Fault detection method, system, and storage medium

Abstract

The application provides a fault detection method, system and storage medium, wherein the method comprises: obtaining device audio of a to-be-detected device; determining an initial fault detection result of the to-be-detected device based on the device audio; and in the case that the initial fault detection result indicates that the to-be-detected device has a fault, controlling the to-be-detected device to start a self-checking program. The method, device, electronic device and storage medium provided by the application realize automatic fault detection of the to-be-detected device, improve the efficiency of device inspection, improve the accuracy of fault detection, and clearly indicate the specific type and specific position of the fault, which is helpful for timely processing of the fault and reduces the loss caused by unplanned downtime to a production unit.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial detection, and in particular to a fault detection method, system and storage medium. BACKGROUND

[0002] In the industrial production process, if the industrial equipment fails, it will lead to unplanned shutdown of the industrial equipment and cause serious loss to the production unit if not handled in time.

[0003] At present, the operation and maintenance personnel mainly manually inspect the industrial equipment to determine whether the equipment fails. However, manual inspection cannot be performed every moment, and generally has a certain periodic interval, so that some failures are missed, and in addition, the experience requirement for the operation and maintenance personnel is high, and misjudgment is prone to occur. SUMMARY

[0004] The present application provides a fault detection method, system and storage medium to solve the defects of low efficiency and poor accuracy of manual inspection in the prior art.

[0005] The present application provides a fault detection method, comprising:

[0006] Obtaining equipment audio of a to-be-detected equipment;

[0007] Based on the equipment audio, determining an initial fault detection result of the to-be-detected equipment;

[0008] In the case where the initial fault detection result represents that the to-be-detected equipment has a fault, controlling the to-be-detected equipment to start a self-checking program.

[0009] According to the fault detection method provided by the present application, the initial fault detection result of the to-be-detected equipment is determined based on the equipment audio, comprising:

[0010] Frame the equipment audio to obtain each audio frame of the equipment audio;

[0011] Sound source localization is performed on the target audio signal in each audio frame to obtain sound source position information corresponding to each audio frame;

[0012] Based on the sound source position information corresponding to each audio frame, the initial fault detection result of the to-be-detected equipment is determined.

[0013] According to the fault detection method provided by the present application, the initial fault detection result of the to-be-detected equipment is determined based on the sound source position information corresponding to each audio frame, comprising:

[0014] determine an initial fault detection result of the to-be-detected device based on the difference between the elevation angles and the difference between the azimuth angles in the sound source position information corresponding to each audio frame.

[0015] According to the fault detection method provided by the application, the initial fault detection result of the to-be-detected device is determined based on the difference between the elevation angles and the difference between the azimuth angles in the sound source position information corresponding to each audio frame, which comprises:

[0016] In the case that the difference between the elevation angles corresponding to the first preset number of continuous audio frames is less than the first difference threshold and the difference between the azimuth angles is less than the second difference threshold, the position of the fault in the initial fault detection result is determined based on the elevation angles and the azimuth angles.

[0017] In the case that the difference between the elevation angles corresponding to every second preset number of audio frames is less than the first difference threshold and the difference between the azimuth angles is less than the second difference threshold, the position of the fault in the initial fault detection result is determined based on the elevation angles and the azimuth angles.

[0018] According to the fault detection method provided by the application, the self-checking program of the to-be-detected device is controlled to start, which comprises:

[0019] The self-checking range and / or self-checking sequence of the to-be-detected device are determined based on the position of the fault in the initial fault detection result.

[0020] The self-checking program of the to-be-detected device is controlled to start based on the self-checking range and / or self-checking sequence of the to-be-detected device.

[0021] According to the fault detection method provided by the application, the self-checking program of the to-be-detected device is controlled to start, which comprises:

[0022] The self-checking program of the to-be-detected device is controlled to start, and a self-checking result is obtained.

[0023] Alternatively, a self-checking command is sent to the to-be-detected device, and a self-checking result returned by the to-be-detected device is received.

[0024] According to the fault detection method provided by the application, the self-checking program of the to-be-detected device is controlled to start, and a self-checking result is obtained, which further comprises:

[0025] The self-checking result is sent to a preset terminal device.

[0026] The application further provides a fault detection system, comprising an audio acquisition device, a processor and a device to be detected, the audio acquisition device is used for acquiring device audio of the device to be detected and sending the device audio to the processor, and the processor is used for executing any one of the above fault detection methods.

[0027] According to the fault detection system provided by the application, the audio acquisition device, the processor and the device to be detected are independently arranged, or the audio acquisition device and / or the processor are arranged on the device to be detected.

[0028] The application further provides a non-transitory computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement any one of the above fault detection methods.

[0029] The fault detection method, system and storage medium provided by the application can detect whether the device to be detected has a fault according to the device audio, and control the device to be detected to start a self-checking program when the device to be detected has a fault, so that automatic fault detection of the device to be detected can be realized, the efficiency of device inspection is improved, the accuracy of fault detection is improved, the specific type and specific position of the fault are determined, the fault can be processed in time, and the loss caused by unplanned downtime to a production unit is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative effort.

[0031] Figure 1 is one of the flowcharts of the fault detection method provided by the application;

[0032] Figure 2 is the second flowchart of the fault detection method provided by the application;

[0033] Figure 3 is the third flowchart of the fault detection method provided by the application;

[0034] Figure 4 is the fourth flowchart of the fault detection method provided by the application;

[0035] Figure 5 is the structural schematic diagram of the fault detection device provided by the application;

[0036] Figure 6is a structural schematic diagram of a fault detection system provided by the present application.

[0037] Figure 7 is a structural schematic diagram of an electronic device provided by the present application. DETAILED DESCRIPTION

[0038] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below in combination with the drawings in the present application. Obviously, the described embodiments are some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0039] In the field of industrial equipment inspection, the operation and maintenance personnel arrive at the equipment every certain period, and use a mobile acoustic imager to locate the sound of the equipment. After positioning, it cannot be determined whether the equipment is faulty, the type of fault and other specific information, and subsequent manual confirmation by the operation and maintenance personnel is required. However, manual inspection needs to arrive at the scene, which generally has a certain period interval, thereby causing some faults to be missed. In addition, the amount of information provided by the acoustic imager is insufficient, and the operation and maintenance personnel with insufficient experience cannot accurately diagnose the fault through the information provided by the acoustic imager, which easily leads to misjudgment.

[0040] In view of the above problems, the present application provides a fault detection method. Figure 1 is one of the flowcharts of the fault detection method provided by the present application, as shown in Figure 1 The execution subject of the method is a processor, which can be specifically arranged on a device to be detected, an intelligent terminal or the like, or can be a server, and the embodiments of the present application do not make specific limitation thereon. The method comprises the following steps.

[0041] Step 110: obtaining device audio of the device to be detected.

[0042] Here, the device to be detected is a device that needs to be detected for fault, which can be, for example, a transformer, a motor, a tobacco factory device, a pipeline, etc. In the running process of the device to be detected, the processor can collect the audio of the device to be detected through a microphone or a microphone array or the like, and obtain the device audio of the device to be detected.

[0043] The device audio can be obtained by the audio collection device originally, or can be obtained after pre-processing such as denoising of the audio collected by the audio collection device, and the embodiments of the present application do not make specific limitation thereon.

[0044] Step 120: determining an initial fault detection result of the device to be detected based on the device audio.

[0045] Step 130, in the case that the initial fault detection result represents that the to-be-detected device exists fault, the to-be-detected device is controlled to start a self-checking program.

[0046] Specifically, considering that the sound generated when the device is in normal operation and when the device is abnormal is different, the embodiment of the present application obtains the device audio, detects whether the to-be-detected device exists fault according to the device audio, and thus obtains the initial fault detection result of the to-be-detected device. For example, the to-be-detected device is a pipeline, whether the pipeline exists gas leakage sound can be detected according to the device audio, and for another example, the to-be-detected device is a transformer, whether the transformer exists discharge sound can be detected according to the device audio.

[0047] Here, detecting whether the to-be-detected device exists fault can be directly detecting the device audio by applying a fault detection model, can be detecting according to the sound source position of the abnormal sound in each audio frame after the device audio is framed, or can be other fault detection manners, which are not limited in the embodiment of the present application. Further, if it is detected that the to-be-detected device exists fault, the device state in the initial fault detection result can be updated to exist fault, and the sound source position of the fault sound can be located by using a sound source positioning algorithm and stored in the initial fault detection result of the to-be-detected device as the position of the fault.

[0048] In the case that the initial fault detection result represents that the to-be-detected device exists fault, the processor can control the to-be-detected device to start a self-checking program, and determine the final fault detection result of the to-be-detected device according to the obtained self-checking result, so as to realize automatic fault detection of the to-be-detected device, save the labor cost, avoid the situation of missed fault detection, and improve the accuracy of fault detection without relying on subjective judgment of human.

[0049] Here, the self-checking result can be in the form of fault code, log, etc., after the self-checking result is obtained, the fault detection result of the to-be-detected device can be determined directly according to the self-checking result, or can be determined in combination with the position information obtained by sound source positioning and other information, which are not limited in the embodiment of the present application. The fault detection result can include specific type and specific position of the fault, for example, a small gap appears in a valve in the pipeline, a component inside the transformer is loose, etc.

[0050] It should be noted that, since the running cost of the self-checking procedure is high, the self-checking procedure is usually started only once at the start of the equipment, and the equipment will not be started again during the running process. According to the device audio, the embodiment of the present application detects whether the to-be-detected equipment has a fault, and controls the to-be-detected equipment to start the self-checking procedure in the case that the to-be-detected equipment has a fault, so that unnecessary self-checking cost can be avoided, and specific fault information can be obtained through self-checking, which facilitates subsequent fault warning and fault processing.

[0051] The method provided by the embodiment of the present application can detect whether the to-be-detected equipment has a fault according to the device audio, and control the to-be-detected equipment to start the self-checking procedure in the case that the to-be-detected equipment has a fault, so that automatic fault detection of the to-be-detected equipment can be realized, the efficiency of equipment inspection is improved, the accuracy of fault detection is improved, the specific type and specific position of the fault are determined, which is helpful for timely processing of the fault and reducing the loss caused by unplanned shutdown to the production unit.

[0052] Based on the above embodiment, Figure 2 is a second flowchart of the fault detection method provided by the present application, as Figure 2 indicated, step 120 comprises:

[0053] Step 121, frame the device audio to obtain each audio frame of the device audio;

[0054] Step 122, perform sound source positioning on the target audio signal in each audio frame to obtain the sound source position information corresponding to each audio frame;

[0055] Step 123, determine the initial fault detection result of the to-be-detected equipment based on the sound source position information corresponding to each audio frame.

[0056] Specifically, in order to improve the accuracy of fault detection, the initial fault detection result of the to-be-detected equipment can be determined by the following method: first, frame the device audio to obtain each audio frame of the device audio, then perform sound source positioning on the target audio signal in each audio frame by using a sound source positioning algorithm to obtain the position information of the sound source of the target audio signal, i.e. the sound source position information, and finally perform fault detection according to the sound source position information corresponding to each audio frame to obtain the initial fault detection result of the to-be-detected equipment.

[0057] Here, the target audio signal refers to an audio signal in the audio frame that belongs to abnormal sound, and such an audio signal needs to be sound source located to further determine whether it belongs to fault sound. Further, the target audio signal can be obtained by filtering out environmental noise, background noise of device operation, etc. in the audio frame, for example, considering that the frequency range of the sound emitted by gas leakage and other environmental sounds is different, when the pipeline has gas leakage, ultrasonic waves will be generated, so the sound frequency range of 20KHz-40KHz can be set to capture the target audio signal, i.e. the sound of gas leakage, and for example, considering that when the transformer is running normally, it will emit low-intensity background noise, and if there is a discharge at a certain place, there will be obvious discharge sound, so the sound intensity threshold can be set to extract the target audio signal, i.e. the sound of discharge.

[0058] The sound source position information can be the distance of the sound source relative to the audio acquisition device, or the pitch angle and azimuth angle of the sound source relative to the audio acquisition device, or other position information, which is not limited in the embodiments of the present application.

[0059] Based on any of the above embodiments, step 123 comprises:

[0060] Based on the difference between the sound source pitch angles and the difference between the sound source azimuth angles in the sound source position information corresponding to each audio frame, an initial fault detection result of the device to be detected is determined.

[0061] Specifically, in order to further improve the accuracy of fault detection, according to the sound source pitch angles and the sound source azimuth angles in the sound source position information corresponding to each audio frame, whether the difference between the sound source pitch angles and the difference between the sound source azimuth angles of each audio frame are within a preset range is judged, thereby determining whether the device to be detected has a fault, so as to obtain the initial fault detection result of the device to be detected.

[0062] Here, the judgment method can be to judge the difference between the sound source pitch angles and the difference between the sound source azimuth angles of any two audio frames, or to judge the difference between the sound source pitch angles and the difference between the sound source azimuth angles of adjacent two audio frames, or other judgment methods, which are not limited in the embodiments of the present application.

[0063] Based on any of the above embodiments, based on the difference between the sound source pitch angles and the difference between the sound source azimuth angles in the sound source position information corresponding to each audio frame, an initial fault detection result of the device to be detected is determined, comprising:

[0064] In a case that the difference between the sound source elevation angles corresponding to the first preset number of continuous audio frames is less than the first difference threshold, and the difference between the sound source azimuth angles is less than the second difference threshold, the position of the fault in the initial fault detection result is determined based on the sound source elevation angles and the sound source azimuth angles.

[0065] In a case that the difference between the sound source elevation angles corresponding to every second preset number of audio frames is less than the first difference threshold, and the difference between the sound source azimuth angles is less than the second difference threshold, the position of the fault in the initial fault detection result is determined based on the sound source elevation angles and the sound source azimuth angles.

[0066] Specifically, the judgment can be performed in the original order of the audio frames of the device audio. The specific process can be that, starting from the second audio frame, it is judged whether the difference between the sound source elevation angle corresponding to the current audio frame and the sound source elevation angle corresponding to the previous audio frame is less than the first difference threshold, and whether the difference between the sound source azimuth angle corresponding to the current audio frame and the sound source azimuth angle corresponding to the previous audio frame is less than the second difference threshold. The above steps are continuously performed until the judgment of the first preset number n of continuous audio frames is completed.

[0067] In a case that the difference between the sound source elevation angles corresponding to the n continuous audio frames is less than the first difference threshold, and the difference between the sound source azimuth angles corresponding to the n continuous audio frames is less than the second difference threshold, it is indicated that the same sound source appears in the n continuous audio frames, and the sound source should be the faulty sound source. That is, it is determined that the device state in the initial fault detection result is faulty, and the position of the fault in the initial fault detection result can also be determined according to the sound source elevation angles and the sound source azimuth angles.

[0068] In addition, a judgment can also be performed every second preset number m of audio frames, for example, it is judged whether the difference between the sound source elevation angle corresponding to the m+1th audio frame and the sound source elevation angle corresponding to the first audio frame is less than the first difference threshold, and whether the difference between the sound source azimuth angle corresponding to the m+1th audio frame and the sound source azimuth angle corresponding to the first audio frame is less than the second difference threshold. The above steps are continuously performed until there is no audio frame with a distance of m audio frames.

[0069] In a case that the difference between the sound source elevation angles corresponding to every m audio frames is less than the first difference threshold, and the difference between the sound source azimuth angles corresponding to every m audio frames is less than the second difference threshold, it is indicated that the same sound source periodically appears every m audio frames, and the sound source should be the faulty sound source. That is, it is determined that the device state in the initial fault detection result is faulty, and the position of the fault in the initial fault detection result can also be determined according to the sound source elevation angles and the sound source azimuth angles.

[0070] It can be understood that if the above two conditions are not met, it means that neither the same sound source appears continuously in multiple frames nor the same sound source appears periodically, and the unstable sound source appearing is a sound source of accidental noise without rules, that is, the device state in the initial fault detection result is determined as no fault.

[0071] In addition, when the pitch angle and the azimuth angle of the sound source satisfy the above two conditions, it means that the device to be detected has multiple faults, and the position of multiple faults is saved in the initial fault detection result.

[0072] Based on any of the above embodiments, Figure 3 is a third flowchart of the fault detection method provided by the present application, as shown in Figure 3 Step 130, control the device to be detected to start the self-checking program, including:

[0073] Step 310, based on the position of the fault in the initial fault detection result, determine the self-checking range and / or the self-checking order of the device to be detected;

[0074] Step 320, based on the self-checking range and / or the self-checking order of the device to be detected, control the device to be detected to start the self-checking program.

[0075] Specifically, considering that the self-checking program of part of the large device to be detected is relatively complex and time-consuming. In order to improve the self-checking efficiency of the device to be detected, the processor in the embodiment of the present application can determine the self-checking range of the device to be detected according to the position of the fault in the initial fault detection result, or determine the self-checking order of the device to be detected according to the position of the fault in the initial fault detection result, that is, the device to be detected preferentially checks the components at the position of the fault during self-checking, and the self-checking range and the self-checking order can also be determined at the same time. On this basis, the device to be detected can be self-checked according to the self-checking range and / or the self-checking order, so as to obtain the self-checking result of the device to be detected.

[0076] Here, the self-checking range can be a spatial range of self-checking and checking, that is, the device to be detected only checks part of the spatial range during self-checking, or a component range of self-checking and checking, which is composed of the components at the position of the fault and related components, that is, the device to be detected only checks the above components during self-checking, which is not limited in the embodiment of the present application.

[0077] Based on any of the above embodiments, in step 130, the control of the device to be detected to start the self-checking program includes:

[0078] Control the device to be detected to start the built-in self-checking program to obtain the self-checking result;

[0079] Or, send a self-checking command to the device to be detected, and receive the self-checking result returned by the device to be detected.

[0080] Specifically, the processor in the embodiments of the present application can be arranged on the device to be detected. In this case, when the processor detects that the device to be detected has a fault according to the device audio, the processor can directly start the self-checking program built in the device to be detected, find the specific fault through self-checking, and obtain the self-checking result.

[0081] Alternatively, in order to realize remote control of the device to be detected, detect faults of multiple devices to be detected, improve the efficiency of device inspection, and reduce costs, the processor in the embodiments of the present application can also not be arranged on the device to be detected, for example, can be arranged on an acoustic imager, a smart terminal, or a server. In this case, when the processor detects that the device to be detected has a fault according to the device audio, the processor can be in communication connection with the device to be detected, send a self-checking command to the device to be detected, trigger the device to be detected to start the self-checking program, so that the device to be detected finds the specific fault through self-checking, obtains the self-checking result, and returns the self-checking result to the processor. Further, after the device to be detected obtains the self-checking result, the self-checking result can also be sent to a preset terminal device, for example, can be another terminal device bound with the device to be detected, and the specific terminal device can be set according to application requirements.

[0082] It can be understood that the audio acquisition device used to acquire the device audio can be self-provided by the device to be detected or independently arranged with the device to be detected, and the embodiments of the present application do not make specific limitation thereto.

[0083] Based on any of the above embodiments, the device to be detected is controlled to start the built-in self-checking program to obtain the self-checking result, and then the following steps are further included:

[0084] The self-checking result is sent to a terminal device bound with the device to be detected.

[0085] Specifically, when the processor is arranged on the device to be detected, the processor can directly start the self-checking program built in the device to be detected to obtain the self-checking result, and then the processor can start the warning device such as the light-emitting device and the loudspeaker provided by the device to be detected, or send the self-checking result to the terminal device bound with the device to be detected, so that the terminal device performs subsequent fault warning or fault processing.

[0086] Here, the terminal device can be a central control room terminal or a mobile terminal (for example, a mobile phone or a specific application program), and the embodiments of the present application do not make specific limitation thereto.

[0087] Based on any of the above embodiments, after obtaining the self-checking result of the to-be-detected device, the position of the fault obtained by the sound source positioning algorithm in the initial fault detection result can be used to verify the position of the fault in the self-checking result. For example, whether the positions indicated by the two are the same or similar can be compared. If the verification result is passed, the fault detection result of the to-be-detected device can be determined according to the self-checking result. If the verification result is not passed, subsequent processing such as re-self-checking and manual verification is needed, and finally the fault detection result of the to-be-detected device is determined.

[0088] It can be understood that the position of the fault obtained by the sound source positioning algorithm is used to verify the position of the fault in the self-checking result, so that the accuracy of the fault detection result can be further improved.

[0089] Based on any of the above embodiments, the existing acoustic imager technology only displays the superposition effect of the video picture and the acoustic image in real time, and the operation and maintenance personnel still need to judge whether the device has a fault. In view of this, the embodiment of the present application provides a method for directly linking the device to carry out device self-checking when the acoustic imager judges that the device has a fault sound, thereby helping the operation and maintenance personnel to diagnose the fault.

[0090] Figure 4 is a fourth flowchart of the fault detection method provided by the present application, as shown in Figure 4 The specific process of the method is as follows:

[0091] S1, the microphone array of the acoustic imager is used to continuously collect audio of the to-be-detected device, obtain device audio, frame the device audio, obtain each audio frame of the to-be-detected device, perform sound source positioning on the target audio signal in each audio frame by a sound source positioning algorithm, obtain the position of the sound source of the target audio signal in each audio frame, and record the position information of all sound sources in each audio frame. The position information here includes the pitch angle of the sound source relative to the microphone array, i.e. the sound source pitch angle, and the azimuth angle of the sound source relative to the microphone array, i.e. the sound source azimuth angle.

[0092] According to the sound intensity information of the target audio signal in each audio frame of the device audio and the sound source position information of the target audio signal, a sound intensity distribution map corresponding to each audio frame is generated, different colors are used to represent different sound intensities, and then the sound intensity distribution map and the visible light image of the to-be-detected device are fused to obtain an acoustic imaging image corresponding to each audio frame and display it, so that the operation and maintenance personnel can intuitively view the position of the sound source on the image.

[0093] S2, considering that angle deviation is prone to occur during visible light image acquisition, and then the accuracy of the pixel coordinates of the sound source on the acoustic imaging diagram is affected, if the gap between the pixel coordinates on the acoustic imaging diagram based on the continuous n audio frames is used to judge whether the to-be-detected device has a fault, the detection result will be inaccurate.

[0094] To solve the problem, the embodiment of the application judges whether the continuous n audio frames have the same sound source position information or the sound source position information with a gap less than a preset gap threshold according to the gap between the sound source pitch angles corresponding to the continuous n audio frames and the gap between the sound source azimuth angles.

[0095] If yes, it indicates that the to-be-detected device has a fault, and it is further judged whether fault diagnosis needs to be carried out, that is, whether the to-be-detected device has a self-checking function, if the to-be-detected device has a self-checking function, the to-be-detected device is controlled to start a self-checking program to generate self-checking results such as logs and detection information, and the self-checking results returned by the to-be-detected device are synchronized to the acoustic imager, so that the operation and maintenance personnel can intuitively view the position, type and other information of the fault.

[0096] S3, the self-checking result is verified according to the position of the fault obtained by the sound source positioning algorithm, and it is judged whether further self-checking work needs to be carried out according to the verification result, if not, the control is ended, and the fault detection result of the to-be-detected device is determined according to the self-checking result. For example, it can be determined from the fault detection result that a small gap occurs in a valve in the pipeline, and the valve can be processed in time, and for example, it can be determined from the fault detection result that a component inside the transformer is loose, and the component can be processed in time.

[0097] If yes, the self-checking program of the to-be-detected device is restarted once. In addition, if the acoustic imager does not receive the self-checking result returned by the to-be-detected device within a preset time length, further self-checking work needs to be carried out.

[0098] The application relates to the field of device inspection, and remote device inspection is carried out through a fixed acoustic imager, sound visualization is used to position device fault sound, when an abnormality is found, a self-checking command is sent to the to-be-detected device in time through a processor built in the acoustic imager, the to-be-detected device carries out self-checking operation, specific abnormalities are found through self-checking, and abnormal log information is reported, so that the fixed acoustic imager is combined with the device self-checking capability to carry out remote fault diagnosis of the device, the effect of device inspection is improved, and the loss caused by non-scheduled shutdown to a production unit is reduced.

[0099] The fault detection device provided by the application is described below, and the fault detection device described below can be correspondingly referred to the fault detection method described above.

[0100] Based on any one of the above embodiments, the application provides a fault detection device. Figure 5 is a structural schematic diagram of the fault detection device provided by the application, as Figure 5 shown, the device comprises:

[0101] an audio acquisition unit 510, configured to acquire device audio of a to-be-detected device;

[0102] a fault detection unit 520, configured to determine an initial fault detection result of the to-be-detected device based on the device audio;

[0103] a self-check starting unit 530, configured to control the to-be-detected device to start a self-check program in a case where the initial fault detection result indicates that the to-be-detected device has a fault.

[0104] The device provided by the embodiment of the application can detect whether the to-be-detected device has a fault based on the device audio, and control the to-be-detected device to start a self-check program in a case where the to-be-detected device has a fault, so as to realize automatic fault detection of the to-be-detected device, improve the efficiency of device inspection, improve the accuracy of fault detection, and determine the specific type and specific position of the fault, which is helpful for timely processing of the fault and reducing the loss caused by unplanned downtime to a production unit.

[0105] Based on any one of the above embodiments, the fault detection unit 520 comprises:

[0106] a framing unit, configured to frame the device audio to obtain each audio frame of the device audio;

[0107] a positioning unit, configured to perform sound source positioning on a target audio signal in each audio frame to obtain sound source position information corresponding to each audio frame;

[0108] a detection unit, configured to determine the initial fault detection result of the to-be-detected device based on the sound source position information corresponding to each audio frame.

[0109] Based on any one of the above embodiments, the detection unit comprises a detection subunit, configured to:

[0110] determine the initial fault detection result of the to-be-detected device based on a difference between sound source elevation angles and a difference between sound source azimuth angles in the sound source position information corresponding to each audio frame.

[0111] Based on any one of the above embodiments, the detection subunit is specifically configured to:

[0112] in a case where the difference between the sound source elevation angles of the first preset number of continuous audio frames is less than a first difference threshold and the difference between the sound source azimuth angles is less than a second difference threshold, determine the position of the fault in the initial fault detection result based on the sound source elevation angles and the sound source azimuth angles;

[0113] In a case that a difference between the sound source elevation angles corresponding to every second preset number of audio frames is less than a first difference threshold, and a difference between the sound source azimuth angles is less than a second difference threshold, a position of the fault in the initial fault detection result is determined based on the sound source elevation angles and the sound source azimuth angles.

[0114] Based on any of the above embodiments, the to-be-detected device is controlled to start a self-checking program, including:

[0115] Based on the position of the fault in the initial fault detection result, a self-checking range and / or a self-checking sequence of the to-be-detected device are determined;

[0116] Based on the self-checking range and / or the self-checking sequence of the to-be-detected device, the to-be-detected device is controlled to start the self-checking program.

[0117] Based on any of the above embodiments, the to-be-detected device is controlled to start a self-checking program, including:

[0118] The to-be-detected device is controlled to start a built-in self-checking program to obtain a self-checking result;

[0119] Alternatively, a self-checking command is sent to the to-be-detected device, and a self-checking result returned by the to-be-detected device is received.

[0120] Based on any of the above embodiments, the to-be-detected device is controlled to start a built-in self-checking program to obtain a self-checking result, and then further including:

[0121] The self-checking result is sent to a terminal device bound to the to-be-detected device.

[0122] Based on any of the above embodiments, the present application provides a fault detection system. Figure 6 is a structural schematic diagram of the fault detection system provided by the present application, as Figure 6 shown, the system includes an audio acquisition device 610, a processor 620 and a to-be-detected device 630, the audio acquisition device 610 is used to acquire device audio of the to-be-detected device 630 and send the device audio to the processor 620, and the processor 620 is used to execute the fault detection method provided by each of the above embodiments.

[0123] The fault detection system provided by the embodiment of the present application can detect whether the to-be-detected device has a fault according to the device audio, and control the to-be-detected device to start a self-checking program in a case that the to-be-detected device has a fault, so as to realize automatic fault detection of the to-be-detected device, improve the efficiency of device inspection, and improve the accuracy of fault detection, and the specific type and specific position of the fault are clear, which is helpful for timely processing of the fault and reducing the loss caused by non-scheduled downtime to the production unit.

[0124] Based on any of the above embodiments, the audio acquisition device 610, the processor 620, and the device under test 630 are set independently of each other, or the audio acquisition device 610 and / or the processor 620 are set on the device under test 630.

[0125] Here, the audio acquisition device used to acquire the audio of the device can be built into the device under test or can be set up independently of the device under test. This embodiment of the invention does not make specific limitations on this.

[0126] It is understandable that when the processor and the device under test are set up independently, such as when the processor is set up on the central control room equipment, acoustic imager or smart terminal, the processor and the device under test are connected in communication. If the processor determines that the device under test has a fault based on the device audio, it can send a self-test command to the device under test to trigger the device under test to start the self-test program.

[0127] When the processor is set on the device under test, if the processor determines that the device under test is faulty based on the device audio, it can directly start the self-test program built into the device under test.

[0128] Figure 7 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 7 As shown, the electronic device may include a processor 710, a communications interface 720, a memory 730, and a communication bus 740, wherein the processor 710, communications interface 720, and memory 730 communicate with each other via the communication bus 740. The processor 710 can call logical instructions in the memory 730 to execute a fault detection method, which includes: acquiring device audio of the device under test; determining an initial fault detection result of the device under test based on the device audio; and, if the initial fault detection result indicates that the device under test has a fault, controlling the device under test to start a self-test program.

[0129] In addition, the logic instructions in the memory 730 described above can be implemented in the form of a software function unit and sold or used as an independent product, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0130] In another aspect, the present application also provides a computer program product, which comprises a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and the computer program is executed by a processor, so that the computer can execute the fault detection method provided by the above-mentioned methods. The method comprises: obtaining device audio of a to-be-detected device; determining an initial fault detection result of the to-be-detected device based on the device audio; and in the case that the initial fault detection result represents that the to-be-detected device has a fault, controlling the to-be-detected device to start a self-checking program.

[0131] In another aspect, the present application also provides a computer program product, which comprises a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and the computer program is executed by a processor, so that the computer can execute the fault detection method provided by the above-mentioned methods. The method comprises: obtaining device audio of a to-be-detected device; determining an initial fault detection result of the to-be-detected device based on the device audio; and in the case that the initial fault detection result represents that the to-be-detected device has a fault, controlling the to-be-detected device to start a self-checking program.

[0132] The device embodiments described above are only schematic, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, that is, they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0133] Those skilled in the art can clearly understand the technical solutions of the various embodiments from the above description of the embodiments, and the various embodiments can be implemented by means of software with the necessary general hardware platforms, and of course, can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part of the prior art that makes a contribution, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, and the like, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0134] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features therein; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A fault detection method characterized by, The method comprises: obtaining device audio of a device to be detected; based on the device audio, determining an initial fault detection result of the device to be detected; the initial fault detection result is used to represent whether the device to be detected has a fault; in the case that the initial fault detection result represents that the device to be detected has a fault, controlling the device to be detected to start a self-checking program; the initial fault detection result is determined based on the device audio, comprising: frame the device audio to obtain each audio frame of the device audio; performing sound source positioning on a target audio signal in each audio frame to obtain sound source position information corresponding to each audio frame; the target audio signal refers to an audio signal in an audio frame that belongs to abnormal sound; determining whether the initial fault detection result represents a fault by judging whether the difference between the sound source pitch angles in the sound source position information is less than a first difference threshold and whether the difference between the sound source azimuth angles is less than a second difference threshold in a first preset number of consecutive audio frames or every second preset number of audio frames; determining the initial fault detection result of the device to be detected based on the sound source position information corresponding to each audio frame.

2. The fault detection method according to claim 1, characterized in that, the initial fault detection result is determined based on the difference between the sound source pitch angles and the difference between the sound source azimuth angles in the sound source position information corresponding to each audio frame, comprising: in the case that the difference between the sound source pitch angles corresponding to a first preset number of consecutive audio frames is less than a first difference threshold and the difference between the sound source azimuth angles is less than a second difference threshold, determining the position of the fault in the initial fault detection result based on the sound source pitch angles and the sound source azimuth angles; in the case that the difference between the sound source pitch angles corresponding to every second preset number of audio frames is less than a first difference threshold and the difference between the sound source azimuth angles is less than a second difference threshold, determining the position of the fault in the initial fault detection result based on the sound source pitch angles and the sound source azimuth angles.

3. The fault detection method of claim 1, wherein, controlling the device to be detected to start a self-checking program, comprising: determining the self-checking range and / or self-checking sequence of the device to be detected based on the position of the fault in the initial fault detection result; controlling the device to be detected to start a self-checking program based on the self-checking range and / or self-checking sequence of the device to be detected.

4. The fault detection method according to any one of claims 1 to 3, characterized in that, controlling the device to be detected to start a self-checking program, comprising: controlling the device to be detected to start a built-in self-checking program to obtain a self-checking result; or, sending a self-checking command to the device to be detected and receiving a self-checking result returned by the device to be detected.

5. The fault detection method of claim 4, wherein, controlling the device to be detected to start a built-in self-checking program to obtain a self-checking result, further comprising: sending the self-checking result to a preset terminal device.

6. A fault detection system characterized by, The method comprises: an audio acquisition device, a processor and a device to be detected, the audio acquisition device is used to acquire device audio of the device to be detected and send the device audio to the processor, and the processor is used to execute the fault detection method according to any one of claims 1 to 5.

7. The fault detection system of claim 6, wherein, The audio acquisition device, the processor and the device to be detected are independently arranged, or the audio acquisition device and / or the processor are arranged on the device to be detected.

8. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the fault detection method according to any one of claims 1 to 5.

Images