CN115700375A

CN115700375A - Insulator contamination detection method, device, equipment and medium

Info

Publication number: CN115700375A
Application number: CN202211552996.8A
Authority: CN
Inventors: 魏东亮; 陈世昌; 王植; 周佳
Original assignee: Dongguan Power Supply Bureau of Guangdong Power Grid Co Ltd
Current assignee: Dongguan Power Supply Bureau of Guangdong Power Grid Co Ltd
Priority date: 2022-12-06
Filing date: 2022-12-06
Publication date: 2023-02-07

Abstract

The embodiment of the invention discloses a method, a device, equipment and a medium for detecting insulator contamination. The method comprises the following steps: acquiring an infrared image of an insulator to be detected and environment data corresponding to an acquisition environment when the infrared image is acquired; respectively extracting infrared characteristic data of the infrared image and environment characteristic data of the environment data; performing feature fusion on the infrared feature data and the environment feature data to obtain target fusion feature data; and determining the target pollution grade of the insulator to be detected according to the target fusion characteristic data. According to the scheme, the precision of insulator contamination detection is improved.

Description

Insulator contamination detection method, device, equipment and medium

Technical Field

The embodiment of the invention relates to the technical field of insulator pollution detection of power equipment, in particular to a method, a device, equipment and a medium for detecting insulator pollution.

Background

The power transmission line is an important life line in a power system, and the insulator has the functions of electrical insulation, mechanical fixation and the like in the power transmission line and is an indispensable element in the power transmission line, so that the pollution detection on the insulator is very important.

In the prior art, an infrared imaging technology is usually adopted to perform pollution detection on an insulator, so that the detection precision is low.

Disclosure of Invention

The invention provides a method, a device, equipment and a medium for detecting insulator contamination, which are used for improving the precision of insulator contamination detection.

According to one aspect of the invention, an insulator contamination detection method is provided, which comprises the following steps:

acquiring an infrared image of an insulator to be detected and environment data corresponding to an acquisition environment when the infrared image is acquired;

respectively extracting infrared characteristic data of the infrared image and environment characteristic data of the environment data;

performing feature fusion on the infrared feature data and the environment feature data to obtain target fusion feature data;

and determining the target pollution grade of the insulator to be detected according to the target fusion characteristic data.

According to another aspect of the present invention, there is provided an insulator contamination detection apparatus, including:

the data acquisition module is used for acquiring an infrared image of the insulator to be detected and environment data corresponding to an acquisition environment when the infrared image is acquired;

the data extraction module is used for respectively extracting infrared characteristic data of the infrared image and environment characteristic data of the environment data;

the characteristic fusion module is used for carrying out characteristic fusion on the infrared characteristic data and the environment characteristic data to obtain target fusion characteristic data;

and the pollution grade determining module is used for determining the target pollution grade of the insulator to be detected according to the target fusion characteristic data.

According to another aspect of the present invention, there is provided an electronic apparatus including:

one or more processors;

a memory 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 can execute any one of the insulator contamination detection methods provided by the embodiments of the present invention.

According to another aspect of the present invention, a computer-readable storage medium is provided, where the computer-readable storage medium stores computer instructions, and the computer instructions are configured to, when executed by a processor, implement any one of the insulator contamination detection methods provided by the embodiments of the present invention.

The embodiment of the invention provides an insulator contamination detection scheme, which comprises the steps of acquiring an infrared image of an insulator to be detected and environment data corresponding to an acquired environment when the infrared image is acquired; respectively extracting infrared characteristic data of the infrared image and environment characteristic data of the environment data; performing feature fusion on the infrared feature data and the environment feature data to obtain target fusion feature data; and determining the target pollution grade of the insulator to be detected according to the target fusion characteristic data. According to the scheme, the environmental data are used as a part for determining the target pollution level of the insulator to be detected, so that the pollution detection of the insulator is realized on the basis of considering environmental factors, the condition that the detection precision is low due to the fact that infrared imaging pollution detection is interfered by the environmental factors is avoided, the accuracy of the determined target pollution level is improved, and the precision of the pollution detection of the insulator is improved.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.

Drawings

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

Fig. 1A is a flowchart of an insulator contamination detection method according to an embodiment of the present invention;

fig. 1B is a schematic diagram of an infrared feature extraction network according to an embodiment of the present invention;

fig. 1C is a schematic diagram of an environmental feature extraction network according to an embodiment of the present invention;

fig. 1D is a schematic diagram of a feature fusion network according to an embodiment of the present invention;

fig. 2 is a flowchart of an insulator contamination detection method according to a second embodiment of the present invention;

fig. 3 is a schematic structural diagram of an insulator contamination detection apparatus according to a third embodiment of the present invention;

fig. 4 is a schematic structural diagram of an electronic device for implementing an insulator contamination detection method according to a fourth embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some structures related to the present invention are shown in the drawings, not all of them.

Example one

Fig. 1A is a flowchart of an insulator contamination detection method according to an embodiment of the present invention, where the present embodiment is applicable to a situation of performing contamination detection on an insulator, and the method may be executed by an insulator contamination detection apparatus, and the apparatus may be implemented in a software and/or hardware manner, and may be configured in an electronic device bearing an insulator contamination detection function.

Referring to fig. 1A, the method for detecting insulator contamination includes:

s110, acquiring an infrared image of the insulator to be detected and environment data corresponding to an acquisition environment when the infrared image is acquired.

The insulator to be detected is an insulator which needs to be subjected to pollution detection. The infrared image is an infrared image containing the insulator to be detected. The environment data refers to data of the environment where the insulator to be detected is located. The embodiment of the invention does not limit the mode of acquiring the infrared image and the environmental data at all, and can be selected by technical personnel according to experience. Illustratively, the infrared image and the environmental data may be collected by an infrared camera.

Specifically, an infrared image of the insulator to be detected is obtained, and meanwhile, environmental data of the insulator to be detected is obtained.

And S120, respectively extracting the infrared characteristic data of the infrared image and the environment characteristic data of the environment data.

The infrared characteristic data refers to data containing infrared image characteristics. The environmental characteristic data refers to data containing an environmental characteristic.

In an alternative embodiment, the environmental data is at least two; correspondingly, the method for extracting the environmental characteristic data from the environmental data comprises the following steps: fusing different environment data to obtain fused environment data; and extracting environment characteristic data from the fusion environment data.

The number of the environmental data is not particularly limited in the embodiments of the present invention, and for example, the environmental data may include temperature data and humidity data. The fusion environment data refers to data obtained by fusing at least two kinds of data in the environment data.

It should be noted that, before the environmental data fusion is performed, normalization processing needs to be performed on different environmental data to unify dimensions of the different environmental data, thereby avoiding influences caused by different dimensions of the different environmental data. The embodiment of the present invention does not limit the way of implementing the normalization process at all, and may be set by a technician according to experience. Illustratively, a normalization algorithm may be employed.

Specifically, different environment data are fused to obtain fused environment data, including: taking smaller data in each environment data as target environment data; determining environmental difference data between different environmental data; and taking the ratio of the target environment data to the environment difference data as fusion environment data.

Wherein, the target environment data refers to smaller data in the environment data. The environment difference data refers to difference data between non-target environment data and target environment data in the environment data.

For example, the environmental data includes temperature data and humidity data; comparing the temperature data with the humidity data, and if the temperature data is greater than the humidity data, taking the humidity data as target environment data; taking the difference value of the temperature data and the humidity data as environment difference data; determining fusion environment data by the following formula:

；

wherein the content of the first and second substances,

fusing the environmental data;

target environment data;

is the environmental difference data;

the environment data is the environment data except the target environment data.

It can be understood that, by introducing the target environment data and the environment difference data to determine the fusion environment data, the accuracy of determining the fusion environment data is improved.

It can be understood that, by introducing the fusion environment data and extracting the environment feature data from the fusion environment data, the extraction efficiency of the environment feature data is improved.

Specifically, infrared characteristic data is extracted from the infrared image, and environmental characteristic data is extracted from the environmental data.

And S130, performing characteristic fusion on the infrared characteristic data and the environment characteristic data to obtain target fusion characteristic data.

The target fusion characteristic data refers to data including infrared image characteristics and environment data characteristics.

Specifically, feature fusion is performed on the infrared feature data and the environment feature data to obtain target fusion feature data.

And S140, determining the target pollution grade of the insulator to be detected according to the target fusion characteristic data.

Wherein, the target pollution grade can quantify the pollution degree of the insulator to be detected. Illustratively, the target pollution level may be one level, two levels, three levels, four levels, and five levels, wherein the pollution level of the insulator to be detected is severe as the level increases.

Specifically, according to the target fusion characteristic data, the target pollution grade of the insulator to be detected is determined, and then the pollution degree of the insulator to be detected is determined.

On the basis of the above embodiments, the acquisition of the infrared characteristic data, the environmental characteristic data and the target fusion characteristic data in the embodiments of the present invention is not limited at all, and may be set by a technician according to experience.

In an optional embodiment, the infrared image can be subjected to feature extraction through an infrared feature extraction network to obtain infrared feature data; extracting the characteristics of the environmental data through an environmental characteristic extraction network to obtain environmental characteristic data; and performing characteristic fusion on the infrared characteristic data and the environment characteristic data through a characteristic fusion network to obtain target fusion characteristic data.

The structure of the infrared feature extraction network in the embodiment of the present invention is not specifically limited, and may be set by a technician according to experience. Illustratively, referring to the schematic diagram of the infrared feature extraction network shown in fig. 1B, the infrared feature extraction network may include a convolution (conv) layer, a max-pooling (maxpoling) layer, a connectivity (FC) layer, and an activation (Relu) layer. Wherein the convolutional layer comprises conv (64 × 3 × 3) × 2, conv (128 × 3 × 3) × 2, conv (256 × 3 × 3) × 3, 2 conv (512 × 3 × 3) × 3. The maximum pooling layer comprises 5 Maxpooling (2X 2). The communication layer includes FC (1 × 4096) and FC (1 × 5). Specifically, in the process of extracting the infrared characteristic data, when the infrared image passes through the maximum pooling layer each time, the width and the height of the infrared image are both reduced to half of those of the infrared image at the initial moment; each time the coiled layer is passed, the size of the channel is doubled; when the infrared image passes through the final maximum pooling layer, infrared characteristic data with the size of 7 multiplied by 512 can be obtained; inputting the infrared characteristic data with the size of 7 multiplied by 512 into two connection layers activated by the activation layer, further performing characteristic extraction, and finally outputting the infrared characteristic data with the size of 1 multiplied by 5.

Where conv (64 × 3 × 3) × 2 represents the same 2 convolutional layers, each having 64 filters of size 3 × 3. conv (128 × 3 × 3) × 2 represents the same 2 convolutional layers, each having 128 filters of size 3 × 3. conv (256 × 3 × 3) × 3 represents the same 3 convolutional layers, each having 256 filters of size 3 × 3. conv (512 × 3 × 3) × 3 represents the same 3 convolutional layers, each having 512 filters of size 3 × 3. Maxpooling (2X 2) represents the largest pooling layer of size 2X 2. FC (1 × 4096) represents a communication layer having a size of 1 × 4096. FC (1 × 5) represents a communication layer having a size of 1 × 5.

Before the infrared feature data is extracted, normalization processing needs to be performed on each infrared image to unify the size of each infrared image. For example, the normalized infrared image may have a size of 224 × 224 × 3. The advantage of setting 2 conv (512 × 3 × 3) × 3 is that the accuracy of the extracted infrared feature data can be further improved.

The structure of the environmental feature extraction network in the embodiment of the present invention is not specifically limited, and may be set by a technician according to experience. Illustratively, referring to the schematic diagram of the ambient feature extraction network shown in fig. 1C, the ambient feature extraction network may include a connectivity (FC) layer and an activation (Relu) layer. Wherein the connectivity (FC) layer includes 2 FCs (1 × 10) and FCs (1 × 5). FC (1 × 10) represents a communication layer having a size of 1 × 10. FC (1 × 5) represents a communication layer having a size of 1 × 5.

It should be noted that, the advantage of setting 2 FCs (1 × 10) is that the accuracy of the extracted environmental feature data can be further improved.

It should be noted that, by unifying the sizes of the infrared characteristic data and the environmental characteristic data to 1 × 5, subsequent characteristic fusion is facilitated.

The structure of the feature fusion network is not specifically limited in the embodiment of the present invention, and may be set by a technician according to experience. Illustratively, referring to the schematic diagram of the feature fusion network shown in fig. 1D, the feature fusion network may include a connectivity (FC) layer and an activation (Relu) layer. Wherein the connectivity (FC) layer includes 2 FCs (1 × 10) and FCs (1 × 5). FC (1 × 10) represents a communication layer having a size of 1 × 10. FC (1 × 5) represents a communication layer having a size of 1 × 5. In order to avoid overfitting of the feature fusion network, the dropout (random deactivation) ratio of the connected layer and the cascade layer may be set to 0.5, respectively.

It can be understood that by introducing the infrared feature extraction network, the environmental feature extraction network and the feature fusion network, the accuracy of the acquired infrared feature data, the acquired environmental feature data and the acquired target fusion feature data can be improved, and the data acquisition efficiency is high.

Example two

Fig. 2 is a flowchart of an insulator contamination detection method according to the second embodiment of the present invention, and in this embodiment, based on the foregoing embodiments, further, the operation of "determining a target contamination level of an insulator to be detected according to target fusion feature data" is refined into "determining candidate contamination level probabilities of the target fusion feature data at different candidate contamination levels"; and selecting a target pollution grade of the insulator to be detected from the candidate pollution grades according to the probability of each candidate pollution grade so as to perfect a determination mechanism of the target pollution grade. In the embodiments of the present invention, reference may be made to other embodiments not specifically described.

Referring to fig. 2, the method for detecting contamination of an insulator includes:

s210, acquiring an infrared image of the insulator to be detected and environment data corresponding to an acquisition environment when the infrared image is acquired.

And S220, respectively extracting the infrared characteristic data of the infrared image and the environmental characteristic data of the environmental data.

And S230, performing characteristic fusion on the infrared characteristic data and the environment characteristic data to obtain target fusion characteristic data.

And S240, determining the candidate pollution grade probability of the target fusion characteristic data under different candidate pollution grades.

The candidate pollution level may be an interval into which the pollution degree of the insulator is divided in advance. The classification of the candidate pollution grades in the embodiment of the invention is not limited at all, and can be set by technical personnel according to experience. For example, the candidate pollution levels may include one, two, three, four, and five levels.

The candidate pollution level probability can be the probability that the insulator to be detected is in any candidate pollution level for any insulator to be detected.

For example, when the candidate pollution level is divided into 5 levels, the probability of the candidate pollution level may be determined by the following formula:

；

wherein x is target fusion characteristic data;

is the candidate pollution grade probability; y is a specific candidate pollution level; m is the category of the candidate pollution level (e.g. 5); j is the jth class candidate pollution level;

and the j-th candidate pollution level probability is obtained.

Specifically, the candidate pollution level probability of the target fusion characteristic data under each candidate pollution level is determined.

And S250, selecting a target pollution grade of the insulator to be detected from the candidate pollution grades according to the probability of each candidate pollution grade.

In an optional embodiment, selecting a target pollution grade of the insulator to be detected from the candidate pollution grades according to the candidate pollution grade probabilities includes: determining the target pollution level probability of the target fusion characteristic data according to the candidate pollution level probabilities; and selecting a target pollution grade from the candidate pollution grades according to the target pollution grade probability.

Wherein the target pollution level probability may be a larger value among the candidate pollution level probabilities. Preferably, the target pollution level probability may be a maximum value among the candidate pollution level probabilities.

Specifically, a larger candidate pollution level probability is determined from the candidate pollution level probabilities and is used as a target pollution level probability of the target fusion characteristic data; and selecting a candidate pollution grade which has a probability closer to the target pollution grade as the target pollution grade.

In the embodiment of the invention, the candidate pollution level corresponding to the target pollution level probability is determined according to the target pollution level probability, and the candidate pollution level is determined as the target pollution level of the insulator to be detected.

The target pollution grade is determined by introducing the target pollution grade probability, so that the accuracy of determining the target pollution grade is improved, the situation that the target pollution grade cannot be determined accurately when the candidate pollution grade probability is high is avoided, and a judgment basis is provided for determining the target pollution grade.

According to the insulator pollution detection scheme provided by the embodiment of the invention, the candidate pollution grade probability of the target fusion characteristic data under different candidate pollution grades is determined; according to the probability of each candidate pollution grade, the target pollution grade of the insulator to be detected is selected from the candidate pollution grades, and the determination mechanism of the target pollution grade is perfected. According to the scheme, the target pollution grade is determined by introducing the candidate pollution grade probability, and data support is provided for determining the target pollution grade; moreover, by introducing the candidate pollution grade probability, the target pollution grade is determined on the basis of considering that the insulator to be detected possibly belongs to each candidate pollution grade, so that the accuracy of the target pollution grade is further improved, and the determination process of the target pollution grade is more comprehensive.

EXAMPLE III

Fig. 3 is a schematic structural diagram of an insulator contamination detection apparatus according to a third embodiment of the present invention, where this embodiment is applicable to a situation of performing contamination detection on an insulator, and the method may be performed by the insulator contamination detection apparatus, and the apparatus may be implemented in a software and/or hardware manner, and may be configured in an electronic device bearing an insulator contamination detection function.

As shown in fig. 3, the apparatus includes: a data acquisition module 310, a data extraction module 320, a feature fusion module 330, and a pollution level determination module 340. Wherein, the first and the second end of the pipe are connected with each other,

the data acquisition module 310 is configured to acquire an infrared image of the insulator to be detected and environment data corresponding to an acquisition environment when the infrared image is acquired;

the data extraction module 320 is configured to extract infrared feature data of the infrared image and environment feature data of the environment data respectively;

the feature fusion module 330 is configured to perform feature fusion on the infrared feature data and the environmental feature data to obtain target fusion feature data;

and the contamination grade determining module 340 is configured to determine a target contamination grade of the insulator to be detected according to the target fusion characteristic data.

The embodiment of the invention provides an insulator contamination detection scheme, which comprises the steps of acquiring an infrared image of an insulator to be detected and environment data of a corresponding acquisition environment when the infrared image is acquired through a data acquisition module; respectively extracting infrared characteristic data of the infrared image and environmental characteristic data of the environmental data through a data extraction module; performing feature fusion on the infrared feature data and the environment feature data through a feature fusion module to obtain target fusion feature data; and determining the target pollution grade of the insulator to be detected according to the target fusion characteristic data through a pollution grade determining module. According to the scheme, the environmental data are used as a part for determining the target pollution level of the insulator to be detected, so that the pollution detection of the insulator is realized on the basis of considering environmental factors, the condition that the detection precision is low due to the fact that infrared imaging pollution detection is interfered by the environmental factors is avoided, the accuracy of the determined target pollution level is improved, and the precision of the pollution detection of the insulator is improved.

Optionally, the filth class determining module 340 includes:

the candidate pollution grade probability determining unit is used for determining candidate pollution grade probabilities of the target fusion characteristic data under different candidate pollution grades;

and the target pollution grade determining unit is used for selecting the target pollution grade of the insulator to be detected from the candidate pollution grades according to the candidate pollution grade probabilities.

Optionally, the target pollution level determining unit includes:

a target pollution level probability determining subunit, configured to determine a target pollution level probability of the target fusion feature data according to each candidate pollution level probability;

and the target pollution grade selecting subunit is used for selecting a target pollution grade from the candidate pollution grades according to the target pollution grade probability.

Optionally, the target pollution level selecting subunit is specifically configured to:

and selecting a candidate pollution grade which has a probability closer to the target pollution grade as the target pollution grade.

Optionally, the device has at least two types of environment data;

accordingly, the data extraction module 320 includes:

the environment data fusion unit is used for fusing different environment data to obtain fused environment data;

and the characteristic data extraction unit is used for extracting the environmental characteristic data from the fusion environmental data.

Optionally, the environment data fusion unit is specifically configured to:

taking smaller data in each environment data as target environment data;

determining environmental difference data between different environmental data;

and taking the ratio of the target environment data to the environment difference data as fusion environment data.

Optionally, the data extracting module 320 includes:

the infrared characteristic data extraction unit is used for extracting the characteristics of the infrared image through an infrared characteristic extraction network to obtain infrared characteristic data; and (c) a second step of,

the environment characteristic data extraction unit is used for extracting the characteristics of the environment data through an environment characteristic extraction network to obtain environment characteristic data;

accordingly, the feature fusion module 330 includes:

and the target fusion characteristic data acquisition unit is used for carrying out characteristic fusion on the infrared characteristic data and the environment characteristic data through a characteristic fusion network to obtain target fusion characteristic data.

The insulator contamination detection device provided by the embodiment of the invention can execute the insulator contamination detection method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing each insulator contamination detection method.

In the technical scheme of the invention, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the related infrared images, environmental data and the like all accord with the regulations of related laws and regulations without violating the good customs of the public order.

Example four

Fig. 4 is a schematic structural diagram of an electronic device implementing the insulator contamination detection method according to the fourth embodiment of the present invention, and the electronic device 410 is intended to represent various forms of digital computers, such as a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, 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. 4, the electronic device 410 includes at least one processor 411, and a memory communicatively connected to the at least one processor 411, such as a Read Only Memory (ROM) 412, a Random Access Memory (RAM) 413, and the like, wherein the memory stores computer programs executable by the at least one processor, and the processor 411 may perform various appropriate actions and processes according to the computer programs stored in the Read Only Memory (ROM) 412 or the computer programs loaded from the storage unit 418 into the Random Access Memory (RAM) 413. In the RAM 413, various programs and data necessary for the operation of the electronic device 410 can also be stored. The processor 411, the ROM 412, and the RAM 413 are connected to each other through a bus 414. An input/output (I/O) interface 415 is also connected to bus 414.

A number of components in the electronic device 410 are connected to the I/O interface 415, including: an input unit 416 such as a keyboard, a mouse, or the like; an output unit 417 such as various types of displays, speakers, and the like; a storage unit 418, such as a magnetic disk, optical disk, or the like; and a communication unit 419 such as a network card, modem, wireless communication transceiver, or the like. The communication unit 419 allows the electronic device 410 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.

Processor 411 can be a variety of general and/or special purpose processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The processor 411 performs the various methods and processes described above, such as the insulator contamination detection method.

In some embodiments, the insulator contamination detection method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of a computer program may be loaded onto and/or installed onto electronic device 410 via ROM 412 and/or communications unit 419. When loaded into RAM 413 and executed by processor 411, may perform one or more of the steps of the insulator contamination detection method described above. Alternatively, in other embodiments, processor 411 may be configured to perform the insulator contamination detection method by any other suitable means (e.g., by way of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a 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 that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Computer programs for implementing the methods of the present invention can 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 data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a 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. A 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 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) by 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 can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end 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 back-end, 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. A client and server are generally 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 host and VPS service are overcome.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired result of the technical solution of the present invention can be achieved.

The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An insulator contamination detection method is characterized by comprising the following steps:

2. The method according to claim 1, wherein the determining the target pollution level of the insulator to be detected according to the target fusion characteristic data comprises:

determining candidate pollution grade probabilities of the target fusion characteristic data under different candidate pollution grades;

and selecting a target pollution grade of the insulator to be detected from each candidate pollution grade according to each candidate pollution grade probability.

3. The method according to claim 2, wherein the selecting a target pollution level of the insulator to be detected from the candidate pollution levels according to the candidate pollution level probabilities includes:

determining a target pollution level probability of the target fusion characteristic data according to each candidate pollution level probability;

and selecting the target pollution grade from the candidate pollution grades according to the target pollution grade probability.

4. The method of claim 3, wherein selecting the target pollution class from the candidate pollution classes according to the target pollution class probability comprises:

and selecting a candidate pollution grade which is closer to the target pollution grade probability as the target pollution grade.

5. The method of claim 1, wherein the environmental data is at least two;

correspondingly, the extracting the environmental feature data from the environmental data includes:

fusing different environment data to obtain fused environment data;

and extracting the environmental characteristic data from the fusion environmental data.

6. The method according to claim 5, wherein the fusing the different environment data to obtain fused environment data comprises:

taking smaller data in each environment data as target environment data;

determining environmental difference data between different environmental data;

and taking the ratio of the target environment data to the environment difference data as the fusion environment data.

7. The method according to claim 1, wherein the extracting of the infrared characteristic data of the infrared image and the environmental characteristic data of the environmental data respectively comprises:

performing feature extraction on the infrared image through an infrared feature extraction network to obtain infrared feature data; and the number of the first and second groups,

extracting the characteristics of the environmental data through an environmental characteristic extraction network to obtain the environmental characteristic data;

correspondingly, the performing feature fusion on the infrared feature data and the environment feature data to obtain target fusion feature data includes:

and performing feature fusion on the infrared feature data and the environment feature data through a feature fusion network to obtain the target fusion feature data.

8. An insulator contamination detection device, comprising:

9. An electronic device, comprising:

one or more processors;

a memory for storing one or more programs;

when executed by the one or more processors, cause the one or more processors to implement a method of insulator contamination detection as recited in any one of claims 1-7.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements a method for insulator contamination detection according to any one of claims 1 to 7.