CN112598027A

CN112598027A - Equipment abnormity identification method and device, terminal equipment and storage medium

Info

Publication number: CN112598027A
Application number: CN202011429871.7A
Authority: CN
Inventors: 郭奎; 程骏; 庞建新
Original assignee: Ubtech Robotics Corp
Current assignee: Ubtech Robotics Corp
Priority date: 2020-12-09
Filing date: 2020-12-09
Publication date: 2021-04-02

Abstract

The application is applicable to the technical field of signal processing, and provides an equipment abnormity identification method, an equipment abnormity identification device, terminal equipment and a storage medium, wherein the method comprises the following steps: collecting audio signals in a target environment, and converting the audio signals into a frequency spectrum image; inputting the frequency spectrum image into a pre-trained neural network model for image recognition to obtain a recognition result of the frequency spectrum image; and outputting corresponding equipment abnormity prompt information when the identification result is detected to be an abnormal audio signal. The embodiment of the application can detect the audio signal, convert the audio signal into the frequency spectrum image, perform image recognition on the frequency spectrum image through the neural network, and make a corresponding device abnormity prompt when the recognition result is abnormal, so that the problem of device abnormity can be accurately and effectively solved.

Description

Equipment abnormity identification method and device, terminal equipment and storage medium

Technical Field

The present application belongs to the field of signal processing technologies, and in particular, to a method and an apparatus for identifying an anomaly of a device, a terminal device, and a storage medium.

Background

With the development of automation technology, various industries increasingly rely on various automation devices (such as information management server devices, power supply and distribution devices, fire fighting devices, security devices and the like), and the abnormality of the automation management devices can cause serious consequences.

At present, manual inspection or guard is usually arranged for various automatic devices, the inspection efficiency of manual inspection and guard is low, and the device abnormity cannot be accurately checked when the experience of managers is insufficient.

Disclosure of Invention

The embodiment of the application provides an equipment abnormity identification method and device, terminal equipment and a storage medium, and aims to solve the problem that the existing equipment abnormity cannot be accurately and effectively checked.

In a first aspect, an embodiment of the present application provides an apparatus anomaly identification method, including:

collecting audio signals in a target environment, and converting the audio signals into a frequency spectrum image;

inputting the frequency spectrum image into a pre-trained neural network model for image recognition to obtain a recognition result of the frequency spectrum image;

and outputting corresponding equipment abnormity prompt information when the identification result is detected to be an abnormal audio signal.

In one embodiment, the converting the audio signal into a spectral image includes:

converting a first function based on a first programming language into a second function in a preset format through a library compiler, and storing the second function in a preset dynamic link library; the preset format is a format which can be called and executed through a second programming language, and the first function is a function which carries out time-frequency analysis on the audio signal and converts the audio signal into a frequency spectrum image on a time domain;

and calling the second function from the preset dynamic link library through a second programming language to convert the audio signal into a frequency spectrum image.

In one embodiment, the first function of the first programming language is a specgram function of matlab language, the second function of the preset format is a specgram function of a preset format, and the second programming language is python language.

In one embodiment, before acquiring the audio signal in the target environment, the method further comprises:

constructing the neural network model based on a preset neural network;

and acquiring training data, and pre-training the neural network model through the training data to obtain the pre-trained neural network model.

In one embodiment, the acquiring an audio signal in a target environment, and converting the audio signal into a spectral image includes:

collecting audio signals in a target environment through an audio collecting device;

and converting the audio signal into the frequency spectrum image at preset time intervals.

In one embodiment, inputting the spectrum image into a pre-trained neural network model for image recognition, and obtaining a recognition result of the spectrum image, includes:

inputting the frequency spectrum image into a pre-trained neural network model for image recognition to obtain a recognition result of an audio signal corresponding to the frequency spectrum image; wherein the identification result comprises normal environment sound, abnormal buzzing sound and warning sound;

and when the identification result is detected to be abnormal buzzing sound or warning sound, judging that the identification result is an abnormal audio signal.

In one embodiment, the outputting, when it is detected that the identification result is an abnormal audio signal, corresponding device abnormality prompting information includes:

when the identification result is detected to be an abnormal audio signal, determining the position information of the abnormal audio signal;

and generating and outputting the equipment abnormity prompt information according to the position information and the identification result.

In a second aspect, an embodiment of the present application provides an abnormality recognition apparatus, including:

the conversion module is used for acquiring audio signals in a target environment and converting the audio signals into a frequency spectrum image;

the acquisition module is used for inputting the frequency spectrum image into a pre-trained neural network model for image recognition to obtain a recognition result of the frequency spectrum image;

and the abnormity prompting module is used for outputting corresponding equipment abnormity prompting information when the identification result is detected to be an abnormal audio signal.

In a third aspect, an embodiment of the present application provides a terminal device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the above-mentioned abnormality identification method when executing the computer program.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where a computer program is stored, and the computer program, when executed by a processor, implements the steps of the above-mentioned abnormality identification method.

In a fifth aspect, the present application provides a computer program product, which when run on an electronic device, causes the electronic device to perform the above-mentioned steps of the anomaly identification method.

Compared with the prior art, the embodiment of the application has the advantages that: the method comprises the steps of collecting audio signals in a target environment, and converting the audio signals into frequency spectrum images; inputting the frequency spectrum image into a pre-trained neural network model for image recognition to obtain a recognition result of the frequency spectrum image; and outputting corresponding equipment abnormity prompt information when the identification result is detected to be an abnormal audio signal. The embodiment of the application can detect the audio signal, convert the audio signal into the frequency spectrum image, perform image recognition on the frequency spectrum image through the neural network, and make a corresponding device abnormity prompt when the recognition result is abnormal, so that the problem of device abnormity can be accurately and effectively solved.

It is understood that the beneficial effects of the second aspect to the fifth aspect can be referred to the related description of the first aspect, and are not described herein again.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.

Fig. 1 is a schematic flowchart of an anomaly identification method for a device according to an embodiment of the present application;

fig. 2 is a schematic specific flowchart of step S101 according to an embodiment of the present application;

fig. 3 is a schematic specific flowchart of step S103 according to an embodiment of the present application;

fig. 4 is a schematic structural diagram of an abnormality recognition device of an apparatus according to another embodiment of the present application;

fig. 5 is a schematic structural diagram of a terminal device according to another embodiment of the present application.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It should also be understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

As used in this specification and the appended claims, the term "if" may be interpreted contextually as "when", "upon" or "in response to" determining "or" in response to detecting ". Similarly, the phrase "if it is determined" or "if a [ described condition or event ] is detected" may be interpreted contextually to mean "upon determining" or "in response to determining" or "upon detecting [ described condition or event ]" or "in response to detecting [ described condition or event ]".

Furthermore, in the description of the present application and the appended claims, the terms "first," "second," "third," and the like are used for distinguishing between descriptions and not necessarily for describing or implying relative importance.

Reference throughout this specification to "one embodiment" or "some embodiments," or the like, means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," or the like, in various places throughout this specification are not necessarily all referring to the same embodiment, but rather "one or more but not all embodiments" unless specifically stated otherwise. The terms "comprising," "including," "having," and variations thereof mean "including, but not limited to," unless expressly specified otherwise.

The method for identifying the abnormality of the device provided in the embodiment of the present application may be applied to various terminal devices such as a robot, a server, a tablet computer, a wearable device, a vehicle-mounted device, an Augmented Reality (AR)/Virtual Reality (VR) device, a notebook computer, a super-mobile personal computer (UMPC), a netbook, a Personal Digital Assistant (PDA), and a mobile phone.

In an application scenario, if abnormal states of various automation devices need to be monitored in one or more machine rooms in which the automation devices are installed, the abnormal states of the automation devices in the machine rooms are usually checked in a manual inspection mode at present, and the problems of low accuracy and low efficiency of the corresponding devices may occur due to insufficient manual experience or untimely manual inspection and other factors.

In another application scenario, for example, in one or more machine rooms in which various automation devices are installed, the abnormal state of the automation device needs to be monitored, an audio acquisition device may be installed in the machine room or in the automation device in advance, and the audio acquisition device may be in communication connection with a terminal device executing the method of the present application.

In order to explain the technical means described in the present application, the following examples are given below.

Referring to fig. 1, an abnormality identification method for a device according to an embodiment of the present application includes:

step S101, collecting audio signals in a target environment, and converting the audio signals into a frequency spectrum image.

Specifically, the target environment is a preset environment where equipment to be detected is located, an audio signal in the target environment is collected in real time, the audio signal includes rich state information, if the equipment fails, the audio signal changes, and the audio signal is directly analyzed to be easily affected by environmental noises such as distance, noise and the like, so that the audio signal is converted into a spectrum image, and the spectrum image is converted according to the audio signal and is also called as a spectrogram.

In one embodiment, the acquiring an audio signal in a target environment, and converting the audio signal into a spectral image includes: collecting audio signals in a target environment through an audio collecting device; and converting the audio signal into the frequency spectrum image at preset time intervals.

Specifically, the audio acquisition device may be an audio acquisition device, and the like, and the audio acquisition device acquires audio information in real time within a preset time period required to be acquired, and converts the acquired audio into a spectral image at preset intervals, for example, converts the acquired audio signal into a spectral image at intervals of 15 seconds.

In one embodiment, before acquiring the audio signal in the target environment, the method further comprises: constructing the neural network model based on a preset neural network; and acquiring training data, and pre-training the neural network model through the training data to obtain the pre-trained neural network model.

Specifically, the neural network model may adopt a lightweight network for network design, such as the above preset neural network may be a shufflentv 2 network, and the deployment of the lightweight neural network model in the terminal device becomes more applicable. The pre-constructed neural network model is trained prior to acquiring audio signals in the target environment. The method comprises the steps of collecting a large number of audio signals in a target environment in advance, converting the audio signals into corresponding frequency spectrum images, marking recognition results of the frequency spectrum images to obtain training data, inputting the training data into a constructed neural network model for training until a preset loss function output value is smaller than or equal to a preset threshold value, wherein the preset threshold value can be preset according to the preset value corresponding to a preset loss function and is used for detecting whether the preset loss function output value meets a preset training standard or not. The neural network model trained at this time is called a pre-trained neural network model. The preset loss function is used for indicating the difference between the frequency spectrum image result obtained in the training and the identification result for labeling the frequency spectrum image, and the preset loss function can be a cross entropy loss function or a mean square error loss function and other types of loss functions.

In one embodiment, as shown in fig. 2, the converting the audio signal into a spectrum image includes steps S1011 to S1012:

step S1011, converting the first function based on the first programming language into a second function in a preset format through a library compiler, and storing the second function in a preset dynamic link library; the preset format is a format which can be called and executed through a second programming language, and the first function is a function which carries out time-frequency analysis on the audio signal and converts the audio signal into a frequency spectrum image on a time domain.

Specifically, in order to convert the audio signal into the spectral image more efficiently, the audio signal may be directly converted by a function capable of converting the audio signal into the spectral image, but since there is no function capable of directly converting the audio signal into the spectral image in the second programming language implementing the embodiment, the first function based on the first programming language is first converted into the second function in the preset format by the library compiler, and the second function in the preset format is a format of a function that can be called and executed later by the second programming language. And converting a first function based on the first programming language into a second function executed in a preset format through a library compiler, and storing the second function into a preset dynamic link library so as to directly call the second programming language and convert the audio signal into a function of a frequency spectrum image.

Specifically, the first function of the first programming language is a specgram function of the matlab language, the specgram function is a spectrum image obtained by converting an audio signal in the matlab language, voiceprints of sounds emitted by different devices are different, transverse, longitudinal and oblique spectrum characteristics are different, and characteristic spectrum lines are different, so that the working state of the automation device can be distinguished and analyzed according to the spectrum image of the audio signal. The abnormality identification method in the embodiment of the application can be realized by using a python language, and cannot directly call the specgram function of the matlab language, so that the specgram function based on the matlab language is converted into the specgram function in a preset format through a library compiler in advance and is stored in a preset dynamic link library, the preset format is a format which can be called and executed through the python language, and the specgram function is a function which carries out time-frequency analysis on an audio signal and is converted into a spectral image in a time domain; dynamic Link Library (DLL) can be used to implement function sharing, and the function of the Dynamic Link Library can be in the format of ". DLL",. oxc ", etc., and can enable a process to call a function which does not belong to its executable code. The specgram function based on the matlab language is converted into the specgram function with the preset format through the library compiler in advance, and the specgram function with the preset format of ". dll" can be the specgram function based on the matlab language and converted into the specgram function with the preset format of ". dll" through the library compiler.

Step S1012, calling the second function from the preset dynamic link library through a second programming language, and converting the audio signal into a spectrum image.

Specifically, the second function in the preset format is called from the preset dynamic link library through the second programming language, and the second function in the preset format is executed, so that the audio signal can be converted into the frequency spectrum image.

In one embodiment, the step of calling the second function from the preset dynamic link library through a second programming language to convert the audio signal into the spectrum image may be calling a specgram function in a preset format from the preset dynamic link library through a python language; and converting the audio signal into a spectral image according to the called specgram function of the preset format (such as ". dll").

And S102, inputting the frequency spectrum image into a pre-trained neural network model for image recognition to obtain a recognition result of the frequency spectrum image.

In application, the frequency spectrum image is input into a pre-trained neural network model for image recognition, and the pre-trained neural network model is used for recognizing whether the image is an abnormal audio signal. The pre-trained neural network model is a pre-constructed and trained neural network model. The output recognition result of the pre-trained neural network model comprises but is not limited to normal environment sound, abnormal buzzing sound, warning sound and the like.

In one embodiment, inputting the spectrum image into a pre-trained neural network model for image recognition, and obtaining a recognition result of the spectrum image, includes: inputting the frequency spectrum image into a pre-trained neural network model for image recognition to obtain a recognition result of an audio signal corresponding to the frequency spectrum image; wherein the identification result comprises normal environment sound, abnormal buzzing sound and warning sound; and when the identification result is detected to be abnormal buzzing sound or warning sound, judging that the identification result is an abnormal audio signal.

And step S103, outputting corresponding equipment abnormity prompt information when the identification result is detected to be an abnormal audio signal.

Specifically, abnormal prompt information associated with different abnormal audio signals is preset, and abnormal prompt information of corresponding equipment is output according to the identification result. If the abnormal prompt information is abnormal buzzing sound, outputting the abnormal prompt information that the abnormal wind buzzing sound exists in the equipment; the abnormal prompt information is a warning sound, and the abnormal prompt information of the warning sound existing in the equipment is output.

In one embodiment, as shown in fig. 3, when it is detected that the identification result is an abnormal audio signal, outputting corresponding device abnormality prompting information includes steps S1031 to S1032:

and step S1031, when detecting that the identification result is an abnormal audio signal, determining the position information of the abnormal audio signal.

Specifically, when the identification result is detected to be an abnormal audio signal, the position information of the abnormal audio signal is determined according to the position of the audio acquisition device acquiring the current abnormal audio signal. If the mobile robot executes the abnormal recognition method, the position information of the abnormal audio signal can be directly determined according to the current position of the mobile robot and the sound source positioning algorithm. If an audio acquisition device is installed in a machine room or in automation equipment in advance, and the terminal equipment in communication connection with the audio acquisition device executes the abnormality identification method in the embodiment of the application, the position information of the abnormal audio signal can be determined according to the position of the machine room or the automation equipment and a sound source positioning algorithm.

And step S1032, generating and outputting the equipment abnormity prompting information according to the position information and the identification result.

Specifically, the position information of the current abnormal audio signal is associated according to the type of the abnormal audio signal, and the corresponding device abnormality prompting information is generated and output, and the output may be performed by a display device, a playing device, and/or sending the device abnormality prompting information to a pre-associated user terminal.

The method comprises the steps of collecting audio signals in a target environment, and converting the audio signals into frequency spectrum images; inputting the frequency spectrum image into a pre-trained neural network model for image recognition to obtain a recognition result of the frequency spectrum image; and outputting corresponding equipment abnormity prompt information when the identification result is detected to be an abnormal audio signal. The embodiment of the application can detect the audio signal, convert the audio signal into the frequency spectrum image, perform image recognition on the frequency spectrum image through the neural network, and make a corresponding device abnormity prompt when the recognition result is abnormal, so that the problem of device abnormity can be accurately and effectively solved.

Fig. 4 shows a block diagram of a device abnormality recognition apparatus according to an embodiment of the present application, and for convenience of description, only the parts related to the embodiment of the present application are shown. Referring to fig. 4, the apparatus includes:

the conversion module 401 is configured to collect an audio signal in a target environment, and convert the audio signal into a spectral image;

an obtaining module 402, configured to input the spectral image into a pre-trained neural network model for image recognition, so as to obtain a recognition result of the spectral image;

an abnormal prompting module 403, configured to output corresponding device abnormal prompting information when the identification result is detected to be an abnormal audio signal.

In one embodiment, the conversion module comprises:

the conversion unit is used for converting a first function based on the first programming language into a second function in a preset format through the library compiler and storing the second function in a preset dynamic link library; the preset format is a format which can be called and executed through a second programming language, and the first function is a function which carries out time-frequency analysis on the audio signal and converts the audio signal into a frequency spectrum image on a time domain;

and the calling unit is used for calling the second function from the preset dynamic link library through a second programming language to convert the audio signal into a frequency spectrum image.

In one embodiment, the abnormality recognition apparatus further includes:

the building module is used for building the neural network model based on a preset neural network;

and the training module is used for acquiring training data and pre-training the neural network model through the training data to obtain the pre-trained neural network model.

In one embodiment, the conversion module is specifically configured to: collecting audio signals in a target environment through an audio collecting device; and converting the audio signal into the frequency spectrum image at preset time intervals.

In one embodiment, the obtaining module includes:

the obtaining unit is used for inputting the frequency spectrum image into a pre-trained neural network model for image recognition to obtain a recognition result of an audio signal corresponding to the frequency spectrum image; wherein the identification result comprises normal environment sound, abnormal buzzing sound and warning sound;

and the detection unit is used for judging that the identification result is an abnormal audio signal when the identification result is detected to be abnormal buzzing sound or warning sound.

In one embodiment, the exception prompting module includes:

a determination unit configured to determine, when it is detected that the identification result is an abnormal audio signal, position information of the abnormal audio signal;

and the generating unit is used for generating and outputting the equipment abnormity prompting information according to the position information and the identification result.

As shown in fig. 5, an embodiment of the present invention further provides a terminal device 500 including: a processor 501, a memory 502 and a computer program 503, such as an exception recognition program, stored in the memory 502 and executable on the processor 501. The processor 501, when executing the computer program 503, implements the steps in the above-described respective abnormality recognition method embodiments, for example, the abnormality recognition method steps of the above-described apparatus. The processor 501, when executing the computer program 503, implements the functions of the modules in the above-described device embodiments, such as the functions of the modules 401 to 403 shown in fig. 4.

Illustratively, the computer program 503 may be partitioned into one or more modules that are stored in the memory 502 and executed by the processor 501 to implement the present invention. The one or more modules may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program 503 in the terminal device 500. For example, the computer program 503 may be divided into a conversion module, an obtaining module, and an exception prompting module, and specific functions of each module are described in the foregoing embodiments, and are not described herein again.

The terminal device 500 may be a terminal device such as a robot or a server, or a computing device such as a desktop computer, a notebook, a palm computer, or a cloud server. The terminal device may include, but is not limited to, a processor 501 and a memory 502. Those skilled in the art will appreciate that fig. 5 is merely an example of a terminal device 500 and is not intended to limit the terminal device 500 and may include more or fewer components than those shown, or some components may be combined, or different components, for example, the terminal device may also include input output devices, network access devices, buses, etc.

The Processor 501 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 502 may be an internal storage unit of the terminal device 500, such as a hard disk or a memory of the terminal device 500. The memory 502 may also be an external storage device of the terminal device 500, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the terminal device 500. Further, the memory 502 may also include both an internal storage unit and an external storage device of the terminal device 500. The memory 502 is used for storing the computer programs and other programs and data required by the terminal device. The memory 502 may also be used to temporarily store data that has been output or is to be output.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated module, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.

Claims

1. An abnormality recognition method for a device, comprising:

2. The method of claim 1, wherein the converting the audio signal into a spectral image comprises:

3. The method according to claim 2, wherein the first function of the first programming language is a specgram function of matlab language, the second function of the preset format is a specgram function of a preset format, and the second programming language is python language.

4. The method of claim 1, further comprising, prior to acquiring the audio signal in the target environment:

constructing the neural network model based on a preset neural network;

5. The method of claim 1, wherein the capturing an audio signal in a target environment, and converting the audio signal into a spectral image comprises:

6. The method according to claim 1, wherein inputting the spectrum image to a pre-trained neural network model for image recognition to obtain a recognition result of the spectrum image comprises:

7. The method according to any one of claims 1 to 6, wherein the outputting of the corresponding device abnormality prompt information when the identification result is detected to be an abnormal audio signal comprises:

8. An abnormality recognition apparatus for a device, comprising:

9. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 7.