CN108830261A - Equipment fault diagnosis method and device based on image recognition - Google Patents

Abstract

The invention discloses a device fault diagnosis method and device based on image recognition. The method includes: acquiring a sampling picture containing a time-domain waveform of vibration of the target device during operation; finding a fault picture matching the sampling picture from a fault database based on an image recognition algorithm; information identifying a failure of the target device. This technical solution can greatly reduce the operation and resource consumption of fault diagnosis, significantly improve diagnosis efficiency, save diagnosis time, and at the same time ensure a certain degree of accuracy, which is suitable for industrial practicality and has a wide range of application scenarios.

Description

Method and device for equipment fault diagnosis based on image recognition

technical field

The invention relates to the field of fault diagnosis, in particular to a device fault diagnosis method and device based on image recognition.

Background technique

At present, the fault diagnosis of equipment is usually based on the time-domain waveform of vibration collected by the detection equipment, and the fault can only be diagnosed after a series of complicated processing, which is very troublesome and wastes a lot of resources. A more efficient and less resource-consuming method is needed Fault diagnosis method.

Contents of the invention

In view of the above problems, the present invention is proposed to provide a device fault diagnosis method and device based on image recognition that overcomes the above problems or at least partially solves the above problems.

According to one aspect of the present invention, a method for diagnosing equipment faults based on image recognition is provided, including:

Obtain a sample picture of the time-domain waveform containing the vibration of the target device during operation;

Find out the fault picture matching the sampled picture from the fault database based on the image recognition algorithm;

The fault of the target device is determined according to the fault description information corresponding to the fault picture.

Optionally, the method also includes:

When there is no fault picture matching the sampling picture in the fault database, analyze according to the time-domain waveform in the sampling picture, determine the fault of the target device, and generate corresponding fault description information;

A fault picture corresponding to the determined fault is generated according to the sampled picture, and the generated fault picture is correspondingly stored with the generated fault description information in the fault database.

Optionally, the acquisition of the sampling picture containing the time-domain waveform when the target device vibrates includes:

Determine the sampling time corresponding to the sampling picture according to the failure period of the target device, so that the sampling picture contains at least time-domain waveforms of several failure periods; the failure period is determined according to the parameters of the target device of;

Finding the fault picture matching the sampling picture from the fault database based on the image recognition algorithm includes:

A fault picture corresponding to the parameter of the target device is found from the fault database as a candidate picture, and a fault picture matching the sampling picture is found from the candidate picture.

Optionally, the acquisition of the sampling picture containing the time-domain waveform of the vibration of the target device includes:

The detection device that detects the target device collects the time-domain waveform of the target device when it vibrates, and generates a sampling picture containing the time-domain waveform by shooting and/or screenshotting.

According to another aspect of the present invention, a device fault diagnosis device based on image recognition is provided, including:

A sampling picture acquisition unit, configured to acquire a sampling picture comprising a time-domain waveform of vibration of the target device during operation;

An identification unit, configured to find a fault picture that matches the sampled picture from the fault database based on an image recognition algorithm;

A fault diagnosis unit, configured to determine the fault of the target device according to the fault description information corresponding to the fault picture.

Optionally, the fault diagnosis unit is further configured to, when there is no fault picture matching the sampled picture in the fault database, analyze the time-domain waveform in the sampled picture to determine the fault, generating corresponding fault description information; generating a fault picture corresponding to the determined fault according to the sampled picture, and correspondingly saving the generated fault picture and the generated fault description information in the fault database.

Optionally, the sampling picture acquisition unit is configured to determine the sampling time corresponding to the sampling picture according to the failure period of the target device, so that the sampling picture at least includes time-domain waveforms of several failure periods; The failure period is determined according to the parameters of the target device;

The identification unit is configured to find out a fault picture corresponding to the parameters of the target device from the fault database as a candidate picture, and find a fault picture that matches the sampling picture from the candidate pictures .

Optionally, the sampling picture acquisition unit is configured to use the detection device that detects the target device to collect the time-domain waveform of the target device when it vibrates, and generate a sample that includes the time-domain waveform by taking pictures and/or screenshots. picture.

According to yet another aspect of the present invention, there is provided an electronic device, comprising: a processor; and a memory arranged to store computer-executable instructions that, when executed, cause the processor to perform any of the above a method as described.

According to still another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by a processor, the following is implemented: any of the methods described above.

As can be seen from the above, the technical solution of the present invention saves the fault description information and corresponding fault pictures in the fault database in advance, and after obtaining the sampled pictures containing the time-domain waveform of the vibration of the target equipment during operation, based on the image recognition algorithm, from the fault database Find the fault picture that matches the sampling picture, and determine the fault of the target device according to the fault description information corresponding to the fault picture. This technical solution can greatly reduce the operation and resource consumption of fault diagnosis, significantly improve diagnosis efficiency, save diagnosis time, and at the same time ensure a certain degree of accuracy. It is suitable for industrial practicality and has a wide range of application scenarios.

The above description is only an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention, it can be implemented according to the contents of the description, and in order to make the above and other purposes, features and advantages of the present invention more obvious and understandable , the specific embodiments of the present invention are enumerated below.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiment. The drawings are only for the purpose of illustrating a preferred embodiment and are not to be considered as limiting the invention. Also throughout the drawings, the same reference numerals are used to designate the same components. In the attached picture:

Fig. 1 shows a schematic flow chart of an image recognition-based equipment fault diagnosis method according to an embodiment of the present invention;

Fig. 2 shows a schematic structural diagram of a device fault diagnosis device based on image recognition according to an embodiment of the present invention;

FIG. 3 shows a schematic structural diagram of an electronic device according to an embodiment of the present invention;

Fig. 4 shows a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present invention.

Detailed ways

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

Fig. 1 shows a schematic flowchart of a method for diagnosing equipment faults based on image recognition according to an embodiment of the present invention. As shown in Figure 1, the method includes:

Step S110, acquiring a sampled picture including a time-domain waveform of vibration of the target device during operation. For example, the target device here may be a mechanical device that generates vibration during operation, so the corresponding time-domain waveform can be collected through detection devices such as various sensors. Since the vibration of the equipment when it fails is different from the vibration under normal working conditions, the generated time domain waveforms are also different.

It should be noted here that the sampled picture may be one or several pictures collected separately, or each frame in a sampled video. That is to say, what is actually collected can be a picture or a video.

Step S120, based on the image recognition algorithm, find the fault picture matching the sampled picture from the fault database.

The image recognition algorithm here can be implemented using existing technologies. In fact, it is to identify whether the time-domain waveform in the sampled picture is similar to the time-domain waveform in the fault picture. If the similarity reaches a certain threshold, it is considered a match. For example, if the similarity between the sampled picture and the fault picture A in the fault database (the similarity here can also be obtained based on the confidence in the image recognition model) reaches 95%, exceeding the preset threshold of 90%, then the sampling The picture matches the fault picture A. The preset threshold here can be set according to requirements, and can be related to the parameters of the equipment, for example, a threshold of 85% is set for a large bearing, and a threshold of 95% is set for a small bearing.

Step S130, determine the fault of the target device according to the fault description information corresponding to the fault picture.

A fault picture can correspond to one fault, that is, the target equipment may be damaged rolling elements of the bearing; it can also correspond to multiple faults, that is, the corresponding time domain waveform is generated by the vibration of the target equipment when multiple faults occur at the same time, For example, not only the rolling elements are damaged, but also the inner or outer ring. The fault pictures corresponding to various faults can be stored in the fault database, and the corresponding fault description information is attached, so that after matching the corresponding fault pictures, the fault type can be directly determined according to the fault description information.

It can be seen that the method shown in Figure 1 saves the fault description information and the corresponding fault pictures in the fault database in advance, after obtaining the sampled pictures containing the time-domain waveform of the vibration of the target equipment during operation, based on the image recognition algorithm, from the fault database Find the fault picture that matches the sampling picture, and determine the fault of the target device according to the fault description information corresponding to the fault picture. This technical solution can greatly reduce the operation and resource consumption of fault diagnosis, significantly improve diagnosis efficiency, save diagnosis time, and at the same time ensure a certain degree of accuracy. It is suitable for industrial practicality and has a wide range of application scenarios.

In one embodiment of the present invention, the above method further includes: when there is no fault picture matching the sampled picture in the fault database, analyze according to the time domain waveform in the sampled picture, determine the fault of the target device, and generate a corresponding Fault description information: Generate a fault picture corresponding to the determined fault according to the sampled picture, and store the generated fault picture and the generated fault description information in the fault database correspondingly.

Generally speaking, the equipment that requires fault diagnosis does have certain faults, but there may also be cases where operators misjudge. Therefore, the time-domain waveforms in the picture may actually correspond to one or several kinds of faults, or may correspond to normal working conditions. Under normal working conditions, it is obviously impossible to find a matching fault picture from the fault database; in addition, there may also be situations where the fault of the equipment has not been included in the fault database. Therefore, when there is no fault picture matching the sampling picture in the database, it is necessary to use a series of methods such as converting the time-domain waveform into a frequency-domain waveform and undergoing Fourier transform for fault analysis. Specifically, the methods in the prior art can be used Realization; the result of the analysis may be that the target device is not faulty, and other follow-up processing may not be performed at this time; another result may be that the target device does have a fault, and this fault is not included in the fault database. At this time, we need to generate a fault picture corresponding to this new fault, for example, directly use the sampling picture as the fault picture; it may also be because the time domain waveform contained in the sampling picture contains too many fault cycles, and only select the one corresponding to one fault cycle The time-domain waveform generates a picture of the fault.

In this way, the continuous improvement of the fault database is realized, which can be iteratively updated to meet actual needs.

In an embodiment of the present invention, in the above method, obtaining the sampled picture containing the time-domain waveform when the target device vibrates includes: determining the sampling time corresponding to the sampled picture according to the fault period of the target device, so that the sampled picture contains at least The time-domain waveforms of several fault cycles; the fault cycle is determined according to the parameters of the target equipment; based on the image recognition algorithm, finding the fault pictures that match the sampling pictures from the fault database includes: finding the fault pictures that match the target equipment from the fault database The fault picture corresponding to the parameter is used as a candidate picture, and the fault picture matching the sampling picture is found from the candidate picture.

Wherein, the parameters of the target device may include device model, rotation speed and so on. In order to ensure the accuracy of image recognition, it is generally required that the collected time-domain waveforms contain at least one fault cycle, and may optionally contain multiple fault cycles. The fault pictures in the fault database may contain at least one fault cycle, so if at least a part of the time-domain waveform in the sampled picture is similar to the time-domain waveform in a fault picture, the two are considered to match.

Since the parameters of different devices may be different, the time-domain waveforms collected during the failure are also different. It is meaningless to compare the time-domain waveforms of different devices. Therefore, in this embodiment, the parameters of the target device are selected first. The fault picture corresponding to the parameters reduces the matching range, improves the accuracy of image recognition, and reduces the false matching rate.

In an embodiment of the present invention, in the above method, acquiring the sampled picture containing the time-domain waveform of the vibration of the target device includes: collecting the time-domain waveform of the vibration of the target device by the detection device that detects the target device, by photographing and/or Or generate a sample picture including a time domain waveform by taking a screenshot.

Sometimes our detection equipment does not provide a good data processing interface, and cannot directly obtain time-domain waveforms to generate pictures, but these detection equipment can output time-domain waveforms on the display screen, so in this embodiment, we can use the The display device that outputs the time-domain waveform takes pictures or screenshots, and the time-domain waveform is not obtained through the interface. It can be seen that although the embodiment of the present invention essentially identifies whether the time-domain waveforms are similar, it is not realized by directly identifying the time-domain waveforms, but by identifying whether the pictures are similar.

Fig. 2 shows a schematic structural diagram of an apparatus for fault diagnosis of equipment based on image recognition according to an embodiment of the present invention. As shown in Figure 2, the device fault diagnosis device 200 based on image recognition includes:

The sampling picture acquiring unit 210 is configured to acquire a sampling picture including a time-domain waveform of vibration of the target device during operation. For example, the target device here may be a mechanical device that generates vibration during operation, so the corresponding time-domain waveform can be collected through detection devices such as various sensors. Since the vibration of the equipment when it fails is different from the vibration under normal working conditions, the generated time domain waveforms are also different.

It should be noted here that the sampled picture may be one or several pictures collected separately, or each frame in a sampled video. That is to say, what is actually collected can be a picture or a video.

The recognition unit 220 is configured to find fault pictures that match the sampled pictures from the fault database based on an image recognition algorithm.

The image recognition algorithm here can be implemented using existing technologies. In fact, it is to identify whether the time-domain waveform in the sampling picture is similar to the time-domain waveform in the fault picture. If the similarity (the similarity here can also be based on the image recognition model) The confidence obtained) reaches a certain threshold and is considered a match. For example, if the similarity between the sampled picture and the faulty picture A in the fault database reaches 95%, and exceeds the preset threshold of 90%, then the sampled picture is considered to match the faulty picture A. The preset threshold here can be set according to requirements, and can be related to the parameters of the equipment, for example, a threshold of 85% is set for a large bearing, and a threshold of 95% is set for a small bearing.

The fault diagnosis unit 230 is configured to determine the fault of the target device according to the fault description information corresponding to the fault picture.

A fault picture can correspond to one fault, that is, the target equipment may be damaged rolling elements of the bearing; it can also correspond to multiple faults, that is, the corresponding time domain waveform is generated by the vibration of the target equipment when multiple faults occur at the same time, For example, not only the rolling elements are damaged, but also the inner or outer ring. The fault pictures corresponding to various faults can be stored in the fault database, and the corresponding fault description information is attached, so that after matching the corresponding fault pictures, the fault type can be directly determined according to the fault description information.

It can be seen that the device shown in Figure 2 saves the fault description information and corresponding fault pictures in the fault database in advance through the mutual cooperation of each unit. The image recognition algorithm finds the fault pictures that match the sampling pictures from the fault database, and determines the fault of the target device according to the fault description information corresponding to the fault pictures. This technical solution can greatly reduce the operation and resource consumption of fault diagnosis, significantly improve diagnosis efficiency, save diagnosis time, and at the same time ensure a certain degree of accuracy. It is suitable for industrial practicality and has a wide range of application scenarios.

In one embodiment of the present invention, in the above-mentioned device, the fault diagnosis unit 230 is also used to analyze the time-domain waveform in the sampled picture and determine the target when there is no fault picture matching the sampled picture in the fault database. For equipment faults, generate corresponding fault description information; generate fault pictures corresponding to the determined faults according to the sampled pictures, and store the generated fault pictures and the generated fault description information in the fault database correspondingly.

Generally speaking, the equipment that requires fault diagnosis does have certain faults, but there may also be cases where operators misjudge. Therefore, the time-domain waveforms in the picture may actually correspond to one or several kinds of faults, or may correspond to normal working conditions. Under normal working conditions, it is obviously impossible to find a matching fault picture from the fault database; in addition, there may also be situations where the fault of the equipment has not been included in the fault database. Therefore, when there is no fault picture matching the sampling picture in the database, it is necessary to use a series of methods such as converting the time-domain waveform into a frequency-domain waveform and undergoing Fourier transform for fault analysis. Specifically, the methods in the prior art can be used Realization; the result of the analysis may be that the target device is not faulty, and other follow-up processing may not be performed at this time; another result may be that the target device does have a fault, and this fault is not included in the fault database. At this time, we need to generate a fault picture corresponding to this new fault, for example, directly use the sampling picture as the fault picture; it may also be because the time domain waveform contained in the sampling picture contains too many fault cycles, and only select the one corresponding to one fault cycle The time-domain waveform generates a picture of the fault.

In this way, the continuous improvement of the fault database is realized, which can be iteratively updated to meet actual needs.

In one embodiment of the present invention, in the above-mentioned device, the sampling picture acquisition unit 210 is configured to determine the sampling time corresponding to the sampling picture according to the failure period of the target device, so that the sampling picture at least includes the time domain of several failure periods Waveform; the fault period is determined according to the parameters of the target device; the identification unit 220 is used to find out the fault picture corresponding to the parameter of the target device from the fault database as an alternative picture, and find out the fault picture corresponding to the sampling picture from the alternative picture. Matching fault pictures.

Wherein, the parameters of the target device may include device model, rotation speed and so on. In order to ensure the accuracy of image recognition, it is generally required that the collected time-domain waveforms contain at least one fault cycle, and may optionally contain multiple fault cycles. The fault pictures in the fault database may contain at least one fault cycle, so if at least a part of the time-domain waveform in the sampled picture is similar to the time-domain waveform in a fault picture, the two are considered to match.

Since the parameters of different devices may be different, the time-domain waveforms collected during the failure are also different. It is meaningless to compare the time-domain waveforms of different devices. Therefore, in this embodiment, the parameters of the target device are selected first. The fault picture corresponding to the parameters reduces the matching range, improves the accuracy of image recognition, and reduces the false matching rate.

In one embodiment of the present invention, in the above-mentioned device, the sampling picture acquisition unit 210 is used to collect the time-domain waveform of the target device by the detection device that detects the target device, and generate the A sample picture of the domain waveform.

Sometimes our detection equipment does not provide a good data processing interface, and cannot directly obtain time-domain waveforms to generate pictures, but these detection equipment can output time-domain waveforms on the display screen, so in this embodiment, we can use the The display device that outputs the time-domain waveform takes pictures or screenshots, and the time-domain waveform is not obtained through the interface. It can be seen that although the embodiment of the present invention essentially identifies whether the time-domain waveforms are similar, it is not realized by directly identifying the time-domain waveforms, but by identifying whether the pictures are similar.

In summary, the technical solution of the present invention saves the fault description information and the corresponding fault pictures in the fault database in advance, after obtaining the sampled pictures containing the time-domain waveform of the vibration of the target device during operation, based on the image recognition algorithm, from The fault picture matching the sampling picture is found in the fault database, and the fault of the target device is determined according to the fault description information corresponding to the fault picture. This technical solution can greatly reduce the operation and resource consumption of fault diagnosis, significantly improve diagnosis efficiency, save diagnosis time, and at the same time ensure a certain degree of accuracy. It is suitable for industrial practicality and has a wide range of application scenarios.

It should be noted:

The algorithms and displays presented herein are not inherently related to any particular computer, virtual appliance, or other device. Various general purpose devices can also be used with the teachings based on this. The structure required to construct such an apparatus will be apparent from the foregoing description. Furthermore, the present invention is not specific to any particular programming language. It should be understood that various programming languages can be used to implement the content of the present invention described herein, and the above description of specific languages is for disclosing the best mode of the present invention.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure the understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, in order to streamline this disclosure and to facilitate an understanding of one or more of the various inventive aspects, various features of the invention are sometimes grouped together in a single embodiment, figure, or its description. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art can understand that the modules in the device in the embodiment can be adaptively changed and arranged in one or more devices different from the embodiment. Modules or units or components in the embodiments may be combined into one module or unit or component, and furthermore may be divided into a plurality of sub-modules or sub-units or sub-assemblies. All features disclosed in this specification (including accompanying claims, abstract and drawings) and any method or method so disclosed may be used in any combination, except that at least some of such features and/or processes or units are mutually exclusive. All processes or units of equipment are combined. Each feature disclosed in this specification (including accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will understand that although some embodiments described herein include some features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the invention. and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of some or all of the components in the device fault diagnosis device based on image recognition according to the embodiment of the present invention Function. The present invention can also be implemented as an apparatus or an apparatus program (for example, a computer program and a computer program product) for performing a part or all of the methods described herein. Such a program for realizing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet site, or provided on a carrier signal, or provided in any other form.

For example, FIG. 3 shows a schematic structural diagram of an electronic device according to an embodiment of the present invention. The electronic device comprises a processor 310 and a memory 320 arranged to store computer executable instructions (computer readable program code). Memory 320 may be electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read Only Memory), EPROM, hard disk, or ROM. The memory 320 has a storage space 330 storing computer readable program code 331 for performing any method step in the method described above. For example, the storage space 330 for storing computer-readable program codes may include respective computer-readable program codes 331 for respectively implementing various steps in the above methods. The computer readable program code 331 can be read from or written into one or more computer program products. These computer program products comprise program code carriers such as hard disks, compact disks (CDs), memory cards or floppy disks. Such a computer program product is typically, for example, a computer-readable storage medium as described in FIG. 4 . Fig. 4 shows a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present invention. The computer-readable storage medium 400 stores computer-readable program code 331 for executing the method steps according to the present invention, which can be read by the processor 310 of the electronic device 300, when the computer-readable program code 331 is run by the electronic device 300 , causing the electronic device 300 to execute each step in the method described above, specifically, the computer-readable program code 331 stored in the computer-readable storage medium may execute the method shown in any of the foregoing embodiments. The computer readable program code 331 can be compressed in a suitable form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. does not indicate any order. These words can be interpreted as names.

Claims (10)

1. a kind of equipment fault diagnosis method based on image recognition, which is characterized in that this method includes：

Obtain the sampling picture of the time domain waveform comprising vibrating when target device operation；

The failure picture to match with the sampling picture is found out from Mishap Database based on image recognition algorithm；

The failure of the target device is determined according to the corresponding failure-description information of the failure picture.

2. the method as described in claim 1, which is characterized in that this method further includes：

When the failure picture to match with the sampling picture is not present in Mishap Database, according in the sampling picture Time domain waveform is analyzed, and determines the failure of the target device, generates corresponding failure-description information；

Failure picture corresponding with the failure determined is generated according to the sampling picture, by generation in the Mishap Database Failure picture is corresponding with the failure-description information of generation to be saved.

3. the method as described in claim 1, which is characterized in that the time domain waveform when acquisition includes target device vibration Sampling picture includes：

The sampling time corresponding with the sampling picture is determined according to the inaction interval of the target device, so that the sample graph The time domain waveform of several inaction intervals is included at least in piece；The inaction interval is determined according to the parameter of the target device 's；

It is described to find out the failure picture packet to match with the sampling picture from Mishap Database based on image recognition algorithm It includes：

Failure picture corresponding with the parameter of the target device alternately picture is found out from the Mishap Database, from The failure picture to match with the sampling picture is found out in the alternative picture.

4. the method as described in claim 1, which is characterized in that described to obtain adopting for the time domain waveform comprising target device vibration Master drawing piece includes：

Time domain waveform when being vibrated by the detection device acquisition target device detected to the target device, passes through shooting And/or screenshotss mode generates the sampling picture comprising the time domain waveform.

5. a kind of equipment fault diagnosis device based on image recognition, which is characterized in that the device includes：

Picture acquiring unit is sampled, for obtaining the sampling picture of the time domain waveform comprising vibrating when target device operation；

Recognition unit, for finding out the event to match with the sampling picture from Mishap Database based on image recognition algorithm Hinder picture；

Failure diagnosis unit, for determining the event of the target device according to the corresponding failure-description information of the failure picture Barrier.

6. device as claimed in claim 5, which is characterized in that

The failure diagnosis unit is also used to when there is no the failure pictures to match with the sampling picture in Mishap Database When, it is analyzed according to the time domain waveform in the sampling picture, determines the failure of the target device, generate corresponding failure Description information；Failure picture corresponding with the failure determined is generated according to the sampling picture, it will in the Mishap Database The failure picture of generation and the failure-description information of generation it is corresponding save.

7. device as claimed in claim 5, which is characterized in that

The sampling picture acquiring unit, for corresponding with the sampling picture according to the determination of the inaction interval of the target device Sampling time so that it is described sampling picture in include at least several inaction intervals time domain waveform；The inaction interval is It is determined according to the parameter of the target device；

The recognition unit, for finding out fault graph corresponding with the parameter of the target device from the Mishap Database Piece alternately picture, finds out and failure picture that the sampling picture matches from the alternative picture.

8. device as claimed in claim 5, which is characterized in that

The sampling picture acquiring unit, for the detection device acquisition target device vibration by being detected to the target device Time domain waveform when dynamic generates the sampling picture comprising the time domain waveform by shooting and/or screenshotss mode.

9. a kind of electronic equipment, wherein the electronic equipment includes：Processor；And it is arranged to the executable finger of storage computer The memory of order, the executable instruction execute the processor as described in any one of claim 1-4 Method.

10. a kind of computer readable storage medium, wherein the computer-readable recording medium storage one or more program, One or more of programs when being executed by a processor, realize such as method of any of claims 1-4.