Gearbox fault diagnosis method, device and equipment and storage medium

By collecting and processing the vibration signals of the gearbox and using automatic machine learning to build a diagnostic model, the problem of inaccurate diagnosis in the existing technology is solved, the accuracy of detection of gearbox failures is improved, and equipment damage and safety accidents are avoided.

CN119063994AInactive Publication Date: 2024-12-03DONGFENG COMML VEHICLE CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202411371963.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-29
Publication Date
2024-12-03
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The prior art cannot automatically build a gearbox fault diagnosis model, resulting in inaccurate diagnosis and may lead to equipment damage and safety accidents.

Method used

By collecting the vibration signals of the gearbox, statistical processing is performed to obtain the diagnostic feature data set, and using automatic machine learning (AutoML) to build the optimal fault diagnosis model to perform fault diagnosis of the gearbox.

Benefits of technology

Improve the accuracy of gearbox fault diagnosis and reduce equipment losses and safety accidents.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119063994A_ABST
    Figure CN119063994A_ABST
Patent Text Reader

Abstract

The invention discloses a gearbox fault diagnosis method, device and equipment and a storage medium, and the method comprises the steps: collecting vibration signals of a gearbox in different directions for a continuous period of time, and carrying out the statistical processing of the collected vibration signals, and obtaining a diagnosis feature data set; and training automatic machine learning by using the diagnosis feature data set to obtain an optimal fault diagnosis model, and performing fault diagnosis on the gearbox by using the optimal fault diagnosis model. According to the method, the optimal diagnosis model can be constructed, excessive dependence on experience is avoided, the constructed model is utilized, the accuracy of gearbox fault diagnosis is improved, equipment loss is effectively avoided, and meanwhile safety accidents are avoided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent network connection technology, and in particular to a gearbox fault diagnosis method, device, equipment and storage medium. Background Art

[0002] The gearbox is a basic transmission device, mainly used to transmit power and adjust the speed. It has a wide range of applications. For example, in wind turbines, the gearbox is an important mechanical component. Its main function is to transmit the power generated by the wind rotor under the action of wind to the generator and make it reach the corresponding speed. Since the gearbox usually works in a harsh environment, various types of failures often occur in the bearings and gears inside the gearbox. When the gearbox fails, the power transmission efficiency of the system will be reduced at the least, and serious personal safety accidents will occur at the worst. Therefore, it is of great significance to quickly and accurately diagnose the gearbox failure.

[0003] Currently, ML models are used to diagnose gearbox failures. However, the existing technology cannot automatically build ML models, and the selection of ML models depends on the experience of researchers. This makes it impossible to accurately diagnose gearbox failures, resulting in equipment damage and even safety accidents. Summary of the invention

[0004] The main purpose of the present invention is to provide a gearbox fault diagnosis method, device, equipment and storage medium, which can construct an optimal diagnostic model to avoid over-reliance on experience, and use the constructed model to improve the accuracy of gearbox fault diagnosis, effectively avoid equipment loss, and also avoid the occurrence of safety accidents.

[0005] In a first aspect, the present application provides a gearbox fault diagnosis method, wherein the method comprises the steps of:

[0006] Collecting vibration signals of the gearbox in different directions for a continuous period of time, and performing statistical processing on the collected vibration signals to obtain a diagnostic feature data set;

[0007] The diagnostic feature data set is used to train automatic machine learning to obtain an optimal fault diagnosis model, and the optimal fault diagnosis model is used to perform gearbox fault diagnosis.

[0008] In combination with the first aspect, as an optional implementation, based on a set step length, the gearbox load increases from a first set value to a second set value with a set step length;

[0009] Based on the vibration sensors installed in the horizontal and vertical directions of the gearbox gears, the healthy vibration signals of the gearbox under each load in a set time period are collected when the gears are in a healthy state;

[0010] When the gear teeth are broken, the fault vibration signal of the gearbox is collected in a set time period under each load.

[0011] In combination with the first aspect above, as an optional implementation manner, the sampling frequency is determined according to the meshing frequency of the gears of the gearbox.

[0012] In combination with the first aspect above, as an optional implementation method, when the comparison result of the gear state signal of the gear box collected by the sensor is inconsistent with the set gear health signal, it is determined that the gear of the gear box is in a broken state;

[0013] When the comparison result of the gear status signal of the gear box collected by the sensor is consistent with the set gear health signal, it is judged that the gear of the gear box is in a healthy state.

[0014] In combination with the first aspect above, as an optional implementation method, the collected vibration signals are grouped according to the health status of the gear, the sensor and the load size, and each group is sliced;

[0015] The distribution characteristics of each slice data are counted and used as the diagnostic feature data set, where the distribution characteristics of each slice data are the statistical characteristics of each vibration sensor signal under different loads and different health conditions of the gearbox, including data mean, standard deviation, data kurtosis and skewness.

[0016] In combination with the first aspect above, as an optional implementation method, the diagnostic feature data set is divided into a training set and a test set according to a set ratio;

[0017] Using automatic machine learning AutoML to search and build an optimal analysis and diagnosis model on the training set, and output an optimal fault diagnosis model;

[0018] The test set is used to detect the performance of the optimal fault diagnosis model, and actual data of the gearbox is input into the optimal fault diagnosis model, and the optimal fault diagnosis model is used to diagnose whether the gearbox is faulty.

[0019] In a second aspect, the present application provides a gearbox fault diagnosis device, the device comprising:

[0020] A processing module, which is used to collect vibration signals of the gearbox in different directions for a continuous period of time, and perform statistical processing on the collected vibration signals to obtain a diagnostic feature data set;

[0021] A diagnosis module is used to train automatic machine learning using the diagnostic feature data set to obtain an optimal fault diagnosis model, and use the optimal fault diagnosis model to perform gearbox fault diagnosis.

[0022] In combination with the above second aspect, as an optional implementation, the processing module is further configured to increase the gearbox load from a first set value to a second set value with a set step length based on the set step length;

[0023] Based on the vibration sensors installed in the horizontal and vertical directions of the gearbox gears, the healthy vibration signals of the gearbox under each load in a set time period are collected when the gears are in a healthy state;

[0024] When the gear teeth are broken, the fault vibration signal of the gearbox is collected in a set time period under each load.

[0025] In a third aspect, the present application further provides an electronic device, comprising: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the method described in any one of the first aspects is implemented.

[0026] In a fourth aspect, the present application further provides a computer-readable storage medium storing computer program instructions, which, when executed by a computer, enables the computer to execute any of the methods described in the first aspect.

[0027] The present application provides a gearbox fault diagnosis method, device, equipment and storage medium, wherein the method includes the steps of: collecting vibration signals of the gearbox in different directions for a continuous period of time, and statistically processing the collected vibration signals to obtain a diagnostic feature data set; using the diagnostic feature data set to train automatic machine learning to obtain an optimal fault diagnosis model, and using the optimal fault diagnosis model to perform gearbox fault diagnosis. The present application can construct an optimal diagnostic model to avoid over-reliance on experience, and use the constructed model to improve the accuracy of gearbox fault diagnosis, effectively avoid equipment loss, and also avoid the occurrence of safety accidents.

[0028] It is to be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0030] Figure 1 A flow chart of a gearbox fault diagnosis method provided in an embodiment of the present application;

[0031] Figure 2 A schematic diagram of a gearbox fault diagnosis device provided in an embodiment of the present application;

[0032] Figure 3A schematic diagram of an electronic device provided in an embodiment of the present application;

[0033] Figure 4 A schematic diagram of a computer-readable program medium provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] Here, exemplary embodiments will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0035] Furthermore, the drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. Some of the blocks shown in the drawings are functional entities and do not necessarily correspond to physically or logically separate entities.

[0036] The embodiments of the present application provide a gearbox fault diagnosis method, apparatus, device and storage medium, which can construct an optimal diagnostic model, avoid over-reliance on experience, and use the constructed model to improve the accuracy of gearbox fault diagnosis, effectively avoid equipment loss, and also avoid the occurrence of safety accidents.

[0037] In order to achieve the above technical effects, the general idea of ​​this application is as follows:

[0038] A gearbox fault diagnosis method, the method comprising the steps of:

[0039] S101: Collect vibration signals of the gearbox in different directions for a continuous period of time, and perform statistical processing on the collected vibration signals to obtain a diagnostic feature data set

[0040] S102: Using the diagnostic feature data set to train automatic machine learning to obtain an optimal fault diagnosis model, and using the optimal fault diagnosis model to perform gearbox fault diagnosis.

[0041] The embodiments of the present application are further described in detail below in conjunction with the accompanying drawings.

[0042] Reference Figure 1 , Figure 1 FIG. 1 is a flow chart of a gearbox fault diagnosis method provided by the present invention, as shown in FIG. Figure 1 As shown, the method comprises the steps of:

[0043] Step S101: collecting vibration signals of the gearbox in different directions for a continuous period of time, and performing statistical processing on the collected vibration signals to obtain a diagnostic feature data set.

[0044] Specifically, based on the set step size, the gearbox load is increased from a first set value to a second set value with a set step size; based on the vibration sensors installed in the horizontal and vertical directions of the gearbox gears, when the gears are in a healthy state, the healthy vibration signals of the gearbox under each load in a set time period are collected; when the gear teeth are broken, the fault vibration signals of the gearbox under each load in a set time period are collected.

[0045] For easy understanding, an example is given. Four vibration sensors are placed on the gears of the gearbox in the horizontal and vertical directions, with consistent spacing and reasonable positions. The sampling frequency f is determined according to the meshing frequency of the gearbox gears. When the gears are in a healthy state, the gearbox load increases from 0 to 90% in steps of 10%, and the vibration signal of the gearbox under each load for a period of time is collected, that is, the gearbox health data is collected. When the gear teeth are broken, the gearbox load increases from 0 to 90% in steps of 10%, and the vibration signal of the gearbox under each load for a period of time is collected, that is, the gearbox fault data is collected.

[0046] It should be noted that when the comparison result of the gear status signal of the gearbox collected by the sensor is inconsistent with the set gear health signal, it is judged that the gear of the gearbox is in a broken state; when the comparison result of the gear status signal of the gearbox collected by the sensor is consistent with the set gear health signal, it is judged that the gear of the gearbox is in a healthy state.

[0047] Specifically, in order to collect actual data, four vibration sensors were first placed horizontally and vertically on the gearbox of a certain model of automatic manual transmission (AMT), with a collection frequency of 14400. Next, the gearbox load was increased from 0 to 90% in steps of 10% under two conditions: healthy gear and broken gear. The vibration signal of the gearbox was collected for about 1 minute under each load, i.e. 20 cases, and about 88,000 data points were collected in each case.

[0048] It should be explained that a single vibration signal cannot determine whether a gear is faulty, so a continuous vibration signal is required, that is, the gearbox load increases from 0 to 90% in steps of 10%, and the vibration signal of the gearbox is collected for about 1 minute under each load.

[0049] In one embodiment, the collected vibration signals are grouped according to the gear health status, sensor and load size, and each group is sliced; the distribution characteristics of each slice data are statistically analyzed, and the statistical distribution characteristics are used as a diagnostic feature data set, wherein the distribution characteristics of each slice data are statistical characteristics of each vibration sensor signal under different loads and different health conditions of the gearbox, including data mean, standard deviation, data kurtosis and skewness.

[0050] Specifically, the vibration signal is grouped according to the gear health state, sensor and load size. Each group is sliced ​​into 100 pieces of data, and the data of each slice is ensured to be continuous. The statistical characteristics of each slice data, that is, the statistical characteristics of each sensor signal under different loads and different health states of the gearbox, such as data mean, standard deviation, data kurtosis and skewness. The statistically processed data is used as a data set and as the input of AutoML, so that the AutoML method can search and build the optimal analysis and diagnosis model. It should be explained that there are four sensors: identified as a1, a2, a3, a4, State: 0 or 1, 1 indicates unhealthy, 0 indicates healthy, and load has 10 levels: 0, 0.1, 0.2...0.9. Grouping method: if s=a1, state=0, load=0 is a group, s=a1, state=0, load=0.1 is a group, s=a1, state=0, load=0.9 is a group, s=a1, state=1, load=0 is a group, s=a1, state=1, load=0.1 is a group, s=a1, state=0, load=0.9 is a group. When s is a2, a3 or a4, the above grouping is also followed.

[0051] Step S102: Use the diagnostic feature data set to train automatic machine learning to obtain an optimal fault diagnosis model, and use the optimal fault diagnosis model to perform gearbox fault diagnosis.

[0052] Specifically, the diagnostic feature data set is divided into a training set and a test set according to a set ratio; the automatic machine learning AutoML is used to search and build the optimal analysis and diagnosis model on the training set, and the optimal fault diagnosis model is output; the performance of the optimal fault diagnosis model is detected by the test set, and the actual data of the gearbox is input into the optimal fault diagnosis model, and the optimal fault diagnosis model is used to diagnose whether the gearbox is faulty. It should be noted that the search for the optimal model can be understood as AutoML first defining an optional machine learning algorithm search space, and then effectively navigating the possible model and model configuration space according to the search strategy algorithm such as Bayesian optimization, evolutionary algorithm, etc., then selecting the corresponding model and training it, and finally evaluating the trained model, outputting the best model, so as to quickly find the most effective method for a given predictive modeling task.

[0053] Specifically, the vibration statistics of the four sensors were used as a data set, and the data set was divided into a training set and a test set at a ratio of 8:2. AutoML was used to search and build the optimal analysis and diagnosis model on the training set, and the optimal model was output. Finally, the test set was used to test the performance of the optimal model, where the accuracy of the optimal model on the test set was as high as 96.115%. In actual use, the actual data of the gearbox (statistical characteristics of the vibration signal) was input into the model to diagnose gearbox faults.

[0054] It needs to be explained that the vibration phenomenon in the operation of the gear can reflect the health status of the gearbox. When the gearbox fails, the vibration waveform and spectrum of the gear will change. Therefore, the vibration signal of the gearbox can be used to detect whether the gearbox is faulty. The specific method is: first, collect the vibration signals in the four directions of the gearbox. A single vibration signal cannot determine whether the gear is faulty, so a continuous vibration signal is required for a period of time; secondly, calculate the statistical characteristics of the vibration signal of the gearbox over a period of time. If a tooth of the gearbox is damaged, only the data of a certain sensor may be reflected. Therefore, calculating the statistical information of each sensor separately can improve the accuracy of diagnosis; next, use the statistical features as input, and use the AutoML method to search and build the optimal analysis and diagnosis model to avoid dependence on the original experience of the research; finally, use the searched and constructed optimal model to diagnose the gearbox fault. It can be understood that this application uses the AutoML method to search and build the optimal diagnostic model to avoid dependence on the original experience of the research. It uses the vibration signals in the four directions of the gear. A single diagnostic signal cannot determine whether the gear is faulty, so the statistical information of the vibration signal over a period of time is used as the diagnostic feature data to improve the accuracy of diagnosis.

[0055] Reference Figure 2 , Figure 2 FIG. 1 is a schematic diagram of a gearbox fault diagnosis device provided by the present invention, such as Figure 2 As shown, the device comprises:

[0056] Processing module 201: It is used to collect vibration signals of the gear box in different directions for a continuous period of time, and perform statistical processing on the collected vibration signals to obtain a diagnostic feature data set.

[0057] Diagnostic module 202: It is used to use the diagnostic feature data set to train automatic machine learning to obtain an optimal fault diagnosis model, and use the optimal fault diagnosis model to perform gearbox fault diagnosis.

[0058] Further, in a possible implementation manner, the processing module is further configured to increase the gearbox load from a first set value to a second set value at a set step length based on the set step length;

[0059] Based on the vibration sensors installed in the horizontal and vertical directions of the gearbox gears, the healthy vibration signals of the gearbox under each load in a set time period are collected when the gears are in a healthy state;

[0060] When the gear teeth are broken, the fault vibration signal of the gearbox is collected in a set time period under each load.

[0061] Furthermore, in a possible implementation manner, the processing module is further configured to determine the sampling frequency according to the meshing frequency of the gears of the gearbox.

[0062] Further, in a possible implementation manner, the diagnostic module is further configured to determine that the gear of the gear box is in a broken state when a comparison result of a gear state signal of the gear box collected by the sensor is inconsistent with a set gear health signal;

[0063] When the comparison result of the gear status signal of the gear box collected by the sensor is consistent with the set gear health signal, it is judged that the gear of the gear box is in a healthy state.

[0064] Furthermore, in a possible implementation manner, the processing module is further used to group the collected vibration signals according to the health status of the gear, the sensor and the load size, and slice each group;

[0065] The distribution characteristics of each slice data are counted and used as the diagnostic feature data set, where the distribution characteristics of each slice data are the statistical characteristics of each vibration sensor signal under different loads and different health conditions of the gearbox, including data mean, standard deviation, data kurtosis and skewness.

[0066] Furthermore, in a possible implementation manner, the diagnosis module is further configured to divide the diagnosis feature data set into a training set and a test set according to a set ratio;

[0067] Using automatic machine learning AutoML to search and build an optimal analysis and diagnosis model on the training set, and output an optimal fault diagnosis model;

[0068] The test set is used to detect the performance of the optimal fault diagnosis model, and actual data of the gearbox is input into the optimal fault diagnosis model, and the optimal fault diagnosis model is used to diagnose whether the gearbox is faulty.

[0069] Refer to the following Figure 3 The electronic device 300 according to this embodiment of the present invention will be described. Figure 3 The electronic device 300 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0070] like Figure 3As shown, the electronic device 300 is in the form of a general computing device. The components of the electronic device 300 may include but are not limited to: at least one processing unit 310, at least one storage unit 320, and a bus 330 connecting different system components (including the storage unit 320 and the processing unit 310).

[0071] The storage unit stores program codes, which can be executed by the processing unit 310, so that the processing unit 310 executes the steps according to various exemplary embodiments of the present invention described in the above “Embodiment Method” section of this specification.

[0072] The storage unit 320 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 321 and / or a cache memory unit 322 , and may further include a read-only memory unit (ROM) 323 .

[0073] The storage unit 320 may also include a program / utility 324 having a set (at least one) of program modules 325, such program modules 325 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0074] Bus 330 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0075] The electronic device 300 may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 300, and / or communicate with any device that enables the electronic device 300 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 350. Furthermore, the electronic device 300 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 360. As shown, the network adapter 360 communicates with other modules of the electronic device 300 via a bus 330. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 300, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0076] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0077] According to the solution of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary implementations of the present invention described in the above "Exemplary Method" section of the present specification.

[0078] refer to Figure 4 As shown, a program product 400 for implementing the above method according to an embodiment of the present invention is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0079] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0080] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0081] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0082] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0083] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0084] In summary, the present application provides a gearbox fault diagnosis method, device, equipment and storage medium, wherein the method includes the steps of: collecting vibration signals of the gearbox in different directions for a continuous period of time, and statistically processing the collected vibration signals to obtain a diagnostic feature data set; using the diagnostic feature data set to train automatic machine learning to obtain an optimal fault diagnosis model, and using the optimal fault diagnosis model to perform gearbox fault diagnosis. The present application can construct an optimal diagnostic model to avoid over-reliance on experience, and use the constructed model to improve the accuracy of gearbox fault diagnosis, effectively avoid equipment loss, and also avoid the occurrence of safety accidents.

[0085] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.

[0086] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

Claims

1. A gearbox fault diagnosis method, characterized in that: include: Collecting vibration signals of the gearbox in different directions for a continuous period of time, and performing statistical processing on the collected vibration signals to obtain a diagnostic feature data set; The diagnostic feature data set is used to train automatic machine learning to obtain an optimal fault diagnosis model, and the optimal fault diagnosis model is used to perform gearbox fault diagnosis.

2. The method according to claim 1, characterized in that The collecting of vibration signals of the gearbox in different directions includes: Based on the set step length, the gearbox load increases from a first set value to a second set value in a set step length; Based on the vibration sensors installed in the horizontal and vertical directions of the gearbox gears, the healthy vibration signals of the gearbox under each load in a set time period are collected when the gears are in a healthy state; When the gear teeth are broken, the fault vibration signal of the gearbox is collected in a set time period under each load.

3. The method according to claim 2, characterized in that Also includes: The sampling frequency is determined according to the meshing frequency of the gearbox gears.

4. The method according to claim 2, characterized in that: Also includes: When the gear status signal of the gear box collected by the sensor is inconsistent with the set gear health signal, it is judged that the gear of the gear box is in a broken state; When the comparison result of the gear status signal of the gear box collected by the sensor is consistent with the set gear health signal, it is judged that the gear of the gear box is in a healthy state.

5. The method according to claim 1, characterized in that The statistical processing of the collected vibration signal to obtain a diagnostic feature data set includes: The collected vibration signals are grouped by gear health status, sensor and load size, and each group is sliced; The distribution characteristics of each slice data are counted and used as the diagnostic feature data set, where the distribution characteristics of each slice data are the statistical characteristics of each vibration sensor signal under different loads and different health conditions of the gearbox, including data mean, standard deviation, data kurtosis and skewness.

6. The method according to claim 1, characterized in that The method of using the diagnostic feature data set to train automatic machine learning to obtain an optimal fault diagnosis model, and using the optimal fault diagnosis model to perform gearbox fault diagnosis, includes: Dividing the diagnostic feature data set into a training set and a test set according to a set ratio; Using automatic machine learning AutoML to search and build an optimal analysis and diagnosis model on the training set, and output an optimal fault diagnosis model; The test set is used to detect the performance of the optimal fault diagnosis model, and actual data of the gearbox is input into the optimal fault diagnosis model, and the optimal fault diagnosis model is used to diagnose whether the gearbox is faulty.

7. A gearbox fault diagnosis device, characterized in that: include: A processing module, which is used to collect vibration signals of the gearbox in different directions for a continuous period of time, and perform statistical processing on the collected vibration signals to obtain a diagnostic feature data set; A diagnosis module is used to train automatic machine learning using the diagnostic feature data set to obtain an optimal fault diagnosis model, and use the optimal fault diagnosis model to perform gearbox fault diagnosis.

8. The device according to claim 7, characterized in that: The processing module is further used to increase the gearbox load from a first set value to a second set value with a set step length based on the set step length; Based on the vibration sensors installed in the horizontal and vertical directions of the gearbox gears, the healthy vibration signals of the gearbox under each load in a set time period are collected when the gears are in a healthy state; When the gear teeth are broken, the fault vibration signal of the gearbox is collected in a set time period under each load.

9. An electronic device, characterized in that: The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium, characterized in that: The computer program instructions are stored therein, and when the computer program instructions are executed by a computer, the computer is caused to execute the method according to any one of claims 1 to 6.

Citation Information

Patent Citations

  • Wind power gear box fault diagnosis method based on time shift cosine similarity entropy

    CN115541227A