Bearing fault detection method and device and train

By using vibration frequency domain data within the bearing running time interval and other bearing data under the same environment in bearing fault detection, combined with similarity and deviation values, the existing technology cannot identify early and mid-term faults and other fault types. Problem, more accurate bearing failure detection is achieved.

CN118936889APending Publication Date: 2024-11-12CRRC QINGDAO SIFANG CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411207483.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-30
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

Existing bearing failure detection methods cannot accurately identify early and mid-term faults of bearings, and cannot detect other faults such as uniform bearing wear, rotor imbalance, and unknown fault types.

Method used

By determining the train running time interval, obtain the vibration frequency domain data corresponding to the historical time window of the bearing to be detected and the vibration frequency domain data in the same environment of other bearings, generate fault information, and use similarity values ​​and deviation values ​​to filter out abnormality degree information. , determine whether the bearing is faulty.

Benefits of technology

It realizes that while early identification of faults in the early and mid-term of bearing failures, it can detect various other types and unknown faults, eliminate interference from speed changes on the spectrum, and improve the accuracy of fault detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118936889A_ABST
    Figure CN118936889A_ABST
Patent Text Reader

Abstract

The invention provides a bearing fault detection method, which comprises the following steps that: a train operation time interval is determined, the train operation time interval comprises N historical time windows, and a train runs at a constant speed in the historical time windows; n sets of first vibration frequency domain data, in one-to-one correspondence with the N historical time windows, of the to-be-detected bearing are obtained, N sets of second vibration frequency domain data, in one-to-one correspondence with the N historical time windows, of other bearings with the same installation environment as the to-be-detected bearing are obtained, and the to-be-detected bearing and the other bearings are installed on the same train; based on the N groups of first vibration frequency domain data and the N groups of second vibration frequency domain data, generating N pieces of fault information in one-to-one correspondence with the N historical time windows; and based on the N pieces of fault information, generating a fault detection result of the to-be-detected bearing in the train operation time interval. The invention further provides a bearing fault detection device and a train.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of rail transit technology, and more specifically, to a bearing fault detection method, device and train. Background Art

[0002] With the current development of railways towards high-speed, heavy-load, and intensive transportation, the increase in train speed and load will lead to an increase in wheel-rail interaction and increased vibration of the train running gear. The operating status and expected life of traction motor bearings, gearbox bearings, and axlebox bearings are greatly affected by vibration. Bearing abnormalities will have a great impact on the safety and stability of train operation, so the identification, maintenance and replacement of bearing abnormalities are extremely important. At present, there are two main methods for detecting train bearing abnormalities: one is to install a temperature sensor near the bearing, and judge whether the bearing is abnormal by comparing the bearing temperature with the preset threshold; the other is to install a vibration sensor near the bearing and judge whether the bearing is abnormal by the bearing vibration signal.

[0003] In the process of realizing the concept disclosed in the present invention, the inventors found that there are at least the following problems in the related art: for the method of judging whether the bearing is abnormal by comparing the bearing temperature with a preset threshold value, it is not possible to accurately identify the early and mid-term faults of the bearing; for the method of judging whether the bearing is abnormal by the vibration signal of the bearing, it is not possible to accurately identify other faults such as uniform bearing wear, rotor imbalance and unknown fault types. Summary of the invention

[0004] In view of this, the present disclosure provides a bearing fault detection method, device and train.

[0005] One aspect of the present disclosure provides a bearing fault detection method, including: determining a train running time interval, wherein the train running time interval includes N historical time windows, and the train travels at a constant speed within the historical time window; obtaining N groups of first vibration frequency domain data corresponding one-to-one to the N historical time windows for the bearing to be detected, and obtaining N groups of second vibration frequency domain data corresponding one-to-one to other bearings with the same installation environment as the bearing to be detected and the N historical time windows, wherein the bearing to be detected and the other bearings are installed on the same train; based on the N groups of first vibration frequency domain data and the N groups of second vibration frequency domain data, generating N fault information corresponding one-to-one to the N historical time windows; based on the N fault information, generating a fault detection result of the bearing to be detected in the train running time interval.

[0006] According to an embodiment of the present disclosure, each group of first vibration frequency domain data includes M groups of first vibration frequency domain sub-data corresponding to M historical time sub-windows, and each group of second vibration frequency domain data includes M groups of second vibration frequency domain sub-data corresponding to M historical time sub-windows; based on N groups of first vibration frequency domain data and N groups of second vibration frequency domain data, N fault information corresponding to the N historical time windows are generated one by one, including: based on M groups of first vibration frequency domain sub-data and M groups of second vibration frequency domain sub-data, M abnormality degree information corresponding to the M historical time sub-windows are generated one by one; based on the M abnormality degree information, fault information corresponding to the historical time window is generated.

[0007] According to an embodiment of the present disclosure, abnormality degree information includes a similarity value and / or a deviation value; based on M abnormality degree information, generating fault information corresponding to the historical time window includes: screening out first abnormality degree information whose similarity value satisfies a first preset numerical condition from the M abnormality degree information; when the number of first abnormality degree information is less than or equal to a first preset threshold, determining that the fault information is first type of fault information, and the first type of fault information is used to characterize that the state of the bearing to be detected in the historical time window is abnormal; when the number of first abnormality degree information is greater than the first preset threshold, determining that the fault information is second type of fault information, and the second type of fault information is used to characterize that the state of the bearing to be detected in the historical time window is normal.

[0008] According to an embodiment of the present disclosure, based on M abnormality degree information, generating fault information corresponding to the historical time window includes: filtering out second abnormality degree information whose deviation value satisfies a second preset numerical condition from the M abnormality degree information; when the number of second abnormality degree information is less than or equal to a second preset threshold, determining that the fault information is first type of fault information; when the number of second abnormality degree information is greater than the second preset threshold, determining that the fault information is second type of fault information.

[0009] According to an embodiment of the present disclosure, based on M abnormality degree information, generating fault information corresponding to the historical time window includes: filtering out first abnormality degree information whose similarity value satisfies a first preset numerical condition from the M abnormality degree information; filtering out second abnormality degree information whose deviation value satisfies a second preset numerical condition from the M abnormality degree information; when the number of first abnormality degree information is less than or equal to a first preset threshold, and the number of second abnormality degree information is less than or equal to a second preset threshold, determining that the fault information is first type of fault information; when the number of first abnormality degree information is greater than the first preset threshold, and the number of second abnormality degree information is greater than the second preset threshold, determining that the fault information is second type of fault information.

[0010] According to an embodiment of the present disclosure, based on N fault information, a fault detection result of the bearing to be detected in the train running time interval is generated, including: when the number of first-category fault information is greater than or equal to a third predetermined threshold, determining the fault detection result of the bearing to be detected is: the bearing to be detected is faulty; when the number of first-category fault information is less than the third predetermined threshold, determining the fault detection result of the bearing to be detected is: the bearing to be detected is not faulty.

[0011] According to an embodiment of the present disclosure, obtaining N groups of first vibration frequency domain data corresponding one-to-one between the bearing to be detected and N historical time windows, and obtaining N groups of second vibration frequency domain data corresponding one-to-one between other bearings with the same installation environment as the bearing to be detected and N historical time windows includes: obtaining N groups of first original vibration data corresponding one-to-one between the bearing to be detected and N historical time windows, and obtaining N groups of second original vibration data corresponding one-to-one between other bearings with the same installation environment as the bearing to be detected and N historical time windows; performing data transformation processing on the N groups of first original vibration data and the N groups of second original vibration data to generate N groups of first vibration frequency domain data and N groups of second vibration frequency domain data.

[0012] According to an embodiment of the present disclosure, data transformation processing is performed on N groups of first original vibration data and N groups of second original vibration data to generate N groups of first vibration frequency domain data and N groups of second vibration frequency domain data, including: performing Fourier transformation processing on the N groups of first original vibration data and N groups of second original vibration data to obtain N groups of first initial vibration frequency domain data and N groups of second initial vibration frequency domain data; performing data filtering processing on the N groups of first initial vibration frequency domain data and N groups of second initial vibration frequency domain data to obtain N groups of first vibration frequency domain data and N groups of second vibration frequency domain data.

[0013] Another aspect of the present disclosure provides a bearing fault detection device, including: a determination module, used to determine a train running time interval, wherein the train running time interval includes N historical time windows, and the train travels at a uniform speed within the historical time window; an acquisition module, used to acquire N groups of first vibration frequency domain data corresponding one-to-one to the N historical time windows of the bearing to be detected, and to acquire N groups of second vibration frequency domain data corresponding one-to-one to the N historical time windows of other bearings with the same installation environment as the bearing to be detected, wherein the bearing to be detected and the other bearings are installed on the same train; a first generation module, used to generate N fault information corresponding one-to-one to the N historical time windows based on the N groups of first vibration frequency domain data and the N groups of second vibration frequency domain data; a second generation module, used to generate a fault detection result of the bearing to be detected in the train running time interval based on the N fault information.

[0014] Another aspect of the present disclosure provides a train, comprising the above-mentioned bearing fault detection device.

[0015] According to the embodiments of the present disclosure, it is determined whether the bearing to be detected has a fault based on the first vibration frequency domain data generated by the bearing to be detected and the second vibration frequency domain data generated by other bearings in the same installation environment as the bearing to be detected. While realizing the early identification of bearing faults in the early and middle stages of bearing faults, the fault detection of the bearing is no longer limited to only checking known types of faults such as the outer ring, inner ring, and roller of the bearing, but can detect other types of faults, and can detect unknown faults. The fault detection result is generated only based on the vibration frequency domain data generated within the historical time window of uniform speed driving, rather than based on the vibration frequency domain data generated within the entire train operation time interval, which can eliminate the interference of speed changes on the bearing spectrum, making the fault detection result more accurate. Therefore, it at least partially solves the technical problem that the existing bearing fault detection method cannot detect other types of faults and unknown fault types, and realizes the technical effect of being able to identify bearing faults in the early and middle stages of bearing faults, and other types of faults and unknown faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0017] Figure 1 An exemplary system architecture to which the bearing fault detection method and apparatus disclosed herein can be applied is schematically shown;

[0018] Figure 2 A flow chart of a bearing fault detection method according to an embodiment of the present disclosure is schematically shown;

[0019] Figure 3 A schematic diagram schematically shows a bearing fault detection method according to an embodiment of the present disclosure;

[0020] Figure 4 A flow chart of a bearing fault detection method according to another embodiment of the present disclosure is schematically shown;

[0021] Figure 5 A block diagram schematically shows a bearing fault detection device according to an embodiment of the present disclosure; and

[0022] Figure 6 A block diagram of an electronic device 600 suitable for implementing a bearing fault detection method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0023] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0024] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0025] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0026] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0027] In the embodiments of the present disclosure, the collection, updating, analysis, processing, use, transmission, provision, disclosure, storage, etc. of the data involved (for example, including but not limited to user personal information) are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information, network security, and national security.

[0028] In the embodiments of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0029] At present, there are two main methods and devices for detecting abnormalities in train bearings: one is to install a temperature sensor near the bearing, and detect bearing abnormalities by setting a temperature alarm threshold. This direct measurement method is low-cost, simple and feasible, but because the bearing temperature generally rises in the late stage of the fault, it is impossible to identify the bearing fault in the early and middle stages of the bearing fault; the other is to install a vibration sensor near the bearing, analyze and transform the vibration signal, extract the amplitude of the fault characteristic frequency of each bearing component (such as the outer ring, inner ring, roller, cage, etc.), and detect bearing abnormalities by setting the amplitude threshold. However, this method can only identify certain periodic impact faults of the outer ring, inner ring, roller, and cage of the bearing, and cannot accurately identify other faults such as uniform wear of the bearing, rotor imbalance, and unknown fault types.

[0030] On this basis, an embodiment of the present disclosure provides a bearing fault detection method, including: determining a train running time interval, wherein the train running time interval includes N historical time windows, and the train travels at a constant speed within the historical time window; obtaining N groups of first vibration frequency domain data corresponding one-to-one to the N historical time windows for the bearing to be detected, and obtaining N groups of second vibration frequency domain data corresponding one-to-one to other bearings with the same installation environment as the bearing to be detected and the N historical time windows, wherein the bearing to be detected and the other bearings are installed on the same train; based on the N groups of first vibration frequency domain data and the N groups of second vibration frequency domain data, generating N fault information corresponding one-to-one to the N historical time windows; based on the N fault information, generating a fault detection result of the bearing to be detected in the train running time interval.

[0031] Figure 1 The exemplary system architecture 100 to which the bearing fault detection method and apparatus of the present disclosure can be applied according to an embodiment of the present disclosure is schematically shown. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0032] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, a server 105, and a train 106. The network 104 is used to provide a medium for communication links between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0033] The user can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103.

[0034] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0035] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0036] It should be noted that the bearing fault detection method provided in the embodiment of the present disclosure can generally be executed by the server 105. The bearing fault detection method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Alternatively, the bearing fault detection method provided in the embodiment of the present disclosure can also be executed by the first terminal device 101, the second terminal device 102 or the third terminal device 103, or can also be executed by other terminal devices different from the first terminal device 101, the second terminal device 102 or the third terminal device 103.

[0037] For example, in the application scenario of the embodiment of the present disclosure, the user can generate a bearing fault detection request through the first terminal device 101, the second terminal device 102, and the third terminal device 103. In response to the above bearing fault detection request, the server 105 can be used to execute the bearing fault detection method of the embodiment of the present disclosure, including: determining the train running time interval, wherein the train running time interval includes N historical time windows, and the train travels at a constant speed in the historical time window; obtaining N groups of first vibration frequency domain data corresponding to the N historical time windows for the bearing to be detected, and obtaining N groups of second vibration frequency domain data corresponding to the N historical time windows for other bearings with the same installation environment as the bearing to be detected, wherein the bearing to be detected and the other bearings are installed on the same train 106; based on the N groups of first vibration frequency domain data and the N groups of second vibration frequency domain data, generating N fault information corresponding to the N historical time windows; based on the N fault information, generating the fault detection result of the bearing to be detected in the running time interval of the train 106.

[0038] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks, servers and trains may be provided as required.

[0039] Figure 2 A flow chart of a bearing fault detection method according to an embodiment of the present disclosure is schematically shown.

[0040] like Figure 2 As shown, the method includes operations S201 to S204.

[0041] In operation S201, a train running time interval is determined, wherein the train running time interval includes N historical time windows, and the train runs at a constant speed in the historical time windows.

[0042] In operation S202, N groups of first vibration frequency domain data corresponding one-to-one to the bearing to be inspected and N historical time windows are obtained, and N groups of second vibration frequency domain data corresponding one-to-one to other bearings in the same installation environment as the bearing to be inspected and the N historical time windows are obtained, wherein the bearing to be inspected and the other bearings are installed on the same train.

[0043] In operation S203 , N pieces of fault information corresponding to the N historical time windows are generated based on the N sets of first vibration frequency domain data and the N sets of second vibration frequency domain data.

[0044] In operation S204, based on the N pieces of fault information, a fault detection result of the bearing to be detected during the train running time interval is generated.

[0045] According to an embodiment of the present disclosure, in operation S201, a reference time range may be preset, and based on the vibration frequency domain data generated by the bearing to be detected within the reference time range, it is determined whether the bearing to be detected has a fault. For example, the reference time range may be preset to 1 day, and the vibration frequency domain data generated by the bearing to be detected within 1 day may be analyzed to determine whether the bearing has a fault.

[0046] Specifically, the number of times the train runs within the reference time range can be determined, and the train running time interval can be determined based on the departure time and arrival time of each run. For example, if train A runs twice in one day, the running time interval of the first run is from 6:00 (departure time) to 10:00 (arrival time), and the running time interval of the second run is from 13:00 (departure time) to 18:00 (arrival time), then the train running time interval includes 6:00 to 10:00 and 13:00 to 18:00. The vibration frequency domain data generated by the bearing to be tested installed on train A within the above train running time interval can be analyzed to determine whether the bearing to be tested has a fault.

[0047] According to the embodiments of the present disclosure, the train speed within the train running time interval can be obtained, so as to screen out the time period when the train runs at a constant speed. The time period when each train runs at a constant speed can be divided according to a predetermined time length to obtain N historical time windows. The train runs at a constant speed within each historical time window, but the running speeds within different historical time windows can be the same or different, which is not limited here.

[0048] Figure 3 A schematic diagram of a bearing fault detection method according to an embodiment of the present disclosure is schematically shown.

[0049] like Figure 3 , the reference time range is set to 1 day. The train runs once in 1 day, with the departure time being t0 and the arrival time being t n Therefore, within the reference time range, the train running time interval is t0-t n The time period of uniform speed operation can be selected from the train running time interval, for example, t1-t4, t8-t 10 Time period…In the above time period, the train runs at a constant speed. The preset time length can be t seconds. Based on the preset time length, the t1-t4 time period can be divided into three historical time windows, including: t1-t2, t2-t3, t3-t4; t8-t 10 The time period is divided into two historical event windows, including: t8-t9, t9-t 10. Among them, for the first historical time window t1-t2: the start time of the historical time window is t1, and the end time is t2. The duration of each historical time window is t seconds. All historical time windows within the train running time interval can be screened out.

[0050] According to the embodiment of the present disclosure, the time length of each historical time window is the same, and each historical time window does not overlap. The preset time length t of each historical time window can be preset, for example, it can be 20-300s; the speed difference percentage of the train in a historical time window can also be preset, for example, it can be 0.1%-5%. According to actual conditions, the values ​​of the time length and the speed difference percentage can also be adjusted, and the embodiment of the present disclosure does not limit this.

[0051] According to the embodiments of the present disclosure, by screening out historical time windows in which the train runs at a constant speed, and only analyzing the vibration frequency domain data generated in each historical time window, rather than analyzing the vibration frequency domain data generated in the entire train running time interval, the interference of speed changes on the vibration frequency domain data can be eliminated, so that the final fault detection result is more accurate.

[0052] According to an embodiment of the present disclosure, in operation S202, for each historical time window, the vibration frequency domain data generated by the bearing to be detected on the train when the train is running in the historical time window, that is, the first vibration frequency domain data, can be obtained. The vibration frequency domain data generated by other bearings in the same installation environment as the bearing to be detected in the historical time window can also be obtained, that is, the second vibration frequency domain data. The same installation environment can be: the other bearings and the bearing to be detected are installed in the same position in the same carriage of the same train. The other bearings can be one or more, and preferably, the number of other bearings is greater than or equal to 3.

[0053] When no bearing fails, the vibration frequency domain data generated by multiple bearings in the same installation environment should be the same or similar. Therefore, when no failure occurs in the bearing to be tested and other bearings in the same installation environment as the bearing to be tested, the first vibration frequency domain data and the second vibration frequency domain data should be the same or similar. On the contrary, if the first vibration frequency domain data is obviously different from the second vibration frequency domain data, or the first vibration frequency domain data obviously deviates from the mean of the first vibration frequency domain data and the second vibration frequency domain data, it indicates that the bearing to be tested may have a failure.

[0054] According to an embodiment of the present disclosure, in operation S203, the first vibration frequency domain data and the second vibration frequency domain data generated in each historical time window can be analyzed respectively to obtain fault information corresponding to the historical time window. Specifically: for each historical time window, it can be determined whether the state of the first vibration frequency domain data of the bearing to be detected in the historical time window is abnormal based on the first vibration frequency domain data and the second vibration frequency domain data corresponding to the historical time window, so as to obtain fault information. For example, it can be: in a certain historical time window, the first vibration frequency domain data is obviously different from the second vibration frequency domain data, indicating that the state of the bearing to be detected in the historical time window is abnormal. The fault information corresponding to each historical time window can be summarized to obtain N fault information.

[0055] According to an embodiment of the present disclosure, in operation S204, it can be determined whether the bearing to be detected is abnormal in the historical time window based on the fault information of each historical time window. When the state of the bearing to be detected in multiple historical time windows is abnormal, it means that the bearing to be detected may have a fault. When the state of the bearing to be detected is abnormal only in a few historical time windows, it means that the bearing to be detected may not have a fault.

[0056] According to the embodiments of the present disclosure, based on the first vibration frequency domain data generated by the bearing to be detected and the second vibration frequency domain data generated by other bearings in the same installation environment as the bearing to be detected, it is determined whether the bearing to be detected has a fault. While realizing the early identification of bearing faults in the early and middle stages of the bearing fault, the fault detection of the bearing is no longer limited to only checking the known types of faults such as the outer ring, inner ring, and roller of the bearing, but can detect many other types of faults, and can detect unknown faults. Generating fault detection results based only on the vibration frequency domain data generated within the historical time window of uniform speed travel, rather than based on the vibration frequency domain data generated within the entire train operation time interval, can eliminate the interference of speed changes on the bearing spectrum, making the fault detection results more accurate.

[0057] According to an embodiment of the present disclosure, according to an embodiment of the present disclosure, each group of first vibration frequency domain data includes M groups of first vibration frequency domain sub-data corresponding to M historical time sub-windows, and each group of second vibration frequency domain data includes M groups of second vibration frequency domain sub-data corresponding to M historical time sub-windows.

[0058] According to an embodiment of the present disclosure, each historical time window can be further divided into M historical time sub-windows, and the duration of each historical time sub-window is the same. For example: the duration of a historical time window is 80 seconds, and the historical time window can be divided into 8 historical time sub-windows, and the duration of each historical time sub-window is 10 seconds. Correspondingly, for a group of first vibration frequency domain data corresponding to the historical time window, it can also be further divided into M groups of first vibration frequency domain sub-data corresponding to the M historical time sub-windows. For a group of second vibration frequency domain data corresponding to the historical time window, it can also be further divided into M groups of second vibration frequency domain sub-data corresponding to the M historical time sub-windows.

[0059] like Figure 3 As shown in the figure, taking the first historical time window (corresponding to t1-t2) as an example, the historical time window can be further divided into 8 historical time sub-windows (that is, M=8): the first historical time sub-window is t1-t 11 , the second historical time sub-window is t 11 -t 12 ...The eighth historical time sub-window is t 17 -t2. Accordingly, the first set of first vibration frequency domain data corresponding to the first historical time window can be further divided into 8 sets of first vibration frequency domain sub-data, each set of first vibration frequency domain sub-data corresponds to a historical time sub-window, for example: the first set of first vibration frequency domain sub-data corresponds to the first historical time sub-window (corresponding to t1-t 11 ). Accordingly, for the 1 group of second vibration frequency domain data corresponding to the first historical time window, it can also be further divided into 8 groups of second vibration frequency domain sub-data, each group of second vibration frequency domain sub-data corresponds to a historical time sub-window, for example: the first group of second vibration frequency domain sub-data corresponds to the first historical time sub-window (corresponding to t1-t 11 ). It should be noted that the values ​​of the historical time sub-window, the first vibration frequency domain sub-data, and the second vibration frequency domain sub-data mentioned in the above example are only used as examples, and the present disclosure is not limited thereto.

[0060] According to an embodiment of the present disclosure, based on N groups of first vibration frequency domain data and N groups of second vibration frequency domain data, generating N fault information corresponding to N historical time windows includes: based on M groups of first vibration frequency domain sub-data and M groups of second vibration frequency domain sub-data, generating M abnormality degree information corresponding to M historical time sub-windows. Based on the M abnormality degree information, generating fault information corresponding to the historical time window.

[0061] Specifically, for a historical time window, after it is divided into M historical time sub-windows, the abnormality degree information corresponding to each historical time sub-window can be calculated respectively. The abnormality degree information corresponding to each historical time sub-window can be summarized to obtain the fault information corresponding to the historical time window. The fault information of each historical time window can be obtained to generate N fault information corresponding to the N historical time windows one by one.

[0062] For example: for the first historical time window, after dividing it into 8 (M=8) historical time sub-windows, the abnormality degree information corresponding to the first historical time sub-window, the abnormality degree information corresponding to the second historical time sub-window, and the abnormality degree information corresponding to the eighth historical time sub-window can be calculated respectively. By summarizing the above eight abnormality degree information, the fault information corresponding to the first historical time window can be obtained. Similarly, for each other historical time window, the abnormality degree information can be obtained according to the above method, and then the fault information corresponding to the historical time window can be obtained.

[0063] According to an embodiment of the present disclosure, by dividing the historical time window into multiple historical time sub-windows, and generating fault information corresponding to the historical time window based on the abnormality degree information corresponding to each historical time sub-window, the interference of abnormal spectrum in a short period of time can be eliminated, thereby improving the accuracy of the acquired fault information.

[0064] According to an embodiment of the present disclosure, the abnormality degree information may include a similarity value and / or a deviation value. For multiple bearings with the same installation environment, when the bearings are not faulty, the vibration frequency domain sub-data generated by the multiple bearings should be the same or similar. Since the second vibration frequency domain sub-data is generated by a bearing with the same installation environment as the bearing to be detected, the similarity value and / or deviation value of the first vibration frequency domain sub-data compared to the second vibration frequency domain sub-data can be calculated. When the similarity value between the first vibration frequency domain sub-data and the second vibration frequency domain sub-data is low, or the deviation value is high, it indicates that there is a large difference between the first vibration frequency domain sub-data and the second vibration frequency domain sub-data, indicating that the first vibration frequency domain sub-data may be abnormal.

[0065] According to an embodiment of the present disclosure, the similarity value can characterize the degree of similarity between the first vibration frequency domain sub-data and the second vibration frequency domain sub-data. For a historical time sub-window, the first vibration frequency domain sub-data and the second vibration frequency domain sub-data corresponding to the historical time sub-window can be obtained, and the similarity value of the first vibration frequency domain sub-data and the second vibration frequency domain sub-data can be calculated. When the similarity value between the first vibration frequency domain sub-data and the second vibration frequency domain sub-data is low, it indicates that the first vibration frequency domain sub-data may be abnormal in the historical time sub-window.

[0066] Calculating the similarity value between the first vibration frequency domain sub-data and the second vibration frequency domain sub-data may be: respectively calculating the similarity between the first vibration frequency domain sub-data and each second vibration frequency domain sub-data to obtain a plurality of initial similarities. Calculating the average of the plurality of initial similarities to obtain the similarity value between the first vibration frequency domain sub-data and the second vibration frequency domain sub-data.

[0067] The similarity value may be calculated by dot product similarity, cosine similarity, or Euclidean similarity, but is not limited thereto. The similarity value may also be calculated by other methods, which are not limited here.

[0068] According to an embodiment of the present disclosure, the deviation value can be used to characterize the distance between the first vibration frequency domain sub-data and the mean of the vibration frequency domain sub-data. The average value of the first vibration frequency domain sub-data and the second vibration frequency domain sub-data can be calculated to obtain the mean of the vibration frequency domain sub-data. When the distance between the first vibration frequency domain sub-data and the mean of the vibration frequency domain sub-data is far, the deviation value is high, indicating that there is a large difference between the first vibration frequency domain sub-data and the mean of the vibration frequency domain sub-data, indicating that the first vibration frequency domain sub-data may be abnormal. The long distance between the first vibration frequency domain sub-data and the mean of the vibration frequency domain sub-data may be, for example, that the similarity between the first vibration frequency domain sub-data and the mean of the vibration frequency domain sub-data is low.

[0069] According to an embodiment of the present disclosure, the abnormality degree information corresponding to each historical time sub-window can be calculated respectively. By summarizing the abnormality degree information corresponding to each historical time sub-window, the fault information corresponding to the historical time window can be obtained, that is, based on M abnormality degree information, the fault information corresponding to the historical time window is generated.

[0070] According to an embodiment of the present disclosure, specifically, the abnormality degree information may only include a similarity value. In this case, based on M abnormality degree information, generating fault information corresponding to the historical time window includes: screening out the first abnormality degree information whose similarity value satisfies the first preset numerical condition from the M abnormality degree information; when the number of the first abnormality degree information is less than or equal to the first preset threshold, determining the fault information as the first type of fault information, the first type of fault information is used to characterize the abnormal state of the bearing to be detected in the historical time window; when the number of the first abnormality degree information is greater than the first preset threshold, determining the fault information as the second type of fault information, the second type of fault information is used to characterize the normal state of the bearing to be detected in the historical time window.

[0071] According to an embodiment of the present disclosure, a similarity threshold may be preset. The similarity value may satisfy the first preset numerical condition that: the similarity value is greater than or equal to the similarity threshold. In a certain historical time sub-window, when the similarity value is greater than or equal to the similarity threshold, it indicates that the similarity value between the first vibration frequency domain sub-data and the second vibration frequency domain sub-data is high, indicating that the first vibration frequency domain sub-data has no abnormality in the historical time sub-window, and it can be determined that the abnormality degree information corresponding to the historical time sub-window belongs to the first abnormality degree information. The first abnormality degree information is used to characterize that the first vibration frequency domain sub-data has no abnormality in the historical time sub-window.

[0072] All the first abnormality degree information can be screened out from the M abnormality degree information. When the amount of the first abnormality degree information is less than or equal to the first preset threshold, it indicates that among the M historical time sub-windows, the first vibration sub-data is not abnormal only in a few historical time sub-windows, so it can be determined that the state of the bearing to be tested in the historical time window corresponding to the above M historical time sub-windows is abnormal.

[0073] On the contrary, when the amount of first abnormality degree information is greater than the first preset threshold, it indicates that among the M historical time sub-windows, the first vibration sub-data has no abnormalities in more historical time sub-windows. Therefore, it can be determined that the state of the bearing to be tested in the historical time window corresponding to the above M historical time sub-windows is normal.

[0074] According to an embodiment of the present disclosure, during the running of the train, other bearings in the same installation environment as the bearing to be detected may also fail, resulting in abnormalities in the second vibration frequency domain data, which in turn leads to a low similarity value between the first vibration frequency domain sub-data and the second vibration frequency domain sub-data. Therefore, in order to accurately determine whether the bearing to be detected has failed or other bearings in the same installation environment as the bearing to be detected have failed, the bearing to be detected and each other bearing may be numbered. In each historical time subwindow, the similarity values ​​between each second vibration frequency domain sub-data may be calculated separately. The first abnormality degree information whose similarity value meets the first preset numerical condition may be screened out from the similarity values ​​between each second vibration frequency domain sub-data and the similarity values ​​between the first vibration frequency domain sub-data and the second vibration frequency domain sub-data.

[0075] When the number of first abnormality degree information is less than or equal to the first preset threshold value, and the bearing numbers corresponding to each first abnormality degree information are all bearing numbers corresponding to the bearing to be detected, the fault information is determined to be the first type of fault information, and the first type of fault information is used to characterize that the state of the bearing to be detected in the historical time window is abnormal; when the number of first abnormality degree information is greater than the second preset threshold value, and the bearing numbers corresponding to each first abnormality degree information are all bearing numbers corresponding to the bearing to be detected, the fault information is determined to be the second type of fault information, and the second type of fault information is used to characterize that the state of the bearing to be detected in the historical time window is normal.

[0076] According to an embodiment of the present disclosure, specifically, the abnormality degree information may only include a deviation value. In this case, based on the M abnormality degree information, generating fault information corresponding to the historical time window also includes: screening out second abnormality degree information whose deviation value satisfies a second preset numerical condition from the M abnormality degree information; when the number of the second abnormality degree information is greater than or equal to a second preset threshold, determining that the fault information is first-class fault information; when the number of the second abnormality degree information is less than the second preset threshold, determining that the fault information is second-class fault information.

[0077] According to an embodiment of the present disclosure, a deviation threshold can be preset. The deviation value satisfies the second preset numerical condition that: the deviation value is less than or equal to the deviation threshold. In a certain historical time sub-window, when the deviation value is less than or equal to the deviation threshold, it indicates that the distance between the first vibration frequency domain sub-data and the mean value of the vibration frequency domain sub-data is relatively close, indicating that the first vibration frequency domain sub-data is not abnormal in the historical time sub-window, so it can be determined that the abnormality degree information corresponding to the historical time sub-window belongs to the second abnormality degree information, that is, the first vibration frequency domain sub-data is not abnormal in the historical time sub-window.

[0078] All the second abnormality degree information can be screened out from the M abnormality degree information. When the number of the second abnormality degree information is less than or equal to the second preset threshold, it indicates that among the M historical time sub-windows, the first vibration sub-data is not abnormal only in a few historical time sub-windows, so it can be determined that the state of the bearing to be detected in the historical time window corresponding to the above M historical time sub-windows is abnormal. Therefore, it can be determined that the state of the bearing to be detected in the historical time window corresponding to the above M historical time sub-windows is abnormal.

[0079] On the contrary, when the amount of second abnormality degree information is greater than the second preset threshold, it indicates that among the M historical time sub-windows, the first vibration sub-data has not shown any abnormalities in more historical time sub-windows. Therefore, it can be determined that the state of the bearing to be tested in the historical time window corresponding to the above M historical time sub-windows is normal.

[0080] According to an embodiment of the present disclosure, when other bearings in the same installation environment as the bearing to be detected may also fail, the deviation values ​​of the first vibration frequency domain sub-data and the second vibration frequency domain sub-data may also be high. Therefore, in order to accurately determine whether the bearing to be detected fails or other bearings in the same installation environment as the bearing to be detected fail, the bearing to be detected and other bearings may be numbered. In each historical time sub-window, the distance between each second vibration frequency domain sub-data and the mean of the vibration frequency domain sub-data may be calculated respectively to obtain the deviation value corresponding to each second vibration frequency domain sub-data. The second abnormality degree information whose deviation value meets the second preset numerical condition can be screened out from the deviation value corresponding to each second vibration frequency domain sub-data and the deviation value corresponding to each first vibration frequency domain sub-data.

[0081] When the number of second abnormality degree information is less than or equal to the second preset threshold, and the bearing numbers corresponding to each second abnormality degree information are all bearing numbers corresponding to the bearing to be detected, the fault information is determined to be first-class fault information; when the number of second abnormality degree information is greater than the second preset threshold, and the bearing numbers corresponding to each second abnormality degree information are all bearing numbers corresponding to the bearing to be detected, the fault information is determined to be second-class fault information.

[0082] According to an embodiment of the present disclosure, specifically, the abnormality degree information includes a similarity value and a deviation value. In this case, based on M abnormality degree information, generating fault information corresponding to the historical time window includes:

[0083] Operation 11: Filter out first abnormality degree information whose similarity value satisfies a first preset numerical condition from the M abnormality degree information.

[0084] Operation 12: Filter out second abnormality degree information whose deviation value satisfies a second preset numerical condition from the M abnormality degree information.

[0085] Operation 13: When the amount of the first abnormality level information is less than or equal to the first preset threshold, and the amount of the second abnormality level information is less than or equal to the second preset threshold, determine that the fault information is the first type of fault information.

[0086] Operation 14: When the amount of first abnormality level information is greater than a first preset threshold, and the amount of second abnormality level information is greater than a second preset threshold, determine that the fault information is second-category fault information.

[0087] According to an embodiment of the present disclosure, when the amount of first abnormality degree information is less than or equal to a first preset threshold, and the amount of second abnormality degree information is less than or equal to a second preset threshold, it indicates that among the M historical time sub-windows, the first vibration sub-data has no abnormality only in a few historical time sub-windows, and therefore it can be determined that the state of the bearing to be tested in the historical time window corresponding to the above-mentioned M historical time sub-windows is abnormal.

[0088] According to an embodiment of the present disclosure, in order to accurately determine whether the bearing to be detected has a fault or other bearings in the same installation environment as the bearing to be detected have a fault, the bearing to be detected and other bearings may be numbered.

[0089] When the number of first abnormality degree information is less than or equal to the first preset threshold, the number of second abnormality degree information is less than or equal to the second preset threshold, and the bearing numbers corresponding to each of the first abnormality degree information and the second abnormality degree information are the bearing numbers corresponding to the bearing to be detected, the fault information is determined to be the first type of fault information; when the number of first abnormality degree information is greater than the first preset threshold, the number of second abnormality degree information is greater than the second preset threshold, and the bearing numbers corresponding to each of the first abnormality degree information and the second abnormality degree information are the bearing numbers corresponding to the bearing to be detected, the fault information is determined to be the second type of fault information.

[0090] According to the embodiments of the present disclosure, whether a fault has occurred is determined based on the first vibration frequency domain data generated by the bearing to be detected and the similarity value or deviation value of the second vibration frequency domain data generated by other bearings with the same installation environment as the bearing to be detected. While realizing the early identification of bearing faults in the early and middle stages of the bearing fault, the bearing fault detection is no longer limited to checking only known types of faults such as the outer ring, inner ring, roller, etc. of the bearing, but can detect many other types of faults and can detect unknown faults.

[0091] According to an embodiment of the present disclosure, based on N fault information, a fault detection result of the bearing to be detected in the train running time interval is generated, including: when the number of first-category fault information is greater than or equal to a third predetermined threshold, determining the fault detection result of the bearing to be detected is: the bearing to be detected is faulty; when the number of first-category fault information is less than the third predetermined threshold, determining the fault detection result of the bearing to be detected is: the bearing to be detected is not faulty.

[0092] According to an embodiment of the present disclosure, since the first type of fault information is used to characterize the abnormal state of the bearing to be detected in the historical time window, when the number of first type of fault information is large, it indicates that the bearing to be detected has shown abnormal state in multiple historical time windows. Therefore, it can be determined that the bearing to be detected has a fault within the train operation time interval.

[0093] A third predetermined threshold value may be preset. When the number of first-category fault information is greater than or equal to the third predetermined threshold value, it indicates that the bearing to be detected has shown abnormal status in more historical time windows, which indicates that the bearing to be detected has indeed failed during the entire train operation time interval, and therefore the fault detection result of the bearing to be detected is determined to be: the bearing to be detected has failed. On the contrary, when the number of first-category fault information is less than the third predetermined threshold value, it indicates that the bearing to be detected has shown abnormal status only in fewer historical time windows, which indicates that the bearing to be detected itself has not failed, and the reason why the first-category fault information is generated in certain historical time windows may be due to measurement errors, or because the bearing to be detected has only accidentally failed in certain historical time windows during the operation of the train, and therefore the fault detection result of the bearing to be detected can be determined to be: the bearing to be detected has not failed.

[0094] Specifically, when the number of first-category fault information is greater than or equal to a third predetermined threshold, determining the fault detection result of the bearing to be detected is that the bearing to be detected is faulty; when the number of first-category fault information is less than the third predetermined threshold, determining the fault detection result of the bearing to be detected is that the bearing to be detected is not faulty can include two determination methods.

[0095] The first determination method: All first-category fault information can be screened out from N fault information. The total number of all first-category fault information is determined. When the total number of all first-category fault information is greater than or equal to the third predetermined threshold, the fault detection result of the bearing to be detected is determined to be: the bearing to be detected is faulty; when the total number of first-category fault information included in the N fault information is less than the third predetermined threshold, the fault detection result of the bearing to be detected is determined to be: the bearing to be detected is not faulty. For the first determination method, preferably, the value of the third predetermined threshold can be 10 to 100.

[0096] For example, the third predetermined threshold is 4. A total of 8 fault information is generated, including 5 first-category fault information. Since the total number of first-category fault information is greater than the third predetermined threshold, it can be determined that the fault detection result of the bearing to be detected is: the bearing to be detected is faulty.

[0097] The second determination method: All first-category fault information can also be screened out from the N fault information, and the historical time window corresponding to each first-category fault information can be determined. Multiple first-category fault information with continuous historical time windows can be screened out from all first-category fault information. When the number of continuous first-category fault information in the historical time window is greater than or equal to the third predetermined threshold, the fault detection result of the bearing to be detected is determined to be: the bearing to be detected is faulty; when the number of continuous first-category fault information in the historical time window is less than the third predetermined threshold, the fault detection result of the bearing to be detected is determined to be: the bearing to be detected is not faulty. For the second determination method, preferably, the value of the third predetermined threshold can be 5 to 10.

[0098] For example, the third predetermined threshold is 4. A total of 8 fault information are generated, including 5 first-class fault information. Among them, the historical time windows corresponding to 4 first-class fault information are continuous. Since the number of first-class fault information in the continuous historical time window is equal to the third predetermined threshold, it can be determined that the fault detection result of the bearing to be detected is: the bearing to be detected is faulty.

[0099] According to an embodiment of the present disclosure, each historical time window may be sorted and numbered in chronological order. Historical time windows with the same number are continuous historical time windows.

[0100] like Figure 3 As shown, each historical time window can be sorted and numbered in chronological order, with the historical time window t1-t2 being numbered 1, the historical time window t2-t3 being numbered 2, the historical time window t3-t4 being numbered 3... the historical time window t9-t 10 The number is 6. Then the historical time windows t1-t2, t2-t3, and t3-t4 are continuous historical time windows; the historical time windows t3-t4 and t9-t 10 is a discontinuous historical time window.

[0101] According to an embodiment of the present disclosure, when it is determined that the fault detection result of the bearing to be detected is that the bearing to be detected is faulty, an alarm message may be generated to prompt a staff member to inspect the bearing to be detected.

[0102] According to an embodiment of the present disclosure, the fault detection result is obtained by aggregating fault information corresponding to multiple historical time windows, rather than directly obtaining the fault detection result based on the first vibration frequency domain data generated by the bearing to be detected during the entire train running time interval. This can eliminate the interference of speed changes on the bearing spectrum, making the fault detection result more accurate.

[0103] According to an embodiment of the present disclosure, obtaining N groups of first vibration frequency domain data corresponding one-to-one to the bearing to be detected and N historical time windows, and N groups of second vibration frequency domain data corresponding one-to-one to other bearings in the same installation environment as the bearing to be detected and N historical time windows includes operations 21 to 22.

[0104] In operation 21, N groups of first original vibration data corresponding one-to-one between the bearing to be tested and N historical time windows are obtained, and N groups of second original vibration data corresponding one-to-one between other bearings in the same installation environment as the bearing to be tested and the N historical time windows are obtained.

[0105] In operation 22 , data transformation processing is performed on the N groups of first original vibration data and the N groups of second original vibration data to generate N groups of first vibration frequency domain data and N groups of second vibration frequency domain data.

[0106] According to an embodiment of the present disclosure, in operation 21, the first original vibration data corresponding to the bearing to be detected and the second original vibration data corresponding to the other bearings can be obtained in real time by installing vibration sensors on the bearing to be detected and other bearings. The first original vibration data and the second original vibration data can be input into a preprocessor to perform data preprocessing on the first original vibration data and the second original vibration data. Data preprocessing may include, for example, data cleaning and digital-to-analog conversion. The first original vibration data and the second original vibration data after data preprocessing may be transmitted to a vehicle data processor or a vehicle network. Specifically, the existing train control network may be used for data transmission, or a dedicated fault diagnosis network may be established for data transmission. Data transmission may be transmitted in a wired manner or in a wireless manner. For example, wired transmission may be transmission in the manner and performance of an S232 interface or Ethernet; wireless transmission may be transmission via WIFI, for example. The first original vibration data and the second original vibration data after data preprocessing may be stored in a train-level memory.

[0107] According to an embodiment of the present disclosure, in operation 22, the data transform process may include a Fourier transform process and a data filtering process.

[0108] According to an embodiment of the present disclosure, specifically, performing data transformation processing on N groups of first original vibration data and N groups of second original vibration data to generate N groups of first vibration frequency domain data and N groups of second vibration frequency domain data includes operations 31 and 32.

[0109] In operation 31 , Fourier transform processing is performed on N groups of first original vibration data and N groups of second original vibration data to obtain N groups of first initial vibration frequency domain data and N groups of second initial vibration frequency domain data.

[0110] In operation 32 , data filtering processing is performed on the N groups of first initial vibration frequency domain data and the N groups of second initial vibration frequency domain data to obtain N groups of first vibration frequency domain data and N groups of second vibration frequency domain data.

[0111] According to an embodiment of the present disclosure, in operation 31, the first original vibration data and the second original vibration data are time series data. Through Fourier transform processing, the first original vibration data and the second original vibration data can be converted from time series data to frequency domain data to obtain first initial vibration frequency domain data and second initial vibration frequency domain data.

[0112] According to an embodiment of the present disclosure, in operation 32, since the frequency domain distribution of the first initial vibration frequency domain data and the second initial vibration frequency domain data is relatively wide, if the first initial vibration frequency domain data and the second initial vibration frequency domain data are directly analyzed, it will result in a large amount of data analysis tasks. Therefore, the reference vibration frequency domain data generated by a reference bearing that has previously failed and has the same installation environment as the bearing to be tested can be used to narrow the frequency domain range of the first initial vibration frequency domain data and the second initial vibration frequency domain data.

[0113] Specifically, the frequency domain distribution range of the reference vibration frequency domain data of the reference bearing that has previously failed can be obtained. The frequency domain distribution range of the reference vibration frequency domain data can be used as the data filtering range. For example, the frequency domain distribution range of the vibration frequency domain data of the reference bearing that has previously failed is [f min ,f max ], can be used as the data filtering range, where f min is the lower limit of data filtering, f max is the upper limit of data filtering.

[0114] According to an embodiment of the present disclosure, the value range of the data filtering lower limit may be 0-30, and the data filtering upper limit may be, for example, 1000-10000. The filter may be, for example, a Butterworth filter, a Chebyshev filter, etc., but is not limited thereto, and may also be other types of filters, which are not limited here.

[0115] Figure 4 A flow chart of a bearing fault detection method according to another embodiment of the present disclosure is schematically shown.

[0116] like Figure 4 As shown, the method includes operations S401 to S405.

[0117] In operation S401 , first original vibration data and second original vibration data are collected.

[0118] In operation S402, Fourier transform processing is performed on the first original vibration data and the second original vibration data to obtain first initial vibration frequency domain data and second initial vibration frequency domain data.

[0119] In operation S403, data filtering is performed on the first initial vibration frequency domain data and the second initial vibration frequency domain data to obtain first vibration frequency domain data and second vibration frequency domain data.

[0120] In operation S404 , N pieces of fault information corresponding to the historical time windows are generated based on the first vibration frequency domain data and the second vibration frequency domain data.

[0121] In operation S405, based on the N fault information, a fault detection result of the bearing to be detected during the train running time interval is generated.

[0122] Figure 5 A block diagram of a bearing fault detection device according to an embodiment of the present disclosure is schematically shown.

[0123] like Figure 5 As shown, the bearing fault detection device 500 includes a determination module 510 , an acquisition module 520 , a first generation module 530 and a second generation module 540 .

[0124] The determination module 510 is used to determine the train running time interval, wherein the train running time interval includes N historical time windows, and the train runs at a constant speed in the historical time windows. In one embodiment, the determination module 510 can be used to perform the operation S201 described above, which will not be repeated here.

[0125] The acquisition module 520 is used to acquire N groups of first vibration frequency domain data corresponding to the bearing to be detected and the N historical time windows, and to acquire N groups of second vibration frequency domain data corresponding to other bearings in the same installation environment as the bearing to be detected and the N historical time windows, wherein the bearing to be detected and the other bearings are installed on the same train. In one embodiment, the acquisition module 520 can be used to perform the operation S202 described above, which will not be repeated here.

[0126] The first generating module 530 is used to generate N fault information corresponding to N historical time windows based on N groups of first vibration frequency domain data and N groups of second vibration frequency domain data. In one embodiment, the first generating module 530 can be used to perform the operation S203 described above, which will not be described in detail here.

[0127] The second generation module 540 is used to generate a fault detection result of the bearing to be detected in the train running time interval based on the N fault information. In one embodiment, the second generation module 540 can be used to perform the operation S204 described above, which will not be repeated here.

[0128] According to an embodiment of the present disclosure, the first generating module includes a first generating submodule and a second generating submodule.

[0129] The first generation submodule is used to generate M abnormality degree information corresponding to M historical time subwindows based on M groups of first vibration frequency domain sub-data and M groups of second vibration frequency domain sub-data; the second generation submodule is used to generate fault information corresponding to the historical time window based on the M abnormality degree information.

[0130] According to an embodiment of the present disclosure, the second generating submodule includes a first screening unit, a first determining unit and a second determining unit.

[0131] The first screening unit is used to screen out the first abnormality degree information whose similarity value meets the first preset numerical condition from M abnormality degree information; the first determination unit is used to determine that the fault information is the first type of fault information when the number of the first abnormality degree information is less than or equal to the first preset threshold value, and the first type of fault information is used to characterize that the state of the bearing to be detected in the historical time window is abnormal; the second determination unit is used to determine that the fault information is the second type of fault information when the number of the first abnormality degree information is greater than the first preset threshold value, and the second type of fault information is used to characterize that the state of the bearing to be detected in the historical time window is normal.

[0132] According to an embodiment of the present disclosure, the second generating submodule includes a second screening unit, a third determining unit and a fourth determining unit.

[0133] The second screening unit is used to screen out the second abnormality degree information whose deviation value meets the second preset numerical condition from the M abnormality degree information; the third determination unit is used to determine that the fault information is the first type of fault information when the number of the second abnormality degree information is less than or equal to the second preset threshold value; the fourth determination unit is used to determine that the fault information is the second type of fault information when the number of the second abnormality degree information is greater than the second preset threshold value.

[0134] According to an embodiment of the present disclosure, the second generation submodule includes a fifth determination unit and a sixth determination unit.

[0135] The fifth determination unit is used to determine that the fault information is the first type of fault information when the amount of first abnormality degree information is less than or equal to the first preset threshold and the amount of second abnormality degree information is less than or equal to the second preset threshold; the sixth determination unit is used to determine that the fault information is the second type of fault information when the amount of first abnormality degree information is greater than the first preset threshold and the amount of second abnormality degree information is greater than the second preset threshold.

[0136] According to an embodiment of the present disclosure, the second generating module includes a first determining submodule and a second determining submodule.

[0137] The first determination submodule is used to determine, when the number of first-type fault information is greater than or equal to a third predetermined threshold, that a fault detection result of the bearing to be detected is: a fault occurs in the bearing to be detected; the second determination submodule is used to determine, when the number of first-type fault information is less than a third predetermined threshold, that a fault detection result of the bearing to be detected is: a fault does not occur in the bearing to be detected.

[0138] According to an embodiment of the present disclosure, the acquisition module includes an acquisition submodule and a data transformation processing module.

[0139] The acquisition submodule is used to obtain N groups of first original vibration data corresponding one-to-one to the bearing to be detected and N historical time windows, and to obtain N groups of second original vibration data corresponding one-to-one to other bearings with the same installation environment as the bearing to be detected and N historical time windows; the data transformation processing module is used to perform data transformation processing on the N groups of first original vibration data and the N groups of second original vibration data to generate N groups of first vibration frequency domain data and N groups of second vibration frequency domain data.

[0140] According to an embodiment of the present disclosure, the data transformation processing module includes a Fourier transformation processing module and a data filtering processing module.

[0141] The Fourier transform processing module is used to perform Fourier transform processing on N groups of first original vibration data and N groups of second original vibration data to obtain N groups of first initial vibration frequency domain data and N groups of second initial vibration frequency domain data; the data filtering processing module is used to perform data filtering processing on N groups of first initial vibration frequency domain data and N groups of second initial vibration frequency domain data to obtain N groups of first vibration frequency domain data and N groups of second vibration frequency domain data.

[0142] According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging circuits, or can be implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be performed.

[0143] For example, any of the determination module 510, the acquisition module 520, the first generation module 530, and the second generation module 540 can be combined in one module / unit / sub-unit for implementation, or any of the modules / units / sub-units can be split into multiple modules / units / sub-units. Alternatively, at least part of the functions of one or more of these modules / units / sub-units can be combined with at least part of the functions of other modules / units / sub-units and implemented in one module / unit / sub-unit. According to an embodiment of the present disclosure, at least one of the determination module 510, the acquisition module 520, the first generation module 530, and the second generation module 540 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or by any one of the three implementation methods of software, hardware, and firmware, or by a suitable combination of any of them. Alternatively, at least one of the determination module 510 , the acquisition module 520 , the first generation module 530 , and the second generation module 540 may be at least partially implemented as a computer program module, and when the computer program module is executed, a corresponding function may be performed.

[0144] It should be noted that the bearing fault detection device part in the embodiment of the present disclosure corresponds to the bearing fault detection method part in the embodiment of the present disclosure. The description of the bearing fault detection device part specifically refers to the data processing method part, which will not be repeated here.

[0145] Figure 6 A block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present disclosure is schematically shown. Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0146] like Figure 6 As shown, the electronic device 600 according to an embodiment of the present disclosure includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 to a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include an onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0147] In RAM 603, various programs and data required for the operation of electronic device 600 are stored. Processor 601, ROM 602 and RAM 603 are connected to each other via bus 604. Processor 601 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 602 and / or RAM 603. It should be noted that the program can also be stored in one or more memories other than ROM 602 and RAM 603. Processor 601 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in one or more memories.

[0148] According to an embodiment of the present disclosure, the electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to the bus 604. The electronic device 600 may further include one or more of the following components connected to the input / output (I / O) interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 608 including a hard disk, etc.; and a communication portion 609 including a network interface card such as a LAN card, a modem, etc. The communication portion 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output (I / O) interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage portion 608 as needed.

[0149] According to an embodiment of the present disclosure, the method flow according to an embodiment of the present disclosure can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, the above-mentioned functions defined in the system of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

[0150] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0151] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include, but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0152] For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 602 and / or the RAM 603 described above and / or one or more memories other than the ROM 602 and the RAM 603 .

[0153] An embodiment of the present disclosure also includes a computer program product, which includes a computer program, which contains program code for executing the method provided by the embodiment of the present disclosure. When the computer program product runs on an electronic device, the program code is used to enable the electronic device to implement the bearing fault detection method provided by the embodiment of the present disclosure.

[0154] When the computer program is executed by the processor 601, the above functions defined in the system / device of the embodiment of the present disclosure are executed. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0155] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 609, and / or installed from a removable medium 611. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0156] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0157] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions. It can be understood by those skilled in the art that the features recorded in the various embodiments of the present disclosure can be combined and / or combined in a variety of ways, even if such a combination or combination is not explicitly recorded in the present disclosure. In particular, without departing from the spirit and teaching of the present disclosure, the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0158] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A bearing fault detection method, comprising: Determine a train running time interval, wherein the train running time interval includes N historical time windows, and the train runs at a constant speed within the historical time windows; Obtaining N groups of first vibration frequency domain data corresponding one-to-one between the bearing to be detected and the N historical time windows, and obtaining N groups of second vibration frequency domain data corresponding one-to-one between other bearings in the same installation environment as the bearing to be detected and the N historical time windows, wherein the bearing to be detected and the other bearings are installed on the same train; Based on the N groups of first vibration frequency domain data and the N groups of second vibration frequency domain data, generating N fault information corresponding to the N historical time windows one by one; Based on the N fault information, a fault detection result of the bearing to be detected in the train running time interval is generated.

2. The method according to claim 1, wherein: Each group of the first vibration frequency domain data includes M groups of first vibration frequency domain sub-data corresponding to M historical time sub-windows, and each group of the second vibration frequency domain data includes M groups of second vibration frequency domain sub-data corresponding to M historical time sub-windows; The generating, based on the N groups of first vibration frequency domain data and the N groups of second vibration frequency domain data, N fault information corresponding to the N historical time windows one by one comprises: Based on the M groups of first vibration frequency domain sub-data and the M groups of second vibration frequency domain sub-data, generating M pieces of abnormality degree information corresponding to the M historical time sub-windows one by one; Based on the M pieces of abnormality degree information, fault information corresponding to the historical time window is generated.

3. The method according to claim 2, wherein: The abnormality degree information includes a similarity value and / or a deviation value; The generating, based on the M pieces of abnormality degree information, fault information corresponding to the historical time window comprises: Filter out first abnormality degree information whose similarity value satisfies a first preset numerical condition from the M abnormality degree information; When the amount of the first abnormality degree information is less than or equal to a first preset threshold, determining that the fault information is first type of fault information, the first type of fault information is used to characterize that the state of the bearing to be detected in the historical time window is abnormal; When the amount of the first abnormality degree information is greater than a first preset threshold, the fault information is determined to be second-type fault information, and the second-type fault information is used to characterize that the state of the bearing to be detected in the historical time window is normal.

4. The method according to claim 3, wherein: The generating, based on the M pieces of abnormality degree information, fault information corresponding to the historical time window comprises: Filter out the second abnormality degree information whose deviation value satisfies the second preset numerical condition from the M abnormality degree information; When the amount of the second abnormality degree information is less than or equal to a second preset threshold, determining that the fault information is the first type of fault information; When the amount of the second abnormality degree information is greater than a second preset threshold, it is determined that the fault information is the second type of fault information.

5. The method according to claim 3, wherein: The generating, based on the M pieces of abnormality degree information, fault information corresponding to the historical time window comprises: Filter out first abnormality degree information whose similarity value satisfies a first preset numerical condition from the M abnormality degree information; Filter out the second abnormality degree information whose deviation value satisfies the second preset numerical condition from the M abnormality degree information; When the amount of the first abnormality level information is less than or equal to a first preset threshold, and the amount of the second abnormality level information is less than or equal to a second preset threshold, determining that the fault information is first type fault information; When the amount of the first abnormality level information is greater than a first preset threshold, and the amount of the second abnormality level information is greater than a second preset threshold, it is determined that the fault information is second-type fault information.

6. The method according to any one of claims 3 to 5, wherein: The generating, based on the N fault information, a fault detection result of the bearing to be detected in the train running time interval comprises: When the amount of the first type of fault information is greater than or equal to a third predetermined threshold, determining the fault detection result of the bearing to be detected as: the bearing to be detected is faulty; When the amount of the first type of fault information is less than a third predetermined threshold, it is determined that the fault detection result of the bearing to be detected is: the bearing to be detected has no fault.

7. The method according to claim 1, wherein: The step of obtaining N groups of first vibration frequency domain data corresponding one-to-one between the bearing to be detected and the N historical time windows, and obtaining N groups of second vibration frequency domain data corresponding one-to-one between other bearings in the same installation environment as the bearing to be detected and the N historical time windows includes: Acquire N groups of first original vibration data corresponding one-to-one between the bearing to be detected and the N historical time windows, and acquire N groups of second original vibration data corresponding one-to-one between other bearings in the same installation environment as the bearing to be detected and the N historical time windows; Data transformation processing is performed on the N groups of first original vibration data and the N groups of second original vibration data to generate the N groups of first vibration frequency domain data and the N groups of second vibration frequency domain data.

8. The method according to claim 7, wherein: The performing data transformation processing on the N groups of first original vibration data and the N groups of second original vibration data to generate the N groups of first vibration frequency domain data and the N groups of second vibration frequency domain data comprises: Performing Fourier transform processing on the N groups of first original vibration data and the N groups of second original vibration data to obtain N groups of first initial vibration frequency domain data and the N groups of second initial vibration frequency domain data; Data filtering processing is performed on the N groups of first initial vibration frequency domain data and the N groups of second initial vibration frequency domain data to obtain the N groups of first vibration frequency domain data and the N groups of second vibration frequency domain data.

9. A bearing fault detection device, comprising: A determination module, used to determine a train running time interval, wherein the train running time interval includes N historical time windows, and the train runs at a constant speed within the historical time windows; An acquisition module, used to acquire N groups of first vibration frequency domain data corresponding one-to-one between the bearing to be detected and the N historical time windows, and to acquire N groups of second vibration frequency domain data corresponding one-to-one between other bearings in the same installation environment as the bearing to be detected and the N historical time windows, wherein the bearing to be detected and the other bearings are installed on the same train; A first generating module, configured to generate N pieces of fault information corresponding to the N historical time windows based on the N groups of first vibration frequency domain data and the N groups of second vibration frequency domain data; The second generating module is used to generate the fault detection result of the bearing to be detected in the train running time interval based on the N fault information.

10. A train comprising: The bearing fault detection device as claimed in claim 9.