CN117934897A - Equipment abnormality detection method, device, equipment and storage medium - Google Patents

Abstract

The invention discloses a method, a device, equipment and a storage medium for detecting equipment abnormality, wherein an image of equipment to be detected and operating parameters of the equipment to be detected corresponding to at least one piece of equipment to be detected are obtained; for each device to be detected, determining a similarity value of an image of the device to be detected and a historical normal state image, so as to determine an image detection result based on the similarity value; determining an operation parameter detection result based on the operation parameter of the equipment to be detected and a preset normal equipment threshold range; determining a target detection result based on the image detection result and/or the operation parameter detection result; if the target detection result is an abnormal detection result, determining abnormal prompt information of the target abnormal equipment, and carrying out equipment abnormal warning on the target abnormal equipment based on the abnormal prompt information; the abnormality prompt information comprises position information, abnormality category information and abnormality grade information of the target abnormality equipment. The invention effectively improves the efficiency and accuracy of the abnormality detection of the power equipment.

Description

Equipment abnormality detection method, device, equipment and storage medium

Technical Field

The present invention relates to the field of data processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for detecting an abnormality of a device.

Background

The traditional power equipment monitoring work adopts a manual inspection mode, namely, the abnormality detection is carried out manually on the equipment site through naked eyes, or the abnormality detection is carried out manually through a monitoring video in a video monitoring system, and the manual supervision is seriously relied on. The traditional power equipment monitoring mode is high in cost, low in efficiency, poor in instantaneity and capable of achieving timely positioning and early warning on abnormal behaviors of the power equipment, and workers can look over a large number of videos for a long time to easily cause relaxation and fatigue, so that the safety problem of the power equipment is easily caused.

Disclosure of Invention

The invention provides a method, a device, equipment and a storage medium for detecting equipment abnormality, which are used for improving the efficiency and the accuracy of detecting the power equipment abnormality.

According to a first aspect of the present invention, there is provided an apparatus abnormality detection method comprising:

acquiring an image of equipment to be detected and operation parameters of the equipment to be detected, which correspond to at least one piece of equipment to be detected;

for each device to be detected, determining a similarity value of the device image to be detected and a historical normal state image, so as to determine an image detection result based on the similarity value;

determining an operation parameter detection result based on the operation parameter of the equipment to be detected and a preset normal equipment threshold range;

Determining a target detection result based on the image detection result and/or the operation parameter detection result;

If the target detection result is an abnormal detection result, determining abnormal prompt information of target abnormal equipment, and carrying out equipment abnormality warning on the target abnormal equipment based on the abnormal prompt information;

the abnormality prompt information comprises position information, abnormality category information and abnormality grade information of target abnormality equipment.

According to a second aspect of the present invention, there is provided an apparatus abnormality detection device comprising:

the equipment data acquisition module is used for acquiring an image of equipment to be detected and operation parameters of the equipment to be detected, which correspond to at least one piece of equipment to be detected;

The image detection module is used for determining the similarity value of the image of the equipment to be detected and the historical normal state image for each piece of equipment to be detected so as to determine an image detection result based on the similarity value;

the parameter detection module is used for determining an operation parameter detection result based on the operation parameter of the equipment to be detected and a preset normal equipment threshold range;

the detection result determining module is used for determining a target detection result based on the image detection result and/or the operation parameter detection result;

the warning module is used for determining the abnormality prompt information of the target abnormal equipment if the target detection result is an abnormality detection result and carrying out equipment abnormality warning on the target abnormal equipment based on the abnormality prompt information; the abnormality prompt information comprises position information, abnormality category information and abnormality grade information of target abnormality equipment.

According to a third aspect of the present invention, there is provided an electronic device comprising:

At least one processor; and a memory communicatively coupled to the at least one processor; the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the device abnormality detection method according to any one of the embodiments of the present invention.

According to a fourth aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to execute a device abnormality detection method of any one of the embodiments of the present invention.

According to the technical scheme, through obtaining at least one to-be-detected equipment image and to-be-detected equipment operation parameters corresponding to-be-detected equipment, further, for each to-be-detected equipment, determining similarity values of the to-be-detected equipment image and the historical normal state image, determining an image detection result based on the similarity values, determining an operation parameter detection result based on the to-be-detected equipment operation parameters and a preset normal equipment threshold range, and further, determining a target detection result based on the image detection result and/or the operation parameter detection result, thereby determining abnormal prompt information of the target abnormal equipment if the target detection result is the abnormal detection result, and carrying out equipment abnormal warning on the target abnormal equipment based on the abnormal prompt information, wherein the abnormal prompt information comprises position information, abnormal category information and abnormal grade information of the target abnormal equipment. According to the invention, through the image recognition technology and the operation parameter monitoring technology, the power equipment is subjected to abnormality detection from multiple angles, the safety coefficient of the power equipment is greatly improved, the security risk of the power equipment is reduced, and through reasonably arranging the camera positions of the machine room, when the target abnormal equipment exists, the information of the abnormal equipment can be accurately positioned, the equipment loss is greatly reduced, and the efficiency and the accuracy of the abnormality detection of the power equipment are effectively improved.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flowchart of a device abnormality detection method according to a first embodiment of the present invention;

fig. 2 is a schematic structural diagram of an apparatus for detecting an abnormality of a device according to a second embodiment of the present invention;

Fig. 3 is a schematic structural diagram of an electronic device implementing a device abnormality detection method according to an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example 1

Fig. 1 is a flowchart of a device abnormality detection method according to an embodiment of the present invention, where the method may be applied to the case of intelligently detecting an abnormality of a power device, and the method may be performed by a device abnormality detection apparatus, which may be implemented in hardware and/or software, and the device abnormality detection apparatus may be configured in a terminal and/or a server. As shown in fig. 1, the method includes:

S110, acquiring an image of the equipment to be detected and operation parameters of the equipment to be detected, which correspond to at least one piece of equipment to be detected.

In this embodiment, a plurality of electric devices may be included in the preset area, so that in order to ensure that the electric devices can operate normally, it is necessary to perform inspection on the electric devices, discover problems in time, and solve the problems.

The equipment to be detected is power equipment for abnormality detection. Any power device within the preset area may be referred to as a power device to be detected.

The device image to be detected is an image corresponding to the power device which needs to be subjected to abnormality detection. The operation parameters of the equipment to be detected are various types of parameter information generated in the operation process of the power equipment needing to be subjected to abnormality detection.

Specifically, the inspection of the equipment to be detected can be performed based on the unmanned aerial vehicle in a preset area according to a predefined inspection path, so as to obtain the images of the equipment to be detected corresponding to the equipment to be detected; the device can also be provided with a plurality of preset shooting sites in advance in the range of the preset area, and the image of the device to be detected can be shot on the basis of the shooting device on each shooting site. In the specific application process, communication connection between each device to be detected and the server terminal can be established at the background server terminal, operation parameters of each device to be detected can be obtained in real time, and images of the devices to be detected and operation parameters of the devices to be detected, which correspond to each device to be detected in a preset area range, can be synchronously obtained at intervals of preset time based on preset timing tasks.

In particular, for the device image to be detected, after the original device image to be detected is obtained, data preprocessing is required to be performed on the original device image to be detected, so that the image to be detected which is more suitable for image analysis processing is obtained.

Optionally, preprocessing the original device image to be detected specifically includes the following steps:

(1) And carrying out enhancement processing on the to-be-detected equipment image to obtain a first to-be-detected equipment image.

Preferably, the method specifically includes: performing histogram equalization processing on the equipment image to be detected based on a histogram equalization network to obtain an equalized equipment image; and carrying out image enhancement processing on the to-be-detected equipment image based on the to-be-detected equipment image, the equalization equipment image and the low-illumination image enhancement network to obtain a first to-be-detected equipment image.

In the present embodiment, the visual effect of an image can be improved by the image enhancement processing. Histogram equalization networks are methods in the field of image processing that use image histograms to adjust contrast. In this way, the brightness can be better distributed over the histogram. This can be used to enhance local contrast without affecting overall contrast, and histogram equalization accomplishes this by effectively expanding the usual brightness. The illumination factor is always a key factor influencing the imaging quality, and pictures under the condition of poor illumination environment such as night tend to have lost details, unclear resolution and low signal-to-noise ratio. Low-light image enhancement networks refer to enhancing the visual quality of images taken under low-light or low-light conditions through a range of networks and techniques. For example, a Residual-Unet low-light image enhancement network is employed in this embodiment.

Specifically, inputting the acquired equipment image to be detected into a histogram equalization network, and outputting an equalized equipment image by the histogram equalization network; pre-constructing a low-illumination image enhancement network based on Residual-Unet, and completing network training; further, the device image to be detected and the equalization device image are input to a low-illumination image enhancement network based on the Residual-Unet together, and the first device image to be detected is output by the low-illumination image enhancement network based on the Residual-Unet.

(2) Denoising the first equipment image to be detected based on a preset wavelet transformation network to obtain a second equipment image to be detected.

The wavelet transformation (wavelet transform, WT) can perform local analysis on time (space) frequency, gradually performs multi-scale refinement on the signal (function) through telescopic translation operation, finally achieves time subdivision at high frequency and frequency subdivision at low frequency, can automatically meet the requirement of time-frequency signal analysis, and can focus on any details of the signal, so that noise signals in images can be effectively removed, and the denoising effect is achieved.

Specifically, the first to-be-detected equipment image is input to a preset wavelet transformation network, and the preset wavelet transformation network outputs a denoised second to-be-detected equipment image.

(3) And carrying out smoothing treatment on the second equipment image to be detected based on a preset bilateral filter network to obtain an enhanced image of the equipment to be detected.

The bilateral filtering is a nonlinear filter, and can achieve the effects of maintaining edges and reducing noise smoothly. Like other filtering principles, bilateral filtering also uses a weighted average method, where the intensity of a pixel is represented by a weighted average of the luminance values of surrounding pixels, and the weighted average is based on a gaussian distribution. Most importantly, the weights of bilateral filtering take into account not only the euclidean distance of the pixels (such as normal gaussian low pass filtering, which only takes into account the effect of position on the center pixel), but also the radiation differences in the pixel range (such as the degree of similarity between pixels in the convolution kernel and the center pixel, the color intensity, the depth distance, etc.), both weights being taken into account simultaneously when computing the center pixel.

Specifically, the second to-be-detected equipment image is input into a preset bilateral filter network, and the preset bilateral filter network outputs the to-be-detected equipment enhanced image after smoothing.

It should be noted that, the images of the device to be detected involved in the subsequent steps are all pre-processed enhanced images of the device to be detected.

S120, for each device to be detected, determining a similarity value of the device image to be detected and the historical normal state image, and determining an image detection result based on the similarity value.

The similarity value is used for representing the similarity degree of the to-be-detected equipment image and the historical normal state image. The image detection results include an image normal detection result and an image abnormal detection result. For each device to be detected, a historical normal state image of the device to be detected can be acquired under the condition that the normal operation of the device to be detected is ensured.

Specifically, for each device to be detected, calculating a similarity value between the image of the device to be detected and the historical normal state image. For example, a similarity threshold is preset, a similarity value is calculated by adopting a cosine similarity calculation method, further, if the similarity value is larger than the similarity threshold, the image detection result is a normal detection result, and if the similarity value is smaller than the similarity threshold, the image detection result is an abnormal detection result, so that the abnormal appearance of the power equipment can be timely detected.

S130, determining an operation parameter detection result based on the operation parameter of the equipment to be detected and a preset normal equipment threshold range.

In this embodiment, for each device to be detected, a normal device threshold range in the case where the device to be detected is operating normally may be preset. The operation parameter detection results comprise an operation parameter normal detection result and an operation parameter abnormal detection result.

Specifically, for each device to be detected, determining whether the operating parameters of the device to be detected are within a normal device threshold range or not on the basis of acquiring the operating parameters of the device to be detected; if yes, the operation parameter detection result is the operation parameter normal detection result; if not, the operation parameter detection result is an operation parameter abnormality detection result, so that the operation parameter abnormality detection result can be timely detected when the internal parameters of the power equipment are abnormal.

And S140, determining a target detection result based on the image detection result and/or the operation parameter detection result.

Wherein the target detection result includes an abnormal detection result and a normal detection result.

In this embodiment, the target detection result is an abnormal detection result, which mainly includes the following three cases: the first image detection result is an image abnormality detection result; secondly, the operation parameter detection result is a parameter abnormality detection result; thirdly, the image detection result is an image abnormality detection result, and the operation parameter detection result is a parameter abnormality detection result.

Particularly, if the operation parameter detection result is a parameter abnormality detection result, determining a data abnormality starting time; and acquiring a device anomaly record video in which the data anomaly starting time is the time starting point preset time length so as to be ready for anomaly rechecking.

In this embodiment, if the operation parameter detection result is a parameter anomaly detection result, determining a timestamp that the operation parameter is not in the normal device threshold range as a data anomaly start time, taking the data anomaly start time as a start point, and capturing a device anomaly record video with a preset duration, so that when a device anomaly is performed subsequently, it can be determined whether a device anomaly operation situation exists in real by combining the device anomaly record video.

And S150, if the target detection result is an abnormal detection result, determining abnormal prompt information of target abnormal equipment, and carrying out equipment abnormality warning on the target abnormal equipment based on the abnormal prompt information.

The abnormality prompt information comprises position information, abnormality category information and abnormality grade information of target abnormality equipment.

Optionally, determining the abnormality prompt information of the target abnormality device specifically includes the following steps:

(1) If the target detection result is an abnormal detection result, a preset device position information corresponding table and device identification information of the target abnormal device are called.

The target abnormal equipment is equipment to be detected, wherein the equipment is an image detection result and/or the operation parameter detection result is an abnormal detection result.

In this embodiment, a device location information correspondence table of correspondence between location information of a device to be detected and device identification information may be preset. And setting unique equipment identification information for each equipment to be detected in the preset area range.

Specifically, if the target detection result is an abnormal detection result, the pre-stored device location information correspondence table may be directly called. On the basis of determining the target detection result, the target abnormal device is easy to determine, and it is understood that the device identification information of the target abnormal device can be directly read.

(2) And inquiring a preset device position information corresponding table based on the device identification information, and determining the position information of the target abnormal device.

In this embodiment, first, device identification information corresponding to a target abnormal device is obtained, and then, according to the device identification information, in a preset device location information correspondence table, location information corresponding to the target abnormal device is queried according to a pre-established index relationship.

(3) If the operation parameter detection result is a parameter abnormality detection result, determining abnormality category information based on a parameter type corresponding to the operation parameter of the equipment to be detected, and determining abnormality grade information based on the operation parameter of the equipment to be detected and a preset parameter threshold.

In this embodiment, since each device to be detected can collect a plurality of kinds of operation parameters,

For example, if the device to be detected is a transformer, the parameter types may include parameter types such as current, voltage, power factor, etc., so that according to the parameter type corresponding to the operation parameter, abnormal category information may be determined. Further, the different abnormal grades correspond to different preset parameter thresholds, and abnormal grade information is determined based on the preset parameter thresholds met by the operation parameters of the equipment to be detected.

(4) If the image detection result is an image abnormality detection result, inputting the image of the equipment to be detected into an abnormality classification model trained in advance, determining abnormality class information, and determining abnormality class information based on the corresponding relation between the abnormality class and the abnormality class information.

In the present embodiment, an abnormality classification model for identifying abnormality category information may be trained in advance. If the image detection result is an image abnormality detection result, the image of the equipment to be detected can be input into an abnormality classification model trained in advance, and abnormality class information is determined according to the class output by the abnormality classification model. Further, according to the corresponding relation between the predefined abnormal class and the abnormal class information output by the abnormal classification model, determining the abnormal class information corresponding to the target abnormal equipment.

Specifically, after determining that the target detection result is an abnormal detection result, abnormal prompt information may be generated, and the abnormal prompt information may be sent to the target terminal of the operation user. The sending of the abnormality notification to the corresponding target terminal may further include at least one of: reporting the abnormal prompt information to target terminal equipment; the reporting comprises at least one of mail, voice communication and information pushing; and feeding back the abnormal prompt information to the target monitoring system.

In this embodiment, the to-be-detected device image, the to-be-detected device operation parameter, the abnormality prompt information, and the device abnormality record video may be stored in a SQLite database or at least one data storage table of a local hard disk in a classified manner.

In this embodiment, if there is a target abnormal device, the device image to be detected, the device operation parameter to be detected, the abnormality prompt information and the device abnormality record video of each target abnormal device may be stored in at least one data storage table of the SQLite database or the local hard disk in a classified manner, and when the target abnormal device needs to be checked again, the data may be directly obtained from the data table.

According to the technical scheme, through obtaining at least one to-be-detected equipment image and to-be-detected equipment operation parameters corresponding to-be-detected equipment, further, for each to-be-detected equipment, determining similarity values of the to-be-detected equipment image and the historical normal state image, determining an image detection result based on the similarity values, determining an operation parameter detection result based on the to-be-detected equipment operation parameters and a preset normal equipment threshold range, and further, determining a target detection result based on the image detection result and/or the operation parameter detection result, thereby determining abnormal prompt information of the target abnormal equipment if the target detection result is the abnormal detection result, and carrying out equipment abnormal warning on the target abnormal equipment based on the abnormal prompt information, wherein the abnormal prompt information comprises position information, abnormal category information and abnormal grade information of the target abnormal equipment. According to the invention, through the image recognition technology and the operation parameter monitoring technology, the power equipment is subjected to abnormality detection from multiple angles, the safety coefficient of the power equipment is greatly improved, the security risk of the power equipment is reduced, and through reasonably arranging the camera positions of the machine room, when the target abnormal equipment exists, the information of the abnormal equipment can be accurately positioned, the equipment loss is greatly reduced, and the efficiency and the accuracy of the abnormality detection of the power equipment are effectively improved.

Example two

Fig. 2 is a schematic structural diagram of an apparatus for detecting an abnormality of a device according to a second embodiment of the present invention. As shown in fig. 2, the apparatus includes: the device data acquisition module 210, the image detection module 220, the parameter detection module 230, the detection result determination module 240, and the warning module 250.

The device data obtaining module 210 is configured to obtain a device image to be detected and a device operation parameter to be detected corresponding to at least one device to be detected;

An image detection module 220, configured to determine, for each device to be detected, a similarity value between an image of the device to be detected and a historical normal state image, so as to determine an image detection result based on the similarity value;

A parameter detection module 230, configured to determine an operation parameter detection result based on the operation parameter of the device to be detected and a preset normal device threshold range;

A detection result determining module 240, configured to determine a target detection result based on the image detection result and/or the operation parameter detection result;

The warning module 250 is configured to determine an abnormality prompt message of a target abnormal device if the target detection result is an abnormality detection result, and perform device abnormality warning on the target abnormal device based on the abnormality prompt message; the abnormality prompt information comprises position information, abnormality category information and abnormality grade information of target abnormality equipment.

According to the technical scheme, through obtaining at least one to-be-detected equipment image and to-be-detected equipment operation parameters corresponding to-be-detected equipment, further, for each to-be-detected equipment, determining similarity values of the to-be-detected equipment image and the historical normal state image, determining an image detection result based on the similarity values, determining an operation parameter detection result based on the to-be-detected equipment operation parameters and a preset normal equipment threshold range, and further, determining a target detection result based on the image detection result and/or the operation parameter detection result, thereby determining abnormal prompt information of the target abnormal equipment if the target detection result is the abnormal detection result, and carrying out equipment abnormal warning on the target abnormal equipment based on the abnormal prompt information, wherein the abnormal prompt information comprises position information, abnormal category information and abnormal grade information of the target abnormal equipment. According to the invention, through the image recognition technology and the operation parameter monitoring technology, the power equipment is subjected to abnormality detection from multiple angles, the safety coefficient of the power equipment is greatly improved, the security risk of the power equipment is reduced, and through reasonably arranging the camera positions of the machine room, when the target abnormal equipment exists, the information of the abnormal equipment can be accurately positioned, the equipment loss is greatly reduced, and the efficiency and the accuracy of the abnormality detection of the power equipment are effectively improved.

Optionally, the device anomaly detection apparatus further includes a data preprocessing module, where the data preprocessing module includes:

The enhancement processing unit is used for carrying out enhancement processing on the to-be-detected equipment image to obtain a first to-be-detected equipment image;

The denoising processing unit is used for denoising the first equipment image to be detected based on a preset wavelet transformation network to obtain a second equipment image to be detected;

And the smoothing processing unit is used for carrying out smoothing processing on the second equipment image to be detected based on a preset bilateral filtering network to obtain an enhanced image of the equipment to be detected.

Optionally, the enhancement processing unit includes:

The equalization processing subunit is used for carrying out histogram equalization processing on the to-be-detected equipment image based on a histogram equalization network to obtain an equalized equipment image;

And the enhancement processing subunit is used for carrying out image enhancement processing on the to-be-detected equipment image based on the to-be-detected equipment image, the equalization equipment image and the low-illumination image enhancement network to obtain a first to-be-detected equipment image.

Optionally, the detection result determining module 240 is specifically configured to determine that the target detection result is an abnormal detection result if the image detection result is an image abnormal detection result or/and the operation parameter detection result is a parameter abnormal detection result.

Optionally, the detection result determining module 240 further includes:

The abnormal data grabbing unit is specifically used for determining the data abnormal starting moment if the operation parameter detection result is a parameter abnormal detection result; and acquiring a device anomaly record video in which the data anomaly starting time is the time starting point preset time length so as to be ready for anomaly rechecking.

The abnormal data storage unit is specifically configured to store the to-be-detected device image, the to-be-detected device operation parameter, the abnormal prompt information and the device abnormal record video in at least one data storage table of the SQLite database storage or the local hard disk in a classified manner.

Optionally, the warning module 250 further includes an abnormal prompt information obtaining sub-module, where the abnormal prompt information obtaining sub-module includes:

The device identification information reading unit is used for calling a preset device position information corresponding table and device identification information of the target abnormal device if the target detection result is an abnormal detection result;

a location information determining unit, configured to query the preset device location information correspondence table based on the device identification information, and determine location information of the target abnormal device;

The parameter abnormality prompting information determining unit is used for determining abnormality category information based on a parameter type corresponding to the operation parameter of the equipment to be detected and determining abnormality grade information based on the operation parameter of the equipment to be detected and a preset parameter threshold value if the operation parameter detection result is a parameter abnormality detection result;

And the image anomaly prompt information determining unit is used for inputting the image of the equipment to be detected into a pre-trained anomaly classification model if the image detection result is an image anomaly detection result, determining anomaly class information and determining anomaly class information based on the corresponding relation between anomaly class and the anomaly class information.

Example III

Fig. 3 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 3, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the respective methods and processes described above, such as the device abnormality detection method.

In some embodiments, the device anomaly detection method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the above-described device abnormality detection method may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the device anomaly detection method by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable apparatus anomaly detection device, such that the computer programs, when executed by the processor, cause the functions/operations specified in the flowchart and/or block diagram to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

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

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims (10)

1. A device abnormality detection method, characterized by comprising:

acquiring an image of equipment to be detected and operation parameters of the equipment to be detected, which correspond to at least one piece of equipment to be detected;

for each device to be detected, determining a similarity value of the device image to be detected and a historical normal state image, so as to determine an image detection result based on the similarity value;

determining an operation parameter detection result based on the operation parameter of the equipment to be detected and a preset normal equipment threshold range;

Determining a target detection result based on the image detection result and/or the operation parameter detection result;

If the target detection result is an abnormal detection result, determining abnormal prompt information of target abnormal equipment, and carrying out equipment abnormality warning on the target abnormal equipment based on the abnormal prompt information;

the abnormality prompt information comprises position information, abnormality category information and abnormality grade information of target abnormality equipment.

2. The method as recited in claim 1, further comprising:

Performing enhancement processing on the to-be-detected equipment image to obtain a first to-be-detected equipment image;

denoising the first equipment image to be detected based on a preset wavelet transformation network to obtain a second equipment image to be detected;

and carrying out smoothing treatment on the second equipment image to be detected based on a preset bilateral filter network to obtain an enhanced image of the equipment to be detected.

3. The method of claim 2, wherein the enhancing the device image to be detected to obtain a first device image to be detected includes:

performing histogram equalization processing on the to-be-detected equipment image based on a histogram equalization network to obtain an equalized equipment image;

and carrying out image enhancement processing on the to-be-detected equipment image based on the to-be-detected equipment image, the equalization equipment image and a low-illumination image enhancement network to obtain a first to-be-detected equipment image.

4. The method according to claim 1, wherein the determining a target detection result based on the image detection result and/or the operation parameter detection result comprises:

And if the image detection result is an image abnormality detection result or/and the operation parameter detection result is a parameter abnormality detection result, determining that the target detection result is an abnormality detection result.

5. The method as recited in claim 4, further comprising:

If the operation parameter detection result is a parameter abnormality detection result, determining a data abnormality starting moment;

And acquiring a device anomaly record video in which the data anomaly starting time is the time starting point preset time length so as to be ready for anomaly rechecking.

6. The method as recited in claim 5, further comprising:

and storing the to-be-detected equipment image, the to-be-detected equipment operation parameter, the abnormality prompt information and the equipment abnormality record video in at least one data storage table of an SQLite database or a local hard disk in a classified manner.

7. The method according to claim 4, wherein determining the abnormality notification of the target abnormality device if the target detection result is an abnormality detection result comprises:

if the target detection result is an abnormal detection result, a preset device position information corresponding table and device identification information of target abnormal devices are called;

Inquiring the preset equipment position information corresponding table based on the equipment identification information, and determining the position information of the target abnormal equipment;

If the operation parameter detection result is a parameter abnormality detection result, determining abnormality category information based on a parameter type corresponding to the operation parameter of the equipment to be detected, and determining abnormality level information based on the operation parameter of the equipment to be detected and a preset parameter threshold;

If the image detection result is an image abnormality detection result, inputting the to-be-detected equipment image into a pre-trained abnormality classification model, determining abnormality class information, and determining abnormality class information based on the corresponding relation between the abnormality class and the abnormality class information.

8. An apparatus abnormality detection device, comprising:

the equipment data acquisition module is used for acquiring an image of equipment to be detected and operation parameters of the equipment to be detected, which correspond to at least one piece of equipment to be detected;

The image detection module is used for determining the similarity value of the image of the equipment to be detected and the historical normal state image for each piece of equipment to be detected so as to determine an image detection result based on the similarity value;

the parameter detection module is used for determining an operation parameter detection result based on the operation parameter of the equipment to be detected and a preset normal equipment threshold range;

the detection result determining module is used for determining a target detection result based on the image detection result and/or the operation parameter detection result;

the warning module is used for determining the abnormality prompt information of the target abnormal equipment if the target detection result is an abnormality detection result and carrying out equipment abnormality warning on the target abnormal equipment based on the abnormality prompt information; the abnormality prompt information comprises position information, abnormality category information and abnormality grade information of target abnormality equipment.

9. An electronic device, the electronic device comprising:

One or more processors;

Storage means for storing one or more programs,

When the one or more programs are executed by the one or more processors, the one or more processors implement the device anomaly detection method according to any one of the embodiments of the present invention.

10. A storage medium containing computer executable instructions which, when executed by a computer processor, are for performing a device anomaly detection method according to any one of the embodiments of the present invention.