obtains the local mean and local standard deviation of the frequency domain signal.

[0044] S220, determine the adaptive threshold based on the local mean and local standard deviation.

[0045] Optionally, the adaptive threshold is ,in, Represents the local mean. Indicates local standard deviation. It is a constant, usually taken as 3 to 5.

[0046] S230 identifies and removes transient impact points in frequency domain signals based on adaptive thresholding.

[0047] S240 performs a moving average process on the frequency domain signal after removing transient impact points to obtain the noise floor signal.

[0048] Moving average processing can be understood as performing moving average completion on the transient impact points of the discarded signal.

[0049] S250 obtains the noise index of the rolling bearing based on the noise floor signal.

[0050] Building upon the preceding text, this embodiment of the invention also provides an optional implementation method for the content in S250, as detailed below. Obtaining the noise index of the rolling bearing based on the noise floor signal includes S251 and S252, which are specifically described below.

[0051] S251 extracts the noise energy percentage, noise significance, noise distribution width, and signal ratio from the noise background signal.

[0052] The signal-to-noise ratio is defined as the ratio of the maximum amplitude of the noise background signal to the maximum amplitude of the original spectrum.

[0053] S252, based on the noise energy ratio, noise significance, noise distribution width and signal ratio, performs a fusion calculation to obtain the noise index of the rolling bearing.

[0054] The specific implementation of fusion computing can be as follows: Normalize each indicator; calculate the weight of each indicator based on the entropy weight method using a large amount of rolling bearing sample data; then, manually adjust the weights of each indicator by multiplying the weight of the noise energy ratio by a coefficient greater than 1 and the weight of the signal-to-weight ratio by a coefficient less than 1. The noise index is then the weighted sum of all indicators.

[0055] Building upon the preceding text, this embodiment of the invention also provides an optional implementation method for obtaining the sideband index of the rolling bearing based on the envelope spectrum in step S30, as detailed below. Obtaining the sideband index of the rolling bearing based on the envelope spectrum includes steps S310 to S340, which are specifically described below.

[0056] S310, determine the bearing failure characteristic frequency (fb) based on the rolling bearing size and rotational frequency.

[0057] Among them, the rotational frequency fr refers to the actual rotational frequency of the shaft on which the rolling bearing is installed. When the motor is directly connected to the bearing shaft, it can be approximately equal to the rotational frequency of the drive motor.

[0058] S320 extracts the left n-order sideband group and the right n-order sideband group (i.e., fb±n×fr) from the envelope spectrum, centered on the bearing fault characteristic frequency (fb).

[0059] The left n-order sideband set and the right n-order sideband set can be represented as fb±n×fr.

[0060] S330, calculate the total energy and saliency of each sideband group.

[0061] Sideband significance is defined as the ratio of the total energy of the sideband group to the energy at the center frequency. The greater the sideband significance, the more likely it is to indicate a fault in the inner ring of the bearing.

[0062] Obtain the left n-order sideband set and the right n-order sideband set respectively, and calculate the total energy and saliency of the sideband set.

[0063] S340 performs a fusion calculation based on the saliency of each sideband group and the total energy to obtain the sideband index of the rolling bearing.

[0064] The sideband group energy is normalized, and the normalized sideband energy is the ratio of the sideband group energy to the total energy of the envelope spectrum. Optionally, the sideband significance of the sideband group is used as the fusion weight for its normalized sideband energy, and a weighted fusion calculation is performed to obtain the sideband index of the rolling bearing.

[0065] Building upon the preceding text, this embodiment of the invention also provides an optional implementation method for obtaining the impact index of the rolling bearing based on the filtered time-domain signal in step S40, as detailed below. Obtaining the impact index of the rolling bearing based on the filtered time-domain signal includes steps S410 to S450, which are specifically described below.

[0066] S410 performs downsampling on the filtered time-domain signal to determine the location of the impact peak and the corresponding impact energy.

[0067] S420, the impact baseline is determined based on the impact peak location and the corresponding impact energy.

[0068] The impact baseline calculation is explained as follows: based on the determined impact peak position, significant impact points are removed from the downsampled signal, and the remaining signal points are filled by interpolation. The impact baseline is then calculated using statistical methods on the filled signal, such as following the 3σ criterion.

[0069] S430 divides the filtered time-domain signal into multiple sub-segments.

[0070] It should be understood that the waveform can be divided into 8 sub-segments, but is not limited to this.

[0071] S440, calculate the kurtosis, peak value, impact count, and weight of each segment waveform. The impact count is the number of times the impact energy is greater than the impact baseline. The peak value is the maximum impact amplitude in the segment waveform and the maximum positive amplitude in the segment waveform. The weight of the segment is the ratio of the impact count of each segment to the total impact count.

[0072] S450, based on the kurtosis K of each sub-segment waveform i Sub-segment peak P i Impact counting ct i and sub-segment weight w i We perform weighted calculations to determine the impact index of the rolling bearing.

[0073] Impact Index Fusion Calculation Logic: , where α, β, and γ are adjustable coefficients.

[0074] Building upon the preceding text, this embodiment of the invention also provides an optional implementation method for the content in S50, as detailed below. Multimodal feature weighted fusion is performed based on the noise index, sideband index, and impact index to obtain a bearing health index reflecting the health status of the rolling bearing, including: S501 and S502, which are specifically described below.

[0075] S501 performs dimensionless processing on the noise index, sideband index, and impact index to obtain dimensionless noise index, dimensionless sideband index, and dimensionless impact index.

[0076] By using a large amount of sample data on the healthy state of rolling bearings, the noise index, sideband index, and impact index are calculated. The quantile of each index is used as the health benchmark value for that index, with the 90th quantile being an option. The dimensionless index is then the ratio of the actual index to the health benchmark value, representing the multiple by which the index exceeds the healthy state.

[0077] S502, based on the dimensionless noise index, dimensionless sideband index and dimensionless impact index, multimodal feature weighted fusion is performed to obtain the bearing health index reflecting the health status of the rolling bearing.

[0078] Weighted fusion logic: First, initial weights w are assigned to each index, including noise, sideband, and impulse. n w s w i w n +w s +w i =1, for example, assigning values ​​of 0.4, 0.3, and 0.3; next, calculate the fault contribution of each index, defined as max(0, dimensionless exponent - 1); then, based on the fault contribution, adjust the contribution based on the original feature dimensions associated with each index. For example, if the noise energy ratio and noise distribution width are high, indicating rich spectral noise features, then assign relative importance to the noise index; if the sideband energy and sideband significance are high, then assign relative importance to the sideband index; if the impulse count is rich and the kurtosis is high, then assign relative importance to the impulse index. The relative importance is defined as the fault contribution raised to the power of α. The dynamic weight of each index is the ratio of the relative importance of that index to the sum of the relative importance of all indices. Finally, calculate the weighted weight of each index as: β Initial weights + (1-β) Dynamic weighting. The bearing condition index is a weighted average of the dimensionless indices.

[0079] Please refer to Figure 3 In an optional implementation, the rolling bearing condition assessment method further includes S601, S602 and S603, which are described in detail below.

[0080] S601, when the bearing health index is less than the first threshold, the rolling bearing is determined to be in a healthy state.

[0081] The first threshold can be, but is not limited to, 1. A bearing health index < 1 indicates that the bearing is in good operating condition, lubricated well, and the unit can continue to operate normally without human intervention for equipment maintenance. The rolling bearing is in a healthy state.

[0082] S602, when the bearing health index is greater than or equal to the first threshold and less than the second threshold, the rolling bearing is determined to be in a sub-healthy state.

[0083] The second threshold can be, but is not limited to, 2. If the bearing health index is between 1 and 2, it indicates that the bearing is in slightly poor operating condition, with early to mid-stage physical damage or poor lubrication. It is recommended to improve lubrication and continue to operate under monitoring to confirm that the rolling bearing is in a sub-healthy state.

[0084] S603, when the bearing health index is greater than or equal to the second threshold, the rolling bearing is determined to be in a damaged state.

[0085] A bearing health index >2 indicates that the bearing is in poor operating condition, with significant physical damage, or very poor lubrication, or dynamic and static friction. The unit is not recommended to operate continuously for a long time and requires manual maintenance.

[0086] This invention can acquire vibration signals of rolling bearings in real time. It creatively proposes three physically complementary features: impact index, noise index, and sideband index. The impact index specifically captures transient impacts caused by local damage (such as pitting and spalling). The noise index quantifies the progressive degradation caused by generalized wear and deterioration of lubrication conditions by accurately separating the noise background. The sideband index targets periodically modulated faults and provides fault location information through sideband analysis. Inner ring faults have significant sideband characteristics with the shaft rotation frequency fr as the interval, while outer ring faults have harmonic characteristics. A sideband index greater than 1.5 indicates an inner ring fault, while a sideband index less than 0.5 indicates an outer ring fault. Faults in between are generally mixed faults. By extracting these three types of features, a multi-dimensional feature profile is constructed, capable of simultaneously perceiving instantaneous damage, progressive degradation, and fault type of the bearing. The fault type classification is jointly determined by the magnitudes of the impact index, sideband index, and noise index. If all three indices are low, the equipment is in a healthy state; if the impact index and sideband index are relatively low, but the noise index is high, it generally indicates a poor lubrication fault; if the impact index and sideband index are high, but the noise index is medium or low, it generally indicates an inner ring fault; if the impact index is high, the sideband index is low, and the noise index is medium or low, it generally indicates an outer ring fault; if all three indices are high, it generally indicates a combined or severe fault. For example, when early inner ring pitting occurs in a bearing, this invention can not only provide a bearing health status assessment through the bearing health index, but also identify whether the fault points to an inner ring or outer ring fault based on the magnitude of the sideband index—something that no single parameter can accomplish independently. This fundamentally solves the problem of a single assessment dimension and a lack of diagnostic information.

[0087] This invention integrates adaptive threshold detection and moving average filtering to extract noise background features, and combines this with multi-parameter time-domain impact extraction to improve the sensitivity of early fault detection. Noise background is extremely sensitive to lubrication degradation and uniform wear; these changes precede macroscopic damage, and changes in their energy proportion and distribution width can serve as early warning signals. The comprehensive impact index integrates multiple impact-sensitive parameters such as kurtosis and peak value, making it more stable and sensitive than a single peak value or kurtosis, and enabling earlier detection of weak damage impacts. When bearing lubrication begins to deteriorate or slight spalling occurs in the early stages, both the noise index and impact index show an upward trend.

[0088] Please see Figure 4 , Figure 4 The present invention provides a rolling bearing condition assessment device, which is optionally applied to the electronic device described above.

[0089] The rolling bearing condition assessment device includes: a first processing unit 701 and a second processing unit 702.

[0090] The first processing unit 701 is used to perform mean-removal processing on the vibration signal of the rolling bearing to obtain the first-order time-domain signal. The first processing unit 701 is also used to perform Fourier transform processing on the initial time domain signal to obtain its corresponding frequency domain signal, and to obtain the noise index of the rolling bearing based on the frequency domain signal. The first processing unit 701 is also used to perform envelope demodulation processing on the initial time domain signal to obtain its corresponding envelope spectrum, and to obtain the sideband index of the rolling bearing based on the envelope spectrum. The first processing unit 701 is also used to perform bandpass filtering on the initial time domain signal to obtain its corresponding filtered time domain signal, and to obtain the impact index of the rolling bearing based on the filtered time domain signal. The second processing unit 702 is used to perform multimodal feature weighted fusion based on the noise index, sideband index and impact index to obtain a bearing health index that reflects the health status of the rolling bearing.

[0091] It should be noted that the rolling bearing condition assessment device provided in this embodiment can execute the method flow shown in the above-described method flow embodiment to achieve the corresponding technical effects. For the sake of brevity, any parts not mentioned in this embodiment can be referred to the corresponding content in the above-described embodiments.

[0092] This invention also provides a storage medium storing computer instructions and programs, which, when read and executed, perform the rolling bearing condition assessment method described above. The storage medium may include memory, flash memory, registers, or a combination thereof.

[0093] The following provides an electronic device, which may be a mobile phone, a computer, or a server. This electronic device, such as... Figure 1 As shown, the above-described rolling bearing condition assessment method can be implemented. Specifically, the electronic device includes: a processor 10, a memory 11, and a bus 12. The processor 10 may be a CPU. The memory 11 is used to store one or more programs, which, when executed by the processor 10, perform the rolling bearing condition assessment method of the above embodiment.

[0094] In summary, the rolling bearing condition assessment method and related equipment provided in this embodiment of the invention perform mean-removal processing on the vibration signal of the rolling bearing to obtain an initial time-domain signal; perform Fourier transform processing on the initial time-domain signal to obtain its corresponding frequency-domain signal, and obtain the noise index of the rolling bearing based on the frequency-domain signal; perform envelope demodulation processing on the initial time-domain signal to obtain its corresponding envelope spectrum, and obtain the sideband index of the rolling bearing based on the envelope spectrum; perform bandpass filtering processing on the initial time-domain signal to obtain its corresponding filtered time-domain signal, and obtain the impact index of the rolling bearing based on the filtered time-domain signal; and perform multi-modal feature weighted fusion based on the noise index, sideband index, and impact index to obtain a bearing health index reflecting the health status of the rolling bearing. This multi-modal feature weighted fusion based on the noise index, sideband index, and impact index overcomes the shortcomings of single assessment dimensions, lack of information on deterioration causes, and insensitivity to early faults, achieving early, accurate, and continuous quantitative assessment and trend prediction of the rolling bearing health status.

[0095] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0096] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A method for assessing the condition of a rolling bearing, characterized in that, The method includes: The vibration signal of the rolling bearing is subjected to mean-removal processing to obtain the first-order time-domain signal; The initial time-domain signal is subjected to Fourier transform processing to obtain its corresponding frequency-domain signal, and the noise index of the rolling bearing is obtained based on the frequency-domain signal. The initial time-domain signal is subjected to envelope demodulation to obtain its corresponding envelope spectrum, and the sideband index of the rolling bearing is obtained based on the envelope spectrum. The initial time-domain signal is subjected to bandpass filtering to obtain its corresponding filtered time-domain signal, and the impact index of the rolling bearing is obtained based on the filtered time-domain signal. Multimodal feature weighted fusion is performed based on the noise index, the sideband index, and the impact index to obtain a bearing health index that reflects the health status of the rolling bearing.

2. The rolling bearing condition assessment method as described in claim 1, characterized in that, The step of obtaining the noise index of the rolling bearing based on the frequency domain signal includes: Obtain the local mean and local standard deviation of the frequency domain signal; An adaptive threshold is determined based on the local mean and the local standard deviation; Based on the adaptive threshold, transient impact points in the frequency domain signal are identified and eliminated; The frequency domain signal after removing transient impact points is processed by moving average to obtain the noise floor signal; The noise index of the rolling bearing is obtained based on the noise background signal.

3. The rolling bearing condition assessment method as described in claim 2, characterized in that, The step of obtaining the noise index of the rolling bearing based on the noise background signal includes: Extract the noise energy percentage, noise significance, noise distribution width, and signal-to-noise ratio from the noise background signal; The noise index of the rolling bearing is obtained by performing a fusion calculation based on the sound energy ratio, the noise saliency, the noise distribution width, and the signal ratio.

4. The rolling bearing condition assessment method as described in claim 1, characterized in that, The step of obtaining the sideband index of the rolling bearing based on the envelope spectrum includes: Determine the characteristic frequency of bearing failure based on the size and rotational frequency of the rolling bearing; Using the bearing fault characteristic frequency as the center, extract the left nth order sideband group and the right nth order sideband group from the envelope spectrum; Calculate the total energy and sideband saliency of each sideband group; The sideband index of the rolling bearing is obtained by performing a fusion calculation based on the sideband saliency and total energy of each sideband group.

5. The rolling bearing condition assessment method as described in claim 1, characterized in that, The step of obtaining the impact index of the rolling bearing based on the filtered time-domain signal includes: The filtered time-domain signal is downsampled to determine the location of the impact peak and the corresponding impact energy. The impact baseline is determined based on the impact peak location and the corresponding impact energy. The filtered time-domain signal is divided into multiple sub-segments; Calculate the kurtosis, peak value, impact count, and weight of each sub-segment waveform, where the impact count is the number of times the impact energy in the sub-segment is greater than the impact baseline, and the peak value of the sub-segment is the maximum impact amplitude in the sub-segment waveform; The impact index of the rolling bearing is determined by weighted calculation based on the kurtosis, peak value, impact count, and weight of each sub-segment waveform.

6. The rolling bearing condition assessment method as described in claim 1, characterized in that, The step of performing multimodal feature weighted fusion based on the noise index, the sideband index, and the impact index to obtain a bearing health index reflecting the health status of the rolling bearing includes: The noise index, the sideband index, and the impact index are dimensionless to obtain the dimensionless noise index, the dimensionless sideband index, and the dimensionless impact index. Multimodal feature weighting and fusion are performed based on dimensionless noise index, dimensionless sideband index and dimensionless impact index to obtain a bearing health index that reflects the health status of rolling bearings.

7. The rolling bearing condition assessment method as described in claim 1, characterized in that, The method further includes: When the bearing health index is less than a first threshold, the rolling bearing is determined to be in a healthy state. When the bearing health index is greater than or equal to a first threshold and less than a second threshold, the rolling bearing is determined to be in a sub-healthy state. When the bearing health index is greater than or equal to the second threshold, the rolling bearing is determined to be in a damaged state.

8. A rolling bearing condition assessment device, characterized in that, The device includes: The first processing unit is used to perform mean-removal processing on the vibration signal of the rolling bearing to obtain the first-order time-domain signal. The first processing unit is further configured to perform Fourier transform processing on the initial time domain signal to obtain its corresponding frequency domain signal, and obtain the noise index of the rolling bearing based on the frequency domain signal. The first processing unit is further configured to perform envelope demodulation processing on the initial time-domain signal to obtain its corresponding envelope spectrum, and obtain the sideband index of the rolling bearing based on the envelope spectrum; The first processing unit is further configured to perform bandpass filtering on the initial time-domain signal to obtain its corresponding filtered time-domain signal, and obtain the impact index of the rolling bearing based on the filtered time-domain signal; The second processing unit is used to perform multimodal feature weighted fusion based on the noise index, the sideband index, and the impact index to obtain a bearing health index that reflects the health status of the rolling bearing.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method as described in any one of claims 1-7.

10. An electronic device, characterized in that, include: Processor and memory, the memory being used to store one or more programs; When the one or more programs are executed by the processor, the method as described in any one of claims 1-7 is implemented.

Images