Railway bearing health monitoring method, device, system, terminal and storage medium

Abstract

The present invention provides a railway bearing health monitoring method, device, system, terminal, and storage medium. The railway bearing health monitoring method comprises: obtaining the original vibration signal of the rolling bearing to be monitored; using a cyclic envelope empirical Fourier decomposition method to determine health index data of the rolling bearing to be monitored based on the original vibration signal; performing fault diagnosis on the rolling bearing to be monitored based on the health index data to obtain a fault diagnosis result for the rolling bearing to be monitored; and predicting the remaining life of the rolling bearing to be monitored based on the health index data to obtain a remaining life prediction result for the rolling bearing to be monitored. The present invention can accurately determine the health status and service life of the rolling bearing, promote the development of intelligent operation and maintenance systems, and avoid the large amount of resource waste caused by regular maintenance.

Description

Technical Field

[0001] The present invention relates to the technical field of bearing health monitoring, and in particular to a railway bearing health monitoring method, device, system, terminal and storage medium. Background Art

[0002] As one of the key rotating components of the running gear, rolling bearings are prone to various types of failures due to their harsh and complex working environment, which can lead to equipment abnormalities and even major safety accidents, resulting in serious casualties and economic losses.

[0003] For a long time, rolling bearing maintenance has been dominated by excessive maintenance, with regular inspections and forced scrapping, resulting in a significant waste of resources. Therefore, accurately determining the health and service life of rolling bearings and promoting the development of intelligent operation and maintenance systems are urgent issues that need to be addressed. Summary of the Invention

[0004] Embodiments of the present invention provide a railway bearing health monitoring method, device, system, terminal and storage medium to solve the current problem of being unable to accurately determine the health status and service life of rolling bearings, resulting in a large amount of resource waste.

[0005] In a first aspect, an embodiment of the present invention provides a railway bearing health monitoring method, comprising:

[0006] Obtaining the original vibration signal of the rolling bearing to be monitored;

[0007] The health index data of the rolling bearing to be monitored is determined based on the original vibration signal using the cyclic envelope empirical Fourier decomposition method.

[0008] According to the health indicator data, the rolling bearing to be monitored is diagnosed for faults, and the fault diagnosis results of the rolling bearing to be monitored are obtained;

[0009] The remaining life of the rolling bearing to be monitored is predicted based on the health indicator data to obtain a remaining life prediction result of the rolling bearing to be monitored.

[0010] In one possible implementation, a cyclic envelope empirical Fourier decomposition method is used to determine the health indicator data of the rolling bearing to be monitored based on the original vibration signal, including:

[0011] Perform fast Fourier transform on the original vibration signal to obtain the corresponding signal spectrum;

[0012] Cyclic envelope is performed on the signal spectrum to obtain a spectrum envelope curve;

[0013] Performing frequency band division on the spectrum envelope curve to obtain multiple frequency band envelope curves;

[0014] A zero-phase filter is constructed and the inverse fast Fourier transform is used to reconstruct the envelope curve of each frequency band to obtain multiple single-component signals.

[0015] Based on multiple single-component signals, health indicator data of the rolling bearing to be monitored is determined.

[0016] In one possible implementation, the single-component signal includes a component time-domain waveform and a component envelope curve;

[0017] Accordingly, based on the multiple single-component signals, the health indicator data of the rolling bearing to be monitored is determined, including:

[0018] Based on the time domain waveform and envelope curve of each component, the health index data of the rolling bearing to be monitored is determined.

[0019] In one possible implementation, the remaining life of the rolling bearing to be monitored is predicted based on the health indicator data, and the remaining life prediction result of the rolling bearing to be monitored is obtained, including:

[0020] The health indicator data is input into the pre-trained bidirectional long short-term memory DA-BLSTM network model based on the attention mechanism to obtain the remaining life prediction results of the rolling bearing to be monitored.

[0021] In one possible implementation, before inputting the health indicator data into a pre-trained attention-based bidirectional long short-term memory (DA-BLSTM) network model to obtain the remaining life prediction result of the rolling bearing to be monitored, the following steps are also included:

[0022] Obtain a health indicator data sample set, the health indicator data sample set including a plurality of health indicator sample data with marked remaining lifespan;

[0023] The clustering and classification GRACC method based on grey correlation was used to cluster the health indicator data sample set and obtain multiple clusters;

[0024] For each cluster, the cluster is divided into a training set and a test set. The pre-built DA-BLSTM network model is trained separately based on the training set corresponding to the cluster, and the trained DA-BLSTM network model is tested separately based on the test set corresponding to the cluster to obtain a pre-trained DA-BLSTM network model.

[0025] In one possible implementation, the DA-BLSTM network model includes a first convolutional layer, a second convolutional layer, a first maximum pooling layer, a third convolutional layer, a second maximum pooling layer, an input attention layer, a bidirectional LSTM layer, a directional attention layer, and a fully connected layer, which are connected in sequence.

[0026] In a second aspect, an embodiment of the present invention provides a railway bearing health monitoring device, comprising:

[0027] An acquisition module, used for acquiring the original vibration signal of the rolling bearing to be monitored;

[0028] A health index data extraction module is used to determine the health index data of the rolling bearing to be monitored based on the original vibration signal using a cyclic envelope empirical Fourier decomposition method;

[0029] A fault diagnosis module is used to perform fault diagnosis on the rolling bearing to be monitored based on the health indicator data and obtain a fault diagnosis result of the rolling bearing to be monitored;

[0030] The life prediction module is used to predict the remaining life of the rolling bearing to be monitored based on the health indicator data, and obtain the remaining life prediction result of the rolling bearing to be monitored.

[0031] In a third aspect, an embodiment of the present invention provides a terminal comprising a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the railway bearing health monitoring method as described in the first aspect or any possible implementation of the first aspect.

[0032] In a fourth aspect, an embodiment of the present invention provides a railway bearing health monitoring system, comprising an accelerometer, an acquisition card, a power adapter, and the terminal as described in the third aspect;

[0033] The accelerometer is connected to the GPIO port of the terminal through the acquisition card; the power adapter is connected to the power interface of the terminal;

[0034] Among them, the terminal is Raspberry Pi.

[0035] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the railway bearing health monitoring method as described in the first aspect or any possible implementation of the first aspect.

[0036] Embodiments of the present invention provide a railway bearing health monitoring method, device, system, terminal and storage medium, which obtain the original vibration signal of the rolling bearing to be monitored; adopt the cyclic envelope empirical Fourier decomposition method to determine the health index data of the rolling bearing to be monitored according to the original vibration signal; diagnose the fault of the rolling bearing to be monitored based on the health index data to obtain the fault diagnosis result of the rolling bearing to be monitored; predict the remaining life of the rolling bearing to be monitored based on the health index data to obtain the remaining life prediction result of the rolling bearing to be monitored, which can accurately judge the health status and service life of the rolling bearing, promote the development of intelligent operation and maintenance systems, and avoid a large amount of resource waste caused by regular maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 any creative work.

[0038] Figure 1 1 is a flow chart of a railway bearing health monitoring method provided by an embodiment of the present invention;

[0039] Figure 2 Schematic diagram of the structure of a railway bearing health monitoring device provided by an embodiment of the present invention;

[0040] Figure 3 is a schematic diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In the following description, specific details such as particular system structures and techniques are provided for purposes of illustration, not limitation, to facilitate a thorough understanding of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

[0042] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below with reference to the accompanying drawings.

[0043] See also Figure 1 , which shows a flow chart for implementing a railway bearing health monitoring method provided by an embodiment of the present invention. The railway bearing health monitoring method may be executed by a terminal, which may be a Raspberry Pi.

[0044] See also Figure 1, the above railway bearing health monitoring method includes:

[0045] In S101 , an original vibration signal of the rolling bearing to be monitored is obtained.

[0046] The raw vibration signal of the rolling bearing to be monitored can be collected by an accelerometer attached to the axle box. The accelerometer can be an IEPE (Integrated Electronics Piezo Electric) accelerometer, which can generate the vibration signal data required to analyze the corresponding characteristics and damage characteristics of the motor current signal.

[0047] In S102, a cyclic envelope empirical Fourier decomposition method is used to determine health indicator data of the rolling bearing to be monitored according to the original vibration signal.

[0048] The health indicator data of the rolling bearing to be monitored includes relevant indicator data that can be used to perform health monitoring on the rolling bearing to be monitored. The health indicator data of the rolling bearing to be monitored can be obtained based on the original vibration signal using a cyclic envelope empirical Fourier decomposition method.

[0049] In S103, a fault diagnosis is performed on the rolling bearing to be monitored based on the health indicator data to obtain a fault diagnosis result of the rolling bearing to be monitored.

[0050] This embodiment does not impose any specific restrictions on the means for performing fault diagnosis on the rolling bearing to be monitored based on the health indicator data to obtain the fault diagnosis result of the rolling bearing to be monitored. Any feasible means may be used.

[0051] For example, the health indicator data can be input into a pre-trained fault diagnosis model to obtain a fault diagnosis result for the rolling bearing to be monitored. The fault diagnosis model can be a convolutional neural network model, a random forest model, etc.

[0052] The fault diagnosis result of the rolling bearing to be monitored may be healthy, slightly faulty or seriously faulty. The fault diagnosis result of the rolling bearing to be monitored may also include the fault type, etc.

[0053] In S104, the remaining life of the rolling bearing to be monitored is predicted based on the health indicator data to obtain a remaining life prediction result of the rolling bearing to be monitored.

[0054] This embodiment can also predict the remaining life of the rolling bearing to be monitored based on the health indicator data of the rolling bearing to be monitored, and obtain a remaining life prediction result of the rolling bearing to be monitored, that is, how long it can be used.

[0055] In some possible implementations, the above S104 may include:

[0056] If the fault diagnosis result of the rolling bearing to be monitored is healthy (ie, no fault), the remaining life of the rolling bearing to be monitored is predicted based on the health indicator data to obtain a remaining life prediction result of the rolling bearing to be monitored.

[0057] This embodiment obtains the original vibration signal of the rolling bearing to be monitored; adopts the cyclic envelope empirical Fourier decomposition method to determine the health index data of the rolling bearing to be monitored according to the original vibration signal; performs fault diagnosis on the rolling bearing to be monitored according to the health index data to obtain the fault diagnosis result of the rolling bearing to be monitored; predicts the remaining life of the rolling bearing to be monitored according to the health index data to obtain the remaining life prediction result of the rolling bearing to be monitored, which can accurately judge the health status and service life of the rolling bearing, promote the development of the intelligent operation and maintenance system, and avoid a large amount of resource waste caused by regular maintenance.

[0058] In some embodiments, the above S102 may include:

[0059] Perform fast Fourier transform on the original vibration signal to obtain the corresponding signal spectrum;

[0060] Cyclic envelope is performed on the signal spectrum to obtain a spectrum envelope curve;

[0061] Performing frequency band division on the spectrum envelope curve to obtain multiple frequency band envelope curves;

[0062] A zero-phase filter is constructed and the inverse fast Fourier transform is used to reconstruct the envelope curve of each frequency band to obtain multiple single-component signals.

[0063] Based on multiple single-component signals, health indicator data of the rolling bearing to be monitored is determined.

[0064] In some possible implementations, the above-mentioned frequency band segmentation of the spectrum envelope curve to obtain multiple frequency band envelope curves may include:

[0065] A local maximum-minimum value (localmaxmin) segmentation technique or an improved local maximum-minimum value (localmaxmin) segmentation technique is used to perform frequency band segmentation on the spectrum envelope curve to obtain multiple frequency band envelope curves.

[0066] This embodiment can perform a fast Fourier transform (FFT) on the original vibration signal to obtain a corresponding signal spectrum; perform cyclic envelope on the signal spectrum to obtain a spectrum envelope curve, which can reduce the number of useless extreme points and suppress the interference of noise on the components; use an improved local maximum and minimum value segmentation technology to perform frequency band segmentation on the spectrum envelope curve to obtain spectrum segmentation boundaries, and based on the spectrum segmentation boundaries, obtain multiple frequency band envelope curves; construct a zero-phase filter, and use an inverse fast Fourier transform (IFFT) to reconstruct the signal of each frequency band envelope curve to obtain multiple single-component signals with instantaneous frequencies and physical meanings; analyze the multiple single-component signals, and construct health indicator data of the rolling bearing to be monitored.

[0067] Among them, based on multiple single-component signals, the health indicator data of the rolling bearing to be monitored can be determined using existing technologies, and no specific restrictions are made here.

[0068] In some embodiments, the single component signal includes a component time domain waveform and a component envelope curve;

[0069] Accordingly, the above-mentioned determination of the health indicator data of the rolling bearing to be monitored based on multiple single-component signals includes:

[0070] Based on the time domain waveform and envelope curve of each component, the health index data of the rolling bearing to be monitored is determined.

[0071] This embodiment can analyze the time domain waveform of each component and the envelope curve of each component, and construct health index data based on them.

[0072] In some embodiments, the above S104 may include:

[0073] The health indicator data is input into a pre-trained attention-based bidirectional long short-term memory (DA-BLSTM) network model to obtain the remaining life prediction results of the rolling bearing to be monitored.

[0074] In some embodiments, before inputting the health indicator data into a pre-trained attention-based bidirectional long short-term memory (DA-BLSTM) network model to obtain the remaining life prediction result of the rolling bearing to be monitored, the method further includes:

[0075] Obtain a health indicator data sample set, the health indicator data sample set including a plurality of health indicator sample data with marked remaining lifespan;

[0076] The GRA-based Clustering and Classifying (GRACC) method was used to cluster the health indicator data sample set and obtain multiple clusters.

[0077] For each cluster, the cluster is divided into a training set and a test set. The pre-built DA-BLSTM network model is trained separately based on the training set corresponding to the cluster, and the trained DA-BLSTM network model is tested separately based on the test set corresponding to the cluster to obtain a pre-trained DA-BLSTM network model.

[0078] Among them, GRACC is a clustering and classification method based on GRA (Grey Relation Analysis).

[0079] This embodiment can cluster the health indicator data sample set using the GRACC method to obtain multiple clusters, making the similarity within each cluster as large as possible. For example, it can be divided into three clusters, namely a healthy cluster, a minor fault cluster, and a major fault cluster.

[0080] Each cluster is divided into a training set and a test set. For example, 80% of each cluster is used as a training set and 20% as a test set. Existing training methods can be used to train each cluster separately based on the training set and test set corresponding to each cluster, and finally a pre-trained DA-BLSTM network model is obtained.

[0081] In some embodiments, the DA-BLSTM network model includes a first convolutional layer, a second convolutional layer, a first maximum pooling layer, a third convolutional layer, a second maximum pooling layer, an input attention layer, a bidirectional LSTM (Long Short-term Memory) layer, a directional attention layer, and a fully connected layer, which are connected in sequence.

[0082] In this embodiment, the input data size of the DA-BLSTM network model can be 400*1.

[0083] 1) The input data passes through two 1*1 convolutional layers (i.e., the first convolutional layer and the second convolutional layer), and then passes through the maximum pooling layer (i.e., the first maximum pooling layer), obtaining feature data of 400*16, 400*32, and 50*32 respectively;

[0084] 2) The 50*32 feature data obtained in step 1) is sequentially passed through a 1*1 convolutional layer (i.e., the third convolutional layer) and a maximum pooling layer (i.e., the second maximum pooling layer), and the process is repeated three times to obtain 12*64, 6*256, and 6*512 feature data respectively;

[0085] 3) The 6*512 feature data obtained in step 2) is input into the attention layer to obtain 6*256 feature data;

[0086] 4) The 6*256 feature data obtained in step 3) is passed through the bidirectional LSTM layer to obtain 6*32 feature data respectively;

[0087] 5) The 6*32 feature data obtained in step 4) is passed through the directional attention layer to finally obtain 1*16 feature data;

[0088] 6) The 1*16 feature data obtained in step 5) is passed through the fully connected layer to finally obtain 1*6 data.

[0089] The railway bearing health monitoring method provided in this application can realize the service performance evaluation and status prediction of rolling bearings under complex operating conditions, and develop a monitoring method that integrates detection, diagnosis, and prediction. It is of great significance to guiding the operation and maintenance of rolling bearings, and can achieve high automation and accuracy.

[0090] This application adopts PHM (Prognostics and Health Management) technology, which refers to the use of sensors to collect system data information, and the use of information technology and artificial intelligence reasoning algorithms to evaluate, monitor and manage the health status of the system, predict system failures before the system fails, and combine existing resource information to provide a series of maintenance and guarantee suggestions or decisions. It is a comprehensive technology that integrates fault detection, isolation, health assessment, prediction and maintenance decision-making. It is also an important technology that needs to be used in the study of intelligent operation and maintenance of rolling bearings. The core of PHM is to use a large number of high-end sensors to widely collect data that can reflect the operating status of rolling bearings. Then, based on the collected data, with the help of various scientific algorithms, the cause of the fault is found, the location of the fault is determined, the remaining life of the rolling bearing is predicted, and visualization is achieved, thereby making the health management of rolling bearings more convenient.

[0091] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order 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.

[0092] The following are device embodiments of the present invention. For details not fully described therein, reference may be made to the corresponding method embodiments described above.

[0093] Figure 2 The following is a schematic diagram of the structure of a railway bearing health monitoring device provided by an embodiment of the present invention. For ease of explanation, only the parts related to the embodiment of the present invention are shown, which are described in detail as follows:

[0094] like Figure 2 As shown, the railway bearing health monitoring device 30 may include: an acquisition module 31 , a health indicator data extraction module 32 , a fault diagnosis module 33 and a life prediction module 34 .

[0095] An acquisition module 31 is used to acquire an original vibration signal of the rolling bearing to be monitored;

[0096] The health index data extraction module 32 is used to determine the health index data of the rolling bearing to be monitored according to the original vibration signal by using the cyclic envelope empirical Fourier decomposition method;

[0097] A fault diagnosis module 33 is used to perform fault diagnosis on the rolling bearing to be monitored based on the health indicator data and obtain a fault diagnosis result of the rolling bearing to be monitored;

[0098] The life prediction module 34 is used to predict the remaining life of the rolling bearing to be monitored based on the health indicator data, and obtain a remaining life prediction result of the rolling bearing to be monitored.

[0099] In one possible implementation, the health indicator data extraction module 32 is specifically configured to:

[0100] Perform fast Fourier transform on the original vibration signal to obtain the corresponding signal spectrum;

[0101] Cyclic envelope is performed on the signal spectrum to obtain a spectrum envelope curve;

[0102] Performing frequency band division on the spectrum envelope curve to obtain multiple frequency band envelope curves;

[0103] A zero-phase filter is constructed and the inverse fast Fourier transform is used to reconstruct the envelope curve of each frequency band to obtain multiple single-component signals.

[0104] Based on multiple single-component signals, health indicator data of the rolling bearing to be monitored is determined.

[0105] In one possible implementation, in the health indicator data extraction module 32 , the single component signal includes a component time domain waveform and a component envelope curve;

[0106] Accordingly, based on the multiple single-component signals, the health indicator data of the rolling bearing to be monitored is determined, including:

[0107] Based on the time domain waveform and envelope curve of each component, the health index data of the rolling bearing to be monitored is determined.

[0108] In one possible implementation, the lifespan prediction module 34 is specifically configured to:

[0109] The health indicator data is input into the pre-trained bidirectional long short-term memory DA-BLSTM network model based on the attention mechanism to obtain the remaining life prediction results of the rolling bearing to be monitored.

[0110] In a possible implementation, the lifespan prediction module 34 is further configured to:

[0111] Before inputting the health indicator data into a pre-trained bidirectional long short-term memory (DA-BLSTM) network model based on an attention mechanism to obtain the remaining life prediction result of the rolling bearing to be monitored, a health indicator data sample set is obtained. The health indicator data sample set includes multiple health indicator sample data with marked remaining life;

[0112] The clustering and classification GRACC method based on grey correlation was used to cluster the health indicator data sample set and obtain multiple clusters;

[0113] For each cluster, the cluster is divided into a training set and a test set. The pre-built DA-BLSTM network model is trained separately based on the training set corresponding to the cluster, and the trained DA-BLSTM network model is tested separately based on the test set corresponding to the cluster to obtain a pre-trained DA-BLSTM network model.

[0114] In one possible implementation, the DA-BLSTM network model includes a first convolutional layer, a second convolutional layer, a first maximum pooling layer, a third convolutional layer, a second maximum pooling layer, an input attention layer, a bidirectional LSTM layer, a directional attention layer, and a fully connected layer, which are connected in sequence.

[0115] Figure 3 Schematic diagram of a terminal provided by an embodiment of the present invention. Figure 3 As shown, the terminal 4 of this embodiment includes: a processor 40 and a memory 41. The memory 41 is used to store a computer program 42, and the processor 40 is used to call and run the computer program 42 stored in the memory 41 to perform the steps in the above-mentioned embodiments of the railway bearing health monitoring method, such as Figure 1 Alternatively, the processor 40 is used to call and run the computer program 42 stored in the memory 41 to implement the functions of each module / unit in the above-mentioned device embodiments, such as Figure 2 Functions of the modules / units 31 to 34 are shown.

[0116] Exemplarily, the computer program 42 may be divided into one or more modules / units, which are stored in the memory 41 and executed by the processor 40 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 42 in the terminal 4. For example, the computer program 42 may be divided into Figure 2 Modules / units 31 to 34 are shown.

[0117] The terminal 4 may be a computer, a server, a Raspberry Pi or other computing device. The terminal 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will understand that Figure 3 It is only an example of terminal 4 and does not constitute a limitation on terminal 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0118] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0119] The memory 41 may be an internal storage unit of the terminal 4, such as a hard disk or memory of the terminal 4. The memory 41 may also be an external storage device of the terminal 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash memory card, etc. equipped on the terminal 4. Furthermore, the memory 41 may include both an internal storage unit of the terminal 4 and an external storage device. The memory 41 is used to store the computer program and other programs and data required by the terminal. The memory 41 may also be used to temporarily store data that has been output or is about to be output.

[0120] Corresponding to the above-mentioned terminal, an embodiment of the present application further provides a railway bearing health monitoring system, comprising an accelerometer, an acquisition card, a power adapter and the above-mentioned terminal;

[0121] The accelerometer is connected to the GPIO (General-purpose input / output) port of the terminal through the acquisition card; the power adapter is connected to the power interface of the terminal;

[0122] Among them, the terminal is Raspberry Pi.

[0123] The accelerometer is connected directly to the acquisition card. A BNC to UNF10-32 cable can be used to connect the accelerometer and acquisition card. The acquisition card is connected directly to the terminal's built-in GPIO port. A 2x20 socket with an extension lead can be used to connect the acquisition card and the terminal's built-in GPIO port.

[0124] The accelerometer can be an IEPE accelerometer. The acquisition card can be an MCC172 acquisition card. The Raspberry Pi can be a Raspberry Pi 4 Model B, with a Linux operating system installed. The system includes a central processing unit (CPU), memory connected to the CPU, an SD card, a Wi-Fi module, a power port, and GPIO ports. The power adapter can be a 5V-1500mA power adapter.

[0125] Compared with traditional rolling bearing fault detection methods, this embodiment only needs to use Raspberry Pi and related sensor peripherals to build a monitoring system to achieve complex functions such as data collection, status monitoring, fault diagnosis, and life prediction, which greatly reduces costs and realizes complex functions at a low cost.

[0126] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be 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 one processing unit, or each unit can exist physically alone, 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 this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0127] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0128] 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. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0129] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical functional division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices or units, and can be electrical, mechanical, or other forms.

[0130] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0131] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0132] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the processes in the above-mentioned embodiment method by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned railway bearing health monitoring method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media does not include electric carrier signals and telecommunication signals.

[0133] The embodiments described above 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 they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A railway bearing health monitoring method, characterized in that: include: Obtaining the original vibration signal of the rolling bearing to be monitored; Determining the health index data of the rolling bearing to be monitored according to the original vibration signal using a cyclic envelope empirical Fourier decomposition method; Performing fault diagnosis on the rolling bearing to be monitored based on the health indicator data to obtain a fault diagnosis result of the rolling bearing to be monitored; Predicting the remaining life of the rolling bearing to be monitored based on the health indicator data to obtain a remaining life prediction result of the rolling bearing to be monitored; The method of using a cyclic envelope empirical Fourier decomposition method to determine the health indicator data of the rolling bearing to be monitored according to the original vibration signal includes: Performing a fast Fourier transform on the original vibration signal to obtain a corresponding signal spectrum; Cyclic enveloping the signal spectrum to obtain a spectrum envelope curve; Performing frequency band division on the spectrum envelope curve to obtain multiple frequency band envelope curves; Constructing a zero-phase filter and reconstructing the envelope curve of each frequency band using an inverse fast Fourier transform to obtain a plurality of single-component signals; the single-component signals include a component time domain waveform and a component envelope curve; Determining health indicator data of the rolling bearing to be monitored based on the multiple single-component signals; Predicting the remaining life of the rolling bearing to be monitored based on the health indicator data to obtain a remaining life prediction result of the rolling bearing to be monitored includes: The health indicator data is input into a pre-trained bidirectional long short-term memory DA-BLSTM network model based on the attention mechanism to obtain the remaining life prediction result of the rolling bearing to be monitored.

2. The railway bearing health monitoring method according to claim 1, characterized in that: Determining the health indicator data of the rolling bearing to be monitored based on the multiple single-component signals includes: Based on the time domain waveform of each component and the envelope curve of each component, the health indicator data of the rolling bearing to be monitored is determined.

3. The railway bearing health monitoring method according to claim 1, characterized in that: Before inputting the health indicator data into a pre-trained bidirectional long short-term memory (DA-BLSTM) network model based on an attention mechanism to obtain a remaining life prediction result of the rolling bearing to be monitored, the method further includes: Acquire a health indicator data sample set, wherein the health indicator data sample set includes a plurality of health indicator sample data with marked remaining lifespan; The health indicator data sample set is clustered using the grey relational clustering and classification GRACC method to obtain multiple clusters; For each cluster, the cluster is divided into a training set and a test set. The pre-built DA-BLSTM network model is trained separately based on the training set corresponding to the cluster, and the trained DA-BLSTM network model is tested separately based on the test set corresponding to the cluster to obtain a pre-trained DA-BLSTM network model.

4. The railway bearing health monitoring method according to claim 1, characterized in that: The DA-BLSTM network model includes a first convolutional layer, a second convolutional layer, a first maximum pooling layer, a third convolutional layer, a second maximum pooling layer, an input attention layer, a bidirectional LSTM layer, a directional attention layer and a fully connected layer, which are connected in sequence.

5. A railway bearing health monitoring device, characterized in that: include: An acquisition module, used for acquiring the original vibration signal of the rolling bearing to be monitored; A health index data extraction module is used to determine the health index data of the rolling bearing to be monitored according to the original vibration signal by adopting a cyclic envelope empirical Fourier decomposition method; a fault diagnosis module, configured to perform fault diagnosis on the rolling bearing to be monitored based on the health indicator data, and obtain a fault diagnosis result of the rolling bearing to be monitored; A life prediction module, configured to predict the remaining life of the rolling bearing to be monitored based on the health indicator data, and obtain a remaining life prediction result of the rolling bearing to be monitored; The health indicator data extraction module is specifically used to: Performing a fast Fourier transform on the original vibration signal to obtain a corresponding signal spectrum; Cyclic enveloping the signal spectrum to obtain a spectrum envelope curve; Performing frequency band division on the spectrum envelope curve to obtain multiple frequency band envelope curves; Constructing a zero-phase filter and reconstructing the envelope curve of each frequency band using an inverse fast Fourier transform to obtain a plurality of single-component signals; the single-component signals include a component time domain waveform and a component envelope curve; Determining health indicator data of the rolling bearing to be monitored based on the multiple single-component signals; The life prediction module is specifically used for: The health indicator data is input into a pre-trained bidirectional long short-term memory DA-BLSTM network model based on the attention mechanism to obtain the remaining life prediction result of the rolling bearing to be monitored.

6. A terminal, characterized in that: The system comprises a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the railway bearing health monitoring method according to any one of claims 1 to 4.

7. A railway bearing health monitoring system, characterized in that: comprising an accelerometer, an acquisition card, a power adapter, and the terminal according to claim 6; The accelerometer is connected to the GPIO port of the terminal through the acquisition card; the power adapter is connected to the power interface of the terminal; Wherein, the terminal is a Raspberry Pi.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the railway bearing health monitoring method according to any one of claims 1 to 4 are implemented.

Images