Method, device and electronic equipment for identifying equipment failure

Abstract

The present disclosure provides a method, device and electronic device for identifying equipment failures, which relate to the field of industrial big data, and in particular to the field of artificial intelligence. The specific implementation scheme is: obtaining sound data when a failure occurs in the equipment to be detected; extracting features from the sound data to obtain sound combination features corresponding to the sound data; determining a target combination feature from multiple combination features contained in a preset sample library, wherein the similarity between the target combination feature and the sound combination feature meets a preset condition, and the preset sample library at least includes: at least one fault type label, multiple combination features, and the multiple combination features are determined based on the historical environmental information of the equipment to be detected and the sound data when the equipment to be detected has a historical failure; determining the fault type of the equipment to be detected according to the target fault type label corresponding to the target combination feature. The present disclosure at least solves the technical problem of low accuracy in fault sound recognition existing in the prior art.

Description

Technical Field

[0001] The present disclosure relates to the field of industrial big data, and in particular to the field of artificial intelligence. Specifically, it relates to a method, device and electronic device for identifying equipment failure. Background Art

[0002] Sound is a very common and important factor in industrial scenarios. Industrial equipment will make a variety of sounds during operation, and when industrial equipment fails, the corresponding sound will also change. Therefore, by collecting and analyzing the sounds emitted by industrial equipment, the operating status of industrial equipment can be identified.

[0003] However, the existing technology for studying sound in industrial scenarios is based on speech recognition technology, which has very high requirements for the quantity and quality of sound data. Any slight change in the sound data will affect the accuracy of the overall analysis results. Summary of the invention

[0004] The present disclosure provides a method, apparatus and electronic device for identifying equipment failure. According to one aspect of the present disclosure, a method for identifying equipment failure is provided, comprising: obtaining sound data when a failure occurs in a device to be detected; performing feature extraction on the sound data to obtain a sound combination feature corresponding to the sound data, wherein the sound combination feature is composed of multiple sound features; determining a target combination feature from multiple combination features contained in a preset sample library, wherein the similarity between the target combination feature and the sound combination feature meets a preset condition, and the preset sample library at least includes: at least one fault type label, multiple combination features, and the multiple combination features are determined based on historical environmental information of the device to be detected and sound data when a historical failure occurs in the device to be detected; determining the fault type of the device to be detected according to the target fault type label corresponding to the target combination feature.

[0005] Furthermore, the method for identifying equipment failure also includes: performing a first feature extraction on the sound data to obtain a spectrum feature; performing a second feature extraction on the sound data to obtain a frequency cepstrum coefficient feature, wherein the sound combination feature includes at least a spectrum feature and a frequency cepstrum coefficient feature.

[0006] Furthermore, the method for identifying device failure also includes: before determining the target combined feature from multiple combined features included in the preset sample library, obtaining a device identification corresponding to the device to be detected; and determining a preset sample library corresponding to the device identification from multiple sample libraries.

[0007] Furthermore, the method for identifying equipment failure also includes: obtaining multiple first sound features and multiple second sound features from a preset sample library, wherein the feature type of the multiple first sound features is the same as the feature type of the spectral feature, and the feature type of the multiple second sound features is the same as the feature type of the frequency cepstrum coefficient feature; calculating the cosine similarity between each first sound feature in the multiple first sound features and the spectral feature to obtain multiple first similarities; determining multiple first target features from the multiple first sound features based on the multiple first similarities; calculating the cosine similarity between each second sound feature in the multiple second sound features and the frequency cepstrum coefficient feature to obtain multiple second similarities; determining multiple second target features from the multiple second sound features based on the multiple second similarities; combining the multiple first target features and the multiple second target features to obtain multiple combined features; and determining the target combined feature from the multiple combined features.

[0008] Furthermore, the method for identifying equipment failure also includes: obtaining a first weight value corresponding to a first target feature in each of a plurality of combined features, and a second weight value corresponding to a second target feature in each of a plurality of combined features; calculating a third similarity between the first target feature in each of a plurality of combined features and a spectrum feature, and a fourth similarity between the second target feature in each of a plurality of combined features and a frequency cepstral coefficient feature; calculating a score value corresponding to each of a plurality of combined features according to the first weight value, the second weight value, the third similarity and the fourth similarity; and determining a target combined feature from a plurality of combined features according to the score value.

[0009] Furthermore, the method for identifying equipment failures also includes: after determining the fault type of the equipment to be detected based on the target fault type label corresponding to the target combination feature, responding to the target object's adjustment instruction for the fault type; adjusting any one or more of the parameters, first weight value, and second weight value in the feature extraction function based on the adjustment instruction, wherein the feature extraction function is used to extract features from sound data.

[0010] Furthermore, the method for identifying equipment failures also includes: after determining the failure type of the equipment to be detected according to the target failure type label corresponding to the target combination feature, updating the preset sample library based on the sound spectrum feature and / or the frequency cepstrum coefficient feature.

[0011] Furthermore, the method for identifying equipment failure also includes: performing frame processing on the sound data to obtain multiple frames of first sound data; performing windowing processing on the multiple frames of first sound data to obtain multiple frames of second sound data; performing Fourier transform on the multiple frames of second sound data to obtain multiple frames of third sound data; and performing stacking processing on the multiple frames of third sound data to obtain spectral features.

[0012] Furthermore, the method for identifying equipment failure also includes: pre-emphasizing the sound data to obtain fourth sound data; framing and windowing the fourth sound data to obtain fifth sound data; performing Fourier transform on the fifth sound data to obtain sixth sound data; filtering the sixth sound data to obtain filtered sixth sound data; performing logarithmic calculation on the filtered sixth sound data to obtain seventh sound data; performing discrete cosine transform on the seventh sound data to obtain frequency cepstrum coefficient characteristics.

[0013] According to another aspect of the present disclosure, there is provided a device for identifying equipment failure, comprising: an acquisition module for acquiring sound data when a failure occurs in the equipment to be detected; a feature extraction module for performing feature extraction on the sound data to obtain a sound combination feature corresponding to the sound data, wherein the sound combination feature is composed of a plurality of sound features; a feature determination module for determining a target combination feature from a plurality of combination features contained in a preset sample library, wherein a similarity between the target combination feature and the sound combination feature satisfies a preset condition, and the preset sample library comprises at least: at least one fault type label, a plurality of combination features, and the plurality of combination features are determined based on historical environmental information of the equipment to be detected and sound data when historical failures occur in the equipment to be detected; and an identification module for determining the fault type of the equipment to be detected according to the target fault type label corresponding to the target combination feature.

[0014] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to 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 execute the above-mentioned method for identifying device failures.

[0015] 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 a computer to execute the above-mentioned method for identifying device failures.

[0016] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the computer program implements the above-mentioned method for identifying device failure.

[0017] In the technical solution disclosed in the present invention, a method of associating multiple combined features with at least one fault type label is adopted. After obtaining the sound data when the device to be detected fails, the sound data is feature extracted to obtain the sound combined features corresponding to the sound data, and then the target combined features are determined from the multiple combined features contained in the preset sample library, and then the fault type of the device to be detected is determined according to the target fault type label corresponding to the target combined features. Among them, the sound combined features are composed of multiple sound features, and the similarity between the target combined features and the sound combined features meets the preset conditions. The preset sample library at least includes: at least one fault type label, multiple combined features, and the multiple combined features are determined based on the historical environmental information of the device to be detected and the sound data when the device to be detected has historical faults.

[0018] As can be seen from the above content, since the sound combination feature in the present disclosure includes a plurality of sound features, the present disclosure can comprehensively determine the target combination feature from the preset sample library from multiple dimensions. Compared with determining the target combination feature according to one sound feature, the technical solution of the present disclosure has the advantages of being more comprehensive and more accurate when determining the target combination feature, thereby improving the recognition accuracy of the equipment fault sound. In addition, since the plurality of combination features in the preset sample library in the present disclosure are determined based on the historical environmental information of the equipment to be detected and the sound data when the equipment to be detected has a historical fault, even if there is an interference sound in the external environment, the present disclosure can still determine the target combination feature corresponding to the equipment to be detected by combining the environmental sound with the equipment operation sound, and determine the fault type of the equipment to be detected according to the target combination feature, thereby solving the technical problem of low fault sound recognition accuracy caused by poor anti-interference ability in the prior art. In addition, the present disclosure can not only determine whether the equipment to be detected has a fault, but also determine the fault type of the equipment to be detected when the equipment to be detected has a fault through the target fault type label corresponding to the target combination feature, which is conducive to improving the equipment maintenance efficiency.

[0019] It can be seen that through the technical solution of the present application, the purpose of accurately determining the fault type of the equipment to be detected through sound data is achieved, thereby achieving the effect of ensuring the stable operation of the equipment, and further solving the technical problem of low accuracy of fault sound recognition existing in the prior art.

[0020] 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

[0021] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0022] Figure 1 is a flow chart of a method for identifying a device failure according to an embodiment of the present disclosure;

[0023] Figure 2 is a flowchart of a first feature extraction process according to an embodiment of the present disclosure;

[0024] Figure 3 is a flowchart of a second feature extraction process according to an embodiment of the present disclosure;

[0025] Figure 4 is a flow chart of a method for identifying a device failure according to an embodiment of the present disclosure;

[0026] Figure 5 is a schematic diagram of an apparatus for identifying equipment failure according to an embodiment of the present disclosure;

[0027] Figure 6 The present invention is a block diagram of an electronic device for implementing the method for identifying device failure according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] 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, the description of well-known functions and structures is omitted in the following description.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0030] In addition, it should be noted that the acquisition, storage and application of user personal information involved in the technical solution of the present disclosure are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0031] Example 1

[0032] According to an embodiment of the present disclosure, a method embodiment for identifying equipment failure is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0033] In addition, it should be noted that the electronic device can be used as the executor of the method for identifying device failure in the present disclosure.

[0034] Figure 1 is a flow chart of a method for identifying a device failure according to an embodiment of the present disclosure, such as Figure 1 As shown, the method comprises the following steps:

[0035] Step S102, obtaining sound data when a failure occurs in the device to be detected.

[0036] In step S102, the device to be detected may be industrial equipment in an industrial scenario, such as machine tools, manipulators, and mechanical arms. Wherein, the industrial equipment will make a sound when it is working normally, and when the industrial equipment fails, the sound emitted by the industrial equipment will change according to different fault types. In addition, the electronic device can obtain the sound data of the device to be detected through a sound sensor installed on the device to be detected. Wherein, the sound sensor can be installed in the device to be detected, and after the sound sensor collects the sound data of the device to be detected, the sound data is sent to the electronic device, and the electronic device saves the sound data as an audio file. In addition, the sound data of the device to be detected at least includes the sound data when the device to be detected fails, and the sound data when the device to be detected is operating normally. In addition, the sound data of the device to be detected may also include environmental sound data in the surrounding environment.

[0037] It should be noted that the existing technologies for studying sound data in industrial scenarios are all based on speech recognition technology. Specifically, the existing technologies can extract standard features from sound data, train Markov models, neural network models, and some hybrid models based on the standard features, thereby generating a fault sound detection model, and identify the sound emitted by industrial equipment based on the fault sound detection model to determine the status of the industrial equipment.

[0038] However, judging the status of industrial equipment based on the fault sound detection model requires a high amount of sound data and quality. However, due to the complexity of the actual production environment, it is difficult to collect a large amount of sound data in industrial scenarios, especially a large amount of high-quality sound data. This will lead to the problem of low fault sound recognition accuracy of the fault sound detection model. In addition, the accuracy of the fault sound detection model is easily affected by the external environment. When the collected sound data changes slightly, the prediction results of the fault sound detection model may be wrong. Especially in some scenarios with high requirements for fault type location, the recognition accuracy of the fault sound detection model is often difficult to achieve ideal results.

[0039] In the present disclosure, since the collected sound data includes ambient sounds, and the multiple combination features in the preset sample library are also determined based on the historical environmental information of the device to be detected and the sound data when the device to be detected has historical faults, even if interference sounds appear in the external environment, the present disclosure can still combine the ambient sounds and the device operation sounds to jointly determine the target combination features corresponding to the device to be detected, and determine the fault type of the device to be detected based on the target combination features, thereby solving the problem of low fault sound recognition accuracy caused by the poor anti-interference ability of the fault sound detection model, and achieving the effect of stably identifying the fault type of the device to be detected without the need for a lot of high-quality sound data.

[0040] Step S104, extracting features from the sound data to obtain sound combination features corresponding to the sound data.

[0041] In step S104, the sound combination feature is composed of a plurality of sound features, wherein the plurality of sound features at least include: a spectrum feature and a frequency cepstrum coefficient feature.

[0042] Optionally, the electronic device can generate a sound spectrum Figure 2 The electronic device can also extract features from the sound data by using the MFCC (Mel Frequency Cepstrum Coefficient) feature extraction method to obtain the frequency cepstrum coefficient features (i.e., MFCC features) corresponding to the sound data.

[0043] It should be noted that since the sound combination features in the present disclosure are composed of at least two sound features, the present disclosure can comprehensively consider multiple dimensions to determine the target combination features from a preset sample library. Compared with determining the target combination features based on one sound feature, the present disclosure has the advantages of being more comprehensive and accurate, which is conducive to further improving the recognition accuracy of equipment fault sounds.

[0044] Step S106: determining a target combined feature from a plurality of combined features included in a preset sample library.

[0045] In step S106, the similarity between the target combined feature and the sound combined feature meets the preset condition. The preset sample library includes at least: at least one fault type label and multiple combined features. In addition, the multiple combined features are determined based on the historical environment information of the device to be detected and the sound data when the device to be detected has a historical fault.

[0046] Optionally, the preset conditions can be customized by the operator according to the actual situation of the device to be detected, for example, different preset conditions can be set according to the type of the device to be detected, and different preset conditions can be set according to the different environments in which the device to be detected is located. Among them, the preset conditions can calculate the similarity score between the sound combination feature and each combination feature in the sample library, and determine the combination feature with the highest similarity score as the target combination feature.

[0047] Optionally, when constructing a preset sample library, the electronic device can determine at least one combination feature corresponding to each fault type through historical inspection and maintenance records, and establish a fault type label for each fault type. It should be noted that when the same fault occurs, the external environment may not be exactly the same, so one fault type may correspond to at least one combination feature. In addition, the preset sample library also contains the combination features corresponding to the normal operation of the device to be tested. For example, the following shows the data in a preset sample library:

[0048] Fault A: (spectral feature A1 / MFCC feature A1, spectral feature A2 / MFCC feature A2…spectral feature An / MFCC feature An);

[0049] Fault B: (spectral feature B1 / MFCC feature B1, spectral feature B2 / MFCC feature B2…spectral feature Bn / MFCC feature Bn);

[0050] Fault C: (spectral feature C1 / MFCC feature C1, spectral feature C2 / MFCC feature C2…spectral feature Cn / MFCC feature Cn)…

[0051] Fault N: (spectral feature N1 / MFCC feature N1, spectral feature N2 / MFCC feature N2…spectral feature Nn / MFCC feature Nn);

[0052] Normal data: (spectral feature 1 / MFCC feature 1, spectral feature 2 / MFCC feature 2…spectral feature n / MFCC feature n).

[0053] It can be seen from the above process that the present disclosure achieves the effect of accurately determining the fault type of the equipment to be detected based on sound data by associating multiple combined features with at least one fault type label, thereby reducing the cost of fault detection and improving equipment maintenance efficiency.

[0054] Step S108, determining the fault type of the device to be detected according to the target fault type label corresponding to the target combination feature.

[0055] In step S108, after the electronic device determines the target combination feature, the electronic device will obtain the target fault type label corresponding to the target combination feature, and determine the fault type of the device to be detected according to the information of the target fault type label. For example, the electronic device determines that the target combination feature corresponding to the device A to be detected is the target combination feature 1. Among them, the target fault type label of the target combination feature 1 indicates that the fault type corresponding to the target combination feature 1 is a power failure fault, so that the electronic device can determine that the device to be detected currently has a power failure fault.

[0056] It should be noted that the present disclosure can not only determine whether the device to be detected has a fault, but also determine the fault type of the device to be detected when the device to be detected has a fault, thereby achieving the effect of ensuring the stable operation of the device.

[0057] In the technical solution disclosed in the present invention, a method of associating multiple combined features with at least one fault type label is adopted. After obtaining the sound data when the device to be detected fails, the sound data is feature extracted to obtain the sound combined features corresponding to the sound data, and then the target combined features are determined from the multiple combined features contained in the preset sample library, and then the fault type of the device to be detected is determined according to the target fault type label corresponding to the target combined features. Among them, the sound combined features are composed of multiple sound features, and the similarity between the target combined features and the sound combined features meets the preset conditions. The preset sample library at least includes: at least one fault type label, multiple combined features, and the multiple combined features are determined based on the historical environmental information of the device to be detected and the sound data when the device to be detected has historical faults.

[0058] As can be seen from the above content, since the sound combination feature in the present disclosure includes a plurality of sound features, the present disclosure can comprehensively determine the target combination feature from the preset sample library from multiple dimensions. Compared with determining the target combination feature according to one sound feature, the technical solution of the present disclosure has the advantages of being more comprehensive and more accurate when determining the target combination feature, thereby improving the recognition accuracy of the equipment fault sound. In addition, since the plurality of combination features in the preset sample library in the present disclosure are determined based on the historical environmental information of the equipment to be detected and the sound data when the equipment to be detected has a historical fault, even if there is an interference sound in the external environment, the present disclosure can still determine the target combination feature corresponding to the equipment to be detected by combining the environmental sound with the equipment operation sound, and determine the fault type of the equipment to be detected according to the target combination feature, thereby solving the technical problem of low fault sound recognition accuracy caused by poor anti-interference ability in the prior art. In addition, the present disclosure can not only determine whether the equipment to be detected has a fault, but also determine the fault type of the equipment to be detected when the equipment to be detected has a fault through the target fault type label corresponding to the target combination feature, which is conducive to improving the equipment maintenance efficiency.

[0059] It can be seen that through the technical solution of the present application, the purpose of accurately determining the fault type of the equipment to be detected through sound data is achieved, thereby achieving the effect of ensuring the stable operation of the equipment, and further solving the technical problem of low accuracy of fault sound recognition existing in the prior art.

[0060] In an optional embodiment, the electronic device may perform a first feature extraction on the sound data to obtain a spectral feature, and perform a second feature extraction on the sound data to obtain a frequency cepstrum coefficient feature, wherein the sound combination feature includes at least a spectral feature and a frequency cepstrum coefficient feature.

[0061] Optionally, after acquiring the sound data, the electronic device may generate a sound spectrum Figure 2 The first feature extraction is performed on the sound data in the form of a dimensional matrix, so as to obtain the sound spectrum feature corresponding to the sound data. Specifically, Figure 2 As shown, the electronic device may first perform frame processing on the sound data to obtain multiple frames of first sound data, then perform windowing processing on the multiple frames of first sound data to obtain multiple frames of second sound data, then perform Fourier transform on the multiple frames of second sound data to obtain multiple frames of third sound data, and finally perform stacking processing on the multiple frames of third sound data (corresponding to Figure 2 The sound spectrum feature can be displayed in the form of a sound spectrum matrix, and the sound data can be a continuous sound signal.

[0062] Furthermore, after acquiring the sound data, the electronic device may also perform a second feature extraction on the sound data by means of MFCC feature extraction, thereby obtaining a frequency cepstrum coefficient feature. Figure 3 As shown, the electronic device may first perform pre-emphasis processing on the sound data to obtain fourth sound data, and then the electronic device may perform frame division and windowing processing on the fourth sound data to obtain fifth sound data. Further, the electronic device may perform fast Fourier transform on the fifth sound data to obtain sixth sound data, and then the electronic device may perform filtering processing on the sixth sound data using a Mel filter group to obtain filtered sixth sound data. After that, the electronic device may perform logarithm calculation on the filtered sixth sound data to obtain seventh sound data. Finally, the electronic device may perform discrete cosine transform on the seventh sound data to obtain frequency inverse spectrum coefficient features (i.e., MFCC features).

[0063] It should be noted that the combined features in the preset sample library are also extracted based on the first feature extraction method and the second feature extraction method.

[0064] In the above process, by extracting the spectral features and MFCC features of the sound data respectively, it is possible to analyze the fault type of the device to be detected through the sound data in at least two dimensions, thereby improving the recognition accuracy of the device fault sound.

[0065] In an optional embodiment, before determining the target combined feature from multiple combined features included in a preset sample library, the electronic device may obtain a device identification corresponding to the device to be detected, and determine a preset sample library corresponding to the device identification from multiple sample libraries.

[0066] Optionally, since the usage and environment of each device to be detected are different, the sound data corresponding to different devices to be detected may also be different. In order to ensure accurate identification of the fault type of each device to be detected, when constructing the preset sample library, the electronic device can construct a corresponding preset sample library according to each device to be detected. For example, the device to be detected with the device identification of device 1 is located at the first station, and the electronic device uses the first sample library as the preset sample library corresponding to device 1; the device to be detected with the device identification of device 2 is located at the second station, and the electronic device uses the second sample library as the preset sample library corresponding to device 2. Among them, the first sample library is constructed by the electronic device based on the sound data collected from device 1, and the second sample library is constructed by the electronic device based on the sound data collected from device 2.

[0067] It should be noted that by establishing a preset sample library corresponding to each device to be detected, refined management of each device to be detected is achieved, thereby achieving the effect of improving the management efficiency of the preset sample library.

[0068] In an optional embodiment, the electronic device may obtain multiple first sound features and multiple second sound features from a preset sample library, and calculate the cosine similarity between each of the multiple first sound features and the spectrum feature to obtain multiple first similarities, thereby determining multiple first target features from the multiple first sound features based on the multiple first similarities. In addition, the electronic device may also calculate the cosine similarity between each of the multiple second sound features and the frequency cepstral coefficient feature to obtain multiple second similarities, thereby determining multiple second target features from the multiple second sound features based on the multiple second similarities. Finally, the electronic device combines the multiple first target features and the multiple second target features to obtain multiple combined features, and determines the target combined feature from the multiple combined features. Among them, the feature type of the multiple first sound features is the same as the feature type of the spectrum feature, and the feature type of the multiple second sound features is the same as the feature type of the frequency cepstral coefficient feature.

[0069] Optionally, the electronic device may determine the target combination feature that is most similar to the sound combination feature according to the spectral feature and the frequency cepstrum coefficient feature in the sound combination feature. For example, the sound data of the device 1 to be detected is sound A, wherein the spectral feature corresponding to the sound A is the spectral feature A, and the frequency cepstrum coefficient feature corresponding to the sound A is the MFCC feature A. In addition, there are three first sound features in the preset sample library corresponding to the device 1 to be detected. By calculating the cosine similarity between each first sound feature and the spectral feature A, the electronic device determines that the first sound features with the first similarity from high to low are the first sound feature 1, the first sound feature 2, and the first sound feature 3. On this basis, the electronic device may preliminarily screen the first sound features according to the first similarity, thereby filtering out the first sound 3 with the lowest first similarity, and determining the first sound feature 1 and the first sound feature 2 as the first target features. Among them, when there are multiple first sound features, in order to improve the calculation efficiency, the electronic device may select the N first sound features with the highest first similarity as the first target features. Further, the determination process of the second target feature is the same as the determination process of the first target feature, which will not be repeated here.

[0070] Optionally, after obtaining the plurality of first target features and the plurality of second target features, the electronic device may combine the plurality of first target features and the plurality of second target features to obtain a plurality of target combination features, wherein the combination method may be a permutation combination method, that is, any first target feature is combined with any second target feature.

[0071] In the above process, the electronic device uses a similarity retrieval algorithm to quickly and accurately match the newly input sound data. Since the entire process is simple to calculate and the effect is stable, the fault type of the device to be detected can be determined efficiently.

[0072] In an optional embodiment, after obtaining multiple combined features, the electronic device may obtain a first weight value corresponding to a first target feature in each of the multiple combined features, and a second weight value corresponding to a second target feature in each of the multiple combined features, and calculate a third similarity between the first target feature in each of the combined features and the spectrum feature, and a fourth similarity between the second target feature in each of the combined features and the frequency cepstral coefficient feature, thereby calculating a score value corresponding to each combined feature according to the first weight value, the second weight value, the third similarity and the fourth similarity, and then determining a target combined feature from the multiple combined features according to the score value.

[0073] Optionally, the operator may assign different weight values ​​to the first target feature and the second target feature on the electronic device according to the actual application scenario. For example, the first weight value corresponding to the first target feature may be w 1 Indicates that the second weight value corresponding to the second target feature can be used w 2 At the same time, the electronic device will also calculate the third similarity between the first target feature in each combined feature and the sound spectrum feature, and the fourth similarity between the second target feature in each combined feature and the frequency cepstrum coefficient feature. The third similarity can be expressed as S 声谱特征 Indicates that the fourth similarity can be used S MFCC Finally, after obtaining the first weight value, the second weight value, the third similarity and the fourth similarity, the electronic device can calculate the score value corresponding to each combination feature (ie, the Score in the formula) by the following formula, and determine the combination feature with the highest score value as the target combination feature.

[0074] Score = w 1 *S 声谱特征 +w 2 *S MFCC

[0075] It should be noted that by calculating the score value of each combination feature, it is ensured that the combination feature that is most similar to the sound data is determined as the target combination feature, thereby ensuring that the electronic device can stably and accurately identify the fault sound. In addition, through the design of the weight value, the operator can adjust the recognition process of the electronic device according to the actual scenario, thereby improving the flexibility of the recognition process.

[0076] In an optional embodiment, after determining the fault type of the device to be detected according to the target fault type label corresponding to the target combination feature, the electronic device responds to the target object's adjustment instruction for the fault type, thereby adjusting any one or more of the parameters, first weight value, and second weight value in the feature extraction function based on the adjustment instruction, wherein the feature extraction function is used to extract features from sound data.

[0077] Optionally, after the electronic device determines the fault type of the device to be detected according to the target fault type label corresponding to the target combination feature, the operator can verify the fault identification result of the electronic device. Specifically, for the fault identification result of the electronic device, the operator can judge the accuracy of the fault identification result through expert experience and data analysis. If the fault identification result of the electronic device is inaccurate, the operator can optimize the fault identification process of the electronic device by adjusting the feature extraction function, adjusting the first weight value, adjusting the second weight value, and increasing the number of samples in the preset sample library.

[0078] It should be noted that by verifying the fault identification results and adjusting the calculation parameters in the identification process, the effect of timely adjusting the identification process of the electronic device according to the actual situation is achieved, thereby further ensuring the accurate identification of the fault type.

[0079] In an optional embodiment, after determining the fault type of the device to be detected according to the target fault type label corresponding to the target combination feature, the electronic device may update the preset sample library based on the sound spectrum feature and / or the frequency cepstrum coefficient feature.

[0080] Optionally, if the fault identification result of the electronic device is accurate, the operator can confirm the fault identification result on the electronic device. After receiving the confirmation instruction, the electronic device actively adds the spectral characteristics and / or frequency cepstral coefficient characteristics to the preset sample library corresponding to the device to be tested, thereby realizing automatic updating of the preset sample library.

[0081] It should be noted that by automatically updating the preset sample library, the effect of enriching the data in the preset sample library is achieved, which is conducive to further improving the accuracy of fault identification.

[0082] In an optional embodiment, Figure 4 A flow chart of a method for identifying a device failure according to an embodiment of the present disclosure is shown. Figure 4As shown, first, the electronic device collects sound data through a sound sensor, and then extracts features from the collected sound data, wherein the electronic device at least extracts the spectral features and MFCC features of the sound data. Then, the electronic device calls a preset sample library constructed based on historical maintenance records and fault maintenance records, and analyzes the sound data based on the preset sample library, wherein the specific analysis process at least includes: preset sample library retrieval, similarity calculation, and weighted summation of calculation results. Finally, the electronic device outputs a fault identification result based on the analysis result, and the operator verifies the fault identification result. When the fault identification result output by the electronic device is correct, the electronic device can add the sound features extracted during the identification process to the preset sample library, thereby achieving the effect of updating the preset sample library.

[0083] As can be seen from the above content, since the sound combination feature in the present disclosure includes a plurality of sound features, the present disclosure can comprehensively determine the target combination feature from the preset sample library from multiple dimensions. Compared with determining the target combination feature according to one sound feature, the technical solution of the present disclosure has the advantages of being more comprehensive and more accurate when determining the target combination feature, thereby improving the recognition accuracy of the equipment fault sound. In addition, since the plurality of combination features in the preset sample library in the present disclosure are determined based on the historical environmental information of the equipment to be detected and the sound data when the equipment to be detected has a historical fault, even if there is an interference sound in the external environment, the present disclosure can still determine the target combination feature corresponding to the equipment to be detected by combining the environmental sound with the equipment operation sound, and determine the fault type of the equipment to be detected according to the target combination feature, thereby solving the technical problem of low fault sound recognition accuracy caused by poor anti-interference ability in the prior art. In addition, the present disclosure can not only determine whether the equipment to be detected has a fault, but also determine the fault type of the equipment to be detected when the equipment to be detected has a fault through the target fault type label corresponding to the target combination feature, which is conducive to improving the equipment maintenance efficiency.

[0084] It can be seen that through the technical solution of the present application, the purpose of accurately determining the fault type of the equipment to be detected through sound data is achieved, thereby achieving the effect of ensuring the stable operation of the equipment, and further solving the technical problem of low accuracy of fault sound recognition existing in the prior art.

[0085] Example 2

[0086] According to an embodiment of the present disclosure, there is also provided an embodiment of a device for identifying a device failure, wherein: Figure 5 is a schematic diagram of a device for identifying equipment failure according to an embodiment of the present disclosure, such as Figure 5 As shown, the device includes the following modules: an acquisition module 501 , a feature extraction module 503 , a feature determination module 505 and an identification module 507 .

[0087] Among them, the acquisition module 501 is used to obtain the sound data when the device to be detected fails; the feature extraction module 503 is used to extract features from the sound data to obtain the sound combination features corresponding to the sound data, wherein the sound combination features are composed of multiple sound features; the feature determination module 505 is used to determine the target combination features from the multiple combination features contained in the preset sample library, wherein the similarity between the target combination features and the sound combination features meets the preset conditions, and the preset sample library at least includes: at least one fault type label, multiple combination features, and the multiple combination features are determined based on the historical environmental information of the device to be detected and the sound data when the device to be detected has historical faults; the identification module 507 is used to determine the fault type of the device to be detected according to the target fault type label corresponding to the target combination feature.

[0088] It should be noted that the above-mentioned acquisition module 501, feature extraction module 503, feature determination module 505 and identification module 507 correspond to steps S102 to S108 in the above-mentioned embodiment, and the examples and application scenarios implemented by the four modules are the same as the corresponding steps, but are not limited to the contents disclosed in the above-mentioned embodiment 1.

[0089] Optionally, the feature extraction module further includes: a first feature extraction module and a second feature extraction module. The first feature extraction module is used to perform a first feature extraction on the sound data to obtain a spectrum feature; the second feature extraction module is used to perform a second feature extraction on the sound data to obtain a frequency cepstrum coefficient feature, wherein the sound combination feature at least includes a spectrum feature and a frequency cepstrum coefficient feature.

[0090] Optionally, the device for identifying device failure further includes: a first acquisition module and a determination module, wherein the first acquisition module is used to acquire a device identification corresponding to the device to be detected; and the determination module is used to determine a preset sample library corresponding to the device identification from multiple sample libraries.

[0091] Optionally, the determination module further includes: a second acquisition module, a first calculation module, a first determination module, a second calculation module, a second determination module, a combination module, and a third determination module. The second acquisition module is used to acquire a plurality of first sound features and a plurality of second sound features from a preset sample library, wherein the feature types of the plurality of first sound features are the same as the feature types of the spectral features, and the feature types of the plurality of second sound features are the same as the feature types of the frequency cepstrum coefficient features; the first calculation module is used to calculate the cosine similarity between each of the plurality of first sound features and the spectral features to obtain a plurality of first similarities; the first determination module is used to determine a plurality of first target features from the plurality of first sound features according to the plurality of first similarities; the second calculation module is used to calculate the cosine similarity between each of the plurality of second sound features and the frequency cepstrum coefficient features to obtain a plurality of second similarities; the second determination module is used to determine a plurality of second target features from the plurality of second sound features according to the plurality of second similarities; the combination module is used to combine the plurality of first target features and the plurality of second target features to obtain a plurality of combined features; and the third determination module is used to determine a target combined feature from the plurality of combined features.

[0092] Optionally, the third determination module also includes: a third acquisition module, a third calculation module, a fourth calculation module and a fourth determination module. The third acquisition module is used to obtain the first weight value corresponding to the first target feature in each of the multiple combined features, and the second weight value corresponding to the second target feature in each of the combined features; the third calculation module is used to calculate the third similarity between the first target feature in each of the combined features and the sound spectrum feature, and the fourth similarity between the second target feature in each of the combined features and the frequency cepstral coefficient feature; the fourth calculation module is used to calculate the score value corresponding to each combined feature according to the first weight value, the second weight value, the third similarity and the fourth similarity; the fourth determination module is used to determine the target combined feature from the multiple combined features according to the score value.

[0093] Optionally, the device for identifying equipment failures further includes: a response module and an adjustment module. The response module is used to respond to the adjustment instruction of the target object for the fault type; the adjustment module is used to adjust any one or more of the parameters, the first weight value, and the second weight value in the feature extraction function based on the adjustment instruction, wherein the feature extraction function is used to extract features from the sound data.

[0094] Optionally, the apparatus for identifying equipment failure further includes: an updating module, configured to update a preset sample library based on the sound spectrum feature and / or the frequency cepstral coefficient feature.

[0095] Optionally, the first feature extraction module also includes: a framing module, a windowing module, a Fourier transform module and a stacking processing module. Among them, the framing module is used to perform framing processing on the sound data to obtain multiple frames of first sound data; the windowing module is used to perform windowing processing on the multiple frames of first sound data to obtain multiple frames of second sound data; the Fourier transform module is used to perform Fourier transform on the multiple frames of second sound data to obtain multiple frames of third sound data; the stacking processing module is used to perform stacking processing on the multiple frames of third sound data to obtain spectrum features.

[0096] Optionally, the second feature extraction module also includes: a pre-emphasis processing module, a first framing module, a first Fourier transform module, a filtering processing module, a logarithmic calculation module and a discrete cosine transform module. Among them, the pre-emphasis processing module is used to pre-emphasize the sound data to obtain the fourth sound data; the first framing module is used to perform framing and windowing on the fourth sound data to obtain the fifth sound data; the first Fourier transform module is used to perform Fourier transform on the fifth sound data to obtain the sixth sound data; the filtering processing module is used to perform filtering on the sixth sound data to obtain the filtered sixth sound data; the logarithmic calculation module is used to perform logarithmic calculation on the filtered sixth sound data to obtain the seventh sound data; the discrete cosine transform module is used to perform discrete cosine transform on the seventh sound data to obtain the frequency cepstrum coefficient feature.

[0097] Example 3

[0098] According to an embodiment of the present disclosure, the present disclosure further provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the method for identifying device failure in the above-mentioned embodiment 1.

[0099] Example 4

[0100] According to an embodiment of the present disclosure, the present disclosure further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method for identifying a device failure in the above-mentioned embodiment 1 is implemented.

[0101] Example 5

[0102] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, comprising: at least one processor; and a memory communicatively connected to 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 execute the method for identifying device failure in the above-mentioned embodiment 1.

[0103] Figure 6A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present disclosure is shown. The electronic device 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.

[0104] like Figure 6 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0105] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0106] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 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 801 performs the various methods and processes described above, such as a method for identifying a device failure. For example, in some embodiments, the method for identifying a device failure may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the method for identifying a device failure described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform a method for identifying a device failure in any other appropriate manner (e.g., by means of firmware).

[0107] 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), load 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.

[0108] 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 data processing 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 and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0109] 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.

[0110] 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).

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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 method for identifying equipment failure, include: Acquire sound data when the device to be detected fails; Performing feature extraction on the sound data to obtain a sound combination feature corresponding to the sound data, wherein the sound combination feature is composed of a plurality of sound features, and the sound combination feature at least includes a spectrum feature and a frequency cepstrum coefficient feature; Determine a target combination feature from a plurality of combination features included in a preset sample library, wherein the similarity between the target combination feature and the sound combination feature satisfies a preset condition, and the preset sample library at least includes: at least one fault type label, the plurality of combination features, and the plurality of combination features are determined based on historical environmental information of the device to be detected and sound data when the device to be detected has a historical fault; Determine the fault type of the device to be detected according to the target fault type label corresponding to the target combination feature, The target combination feature is determined from a plurality of combination features included in the preset sample library, including: Acquire a plurality of first sound features and a plurality of second sound features from the preset sample library, wherein the feature types of the plurality of first sound features are the same as the feature type of the sound spectrum feature, and the feature types of the plurality of second sound features are the same as the feature type of the frequency cepstrum coefficient feature; Determining a plurality of first target features from the plurality of first sound features based on a first similarity between the first sound feature and the sound spectrum feature and the preset condition, and determining a plurality of second target features from the plurality of second sound features based on a second similarity between the second sound feature and the frequency cepstral coefficient feature and the preset condition; Combining the plurality of first target features and the plurality of second target features to obtain a plurality of combined features; The target combined feature is determined from the plurality of combined features.

2. The method according to claim 1, in, Extracting features from the sound data to obtain sound combination features corresponding to the sound data includes: Performing a first feature extraction on the sound data to obtain a sound spectrum feature; A second feature extraction is performed on the sound data to obtain a frequency cepstrum coefficient feature.

3. The method according to claim 1, before determining the target combined feature from the plurality of combined features included in the preset sample library, the method further comprises: include: Obtaining a device identifier corresponding to the device to be detected; A preset sample library corresponding to the device identification is determined from multiple sample libraries.

4. The method according to claim 2, in, Determining the plurality of first target features from the plurality of first sound features based on a first similarity between the first sound feature and the sound spectrum feature, and determining the plurality of second target features from the plurality of second sound features based on a second similarity between the second sound feature and the frequency cepstral coefficient feature, comprises: Calculating the cosine similarity between each of the plurality of first sound features and the spectral feature to obtain a plurality of first similarities; determining a plurality of first target features from the plurality of first sound features according to the plurality of first similarities; Calculating the cosine similarity between each second sound feature of the plurality of second sound features and the frequency cepstral coefficient feature to obtain a plurality of second similarities; A plurality of second target features are determined from the plurality of second sound features according to the plurality of second similarities.

5. The method according to claim 4, in, Determining the target combined feature from the multiple combined features includes: Obtaining a first weight value corresponding to a first target feature in each of the plurality of combined features, and a second weight value corresponding to a second target feature in each of the plurality of combined features; Calculating a third similarity between the first target feature in each combined feature and the sound spectrum feature, and a fourth similarity between the second target feature in each combined feature and the frequency cepstrum coefficient feature; Calculate the score value corresponding to each combined feature according to the first weight value, the second weight value, the third similarity and the fourth similarity; A target combined feature is determined from the multiple combined features according to the score value.

6. The method according to claim 5, after determining the fault type of the device to be detected according to the target fault type label corresponding to the target combination feature, the method further include: Responding to the target object's adjustment instruction for the fault type; Based on the adjustment instruction, any one or more of the parameters in the feature extraction function, the first weight value, and the second weight value are adjusted, wherein the feature extraction function is used to extract features from the sound data.

7. The method according to claim 2, after determining the fault type of the device to be detected according to the target fault type label corresponding to the target combination feature, the method further include: The preset sample library is updated based on the sound spectrum feature and / or the frequency cepstral coefficient feature.

8. The method according to claim 2, in, Performing a first feature extraction on the sound data to obtain a sound spectrum feature includes: Performing frame processing on the sound data to obtain multiple frames of first sound data; Performing windowing processing on the multiple frames of first sound data to obtain multiple frames of second sound data; Performing Fourier transform on the multiple frames of second sound data to obtain multiple frames of third sound data; The multiple frames of third sound data are stacked to obtain the sound spectrum feature.

9. The method according to claim 2, in, Performing a second feature extraction on the sound data to obtain a frequency cepstrum coefficient feature includes: Pre-emphasize the sound data to obtain fourth sound data; performing frame division and windowing processing on the fourth sound data to obtain fifth sound data; Performing Fourier transform on the fifth sound data to obtain sixth sound data; performing filtering processing on the sixth sound data to obtain filtered sixth sound data; performing logarithmic calculation on the filtered sixth sound data to obtain seventh sound data; Performing discrete cosine transform on the seventh sound data to obtain the frequency cepstrum coefficient feature.

10. A device for identifying equipment failure, include: An acquisition module is used to acquire sound data when a failure occurs in the device to be detected; A feature extraction module, used for performing feature extraction on the sound data to obtain a sound combination feature corresponding to the sound data, wherein the sound combination feature is composed of a plurality of sound features, and the sound combination feature at least includes a spectrum feature and a frequency cepstrum coefficient feature; A feature determination module, used to determine a target combination feature from a plurality of combination features included in a preset sample library, wherein the similarity between the target combination feature and the sound combination feature satisfies a preset condition, and the preset sample library at least includes: at least one fault type label, the plurality of combination features, and the plurality of combination features are determined based on historical environmental information of the device to be detected and sound data when the device to be detected has a historical fault; An identification module, used to determine the fault type of the device to be detected according to the target fault type label corresponding to the target combination feature; Wherein, the feature determination module is also used to: obtain multiple first sound features and multiple second sound features from the preset sample library, wherein the feature type of the multiple first sound features is the same as the feature type of the spectral feature, and the feature type of the multiple second sound features is the same as the feature type of the frequency cepstral coefficient feature; based on the first similarity between the first sound feature and the spectral feature and the preset condition, determine multiple first target features from the multiple first sound features, and based on the second similarity between the second sound feature and the frequency cepstral coefficient feature and the preset condition, determine multiple second target features from the multiple second sound features; combine the multiple first target features and the multiple second target features to obtain multiple combined features; and determine the target combined feature from the multiple combined features.

11. 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 for identifying equipment failure according to any one of claims 1 to 9.

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

13. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method for identifying a device failure according to any one of claims 1 to 9.

Images