Fault detection method, device, electronic device and medium

Abstract

The present disclosure provides a fault detection method, device, equipment, medium and product, which relate to the field of computer technology, specifically to the field of industrial big data and machine learning technology. The fault detection method includes: based on the target frequency range and the frequency of the operating status data of the target device, decomposing the operating status data to obtain frequency interval data corresponding to the target frequency range; extracting features from the frequency interval data to obtain an initial feature set corresponding to the frequency interval data, wherein the initial features in the initial feature set include a category identifier; based on the category identifier, processing the initial feature set to obtain a target feature; based on the target feature, determining fault information for the target device.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, specifically the field of industrial big data and machine learning technology, and more specifically, to a fault detection method, device, electronic device, medium and program product. Background Art

[0002] During the operation of the target equipment, equipment failure may occur in some cases. The target equipment includes mechanical equipment. In order to ensure the normal operation of the equipment, it is necessary to detect the equipment failure in time so as to take relevant measures in time. However, the equipment failure detection method of the related technology has the problems of low accuracy and high cost. Summary of the invention

[0003] The present disclosure provides a fault detection method, device, electronic device, storage medium and program product.

[0004] According to one aspect of the present disclosure, a fault detection method is provided, comprising: based on a target frequency range and the frequency of operating status data of a target device, decomposing the operating status data to obtain frequency interval data corresponding to the target frequency range; performing feature extraction on the frequency interval data to obtain an initial feature set corresponding to the frequency interval data, wherein the initial features in the initial feature set include a category identifier; based on the category identifier, processing the initial feature set to obtain a target feature; and determining fault information for the target device based on the target feature.

[0005] According to another aspect of the present disclosure, a fault detection device is provided, comprising: a decomposition module, an extraction module, a processing module and a first determination module. The decomposition module is used to decompose the operating status data based on the target frequency range and the frequency of the operating status data of the target device to obtain frequency interval data corresponding to the target frequency range; the extraction module is used to extract features from the frequency interval data to obtain an initial feature set corresponding to the frequency interval data, wherein the initial features in the initial feature set include a category identifier; the processing module is used to process the initial feature set based on the category identifier to obtain the target feature; the first determination module is used to determine the fault information for the target device based on the target feature.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor and a memory in communication with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the above-mentioned fault detection method.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the above-mentioned fault detection method.

[0008] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program / instruction, wherein the computer program / instruction implements the steps of the above-mentioned fault detection method when executed by a processor.

[0009] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0011] Figure 1 The system architecture of fault detection according to an embodiment of the present disclosure is schematically shown;

[0012] Figure 2 A flowchart of a fault detection method according to an embodiment of the present disclosure is schematically shown;

[0013] Figure 3 A system diagram schematically shows a fault detection method according to an embodiment of the present disclosure;

[0014] Figure 4 A system diagram of a fault detection method according to another embodiment of the present disclosure is schematically shown;

[0015] Figure 5 A block diagram schematically shows a fault detection device according to an embodiment of the present disclosure; and

[0016] Figure 6 is a block diagram of an electronic device for performing fault detection for implementing an embodiment of the present disclosure. DETAILED DESCRIPTION

[0017] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0018] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0019] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0020] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0021] Figure 1 The system architecture of fault detection according to an embodiment of the present disclosure is schematically shown. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0022] like Figure 1 As shown, the system architecture 100 according to this embodiment may include data acquisition devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the data acquisition devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0023] The data acquisition devices 101 , 102 , 103 may be various electronic devices with data acquisition functions, including but not limited to temperature sensors, pressure sensors, equipment wear sensors, and the like.

[0024] The server 105 may be a server that provides various services, such as a background management server that provides support for websites browsed by users using the data acquisition devices 101, 102, and 103 (only as an example). The background management server may analyze the received data and process the results. The server 105 may also be a cloud server, that is, the server 105 has a cloud computing function.

[0025] It should be noted that the fault detection method provided in the embodiment of the present disclosure may be executed by the server 105. Accordingly, the fault detection device provided in the embodiment of the present disclosure may be arranged in the server 105.

[0026] In one example, the data acquisition devices 101, 102, and 103 are used to collect operating status data of a target device, and the target device includes, for example, mechanical equipment, including but not limited to aircraft, steam turbines, gas turbines, machine tools, etc. The data acquisition devices 101, 102, and 103 can send the collected operating status data to the server 105 through the network 104. The server 105 can process the operating status data to obtain fault information for the target device.

[0027] It should be understood that Figure 1 The number of data acquisition devices, networks and servers in the embodiment is only for illustration. Any number of data acquisition devices, networks and servers may be provided according to the implementation requirements.

[0028] Combine the following Figure 1 The system architecture of Figure 2 to Figure 4 The fault detection method according to the exemplary embodiment of the present disclosure is described as follows. The fault detection method of the embodiment of the present disclosure can be, for example, Figure 1 The server shown is executed, Figure 1 The server shown is, for example, the same as or similar to the electronic device described below.

[0029] Figure 2 The flowchart of a fault detection method according to an embodiment of the present disclosure is schematically shown.

[0030] like Figure 2 As shown, the fault detection method 200 of the embodiment of the present disclosure may include, for example, operations S210 to S240.

[0031] In operation S210, based on the target frequency range and the frequency of the operating status data of the target device, the operating status data is decomposed to obtain frequency interval data corresponding to the target frequency range.

[0032] In operation S220, feature extraction is performed on the frequency interval data to obtain an initial feature set corresponding to the frequency interval data, where initial features in the initial feature set include a category identifier.

[0033] In operation S230 , the initial feature set is processed based on the category identifier to obtain target features.

[0034] In operation S240 , fault information for the target device is determined based on the target feature.

[0035] Exemplarily, the target frequency range may include multiple ones, for example, a target frequency range [a, b], a target frequency range (b, c], a target frequency range (c, d], etc., where a, b, c, d are frequency values. Of course, there may be some overlap in values ​​between the target frequency ranges, and the embodiments of the present disclosure do not limit the specific values ​​of the target frequency ranges.

[0036] Exemplarily, the target equipment includes mechanical equipment, such as aircraft, steam turbines, gas turbines, machine tools, etc. The operating status data includes pressure data, temperature data, bearing force data, sealing force data, gap airflow excitation data, machine tool tool wear data, etc.

[0037] Based on the target frequency range, the corresponding relationship between the frequency of the operating status data of the target device and the target frequency range is determined, and the operating status data of the target device is decomposed based on the corresponding relationship to obtain multiple frequency interval data corresponding to multiple target frequency ranges. The frequency of each frequency interval data falls within the corresponding target frequency range.

[0038] After decomposing the operating status data into multiple frequency interval data, feature extraction is performed on each frequency interval data to obtain an initial feature set corresponding to each frequency interval. The initial feature set includes multiple initial features, each initial feature has a category label, and the category label represents the category to which the initial feature belongs.

[0039] After obtaining multiple initial feature sets, the multiple initial feature sets can be processed based on the category labels of the initial features to obtain target features. Then, fault information for the target device is determined based on the target features, for example, the fault condition of the target device is predicted based on the target features, that is, the fault information can represent whether the target device has a fault, and can also represent the probability of the target device failing in the future.

[0040] According to an embodiment of the present disclosure, based on the target frequency range and the frequency of the operating status data of the target device, the operating status data is decomposed into multiple frequency interval data, and then feature extraction and feature processing are performed on each frequency interval data to obtain the target feature, and the fault information of the device is determined based on the target feature. It can be understood that since the frequency value span of the operating status data is too large, the accuracy of the feature is improved by decomposing the operating status data and then extracting the feature, thereby improving the accuracy of the fault detection.

[0041] According to another embodiment of the present disclosure, the target frequency range can be pre-set, and the target frequency range can also be determined based on the frequency distribution of the operating status data of the target device. For example, when it is known from the frequency distribution of the operating status data that the frequency of the operating status data is concentrated in certain intervals, the concentrated intervals can be used as the target frequency range, thereby improving the flexibility of determining the target frequency range, improving the matching degree between the target frequency range and the operating status data, and thus improving the effect of subsequent feature extraction.

[0042] Figure 3 A system diagram of a fault detection method according to an embodiment of the present disclosure is schematically shown.

[0043] like Figure 3 As shown, for the operation status data 310 of the target device, the operation status data 310 is decomposed to obtain multiple frequency interval data. The multiple frequency interval data include, for example, first frequency interval data 321, second frequency interval data 322, and third frequency interval data 323. The frequency of the first frequency interval data 321 is greater than or equal to the frequency of the second frequency interval data 322, and the frequency of the second frequency interval data 322 is greater than or equal to the frequency of the third frequency interval data 323. In other words, the first frequency interval data 321 is, for example, high-frequency data, the second frequency interval data 322 is, for example, medium-frequency data, and the third frequency interval data 323 is, for example, low-frequency data, that is, the operation status data 310 is decomposed into high-frequency data, medium-frequency data, and low-frequency data.

[0044] After obtaining the first frequency interval data 321, the second frequency interval data 322, and the third frequency interval data 323, feature extraction is performed on the first frequency interval data 321 to obtain an initial feature set 331, feature extraction is performed on the second frequency interval data 322 to obtain an initial feature set 332, and feature extraction is performed on the third frequency interval data 323 to obtain an initial feature set 333.

[0045] Exemplarily, each of the initial feature set 331, the initial feature set 332, and the initial feature set 333 includes a plurality of initial features, and each initial feature has a category identifier. Based on the category identifier, feature processing is performed on the initial feature set 331, the initial feature set 332, and the initial feature set 333 to obtain a target feature 340, and based on the target feature 340, fault information 350 for the target device is obtained.

[0046] According to the embodiments of the present disclosure, by decomposing the operating status data into high-frequency data, medium-frequency data, and low-frequency data, and performing feature extraction on the high-frequency data, medium-frequency data, and low-frequency data respectively, the extracted features have higher accuracy and higher efficiency of feature extraction, and fault detection is performed based on target features with higher accuracy, thereby improving the effect of fault detection.

[0047] Figure 4 A system diagram of a fault detection method according to another embodiment of the present disclosure is schematically shown.

[0048] like Figure 4 As shown, for the operation status data 410, before decomposing the operation status data 410, the operation status data 410 may be preprocessed. The preprocessing includes filling missing values, removing outliers, unifying quantities, normalizing, and the like.

[0049] For the preprocessed operating state data 410, based on the target frequency range and the frequency of the operating state data 410, the operating state data 410 is decomposed to obtain first frequency interval data 421, second frequency interval data 422, and third frequency interval data 423. The first frequency interval data 421, for example, includes high-frequency data, the second frequency interval data 422, for example, includes medium-frequency data, and the third frequency interval data 423, for example, includes low-frequency data. The decomposition method includes, for example, an empirical mode decomposition (EMD) method.

[0050] Next, feature extraction is performed on the first frequency interval data 421 to obtain an initial feature set 431 , feature extraction is performed on the second frequency interval data 422 to obtain an initial feature set 432 , and feature extraction is performed on the third frequency interval data 423 to obtain an initial feature set 433 .

[0051] For any one of the initial feature set 431, the initial feature set 432, and the initial feature set 433, the set includes, for example, at least one category of features. The at least one category of features includes, for example, time domain category features, frequency domain category features, and time-frequency domain category features. The category identifier of the time domain category feature is, for example, a time domain identifier, the category identifier of the frequency domain category feature is, for example, a frequency domain identifier, and the category identifier of the time-frequency domain category feature is, for example, a time-frequency domain identifier.

[0052] According to the embodiments of the present disclosure, multi-category features are obtained by extracting features from frequency interval data, thereby increasing the breadth of features and making the extracted features include more fault-related information, thereby improving the accuracy of fault detection.

[0053] When performing feature processing on initial feature set 431, initial feature set 432, and initial feature set 433 to obtain target feature 440, the initial features of each set in initial feature set 431, initial feature set 432, and initial feature set 433 may be processed separately, or the initial features in all sets such as initial feature set 431, initial feature set 432, and initial feature set 433 may be processed.

[0054] In an example, when any one or more of the initial feature set 431 , the initial feature set 432 , and the initial feature set 433 include multiple time-domain category features, feature processing is performed on the multiple time-domain category features to obtain the target feature 440 .

[0055] Exemplarily, the category identifier of the time domain category feature is, for example, a time domain identifier. Based on the category identifier, multiple time domain category features are determined from the set, and any multiple of the multiple time domain category features are combined to obtain a first combined feature. Any multiple combinations include any two or more combinations. Then, the multiple time domain category features and the first combined feature are determined as target features 440.

[0056] For example, the time domain category features include mean, root mean square, pulse, kurtosis, margin, peak, mean square error, kurtosis, skewness, etc. The first combination feature includes, for example, a combination feature of mean and root mean square, a combination feature of root mean square and pulse, and the like.

[0057] In another example, when any one or more of the initial feature set 431 , the initial feature set 432 , and the initial feature set 433 include multiple frequency domain category features, feature processing is performed on the multiple frequency domain category features to obtain the target feature 440 .

[0058] Exemplarily, the category identifier of the frequency domain category feature is, for example, a frequency domain identifier. Based on the category identifier, multiple frequency domain category features are determined from the set, and any multiple of the multiple frequency domain category features are combined to obtain a second combined feature. Any multiple combinations include any two or more combinations. Then, the multiple frequency domain category features and the second combined feature are determined as the target feature 440.

[0059] For example, frequency domain category features include power spectrum standard deviation, power spectrum sum, power spectrum mean, power spectrum skewness, power spectrum kurtosis, power spectrum relative peak, maximum frequency, etc. The second combination feature includes, for example, a combination feature of power spectrum standard deviation and power spectrum sum, a combination feature of power spectrum mean and power spectrum skewness, etc.

[0060] In another example, when any one or more of the initial feature set 431 , the initial feature set 432 , and the initial feature set 433 include time domain category features and frequency domain category features, feature processing is performed on the time domain category features and the frequency domain category features to obtain the target feature 440 .

[0061] For example, based on the category identifier, the time domain category feature and the frequency domain category feature are determined from the set, the time domain category feature and the frequency domain category feature are combined to obtain a third combined feature, and then the time domain category feature, the frequency domain category feature and the third combined feature are determined as the target feature 440.

[0062] For example, time domain category features include mean, root mean square, etc., frequency domain category features include power spectrum standard deviation, power spectrum sum, etc. The third combination feature includes, for example, a combination feature of mean and power spectrum standard deviation, a combination feature of root mean square and power spectrum sum, etc.

[0063] In another example, the time-frequency domain category feature can be obtained by extracting features from each frequency interval data using fast Fourier transform, wavelet decomposition, etc., and the category identifier of the time-frequency domain category feature is, for example, the time-frequency domain identifier. When any one or more of the initial feature set 431, the initial feature set 432, and the initial feature set 433 include the time-frequency domain category feature, the time-frequency domain category feature is determined from the set based on the category identifier, and the time-frequency domain category feature is determined as the target feature 440.

[0064] Therefore, the target feature 440 includes, for example, any one or more of the time domain category feature, the frequency domain category feature, the time-frequency domain category feature, the first combination feature, the second combination feature, and the third combination feature.

[0065] According to the embodiments of the present disclosure, initial features are combined to further improve the categories of features, and the fault information obtained by performing fault detection based on multi-category features is more accurate.

[0066] After the target features 440 are obtained, important features 450 may be selected from the target features 440 , and fault information 470 for the target device may be obtained based on the important features 450 .

[0067] For example, the importance of the target feature 440 is determined based on the historical fault information, and then the important feature 450 is selected from the target feature 440 based on the importance.

[0068] For example, a feature evaluation model is trained based on historical fault information, the target feature 440 is input into the feature evaluation model, the feature evaluation model outputs the importance, and based on the importance, an important feature 450 is selected. The feature evaluation model includes, for example, an Extreme Gradient Boosting (XGBoost) model, a Logistic Regression (LR) model, and the like.

[0069] In addition, the important features 450 may be selected from the target features 440 by using principal component analysis (PCA).

[0070] After obtaining the important features 450, the important features 450 can be input into a machine learning model 460 to output fault information 470 for the target device.

[0071] Exemplarily, the machine learning model 460 includes, for example, an autoregressive model (Autoregressive, AR), an autoregressive moving average model (Autoregressive Moving Average, ARMA), an extreme gradient boosting model (Extreme Gradient Boosting, XGBoost), and the like.

[0072] According to the embodiments of the present disclosure, after obtaining the target features, in order to prevent some irrelevant features from affecting the effect of fault detection, important features can be further screened out from the target features, and fault detection can be performed based on the important features, which can improve the detection effect and detection accuracy.

[0073] It can be understood that the fault detection method of the embodiment of the present disclosure is suitable for detecting different types of target devices. There is no need to manually analyze the working principles of different target devices to perform data analysis or feature analysis, which reduces the requirements for professional knowledge in fault prediction, improves the fault detection effect, and reduces the detection cost.

[0074] Figure 5 A block diagram of a fault detection device according to an embodiment of the present disclosure is schematically shown.

[0075] like Figure 5 As shown, the fault detection device 500 of the embodiment of the present disclosure includes, for example, a decomposition module 510 , an extraction module 520 , a processing module 530 and a first determination module 540 .

[0076] The decomposition module 510 may be used to decompose the operating status data based on the target frequency range and the frequency of the operating status data of the target device to obtain frequency interval data corresponding to the target frequency range. According to an embodiment of the present disclosure, the decomposition module 510 may, for example, execute the above reference Figure 2 The operation S210 described above will not be described in detail here.

[0077] The extraction module 520 may be used to extract features from the frequency interval data to obtain an initial feature set corresponding to the frequency interval data, wherein the initial features in the initial feature set include a category identifier. According to an embodiment of the present disclosure, the extraction module 520 may, for example, perform the above reference Figure 2 The operation S220 described above will not be described in detail here.

[0078] The processing module 530 may be used to process the initial feature set based on the category identifier to obtain the target feature. According to the embodiment of the present disclosure, the processing module 530 may, for example, execute the above reference Figure 2 The operation S230 described above will not be described in detail here.

[0079] The first determination module 540 may be used to determine fault information for a target device based on the target feature. According to an embodiment of the present disclosure, the first determination module 540 may, for example, execute the above reference Figure 2 The operation S240 described above will not be described in detail here.

[0080] According to an embodiment of the present disclosure, the initial feature set includes multiple time domain category features; the processing module 530 includes: a first combination submodule and a first determination submodule. The first combination submodule is used to combine any multiple of the multiple time domain category features to obtain a first combination feature; the first determination submodule is used to determine the multiple time domain category features and the first combination feature as the target feature.

[0081] According to an embodiment of the present disclosure, the initial feature set includes multiple frequency domain category features; the processing module 530 includes: a second combination submodule and a second determination submodule. The second combination submodule is used to combine any multiple of the multiple frequency domain category features to obtain a second combination feature; the second determination submodule is used to determine the multiple frequency domain category features and the second combination feature as the target feature.

[0082] According to an embodiment of the present disclosure, the initial feature set includes time domain category features and frequency domain category features; the processing module 530 includes: a third combination submodule and a third determination submodule. The third combination submodule is used to combine the time domain category features and the frequency domain category features to obtain a third combination feature; the third determination submodule is used to determine the time domain category features, the frequency domain category features and the third combination features as target features.

[0083] According to an embodiment of the present disclosure, the initial feature set includes time-frequency domain category features; the processing module 530 includes: a fourth determination submodule, configured to determine the time-frequency domain category features as target features.

[0084] According to an embodiment of the present disclosure, the first determination module 540 includes: a fifth determination submodule, a selection submodule and an acquisition module. The fifth determination submodule is used to determine the importance of the target feature based on historical fault information; the selection submodule is used to select important features from the target features based on the importance; the acquisition module is used to input the important features into the machine learning model to obtain fault information for the target device.

[0085] According to an embodiment of the present disclosure, the apparatus 500 may further include: a second determination module, configured to determine a target frequency range based on a frequency distribution of operating status data of a target device.

[0086] According to an embodiment of the present disclosure, the frequency interval data includes first frequency interval data, second frequency interval data, and third frequency interval data, the frequency of the first frequency interval data is greater than or equal to the frequency of the second frequency interval data, and the frequency of the second frequency interval data is greater than or equal to the frequency of the third frequency interval data.

[0087] According to an embodiment of the present disclosure, the time domain category feature includes at least one of the following: mean, root mean square, pulse, kurtosis, margin, peak, mean square error, kurtosis, and skewness.

[0088] According to an embodiment of the present disclosure, the frequency domain category features include at least one of the following: power spectrum standard deviation, power spectrum sum, power spectrum mean, power spectrum skewness, power spectrum kurtosis, power spectrum relative peak value, and maximum value frequency.

[0089] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision, disclosure and application of user personal information involved comply with the provisions of relevant laws and regulations, take necessary confidentiality measures, and do not violate public order and good morals.

[0090] In the technical solution of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0091] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0092] According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, where the computer instructions are used to enable a computer to execute the fault detection method described above.

[0093] According to an embodiment of the present disclosure, a computer program product is provided, including a computer program / instruction, and when the computer program / instruction is executed by a processor, the fault detection method described above is implemented.

[0094] Figure 6 is a block diagram of an electronic device for performing fault detection for implementing an embodiment of the present disclosure.

[0095] Figure 6A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device 600 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0096] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0097] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0098] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as a fault detection method. For example, in some embodiments, the fault detection method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the fault detection method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the fault detection method in any other appropriate manner (e.g., by means of firmware).

[0099] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0100] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable fault detection device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0101] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), 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 foregoing.

[0102] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0103] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0104] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0105] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0106] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A fault detection method, include: Determining a plurality of frequency intervals based on a frequency distribution of the operating status data of the target device, wherein the frequency of the operating status data of the target device spans the plurality of frequency intervals; Based on the multiple frequency intervals and the frequencies of the operation status data of the target device, the operation status data is decomposed to obtain multiple frequency interval data corresponding to the multiple frequency intervals respectively; Performing feature extraction on the multiple frequency interval data respectively to obtain multiple initial feature sets corresponding to the multiple frequency intervals respectively, wherein the initial features in the initial feature sets include category identifiers, and the categories include time domain and frequency domain; Based on the category identifier, combining the category features in the multiple initial feature sets to obtain a target feature; and Based on the target feature, determining fault information for the target device; The combining of the features of each category in the multiple initial feature sets to obtain the target feature includes: Determine a plurality of time domain category features and a plurality of frequency domain category features from a plurality of initial feature sets corresponding to the plurality of frequency intervals respectively; The target feature is obtained by combining multiple time domain category features and multiple frequency domain category features from different frequency intervals.

2. The method according to claim 1, in, The combining of multiple time domain category features and multiple frequency domain category features from different frequency intervals to obtain the target feature includes: Combining any multiple of the multiple time-domain category features from different frequency intervals to obtain a first combined feature; and The multiple time-domain category features from different frequency intervals and the first combined feature are determined as the target features.

3. The method according to claim 1 or 2, in, The combining of multiple time domain category features and multiple frequency domain category features from different frequency intervals to obtain the target feature includes: Combining any multiple of the multiple frequency domain category features from different frequency intervals to obtain a second combined feature; and The multiple frequency domain category features from different frequency intervals and the second combined feature are determined as the target feature.

4. The method according to claim 1, in, The combining of multiple time domain category features and multiple frequency domain category features from different frequency intervals to obtain the target feature includes: Combining the time domain category features and the frequency domain category features from different frequency intervals to obtain a third combined feature; and The time domain category feature, the frequency domain category feature and the third combined feature from different frequency intervals are determined as the target feature.

5. The method according to claim 1, in, The initial feature set includes time-frequency domain category features; the target feature is obtained by combining multiple time-domain category features and multiple frequency-domain category features from different frequency intervals, including: The time-frequency domain category features from different frequency intervals are determined as the target features.

6. The method according to claim 1, in, The determining, based on the target feature, the fault information of the target device comprises: Based on historical fault information, determining the importance of the target feature; Based on the importance, selecting important features from the target features; and The important features are input into a machine learning model to obtain fault information for the target device.

7. The method according to claim 1, in, The frequency interval data includes first frequency interval data, second frequency interval data, and third frequency interval data. The frequency of the first frequency interval data is greater than or equal to the frequency of the second frequency interval data, and the frequency of the second frequency interval data is greater than or equal to the frequency of the third frequency interval data.

8. The method according to claim 2, in, The time domain category feature includes at least one of the following: Mean, RMS, impulse, kurtosis, margin, peak, mean square error, kurtosis, skewness.

9. The method according to claim 3, in, The frequency domain category feature includes at least one of the following: Power spectrum standard deviation, power spectrum sum, power spectrum mean, power spectrum skewness, power spectrum kurtosis, power spectrum relative peak value, maximum value frequency.

10. A fault detection device, include: a target frequency range determination module, configured to determine a plurality of frequency intervals based on the frequency distribution of the operating status data of the target device, wherein the frequency of the operating status data of the target device spans the plurality of frequency intervals; a decomposition module, configured to decompose the operating status data based on the multiple frequency intervals and the frequencies of the operating status data of the target device to obtain multiple frequency interval data corresponding to the multiple frequency intervals respectively; An extraction module is used to perform feature extraction on the multiple frequency interval data respectively to obtain multiple initial feature sets corresponding to the multiple frequency intervals respectively, wherein the initial features in the initial feature sets include category identifiers, and the categories include time domain and frequency domain; a processing module, configured to combine the features of each category in the plurality of initial feature sets based on the category identifier to obtain a target feature; and A first determination module, configured to determine fault information for the target device based on the target feature; The processing module is also used to determine multiple time domain category features and multiple frequency domain category features from multiple initial feature sets corresponding to the multiple frequency intervals respectively; and combine the multiple time domain category features and multiple frequency domain category features from different frequency intervals to obtain the target feature.

11. The device according to claim 10, in, The processing module comprises: A first combining submodule, configured to combine any multiple of the multiple time domain category features from different frequency intervals to obtain a first combined feature; and The first determination submodule is used to determine the multiple time domain category features from different frequency intervals and the first combined feature as the target feature.

12. The device according to claim 10 or 11, in, The processing module comprises: A second combining submodule, configured to combine any plurality of the plurality of frequency domain category features from different frequency intervals to obtain a second combined feature; and The second determination submodule is used to determine the multiple frequency domain category features from different frequency intervals and the second combined feature as the target feature.

13. The device according to claim 10, in, The processing module comprises: a third combining submodule, configured to combine the time domain category features and the frequency domain category features from different frequency intervals to obtain a third combined feature; and The third determination submodule is used to determine the time domain category feature, the frequency domain category feature and the third combination feature from different frequency intervals as the target feature.

14. The device according to claim 10, in, The initial feature set includes time-frequency domain category features; the processing module includes: The fourth determination submodule is used to determine the time-frequency domain category features from different frequency intervals as the target features.

15. The device according to claim 10, in, The first determining module comprises: A fifth determination submodule, configured to determine the importance of the target feature based on historical fault information; A selection submodule, configured to select important features from the target features based on the importance; and The acquisition module is used to input the important features into the machine learning model to obtain fault information for the target device.

16. The device according to claim 10, in, The frequency interval data includes first frequency interval data, second frequency interval data, and third frequency interval data. The frequency of the first frequency interval data is greater than or equal to the frequency of the second frequency interval data, and the frequency of the second frequency interval data is greater than or equal to the frequency of the third frequency interval data.

17. The device according to claim 11, in, The time domain category feature includes at least one of the following: Mean, RMS, impulse, kurtosis, margin, peak, mean square error, kurtosis, skewness.

18. The device according to claim 12, in, The frequency domain category feature includes at least one of the following: Power spectrum standard deviation, power spectrum sum, power spectrum mean, power spectrum skewness, power spectrum kurtosis, power spectrum relative peak value, maximum value frequency.

19. An electronic device, include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 9.

20. A non-transitory computer-readable storage medium storing computer instructions, in, The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 9.

21. A computer program product comprising a computer program / instructions, It is characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

Images