Fault diagnosis method and device, electronic equipment, readable storage medium and chip

Abstract

The embodiment of the invention provides a fault diagnosis method and device, electronic equipment, a readable storage medium and a chip, and the method comprises the steps: obtaining equipment operation data which comprises a sampling value corresponding to at least one sampling point; setting data acquisition parameters, and determining diagnosis parameters corresponding to the equipment operation data according to the data acquisition parameters; performing feature extraction on the diagnosis parameters to obtain equipment feature data; determining a fault diagnosis model corresponding to the equipment operation data; determining a fault contrast threshold value corresponding to the equipment operation data according to the fault diagnosis model; and inputting the equipment characteristic data into the fault diagnosis model, and determining a fault diagnosis result corresponding to the fault contrast threshold. Through the scheme of the invention, the occurrence of non-planned shutdown caused by the fact that the equipment is disassembled to find the fault information can be reduced, so that the maintenance cost is reduced, the operation efficiency and safety of the equipment are improved, and the service life of the equipment is prolonged.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment maintenance, and in particular to a fault diagnosis method, device, electronic equipment, readable storage medium and chip. Background Art

[0002] At present, equipment maintenance is generally divided into two types: post-maintenance and preventive maintenance. Post-maintenance not only needs to take into account the high spare parts inventory cost and labor cost, but also requires unplanned downtime maintenance of the equipment; preventive maintenance performs maintenance based on time, parameters or status in a specific cycle. Traditional equipment maintenance measures require the equipment to be disassembled to find fault information, resulting in unplanned downtime maintenance, increasing production costs and reducing fault detection efficiency. Summary of the invention

[0003] The purpose of the embodiments of the present invention is to provide a fault diagnosis method, device, electronic device, readable storage medium and chip, which can solve the problem of unplanned downtime caused by disassembling the equipment to find fault information during the production process.

[0004] In view of this, an embodiment of the first aspect of the present invention provides a fault diagnosis method.

[0005] An embodiment of the second aspect of the present invention provides a fault diagnosis device.

[0006] An embodiment of a third aspect of the present invention provides an electronic device.

[0007] An embodiment of a fourth aspect of the present invention provides a readable storage medium.

[0008] An embodiment of the fifth aspect of the present invention provides a chip.

[0009] In order to achieve the above-mentioned purpose, an embodiment of the first aspect of the present invention provides a fault diagnosis method, which includes: acquiring equipment operation data, the equipment operation data including sampling values ​​corresponding to at least one sampling point; determining data acquisition parameters, and determining diagnostic parameters corresponding to the equipment operation data according to the data acquisition parameters; performing feature extraction on the diagnostic parameters to obtain equipment feature data; determining a fault diagnosis model corresponding to the equipment operation data; determining a fault control threshold corresponding to the equipment operation data according to the fault diagnosis model; and inputting the equipment feature data into the fault diagnosis model to determine a fault diagnosis result corresponding to the fault control threshold.

[0010] According to the fault diagnosis method proposed in the present invention, the operation signal of the equipment during operation is collected by the sensor installed at the sampling point of the equipment to determine the operation data of the equipment, wherein at least one sampling point on the equipment corresponds to a sensor, and different types of operation signals are collected by different sensors. The data acquisition parameters are determined by setting the data acquisition frequency and the data cleaning strategy, the operation signals collected by the sensor are cleaned and screened, the noise and abnormal values ​​in the equipment operation signal are filtered out, the diagnostic parameters corresponding to the equipment operation data are determined, the characteristic frequency corresponding to the diagnostic parameter is extracted as the equipment characteristic data through the characteristic frequency algorithm, the equipment characteristic data is imported into the fault diagnosis model and compared with the fault control threshold to determine whether a fault occurs at each sampling point of the equipment, and the fault type corresponding to at least one sampling point is judged through the fault diagnosis model.

[0011] Specifically, the operating signals of the equipment during operation include vibration, noise, temperature or other operating signals that change during the operation of the equipment. Different types of operating signals are collected through vibration sensors, noise sensors and temperature sensors installed on the equipment and sensors corresponding to the operating signals.

[0012] It can be understood that by collecting different operating signals when the equipment is running, extracting the characteristic frequencies of the operating signals and inputting them into the fault diagnosis model, the application scope of the fault diagnosis method can be expanded, the fault diagnosis efficiency can be improved, and the equipment operation data can be cleaned and screened by determining the data acquisition parameters to ensure the accuracy and reliability of the data.

[0013] In the above technical solution, determining data acquisition parameters, and determining diagnostic parameters corresponding to equipment operation data based on the data acquisition parameters include: obtaining equipment fault history record data; determining the equipment fault type based on the equipment fault history record data; determining the data acquisition frequency and data cleaning parameters corresponding to the equipment fault type based on the equipment fault type; determining the diagnostic parameters corresponding to the equipment operation data based on the data acquisition frequency and data cleaning parameters.

[0014] In this technical solution, the data acquisition parameters are determined by determining the equipment failure type of the corresponding equipment, and the corresponding diagnostic parameters are determined by the data acquisition parameters. Specifically, the equipment failure type is determined by the historical record data of the equipment failure and the type of operation signal of the failure in the historical record data, such as abnormal vibration signal data, abnormal temperature signal data, etc., and the data acquisition frequency and data cleaning parameters corresponding to the equipment failure type are determined according to the fault diagnosis algorithm.

[0015] It can be understood that different types of equipment operation signals have different types of abnormal data. By determining the data collection frequency and data cleaning parameters for different fault types, the accuracy of complex equipment signal collection and the adaptability to different equipment can be improved.

[0016] In the above technical solution, the diagnostic parameters corresponding to the equipment operation data are determined according to the data collection frequency and the data cleaning parameters, including: determining the data collection time interval according to the data collection frequency; collecting the equipment operation data according to the data collection time interval to obtain a first data set; determining the outlier boundary according to the data cleaning parameters; screening the data in the first data set that does not exceed the outlier boundary to determine the diagnostic parameters for the equipment operation data.

[0017] In this technical solution, the data collection frequency and data cleaning parameters are used to determine the collection time interval and abnormal value boundary corresponding to the equipment operation data, and the operation data of at least one sampling point position is processed. Specifically, the sensor collects data of the operation signal at the corresponding sampling point position at the set time interval, and then the data cleaner cleans the collected data according to the abnormal value boundary setting, that is, deletes the data in the data set whose value exceeds the abnormal value, and determines the diagnostic parameters. By collecting the raw data collected from the sensor according to the frequency and cleaning the collected data, the efficiency of data collection is improved.

[0018] In the above technical solution, a fault control threshold value corresponding to the equipment operation data is determined according to a fault diagnosis model, including: determining historical fault parameters according to the equipment fault history record data; the fault diagnosis model performs feature extraction on the historical fault parameters to obtain equipment fault feature data; the equipment fault feature data is input into the fault diagnosis model, and the minimum value in the equipment fault feature data is determined as the fault control threshold value.

[0019] In this technical solution, the equipment fault history record data is analyzed by the fault diagnosis model to determine the characteristic data of the equipment fault, and the characteristic data includes the spectrum data or power spectrum data of at least one operating signal. The characteristic data value with the smallest value in the characteristic data is determined as the fault control threshold.

[0020] Among them, the characteristic data can be input into the fault diagnosis model in the form of characteristic spectrum images, power spectrum images or other spectrum images. The fault diagnosis model can analyze the image data according to the fault diagnosis algorithm, determine the characteristic information in the image data, and use the characteristic image data corresponding to the minimum value in the characteristic information as the fault control threshold.

[0021] In the above technical solution, the device characteristic data is input into the fault diagnosis model to determine the fault diagnosis result corresponding to the fault control threshold, including: inputting the device characteristic data into the fault diagnosis model to determine whether the device characteristic data exceeds the fault control threshold; when the value of the device characteristic data does not exceed the fault control threshold, the fault diagnosis model adjusts the data acquisition parameters according to the adjustment range corresponding to the data acquisition time interval; when the value of the device characteristic data exceeds the fault control threshold, the fault diagnosis result corresponding to the sampling point is determined.

[0022] In this technical solution, the device characteristic data obtained by feature extraction of the diagnostic parameters is input into the fault diagnosis model to judge the size of at least one device characteristic data and the fault control threshold. When the value of the device characteristic data does not exceed the value corresponding to the fault control threshold, it is considered that the sampling point corresponding to the device characteristic data has not failed. The data collection time interval corresponding to the device characteristic data is adjusted according to the adjustment amplitude obtained by the fault diagnosis model analysis. When the value of the device characteristic data exceeds the value corresponding to the fault control threshold, it is considered that the sampling point corresponding to the device characteristic data has failed, and it is necessary to perform fault diagnosis analysis on the sampling point to determine the fault diagnosis result.

[0023] In the above technical solution, when the value of the equipment characteristic data exceeds the fault control threshold, the fault diagnosis result corresponding to the sampling point is determined, including: obtaining the equipment fault type corresponding to the equipment characteristic data; obtaining the sampling point position coordinates corresponding to the equipment characteristic data; and determining the fault diagnosis result according to the equipment fault type and the sampling point position coordinates.

[0024] In this technical solution, the fault diagnosis result corresponding to the sampling point where a fault has been determined is analyzed through a fault diagnosis model to obtain the fault type corresponding to the sampling point, that is, the abnormal operation signal type, and the position coordinates of the sampling point are obtained by analyzing the sensor position coordinates to determine the fault diagnosis result corresponding to the sampling point.

[0025] In addition, the fault diagnosis model is used to analyze the abnormal operation signal type and provide maintenance measures corresponding to the equipment fault type.

[0026] An embodiment of the second aspect of the present invention provides a fault diagnosis device, including: an acquisition module, used to acquire equipment operation data; a data acquisition module, used to determine data acquisition parameters, and determine diagnostic parameters corresponding to the equipment operation data based on the data acquisition parameters; an extraction module, used to extract features from the diagnostic parameters to obtain equipment feature data; and a fault determination module, used to input the equipment feature data into a fault diagnosis model to determine a fault diagnosis result corresponding to a fault control threshold.

[0027] The fault diagnosis device proposed in the present invention mainly includes an acquisition module, a data acquisition module, an extraction module and a fault determination module, and performs fault diagnosis on the equipment. Specifically, the sensor component in the acquisition module collects at least one type of operation signal of the equipment to determine the equipment operation data. The data acquisition module cleans and filters the equipment operation data, filters the noise and abnormal values ​​in the equipment operation signal, reduces the interference caused by a large amount of original data, and improves the data acquisition efficiency. Then, the extraction module extracts the characteristics of the cleaned and filtered diagnostic parameters to obtain the characteristic frequency data corresponding to each diagnostic parameter. Finally, at least one characteristic frequency data is input into the fault diagnosis model corresponding to the fault determination module, and compared with the fault control threshold. The sensor sampling point information and the fault type that are judged to have a fault are determined as the fault diagnosis result, and the maintenance measures corresponding to the fault diagnosis result are output. By monitoring and diagnosing different types of operation signals, the efficiency and safety of equipment operation are improved, the maintenance cost is reduced, and the service life of the equipment is extended.

[0028] An embodiment of the third aspect of the present invention provides an electronic device, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, and when the program or instruction is executed by the processor, the steps of the method of the first aspect are implemented.

[0029] An embodiment of the fourth aspect of the present invention provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method of the first aspect are implemented.

[0030] An embodiment of the fifth aspect of the present invention provides a chip, the chip includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the steps of the method of the first aspect.

[0031] Additional aspects and advantages of the present invention will become apparent from the following description or may be learned by practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A schematic diagram of a fault diagnosis method according to an embodiment of the present application is shown; Figure 2 A schematic diagram of a fault diagnosis method according to an embodiment of the present application is shown; Figure 3 A schematic diagram of a fault diagnosis method according to an embodiment of the present application is shown; Figure 4 A schematic diagram of a fault diagnosis method according to an embodiment of the present application is shown; Figure 5A schematic diagram of a fault diagnosis method according to an embodiment of the present application is shown; Figure 6 A schematic diagram of a fault diagnosis method according to an embodiment of the present application is shown; Figure 7 A schematic diagram of the structure of a fault diagnosis device according to an embodiment of the present application is shown; Figure 8 A schematic diagram of the structure of an electronic device according to an embodiment of the present application is shown; Fig. 9 A logical schematic diagram of equipment fault history record data according to an embodiment of the present application is shown; Fig.10 A schematic diagram of a fault diagnosis method according to an embodiment of the present application is shown; Fig.11 A schematic diagram of a fault diagnosis algorithm according to an embodiment of the present application is shown; Fig.12 A schematic flow chart of a fault diagnosis method according to an embodiment of the present application is shown.

[0033] in, Figure 7 and Figure 8 The corresponding relationship between the reference numerals and the component names is as follows: 900: fault diagnosis device; 902: acquisition module; 904: data acquisition module; 906: extraction module; 908: fault determination module; 1000: electronic device; 1110: processor; 1109: memory. DETAILED DESCRIPTION

[0034] In order to more clearly understand the above-mentioned purposes, features and advantages of the embodiments of the present invention, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0035] In the following description, many specific details are set forth to facilitate a full understanding of the present application. However, the embodiments of the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present application is not limited to the specific embodiments disclosed below.

[0036] The following is combined with Figures 1 to 12 , the fault diagnosis method, device, electronic device, readable storage medium and chip provided in the embodiments of the present application are described in detail through specific embodiments and their application scenarios.

[0037] This embodiment provides a fault diagnosis method, the fault diagnosis method is as follows Figure 1 As shown, including: Step S102: Obtaining equipment operation data; Step S104: determining data acquisition parameters, and determining diagnostic parameters corresponding to the equipment operation data according to the data acquisition parameters; Step S106: extracting features from the diagnostic parameters to obtain device feature data; Step S108: determining a fault diagnosis model corresponding to the equipment operation data; Step S110: determining a fault comparison threshold corresponding to the equipment operation data according to the fault diagnosis model; Step S112: input the equipment characteristic data into the fault diagnosis model to determine the fault diagnosis result corresponding to the fault comparison threshold.

[0038] According to the fault diagnosis method proposed in this embodiment, the operation signal of the equipment during operation is collected by sensors installed at the sampling point of the equipment to determine the operation data of the equipment, wherein at least one sampling point on the equipment corresponds to a sensor, and different types of operation signals are collected by different sensors. The data acquisition parameters are determined by setting the data acquisition frequency and the data cleaning strategy, the operation signals collected by the sensor are cleaned and screened, the noise and abnormal values ​​in the equipment operation signals are filtered out, the diagnostic parameters corresponding to the equipment operation data are determined, the characteristic frequencies corresponding to the diagnostic parameters are extracted as the equipment characteristic data through the characteristic frequency algorithm, the equipment characteristic data are imported into the fault diagnosis model and compared with the fault control threshold to determine whether a fault occurs at each sampling point of the equipment, and the fault type corresponding to at least one sampling point is judged through the fault diagnosis model.

[0039] Specifically, the operating signals of the equipment during operation include vibration, noise, temperature or other operating signals that change during the operation of the equipment. Different types of operating signals are collected through vibration sensors, noise sensors and temperature sensors installed on the equipment and sensors corresponding to the operating signals.

[0040] Specifically, the production equipment to which the fault diagnosis method of this embodiment is applied may be shafting production equipment, or other production equipment having operation signals such as vibration, noise, temperature or other changes during operation, as long as the operation data of the production equipment can be collected by installing sensors corresponding to different types of operation signals.

[0041] It can be understood that by collecting different operating signals when the equipment is running, extracting the characteristic frequencies of the operating signals and inputting them into the fault diagnosis model, the application scope of the fault diagnosis method can be expanded, the fault diagnosis efficiency can be improved, and the equipment operation data can be cleaned and screened by determining the data acquisition parameters to ensure the accuracy and reliability of the data.

[0042] In one embodiment, Figure 2 As shown, determining data acquisition parameters, and determining diagnostic parameters corresponding to the equipment operation data according to the data acquisition parameters, including: Step S1042: Obtain equipment failure history record data; Step S1044: determining the equipment failure type according to the equipment failure history record data; Step S1046: determining the data collection frequency and data cleaning parameters corresponding to the device failure type according to the device failure type; Step S1048: Determine diagnostic parameters corresponding to the equipment operation data according to the data collection frequency and the data cleaning parameters.

[0043] In this embodiment, the data acquisition parameters are determined by determining the equipment failure type of the corresponding equipment, and the corresponding diagnostic parameters are determined by the data acquisition parameters. Specifically, the equipment failure type is determined by determining the type of operating signal of the failure in the historical record data, such as abnormal vibration signal data, abnormal temperature signal data, etc., and the data acquisition frequency and data cleaning parameters corresponding to the equipment failure type are determined according to the fault diagnosis algorithm.

[0044] It can be understood that different types of equipment operation signals have different types of abnormal data. By determining the data collection frequency and data cleaning parameters for different fault types, the accuracy of complex equipment signal collection and the adaptability to different equipment can be improved.

[0045] Among them, Fig. 9 As shown, the equipment fault history record data includes different equipment component types, such as equipment component 1 and equipment component 2, fault types corresponding to each equipment component type, such as bent shaft, imbalance, misalignment and abnormal temperature, and characteristic frequencies corresponding to each fault type, such as spectrum characteristics, time domain characteristics and frequency domain characteristics, and records image data corresponding to each characteristic frequency, such as spectrum image data when the component is in the 1-fold frequency state and spectrum image data when the component is in the 2-fold frequency state, and spectrum image data when the 1-fold frequency amplitude is greater than the 2-fold frequency amplitude. The equipment fault type corresponding to each equipment component in the device is matched through the characteristic frequency image data in the equipment fault history record data.

[0046] In one embodiment, Figure 3 As shown, the diagnostic parameters corresponding to the equipment operation data are determined according to the data collection frequency and the data cleaning parameters, including: Step S10482: Determine the data collection time interval according to the data collection frequency; Step S10484: collecting equipment operation data according to a data collection time interval to obtain a first data set; Step S10486: Determine the outlier boundary according to the data cleaning parameters; Step S10488: Filter the data in the first data set that does not exceed the outlier boundary to determine the diagnostic parameters corresponding to the equipment operation data.

[0047] In this embodiment, the data collection frequency and data cleaning parameters are used to determine the collection time interval and abnormal value boundary corresponding to the equipment operation data, and the operation data of at least one sampling point position is processed. Specifically, the sensor collects data of the operation signal of the corresponding sampling point position at the set time interval, and then the data cleaner cleans the collected data according to the abnormal value boundary setting, that is, deletes the data in the data set whose value exceeds the abnormal value, and determines the diagnostic parameters. By collecting the raw data collected from the sensor according to the frequency and cleaning the collected data, the efficiency of data collection is improved.

[0048] In one embodiment, Fig.10 As shown, the data acquisition time interval is determined by setting the data acquisition, and the signal and feature signal are collected according to the data acquisition time interval. The collected signal and feature signal are cleaned by setting the outlier boundary according to the data cleaning algorithm to determine the diagnostic parameters. The diagnostic parameters are feature extracted, and the power spectrum features and frequency spectrum features of the diagnostic parameters are extracted using feature extraction algorithms such as power spectrum density (PSD) feature extraction and Fast Fourier Transfor (FFT), and the power spectrum feature data and frequency spectrum image data corresponding to each diagnostic parameter, as well as the corresponding feature signals, are obtained.

[0049] In one embodiment, Figure 4 As shown, determining a fault comparison threshold corresponding to the equipment operation data according to the fault diagnosis model includes: Step S1102: determining historical fault parameters according to the equipment fault history record data; Step S1104: the fault diagnosis model extracts features from historical fault parameters to obtain equipment fault feature data; Step S1106: input the equipment fault characteristic data into the fault diagnosis model, and determine the minimum value in the equipment fault characteristic data as the fault control threshold.

[0050] In this embodiment, the equipment fault history record data is analyzed by the fault diagnosis model to determine the characteristic data of the equipment fault, the characteristic data including the spectrum data or power spectrum data of at least one operating signal. The characteristic data value with the smallest value in the characteristic data is determined as the fault control threshold.

[0051] Among them, the characteristic data can be input into the fault diagnosis model in the form of characteristic spectrum images, power spectrum images or other spectrum images. The fault diagnosis model can analyze the image data according to the fault diagnosis algorithm, determine the characteristic information in the image data, and use the characteristic image data corresponding to the minimum value in the characteristic information as the fault control threshold.

[0052] Specifically, the frequency characteristic spectrum image of the vibration operation signal can be analyzed, for example, to determine the spectrum image corresponding to the vibration operation signal of the faulty shaft system component in the historical fault parameters corresponding to the equipment, and obtain spectrum image data, which is input into the fault diagnosis model as the equipment fault characteristic data. In at least one equipment fault characteristic data, the characteristic data value with the smallest value corresponding to the spectrum image data is the fault control threshold value of the vibration operation signal of the shaft system component.

[0053] In one embodiment, Figure 5 As shown, the device characteristic data is input into the fault diagnosis model to determine the fault diagnosis result corresponding to the fault control threshold, including: Step S1122: inputting the device characteristic data into the fault diagnosis model to determine whether the device characteristic data exceeds the fault control threshold; Step S1124: the fault diagnosis model adjusts the data collection parameters according to the adjustment range corresponding to the data collection time interval; Step S1126: Determine the fault diagnosis result corresponding to the sampling point.

[0054] In this embodiment, the device characteristic data obtained by feature extraction of the diagnostic parameters is input into the fault diagnosis model, and the size of at least one device characteristic data and the fault control threshold is judged. When the value of the device characteristic data does not exceed the value corresponding to the fault control threshold, it is considered that the sampling point corresponding to the device characteristic data has not failed. The data collection time interval corresponding to the device characteristic data is adjusted according to the adjustment amplitude obtained by the fault diagnosis model analysis. When the value of the device characteristic data exceeds the value corresponding to the fault control threshold, it is considered that the sampling point corresponding to the device characteristic data has failed, and it is necessary to perform fault diagnosis analysis on the sampling point to determine the fault diagnosis result.

[0055] In one embodiment, Figure 6 As shown, when the value of the equipment characteristic data exceeds the fault control threshold, the fault diagnosis result corresponding to the sampling point is determined, including: Step S11262: Obtain the device fault type corresponding to the device characteristic data; Step S11264: Obtaining sampling point position coordinates corresponding to device feature data; Step S11266: Determine the fault diagnosis result according to the equipment fault type and the sampling point location coordinates.

[0056] In this embodiment, the fault diagnosis result corresponding to the sampling point where the fault has been determined to have occurred is analyzed by the fault diagnosis model to obtain the fault type corresponding to the sampling point, that is, the abnormal operation signal type, and the position coordinates of the sampling point are obtained by analyzing the sensor position coordinates to determine the fault diagnosis result corresponding to the sampling point.

[0057] In addition, the fault diagnosis model is used to analyze the abnormal operation signal type and provide maintenance measures corresponding to the equipment fault type.

[0058] Optional, such as Fig.12 As shown, the fault diagnosis method may also include: Step S202: Setting data collection frequency, storage strategy, data cleaning strategy and feature extraction strategy; Step S204: define the diagnosis model and bind the device; Step S206: fault diagnosis, expert calibration; Step S208: Model tuning.

[0059] The equipment operation data is processed by setting the data collection frequency, storage strategy, data cleaning strategy and feature extraction strategy to obtain diagnostic parameters. According to the different equipment fault types, the diagnostic model corresponding to the equipment is bound, and the diagnostic parameters are input into the diagnostic model to perform fault diagnosis and determine the fault diagnosis results. The fault diagnosis results are calibrated by human experts and the model is tuned according to the calibration results.

[0060] Specifically, the logic diagram for tuning the diagnostic model is as follows: Fig.11 As shown in the figure, the fault diagnosis model is trained according to the fault diagnosis algorithm, the fault is diagnosed through the fault diagnosis model, and the diagnosis conclusion is obtained. The manual expert calibrates the diagnosis conclusion, completes the fault diagnosis model optimization, and puts the optimized fault diagnosis model into training. By continuously tuning the fault diagnosis model by manual experts, the diagnostic accuracy of the fault diagnosis model can be improved and the maintenance cost can be reduced.

[0061] like Figure 7 As shown, the embodiment of the present application provides a fault diagnosis device 900. The fault diagnosis device 900 includes: an acquisition module 902, which is used to acquire equipment operation data; a data acquisition module 904, which is used to determine data acquisition parameters, and determine diagnostic parameters corresponding to the equipment operation data according to the data acquisition parameters; an extraction module 906, which extracts features from the diagnostic parameters to obtain equipment feature data; and a fault determination module 908, which is used to input the equipment feature data into a fault diagnosis model to determine a fault diagnosis result corresponding to a fault control threshold.

[0062] The fault diagnosis device proposed in the present invention mainly includes an acquisition module 902, a data acquisition module 904, an extraction module 906 and a fault determination module 908, and performs fault diagnosis on the equipment. Specifically, the sensor component in the acquisition module 902 collects at least one type of operation signal of the equipment to determine the equipment operation data. The data acquisition module 904 cleans and filters the equipment operation data, filters the noise and abnormal values ​​in the equipment operation signal, reduces the interference caused by a large amount of original data, and improves the data acquisition efficiency. Then, the extraction module 906 extracts the characteristics of the cleaned and filtered diagnostic parameters to obtain the characteristic frequency data corresponding to each diagnostic parameter. Finally, at least one characteristic frequency data is input into the fault diagnosis model corresponding to the fault determination module 908, and compared with the fault control threshold, and the sensor sampling point information and fault type determined to have a fault are determined as the fault diagnosis result, and the maintenance measures corresponding to the fault diagnosis result are output. By monitoring and diagnosing different types of operation signals, the efficiency and safety of equipment operation are improved, the maintenance cost is reduced, and the service life of the equipment is extended.

[0063] Optionally, the acquisition module 902 is used to acquire equipment failure history record data; Optionally, the acquisition module 902 is used to determine the data collection time interval according to the data collection frequency; Optionally, an acquisition module 902 is used to determine an outlier boundary according to a data cleaning parameter; Optionally, the acquisition module 902 is used to acquire the device fault type corresponding to the device characteristic data; Optionally, the acquisition module 902 is used to acquire the sampling point position coordinates corresponding to the device characteristic data; Optionally, the data collection module 904 is used to collect the equipment operation data according to the data collection time interval to obtain a first data set; Optionally, the data acquisition module 904 is used to screen the data in the first data set that does not exceed the abnormal value boundary to determine the diagnostic parameters corresponding to the equipment operation data; Optionally, the data acquisition module 904 is used to extract features of historical fault parameters to obtain equipment fault feature data; Optionally, the fault determination module 908 is configured to adjust the data collection parameters according to an adjustment range corresponding to the data collection time interval when the value of the equipment characteristic data does not exceed the fault comparison threshold.

[0064] like Figure 8As shown, an embodiment of the present application provides an electronic device 1000, including a processor 1110, a memory 1109, and a program or instruction stored in the memory 1109 and executable on the processor 1110. When the program or instruction is executed by the processor 1110, the various processes of the embodiment of the above-mentioned fault diagnosis method are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0065] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned fault diagnosis method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0066] The processor is the processor in the electronic device in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0067] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned fault diagnosis method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0068] The fault diagnosis method, device, electronic device, readable storage medium and chip provided by the present invention can reduce the occurrence of unplanned downtime caused by disassembling equipment to find fault information, thereby reducing maintenance costs, improving equipment operating efficiency and safety, and extending equipment service life.

[0069] In the present invention, the terms "first", "second", and "third" are used for descriptive purposes only and should not be understood as indicating or implying relative importance; the term "plurality" refers to two or more, unless otherwise clearly defined. The terms "installed", "connected", "connected", "fixed", etc. should be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral connection; "connected" can be a direct connection or an indirect connection through an intermediate medium. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0070] In the description of the present invention, it is necessary to understand that the directions or positional relationships indicated by terms such as “upper”, “lower”, “left”, “right”, “front” and “back” are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or unit referred to must have a specific direction, be constructed and operated in a specific orientation, and therefore, cannot be understood as a limitation on the present invention.

[0071] In the description of this specification, the description of the terms "one embodiment", "some embodiments", "specific embodiments", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0072] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A fault diagnosis method, characterized in that: include: Acquire device operation data, where the device operation data includes a sampling value corresponding to at least one sampling point; Determining data acquisition parameters, and determining diagnostic parameters corresponding to the device operation data according to the data acquisition parameters; Extracting features of the diagnostic parameters to obtain device feature data; Determining a fault diagnosis model corresponding to the equipment operation data; Determining a fault comparison threshold corresponding to the equipment operation data according to the fault diagnosis model; The device characteristic data is input into the fault diagnosis model to determine a fault diagnosis result corresponding to the fault comparison threshold.

2. The fault diagnosis method according to claim 1, characterized in that: The step of determining the data acquisition parameters and determining the diagnostic parameters corresponding to the device operation data according to the data acquisition parameters includes: Obtain equipment failure history data; Determine the equipment failure type according to the equipment failure history record data; Determine the data collection frequency and data cleaning parameters corresponding to the equipment failure type according to the equipment failure type; A diagnostic parameter corresponding to the equipment operation data is determined according to the data collection frequency and the data cleaning parameter.

3. The fault diagnosis method according to claim 2, characterized in that: The determining of the diagnostic parameter corresponding to the equipment operation data according to the data collection frequency and the data cleaning parameter includes: Determining a data collection time interval according to the data collection frequency; Collecting the equipment operation data according to the data collection time interval to obtain a first data set; Determining outlier boundaries according to the data cleaning parameters; Data in the first data set that does not exceed the abnormal value boundary is screened to determine diagnostic parameters corresponding to the equipment operation data.

4. The fault diagnosis method according to any one of claims 1 to 3, characterized in that: Determining a fault comparison threshold corresponding to the equipment operation data according to the fault diagnosis model includes: Determining historical fault parameters according to the historical fault data of the equipment; The fault diagnosis model extracts features from the historical fault parameters to obtain equipment fault feature data; The equipment fault characteristic data is input into the fault diagnosis model, and a minimum value in the equipment fault characteristic data is determined as a fault comparison threshold.

5. The fault diagnosis method according to claim 4, characterized in that: The step of inputting the device characteristic data into the fault diagnosis model to determine a fault diagnosis result corresponding to the fault comparison threshold value comprises: Inputting the device characteristic data into the fault diagnosis model to determine whether the device characteristic data exceeds the fault comparison threshold; When the value of the device characteristic data does not exceed the fault comparison threshold, the fault diagnosis model adjusts the data acquisition parameter according to the adjustment range corresponding to the data acquisition time interval; When the value of the device characteristic data exceeds the fault comparison threshold, a fault diagnosis result corresponding to the sampling point is determined.

6. The fault diagnosis method according to claim 5, characterized in that: The determining of the fault diagnosis result corresponding to the sampling point includes: Obtaining the device fault type corresponding to the device characteristic data; Obtaining sampling point position coordinates corresponding to the device characteristic data; The fault diagnosis result is determined according to the equipment fault type and the sampling point position coordinates.

7. A fault diagnosis device, characterized in that: include: An acquisition module is used to obtain equipment operation data; A data acquisition module, used to determine data acquisition parameters, and determine diagnostic parameters corresponding to the device operation data according to the data acquisition parameters; An extraction module, used for extracting features from the diagnostic parameters to obtain device feature data; A fault determination module is used to determine a fault diagnosis model corresponding to the equipment operation data; determine a fault comparison threshold corresponding to the equipment operation data according to the fault diagnosis model; input equipment characteristic data into the fault diagnosis model to determine a fault diagnosis result corresponding to the fault comparison threshold.

8. An electronic device, characterized in that: The method comprises a processor, a memory and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the fault diagnosis method as claimed in any one of claims 1 to 6.

9. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the steps of the fault diagnosis method according to any one of claims 1 to 6 are implemented.

10. A chip, characterized in that: The chip includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the steps of the fault diagnosis method according to any one of claims 1 to 6.

Images