Fault detection method, device and equipment for rolling bearing and medium

Abstract

The invention is suitable for the technical field of fault detection, and particularly relates to a fault detection method, device and equipment for a rolling bearing and a medium, the running state of a target rolling bearing is preliminarily judged through collected state data and a preset data threshold value, and when it is judged that the target rolling bearing has an abnormal condition, the target rolling bearing is judged to be abnormal. And predicting state data of the target rolling bearing between any two adjacent preset time periods based on the acquired M state data sequences and the trained data prediction model, thereby complementing the state data of the target rolling bearing in the target time interval. And a gradient sequence and a current fault degree are analyzed from the complemented reference data sequence, the real-time fault state and the fault development state of the target rolling bearing are analyzed, and abundant data of real-time dimension and development dimension are provided for obtaining the target fault degree, so that the accuracy of a fault detection result is improved, and the fault detection efficiency is improved. And early warning information can be provided in time, so that the reliability and safety of the bearing system can be improved.

Description

Technical Field

[0001] The present invention is applicable to the technical field of fault detection, and in particular relates to a rolling bearing fault detection method, device, equipment and medium. Background Art

[0002] Rolling bearings are key components widely used in mechanical equipment. The stability of their operating status is directly related to the performance and reliability of the entire equipment. Therefore, it is crucial to accurately and promptly detect rolling bearing failures.

[0003] At present, in the field of rolling bearing fault detection, it is possible to determine whether a bearing fault occurs by monitoring the status data such as the vibration amplitude, vibration frequency and bearing temperature generated by the rolling bearing during operation. However, in actual application scenarios, the status data is usually collected at fixed time intervals and cannot accurately capture the subtle changes of the rolling bearing over time. Fault diagnosis is usually based on historical status data, lacking the ability to predict future status and comprehensive analysis of status data. It is difficult to assess the exact degree of fault in a timely manner, and cannot meet the accuracy requirements of bearing fault detection in various application fields.

[0004] Therefore, when performing rolling bearing fault detection, how to improve the accuracy of fault detection results becomes an urgent problem to be solved. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a rolling bearing fault detection method, device, equipment and medium to solve the problem of low accuracy of rolling bearing fault detection results.

[0006] In a first aspect, an embodiment of the present invention provides a rolling bearing fault detection method, the rolling bearing fault detection method comprising: A state data sequence of a target rolling bearing within M preset time periods of a target time interval is obtained, wherein each state data sequence includes state data corresponding to N preset time points, and M and N are integers greater than 1.

[0007] The M state data sequences are compared with the preset data threshold to obtain the predicted state corresponding to the target rolling bearing, wherein the predicted state includes a normal state and a state to be analyzed.

[0008] If the predicted state is the state to be analyzed, a reference data sequence of the target rolling bearing within the target time interval is obtained based on M state data sequences and the trained data prediction model, wherein the reference data sequence includes reference data corresponding to K preset time points, K>M×N.

[0009] According to the reference data sequence, a gradient sequence and a current fault degree corresponding to the reference data sequence are obtained.

[0010] According to the gradient sequence corresponding to the reference data sequence, the fault development degree corresponding to the target rolling bearing is obtained.

[0011] According to the current fault degree and fault development degree corresponding to the target rolling bearing, the target fault degree corresponding to the target rolling bearing is obtained.

[0012] In a second aspect, an embodiment of the present invention provides a rolling bearing fault detection device, the rolling bearing fault detection device comprising: The data acquisition module is used to obtain a state data sequence of a target rolling bearing within M preset time periods of a target time interval, wherein each state data sequence includes state data corresponding to N preset time points, and M and N are integers greater than 1.

[0013] The state prediction module is used to compare the M state data sequences with the preset data threshold to obtain the predicted state corresponding to the target rolling bearing, wherein the predicted state includes a normal state and a state to be analyzed.

[0014] The data prediction module is used to obtain a reference data sequence of the target rolling bearing within a target time interval based on M state data sequences and a trained data prediction model if the predicted state is a state to be analyzed, wherein the reference data sequence includes reference data corresponding to K preset time points, K>M×N.

[0015] The data analysis module is used to obtain the gradient sequence and the current fault degree corresponding to the reference data sequence according to the reference data sequence.

[0016] The fault analysis module is used to obtain the fault development degree corresponding to the target rolling bearing according to the gradient sequence corresponding to the reference data sequence.

[0017] The fault detection module is used to obtain a target fault degree corresponding to the target rolling bearing according to the current fault degree and fault development degree corresponding to the target rolling bearing.

[0018] In a third aspect, an embodiment of the present invention provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the rolling bearing fault detection method of the first aspect when executing the computer program.

[0019] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the rolling bearing fault detection method of the first aspect is implemented.

[0020] The beneficial effects of the embodiments of the present invention compared with the prior art are: a preliminary judgment is made on the operating state of the target rolling bearing through the collected state data and the preset data threshold; when it is judged that the target rolling bearing has an abnormal condition, the state data of the target rolling bearing between any two adjacent preset time periods is predicted based on the collected M state data sequences and the trained data prediction model, thereby completing the state data of the target rolling bearing in the target time interval, and analyzing the gradient sequence and the current fault degree from the completed reference data sequence, analyzing the real-time fault state and the development state of the fault of the target rolling bearing, providing rich data in real-time dimension and development dimension for obtaining the target fault degree, thereby improving the accuracy of the fault detection results. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0022] Figure 1 This is a schematic diagram of an application environment of a rolling bearing fault detection method provided by Embodiment 1 of the present invention; Figure 2 It is a schematic flow chart of a rolling bearing fault detection method provided in Embodiment 1 of the present invention; Figure 3 It is a structural schematic diagram of a rolling bearing fault detection device provided in Embodiment 2 of the present invention; Figure 4 It is a structural diagram of a computer device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0023] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0024] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0025] It should also be understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0026] As used in the present specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]", depending on the context.

[0027] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0028] References to "one embodiment" or "some embodiments" etc. described in the present specification mean that one or more embodiments of the present invention include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0029] The embodiments of the present invention can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0030] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0031] It should be understood that the order of execution of the steps in the following embodiments does not imply a precedence of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0032] In order to illustrate the technical solution of the present invention, specific embodiments are provided below for illustration.

[0033] A rolling bearing fault detection method provided in the first embodiment of the present invention can be applied in the following aspects: Figure 1 In the application environment, the client communicates with the server. The client includes but is not limited to PDAs, desktop computers, laptops, ultra-mobile personal computers (UMPCs), netbooks, cloud computing devices, personal digital assistants (PDAs), and other computer devices. The server can be implemented with an independent server or a server cluster consisting of multiple servers.

[0034] See also Figure 2 , is a schematic flow chart of a rolling bearing fault detection method provided in Embodiment 1 of the present invention. The rolling bearing fault detection method can be applied to Figure 1 In the client, the rolling bearing fault detection method may include the following steps: S201, obtaining a state data sequence of a target rolling bearing within M preset time periods of a target time interval, wherein each state data sequence includes state data corresponding to N preset time points, and M and N are integers greater than 1.

[0035] The target rolling bearing refers to the rolling bearing that needs to be fault-detected.

[0036] The target time interval refers to a specific time period during which the status of the rolling bearing needs to be monitored. For example, it can be 1 hour, 1 day or 1 week. There are multiple preset time periods within the target time interval, which can be set by the implementer according to actual conditions to comprehensively capture the status changes of the rolling bearing at different operating stages.

[0037] The status data may be vibration amplitude, vibration frequency, bearing temperature, bearing pressure, bearing speed, etc., which can characterize the working status of the rolling bearing. It can be collected at certain time intervals by vibration collection equipment, temperature collection equipment, pressure collection equipment, speed collection equipment, etc.

[0038] Optionally, the time interval between any two adjacent preset time periods is a first preset time interval T1, and the time interval between any two adjacent preset time points is a second preset time interval T2, wherein T1=Q×T2, and Q is an integer greater than 1.

[0039] Among them, the selected acquisition device can perform data acquisition tasks multiple times within the target time interval based on the first preset time interval, and each time the data acquisition task is performed, multiple status data are collected in each preset time period based on the second preset time interval as the data basis for rolling bearing fault detection.

[0040] The specific values ​​of the first preset time interval T1 and the second preset time interval T2 can be set by the implementer according to actual conditions.

[0041] S202, comparing the M state data sequences with a preset data threshold to obtain a predicted state corresponding to the target rolling bearing, wherein the predicted state includes a normal state and a state to be analyzed.

[0042] The preset data threshold is a value determined based on various state data characteristics of the rolling bearing during normal operation, after a large number of experiments, data analysis, and actual operation experience, as a reference value for judging whether the rolling bearing is in normal operation. Correspondingly, when the state data exceeds the preset data threshold, it indicates that the operation state of the bearing may be abnormal.

[0043] The predicted state is a preliminary judgment and classification of the current operating state of the target rolling bearing based on the comparison results of the M state data sequences and the preset data threshold. The normal state indicates that the operating state of the target rolling bearing basically meets the characteristics of normal operation, and the state to be analyzed indicates that there are some abnormal conditions in the operating state of the target rolling bearing, and further analysis is required to clarify the fault condition of the target rolling bearing.

[0044] Optionally, the M state data sequences are compared with a preset data threshold to obtain a predicted state corresponding to the target rolling bearing, including: The time label corresponding to the i-th preset time period is determined as i, where i=1, 2, ..., M.

[0045] For the i-th state data sequence, if the maximum state data in the i-th state data sequence is greater than or equal to the preset data threshold, the time label i corresponding to the i-th state data sequence is determined as the target label.

[0046] Traverse all state data sequences and obtain all target labels.

[0047] If there are adjacent time labels in all target labels, the predicted state corresponding to the target rolling bearing is determined to be the state to be analyzed; otherwise, the predicted state corresponding to the target rolling bearing is determined to be the normal state.

[0048] If the maximum state data in the i-th state data sequence is greater than or equal to the preset data threshold, it means that the target rolling bearing has an abnormal condition within the i-th preset time period.

[0049] Furthermore, if there are adjacent time labels in all target labels, it means that the target rolling bearing has abnormal conditions for a continuous period of time, and the predicted state corresponding to the target rolling bearing is set as the state to be analyzed to further analyze and clarify the fault condition of the target rolling bearing.

[0050] As described above, a preliminary judgment is made on the operating state of the target rolling bearing quickly based on the collected state data and the preset data threshold, which provides a basis for subsequent fault detection.

[0051] S203, if the predicted state is the state to be analyzed, a reference data sequence of the target rolling bearing in the target time interval is obtained based on M state data sequences and the trained data prediction model, wherein the reference data sequence includes reference data corresponding to K preset time points, K>M×N.

[0052] Among them, the trained data prediction model is obtained by training with a large amount of historical state data of the rolling bearing. During the training process, various state data of the rolling bearing under normal operation and fault state can be used to allow the data prediction model to learn the inherent laws and change patterns between different state data to improve the generalization and accuracy of the trained data prediction model. For the state data sequence under the time series mode in this embodiment, the data prediction model can be a model structure such as a recurrent neural network, a long short-term memory network, etc.

[0053] Since there is a first preset time interval between any two adjacent preset time periods, that is, the acquisition device does not collect the state data of the target rolling bearing within the corresponding first preset time interval, it is difficult to characterize the complete working condition of the target rolling bearing within the target time interval only through M state data sequences. Therefore, based on the trained data prediction model, this embodiment predicts the state data of the target rolling bearing between any two adjacent preset time periods based on the M state data sequences obtained by acquisition, thereby completing the state data of the target rolling bearing within the target time interval, and obtaining a reference data sequence composed of reference data corresponding to K preset time points as the basis for fault detection of the target rolling bearing, so as to improve the accuracy of the fault detection result.

[0054] Optionally, a reference data sequence of a target rolling bearing within a target time interval is obtained according to the M state data sequences and the trained data prediction model, including: The M state data sequences are input into the trained data prediction model to obtain the prediction data sequence within any two adjacent preset time periods, wherein the preset data sequence includes the prediction data corresponding to Q preset time points.

[0055] The state data sequences within M preset time periods and the prediction data sequences within any two adjacent preset time periods are integrated to obtain a reference data sequence of the target rolling bearing within the target time interval.

[0056] Among them, since the first preset time interval T1 is equal to Q second preset time intervals T2, each prediction data sequence includes prediction data corresponding to Q preset time points. Furthermore, M state data sequences correspond to M-1 prediction data sequences. Therefore, the reference data sequence is obtained by integrating M×N state data and (M-1)×Q prediction data in chronological order, that is, K=M×N+(M-1)×Q.

[0057] As described above, on the basis of the trained data prediction model, the state data of the target rolling bearing between any two adjacent preset time periods is predicted based on the collected M state data sequences, thereby completing the state data of the target rolling bearing within the target time interval, providing richer and more detailed data support for subsequent more accurate judgment of the fault degree of the rolling bearing, and improving the accuracy of the fault detection results.

[0058] S204 , obtaining a gradient sequence and a current fault degree corresponding to the reference data sequence according to the reference data corresponding to K preset time points in the reference data sequence.

[0059] Among them, the gradient sequence can reflect the rate of change of the reference data between adjacent time points, that is, it reflects the changing trend of the state of the target rolling bearing within the current time range. The current fault degree reflects the fault situation of the target rolling bearing obtained by intuitive analysis based on the collected state data, which provides an important data basis for the subsequent judgment of the target fault degree of the target rolling bearing.

[0060] Optionally, obtaining a gradient sequence and a current fault degree corresponding to the reference data sequence according to the reference data corresponding to K preset time points in the reference data sequence includes: The 0th reference data is obtained, wherein the 0th reference data is equal to the 1st reference data.

[0061] According to the i-1th reference data and the i-th reference data in the reference data sequence, the i-th data gradient corresponding to the reference data sequence is obtained, where i=1, 2, ..., M.

[0062] According to the 1st, 2nd, ..., Mth data gradients corresponding to the reference data sequence, a gradient sequence corresponding to the reference data sequence is obtained.

[0063] Among them, the i-th data gradient D i =(A i -A i-1 ) / T2,A i is the i-th reference data, A i-1 is the i-1th reference data.

[0064] The calculated data gradients from the 1st to the Mth are arranged in chronological order to form a gradient sequence corresponding to the reference data sequence. The gradient sequence records the change rate information of the reference data between each adjacent time point, providing a data basis for analyzing the fault development of the target rolling bearing after the current time point.

[0065] Optionally, obtaining a gradient sequence and a current fault degree corresponding to the reference data sequence according to the reference data sequence also includes: The average value of the KPth reference data to the Kth reference data in the reference data sequence is determined as the target state data corresponding to the target rolling bearing.

[0066] According to the target state data and the preset data threshold, the current fault degree corresponding to the target rolling bearing is obtained.

[0067] Among them, in order to analyze the working status of the target rolling bearing at the current time point, this embodiment focuses on the reference data near the current time point. Therefore, the reference data from the KPth reference data to the Kth reference data in the reference data sequence are selected for average calculation to obtain the target status data to characterize the comprehensive status of the target rolling bearing in the recent period of time, so as to reduce the impact of data fluctuations and more accurately reflect the current operating status of the target rolling bearing.

[0068] The difference between the target state data and the preset data threshold is calculated, and the ratio of the difference to the preset data threshold is determined as the current fault degree corresponding to the reference data sequence. Correspondingly, the larger the target state data, the greater the current fault degree.

[0069] Among them, the P value determines the time range considered for analyzing the current fault level, and the specific value of P can be set by the implementer according to the actual situation.

[0070] As mentioned above, the gradient sequence and the current fault degree are analyzed from the reference data sequence, which not only reflects the rate of change of the reference data between adjacent time points, but also can characterize the working state of the target rolling bearing near the current time point, and provides rich data in real-time dimension and development dimension for judging the target fault degree of the target rolling bearing, thereby improving the accuracy of the fault detection results.

[0071] S205, obtaining the fault development degree corresponding to the target rolling bearing according to the gradient sequence corresponding to the reference data sequence.

[0072] Among them, a data gradient greater than 0 indicates that the corresponding reference data has an upward trend, and a data gradient less than 0 indicates that the corresponding reference data has a downward trend. Therefore, according to the data gradient in the gradient sequence, the change trend of the state data of the target rolling bearing can be analyzed, thereby measuring the degree of development of the fault of the target rolling bearing. Correspondingly, the larger the data gradient, the greater the fault severity trend of the target rolling bearing, that is, the more serious the fault condition of the target rolling bearing.

[0073] Optionally, obtaining the fault development degree corresponding to the target rolling bearing according to the gradient sequence corresponding to the reference data sequence includes: The ME th data gradient to the M th data gradient in the gradient sequence are respectively determined as the 1 th to the E+1 th reference gradients, where E is an integer greater than 1.

[0074] The preset development weights corresponding to the 1st to E+1th reference gradients are obtained respectively.

[0075] The preset development weights corresponding to the 1st to E+1th reference gradients and the 1st to E+1th reference gradients are respectively weighted calculated to obtain the fault development degree corresponding to the target rolling bearing.

[0076] Among them, in order to analyze the development of the working status of the target rolling bearing after the current time point, this embodiment focuses on the reference data near the current time point. Therefore, the data gradient from the MEth data gradient to the Mth data gradient in the gradient sequence is selected for analysis, and the corresponding preset development weights are assigned respectively, so as to perform weighted calculation on the preset development weights corresponding to the 1st to E+1th reference gradients and the 1st to E+1th reference gradients, respectively, to obtain the fault development degree corresponding to the target rolling bearing.

[0077] As time goes by, the preset development weight corresponding to the reference gradient gradually increases. The specific value of the preset development weight of each reference gradient can be set by the implementer according to the actual situation.

[0078] The E value determines the time range considered for analyzing the degree of fault development. The specific value of E can be set by the implementer based on actual conditions.

[0079] As described above, the fault development degree corresponding to the target rolling bearing is analyzed according to the gradient sequence corresponding to the reference data sequence, and the fault development of the target rolling bearing is characterized, which provides a data basis for accurately measuring the severity of the fault of the target rolling bearing.

[0080] S206, obtaining a target fault degree corresponding to the target rolling bearing according to the current fault degree and the fault development degree corresponding to the reference data sequence.

[0081] Among them, by referring to the current fault degree and fault development degree corresponding to the data sequence, the real-time fault state and fault development state of the target rolling bearing are analyzed, so as to more accurately characterize the fault condition of the target rolling bearing. Correspondingly, the greater the target fault degree, the higher the current fault degree of the rolling bearing and the subsequent fault severity, and the relevant early warning information of the target rolling bearing can be provided in time according to the target fault degree, so as to further improve the reliability and safety of the bearing system.

[0082] As described above, by referring to the current fault degree and gradient sequence corresponding to the data sequence, the real-time fault state and fault development state of the target rolling bearing are analyzed, thereby improving the detection accuracy of the target fault degree of the target rolling bearing.

[0083] The embodiment of the present invention makes a preliminary judgment on the operating state of the target rolling bearing through the collected state data and the preset data threshold. When it is judged that the target rolling bearing has an abnormal situation, the state data of the target rolling bearing between any two adjacent preset time periods is predicted based on the collected M state data sequences and the trained data prediction model, so as to complete the state data of the target rolling bearing in the target time interval, and analyze the gradient sequence and the current fault degree from the completed reference data sequence, analyze the real-time fault state and the development state of the fault of the target rolling bearing, and provide rich data of real-time dimension and development dimension to obtain the target fault degree, thereby improving the accuracy of the fault detection result.

[0084] Corresponding to the rolling bearing fault detection method of the above embodiment, Figure 3 A structural block diagram of a rolling bearing fault detection device provided in a second embodiment of the present invention is given. For ease of description, only the parts related to the embodiment of the present invention are shown.

[0085] See also Figure 3 , the rolling bearing fault detection device comprises: The data acquisition module 31 is used to acquire a state data sequence of a target rolling bearing within M preset time periods of a target time interval, wherein each state data sequence includes state data corresponding to N preset time points, and M and N are integers greater than 1.

[0086] The state prediction module 32 is used to compare the M state data sequences with a preset data threshold to obtain a predicted state corresponding to the target rolling bearing, wherein the predicted state includes a normal state and a state to be analyzed.

[0087] The data prediction module 33 is used to obtain a reference data sequence of the target rolling bearing within the target time interval based on M state data sequences and a trained data prediction model if the predicted state is a state to be analyzed, wherein the reference data sequence includes reference data corresponding to K preset time points, K>M×N.

[0088] The data analysis module 34 is used to obtain the gradient sequence and the current fault degree corresponding to the reference data sequence according to the reference data sequence.

[0089] The fault analysis module 35 is used to obtain the fault development degree corresponding to the target rolling bearing according to the gradient sequence corresponding to the reference data sequence.

[0090] The fault detection module 36 is used to obtain a target fault degree corresponding to the target rolling bearing according to the current fault degree and fault development degree corresponding to the target rolling bearing.

[0091] Optionally, the state prediction module 32 includes: The time number determination submodule is used to determine the time number corresponding to the i-th preset time period as i, where i=1, 2, ..., M.

[0092] The target label determination submodule is used to determine, for the i-th state data sequence, if the maximum state data in the i-th state data sequence is greater than or equal to a preset data threshold, then determine the time label i corresponding to the i-th state data sequence as the target label.

[0093] The data sequence traversal submodule is used to traverse all state data sequences and obtain all target labels.

[0094] The state prediction submodule is used to determine that the predicted state corresponding to the target rolling bearing is the state to be analyzed if there are adjacent time labels in all target labels, otherwise, determine that the predicted state corresponding to the target rolling bearing is the normal state.

[0095] Optionally, the data prediction module 33 includes: The data prediction submodule is used to input M state data sequences into the trained data prediction model to obtain the predicted data sequence within any two adjacent preset time periods, wherein the preset data sequence includes the predicted data corresponding to Q preset time points.

[0096] The data integration submodule is used to integrate the state data sequences within M preset time periods and the prediction data sequences within any two adjacent preset time periods to obtain a reference data sequence of the target rolling bearing within the target time interval.

[0097] Optionally, the data analysis module 34 includes: The reference data setting submodule is used to obtain the 0th reference data, wherein the 0th reference data is equal to the 1st reference data.

[0098] The data gradient calculation submodule is used to obtain the i-th data gradient corresponding to the reference data sequence according to the i-1-th reference data and the i-th reference data in the reference data sequence, where i=1, 2, ..., M.

[0099] The gradient sequence acquisition submodule is used to obtain a gradient sequence corresponding to the reference data sequence according to the 1st, 2nd, ..., Mth data gradients corresponding to the reference data sequence.

[0100] Optionally, the data analysis module 34 further includes: The target state data determination submodule is used to determine the average value of the KPth reference data to the Kth reference data in the reference data sequence as the target state data corresponding to the target rolling bearing, wherein P is an integer greater than 1.

[0101] The current fault degree acquisition submodule is used to obtain the current fault degree corresponding to the target rolling bearing according to the target state data and the preset data threshold.

[0102] Optionally, the fault analysis module 35 includes: The reference gradient acquisition submodule is used to determine the ME-th data gradient to the M-th data gradient in the gradient sequence as the 1st to the E+1th reference gradients, respectively, where E is an integer greater than 1.

[0103] The preset development weight acquisition submodule is used to obtain the preset development weights corresponding to the 1st to E+1th reference gradients respectively.

[0104] The fault development degree acquisition submodule is used to perform weighted calculation on the preset development weights corresponding to the 1st to E+1th reference gradients and the 1st to E+1th reference gradients, respectively, to obtain the fault development degree corresponding to the target rolling bearing.

[0105] It should be noted that the information interaction, execution process and other contents between the above modules are based on the same concept as the embodiment of the method of the present invention. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0106] Figure 4This is a schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention. Figure 4 As shown, the computer device of this embodiment includes: at least one processor ( Figure 4 Only one is shown in the figure), a memory, and a computer program stored in the memory and executable on at least one processor, wherein when the processor executes the computer program, the steps in any of the above rolling bearing fault detection method embodiments are implemented.

[0107] The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that Figure 4 This is merely an example of a computer device and does not constitute a limitation on the computer device. The computer device may include more or fewer components than those shown in the figure, or a combination of certain components, or different components. For example, it may also include a network interface, a display screen, and an input device.

[0108] The processor may be a CPU, or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0109] The memory includes a readable storage medium, an internal memory, etc., wherein the internal memory may be the memory of a computer device, and the internal memory provides an environment for the operation of the operating system and computer-readable instructions in the readable storage medium. The readable storage medium may be a hard disk of a computer device, and in other embodiments, it may also be an external storage device of the computer device, for example, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device. Further, the memory may also include both an internal storage unit of the computer device and an external storage device. The memory is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of a computer program, etc. The memory may also be used to temporarily store data that has been output or is to be output.

[0110] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The specific working process of the units and modules in the above-mentioned device can refer to the corresponding process in the above-mentioned method embodiment, which will not be repeated here. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiment can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying computer program code, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0111] The present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by a computer program product. When the computer program product runs on a computer device, the computer device can implement the steps in the above-mentioned method embodiment when executing.

[0112] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0113] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0114] In the embodiments provided by the present invention, it should be understood that the disclosed devices / computer equipment and methods can be implemented in other ways. For example, the device / computer equipment embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0115] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0116] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A rolling bearing fault detection method, characterized in that: The rolling bearing fault detection method comprises: Acquire a state data sequence of a target rolling bearing within M preset time periods of a target time interval, wherein each state data sequence includes state data corresponding to N preset time points, and M and N are integers greater than 1; Compare the M state data sequences with a preset data threshold to obtain a predicted state corresponding to the target rolling bearing, wherein the predicted state includes a normal state and a state to be analyzed; If the predicted state is a state to be analyzed, a reference data sequence of the target rolling bearing in the target time interval is obtained according to the M state data sequences and the trained data prediction model, wherein the reference data sequence includes reference data corresponding to K preset time points, K>M×N; According to the reference data sequence, a gradient sequence and a current fault degree corresponding to the reference data sequence are obtained; Obtaining the fault development degree corresponding to the target rolling bearing according to the gradient sequence corresponding to the reference data sequence; According to the current fault degree and fault development degree corresponding to the target rolling bearing, the target fault degree corresponding to the target rolling bearing is obtained.

2. The rolling bearing fault detection method according to claim 1, characterized in that: The step of comparing the M state data sequences with a preset data threshold to obtain a predicted state corresponding to the target rolling bearing includes: The time label corresponding to the i-th preset time period is determined as i, where i=1, 2, ..., M; For the i-th state data sequence, if the maximum state data in the i-th state data sequence is greater than or equal to the preset data threshold, then determining the time label i corresponding to the i-th state data sequence as the target label; Traverse all state data sequences and obtain all target labels; If there are adjacent time labels among all the target labels, the predicted state corresponding to the target rolling bearing is determined to be the state to be analyzed; otherwise, the predicted state corresponding to the target rolling bearing is determined to be the normal state.

3. The rolling bearing fault detection method according to claim 1, characterized in that: The time interval between any two adjacent preset time periods is a first preset time interval T1, and the time interval between any two adjacent preset time points is a second preset time interval T2, wherein T1=Q×T2, and Q is an integer greater than 1.

4. The rolling bearing fault detection method according to claim 3, characterized in that: The step of obtaining a reference data sequence of the target rolling bearing within the target time interval according to the M state data sequences and the trained data prediction model includes: Inputting M state data sequences into the trained data prediction model to obtain prediction data sequences within any two adjacent preset time periods, wherein the preset data sequences include prediction data corresponding to Q preset time points; The state data sequences within M preset time periods and the prediction data sequences within any two adjacent preset time periods are integrated to obtain a reference data sequence of the target rolling bearing within the target time interval.

5. The rolling bearing fault detection method according to claim 1, characterized in that: The step of obtaining a gradient sequence and a current fault degree corresponding to the reference data sequence according to the reference data sequence includes: Obtaining the 0th reference data, wherein the 0th reference data is equal to the 1st reference data; According to the i-1th reference data and the i-th reference data in the reference data sequence, obtaining the i-th data gradient corresponding to the reference data sequence, where i=1, 2, ..., M; According to the 1st, 2nd, ..., Mth data gradients corresponding to the reference data sequence, a gradient sequence corresponding to the reference data sequence is obtained.

6. The rolling bearing fault detection method according to claim 5, characterized in that: The step of obtaining the gradient sequence and the current fault degree corresponding to the reference data sequence according to the reference data sequence further includes: Determine the average value of the KPth reference data to the Kth reference data in the reference data sequence as the target state data corresponding to the target rolling bearing, wherein P is an integer greater than 1; According to the target state data and the preset data threshold, the current fault degree corresponding to the target rolling bearing is obtained.

7. The rolling bearing fault detection method according to claim 5, characterized in that: The step of obtaining the fault development degree corresponding to the target rolling bearing according to the gradient sequence corresponding to the reference data sequence includes: Determine the ME th data gradient to the M th data gradient in the gradient sequence as the 1 th to the E+1 th reference gradients, respectively, where E is an integer greater than 1; Obtaining the preset development weights corresponding to the 1st to E+1th reference gradients respectively; The preset development weights corresponding to the 1st to E+1th reference gradients and the 1st to E+1th reference gradients are respectively weighted calculated to obtain the fault development degree corresponding to the target rolling bearing.

8. A rolling bearing fault detection device, characterized in that: The rolling bearing fault detection device comprises: A data acquisition module, used to acquire a state data sequence of a target rolling bearing within M preset time periods of a target time interval, wherein each state data sequence includes state data corresponding to N preset time points, and M and N are integers greater than 1; A state prediction module, used for comparing the M state data sequences with a preset data threshold value to obtain a predicted state corresponding to the target rolling bearing, wherein the predicted state includes a normal state and a state to be analyzed; A data prediction module, for obtaining a reference data sequence of the target rolling bearing within the target time interval according to M state data sequences and a trained data prediction model if the predicted state is a state to be analyzed, wherein the reference data sequence includes reference data corresponding to K preset time points, K>M×N; A data analysis module, used for obtaining a gradient sequence and a current fault degree corresponding to the reference data sequence according to the reference data sequence; A fault analysis module, used for obtaining the fault development degree corresponding to the target rolling bearing according to the gradient sequence corresponding to the reference data sequence; The fault detection module is used to obtain the target fault degree corresponding to the target rolling bearing according to the current fault degree and fault development degree corresponding to the target rolling bearing.

9. A computer device, characterized in that: The computer device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the rolling bearing fault detection method according to any one of claims 1 to 7 is implemented.

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

Images