An infrared image-based distribution overhead line equipment heat abnormality defect intelligent identification method and system

Abstract

The present application relates to a kind of based on infrared image's distribution network overhead line equipment heating abnormality defect intelligent identification method and system, wherein the method includes target identification to infrared thermogram, determine the equipment type of target equipment and locate key part to be measured;The position of key part to be measured is mapped to temperature data, and preliminary screening is carried out based on temperature characteristics Heating abnormality;According to temperature, determine the defect basic level, and according to equipment type and distribution network topological position, determine the key weight of equipment, comprehensively determine the final defect level;According to final defect level, generate defect early warning information.The present application makes defect grading not only reflect heating degree, but also reflect the importance of equipment in distribution network operation, which is beneficial to more reasonably arrange defect disposal priority, improve the efficiency and response accuracy of distribution network inspection and defect management.

Description

Technical Field

[0001] This invention belongs to the field of power equipment monitoring technology, specifically relating to an intelligent identification method and system for abnormal heating defects in distribution network overhead line equipment based on infrared images. Background Technology

[0002] With the continuous expansion of distribution network scale and the increasing requirements for power supply reliability, the monitoring of the operational status and early warning of defects in distribution network overhead line equipment have gradually become important aspects of distribution network operation and maintenance. Distribution network overhead line equipment typically includes overhead lines, pole-mounted vacuum switches, drop-out fuses, distribution transformers, and other equipment. These devices operate outdoors for extended periods and are susceptible to factors such as load variations, changes in ambient temperature and humidity, rain and snow erosion, hardware aging, increased contact resistance, and differences in installation processes. When critical components such as equipment connections, conductive joints, clamps, fuse tubes, and terminals experience poor contact, oxidation, loosening, or localized overload, abnormal heating often occurs. If the degree of defect is not detected and accurately assessed in a timely manner, it may escalate into safety accidents such as line tripping, equipment damage, or even fire.

[0003] Existing infrared defect identification methods based on image processing or artificial intelligence can identify targets or abnormal areas in infrared images of power equipment. However, these methods typically focus on judging a single temperature threshold, making it difficult to simultaneously consider the highest temperature, phase-to-phase temperature difference, and the importance of the equipment in the distribution network topology. They also fail to classify heat-related defects, and the priority of defect handling does not fully match the actual operational risks.

[0004] Therefore, it is necessary to propose an intelligent identification method for abnormal heating defects in overhead power distribution line equipment, so as to achieve automatic identification of key equipment and key parts based on hierarchical conditions. Summary of the Invention

[0005] One of the objectives of this invention is to at least solve one or more of the aforementioned problems in the prior art. In other words, one of the objectives of this invention is to provide an intelligent identification method and system for abnormal heating defects in overhead power distribution line equipment based on infrared images that meets one or more of the aforementioned requirements.

[0006] To achieve the above-mentioned objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides an intelligent identification method for abnormal heating defects in overhead power distribution line equipment based on infrared images, comprising the following steps: Acquire infrared thermal images of overhead power distribution line equipment and corresponding temperature data; Target identification is performed on infrared thermal images to determine the type of target equipment and locate the key parts to be tested within the target equipment; Map the position information of the key part to be measured in the infrared thermal image to the temperature data, and extract the temperature characteristics of the region of interest corresponding to the key part to be measured; Perform a preliminary screening for abnormal heating of the key part to be measured based on the temperature characteristics of the region of interest; For the key part to be measured after the preliminary screening, determine the basic defect level according to the highest temperature and the phase-to-phase temperature difference in the temperature characteristics of the region of interest; Determine the equipment criticality weight according to the equipment type and the distribution network topological position of the target equipment, and determine the final defect level according to the basic defect level and the equipment criticality weight; Generate a defect warning message according to the final defect level.

[0007] As a preferred implementation manner, performing a preliminary screening for abnormal heating of the key part to be measured based on the temperature characteristics of the region of interest includes: Compare the highest temperature with the basic warning threshold; When the highest temperature is greater than the basic warning threshold, determine the key part to be measured as an abnormal heating point.

[0008] As a further preferred implementation manner, the basic warning threshold is a preset fixed threshold or a threshold dynamically adjusted according to the ambient temperature.

[0009] As a preferred implementation manner, determining the basic defect level according to the highest temperature and the phase-to-phase temperature difference in the temperature characteristics of the region of interest according to the distribution network equipment heating defect diagnosis criterion includes: When 75°C < Tmax ≤ 80°C or 10K < ΔT ≤ 30K, determine the corresponding criterion level as a general defect;4] When 80°C < Tmax ≤ 90°C or 30K < ΔT ≤ 40K, determine the corresponding criterion level as a serious defect; When Tmax > 90°C or ΔT > 40K, determine the corresponding criterion level as a critical defect; Where, Tmax represents the highest temperature of the key part to be measured, and ΔT represents the phase-to-phase temperature difference of the key part to be measured relative to the corresponding part in the same target equipment or the same section of the line.

[0010] As a further preferred implementation manner, when the same key part to be measured simultaneously meets the highest temperature criterion and the phase-to-phase temperature difference criterion, determine the criterion level with a higher corresponding defect degree in the highest temperature criterion and the phase-to-phase temperature difference criterion as the basic defect level.

[0011] As a preferred implementation manner, determining the equipment criticality weight according to the equipment type and the distribution network topological position of the target equipment specifically includes: The criticality weight of the equipment corresponding to the distribution transformer is 1.0, the criticality weight of the equipment corresponding to the pole-mounted vacuum switch is 0.8, the criticality weight of the equipment corresponding to the drop-out fuse on the main line is 0.5, the criticality weight of the equipment corresponding to the overhead line on the main line is 0.3, and the criticality weight of the equipment corresponding to the overhead line on the branch line is 0.

[0012] As a preferred implementation method, generating defect warning information specifically includes: Generate and output early warning information that includes equipment type, defect location, maximum temperature, defect severity, final defect level, and defect description.

[0013] On the other hand, the present invention provides an intelligent identification system for abnormal heating defects in overhead power distribution line equipment based on infrared images, comprising: The image acquisition module is used to acquire infrared thermal images of distribution network overhead line equipment and the corresponding temperature data; The target localization module is used to identify targets in infrared thermal images, determine the equipment type of the target device, and locate the key parts to be tested in the target device. The temperature feature extraction module is used to map the location information of the key test part in the infrared thermal image to the temperature data and extract the temperature features of the region of interest corresponding to the key test part. The anomaly screening module is used to perform initial screening for heating anomalies in key test sites based on the temperature characteristics of the region of interest. The basic grading module is used to determine the basic defect grade for key test parts after initial screening, based on the highest temperature and interphase temperature difference in the temperature characteristics of the region of interest. The comprehensive rating module is used to determine the criticality weight of the target equipment based on its equipment type and distribution network topology location, and to determine the final defect level based on the basic defect level and the criticality weight of the equipment. The early warning generation module is used to generate defect early warning information based on the final defect level. Compared with existing technologies, the intelligent identification method and system for abnormal heating defects in overhead power distribution line equipment based on infrared images provided by this invention has the following advantages: This invention determines the level of heating defects based on the highest temperature and phase-to-phase temperature difference, and determines the criticality weight of the equipment by combining the equipment type and distribution network topology location, thereby determining the final defect level. This makes the defect level not only reflect the degree of heating, but also the importance of the equipment in the operation of the distribution network. It is conducive to more rationally arranging the priority of defect handling and improving the efficiency and response accuracy of distribution network inspection and defect management. Attached Figure Description

[0014] Figure 1This is a flowchart of the intelligent identification method for abnormal heating defects in overhead power distribution line equipment based on infrared images according to the present invention; Figure 2 This is an infrared recognition image of the target device in a specific example of the present invention; Figure 3 This is the target recognition result of the target device in a specific example of the present invention. Detailed Implementation

[0015] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0016] The following description provides examples and does not limit the scope, applicability, or examples set forth in the claims. Changes may be made to the function and arrangement of the described elements without departing from the scope of this application. Various processes or components may be appropriately omitted, substituted, or added to the examples. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Furthermore, features described with respect to some examples may be combined into other examples.

[0017] This application provides a method for intelligent identification of abnormal heating defects in overhead power distribution line equipment based on infrared images, the flowchart of which is shown below. Figure 1 As shown, it includes steps S100-S700.

[0018] S100: Acquire infrared thermal images of overhead power distribution line equipment and corresponding temperature data.

[0019] Specifically, by acquiring an infrared thermal image of the target area, and then obtaining temperature data corresponding to the infrared thermal image based on the temperature information in the infrared thermal image, the target area in the image can be mapped to a readable temperature value.

[0020] During the acquisition process, information such as collection time, collection location, ambient temperature, and humidity can be recorded. Among them, the collection time and collection location are used to correspond to the inspected equipment or line section, and the ambient temperature can be used for subsequent configuration or dynamic adjustment of basic early warning thresholds.

[0021] In some feasible examples, infrared thermal images can be acquired using drone infrared inspection equipment or other acquisition devices capable of obtaining infrared thermal images.

[0022] S200: Perform target identification on the infrared thermal image, determine the equipment type of the target device, and locate the key parts to be tested in the target device.

[0023] In some embodiments, infrared thermal images can be input into a configured deep learning object detection model to identify overhead power line equipment in the image, thereby achieving the identification of infrared thermal images.

[0024] This deep learning object detection model can use commonly used image recognition models such as YOLO and Faster R-CNN to output the category and location information of the target device during the inference stage.

[0025] Specifically, the equipment type can be identified from four types: overhead lines, pole-mounted vacuum switches, drop-out fuses, and distribution transformers.

[0026] After determining the type of target equipment, further identification is needed for key test components within the target equipment. These key test components may include the equipment body, hardware and leads, wire connections, conductive connectors, knife switches, fuses, terminal blocks, and other parts related to the diagnosis of abnormal heating.

[0027] After the identification in step S200 is completed, the output includes the identification information of the target device category, the category of the key part to be tested, and the location area of ​​the key part to be tested in the infrared thermal image, which serves as the basis for subsequent extraction of temperature features.

[0028] S300: Map the location information of the key part to be measured in the infrared thermal image to the temperature data, and extract the temperature features of the region of interest corresponding to the key part to be measured.

[0029] Specifically, step S300 receives the location information of the key test area in the infrared thermal image and maps the location information to temperature data aligned with the infrared thermal image. After mapping, the temperature feature extraction module determines the region of interest (ROI) corresponding to the key test area and extracts the temperature values ​​corresponding to each pixel or temperature sampling point within the ROI to form an ROI temperature matrix.

[0030] Based on the ROI temperature matrix, the highest temperature of each key test area was calculated. , This represents the highest temperature value in the ROI temperature matrix corresponding to each key test site.

[0031] For devices with multiphase structures, step S300 also simultaneously extracts the temperature of each phase or corresponding part of each phase, and forms the interphase temperature difference Δ. T .

[0032] Δ T Used to represent the temperature difference between different key test parts in the same target device, in order to identify heat-generating parts whose absolute temperature does not exceed the limit but have obvious abnormal temperature rise relative to similar parts.

[0033] S400: Based on the temperature characteristics of the region of interest, perform preliminary screening for heating anomalies in key test parts.

[0034] Specifically, the highest temperature of the key part to be tested. Compare with the preset basic warning threshold θ.

[0035] Among them, the basic early warning threshold θ is the screening condition for screening out abnormally high temperatures.

[0036] In some implementations, θ is set to a preset fixed threshold, such as 75°C. In other implementations, θ is dynamically adjusted to the ambient temperature recorded during data acquisition, thereby adapting to the temperature background under different inspection environments.

[0037] When the temperature of a key detection area meets At that time, the key area to be tested was identified as the point of abnormal fever.

[0038] S500. For key test areas after initial screening, the defect baseline level is determined based on the highest temperature and interphase temperature difference in the temperature characteristics of the region of interest.

[0039] Step S500 involves determining the basic defect level of key test areas that have passed the initial screening for abnormal heating. Specifically, based on... and Δ T Two types of temperature characteristics are used to determine the basic level of the defect according to the preset diagnostic criteria for thermal defects. .

[0040] As a feasible example, the base defect level is set to 1. , Indicates a general defect. Indicates a serious defect. Indicates a critical defect.

[0041] Specifically, according to and Δ T The diagnostic criteria for thermal defects, which determine the basic level of defects based on two types of temperature characteristics, are set according to the following table:

[0042] Table 1 When the same critical test component simultaneously meets both the maximum temperature criterion and the interphase temperature difference criterion, and the defect severity corresponding to the two criteria is inconsistent, the criterion level with the higher defect severity between the maximum temperature criterion and the interphase temperature difference criterion shall be determined as the basic defect level. For example, a key area to be tested. It falls within the general defect range, while Δ T If it falls into the severe defect range, then the critical test area... The numerical value corresponding to a critical defect.

[0043] S600. Determine the criticality weight of the target device based on its device type and distribution network topology location, and determine the final defect level based on the defect basic level and the criticality weight of the device.

[0044] Equipment criticality weights are used to reflect the impact of different equipment types and different line locations on the priority of defect handling.

[0045] As an example, when including four equipment types—overhead lines, pole-mounted vacuum switches, drop-out fuses, and distribution transformers—the equipment criticality weights are set according to the following table:

[0046] Table 2 According to the basic defect level and equipment criticality weight W Calculate the final defect level The calculation formula is as follows: .

[0047] in, Indicates the final defect level; This indicates the basic defect level determined by the highest temperature and the interphase temperature difference; W Indicates the criticality weight of the equipment; round() indicates rounding operation; This indicates that the maximum limit for the final defect level is 3.

[0048] To facilitate understanding of step S600, this application also provides a specific example of S600.

[0049] In this example, the target device is an overhead line on the main trunk line, and the key part to be tested is the line clamp. Its infrared recognition image and target recognition results are as follows: Figure 2 and Figure 3 As shown, the highest temperature of the wire clamp was obtained through infrared image recognition and ROI temperature matrix extraction. The temperature of the corresponding clamp in the same circuit is approximately 55℃, from which the phase-to-phase temperature difference Δ is obtained. T =23.6K. According to the defect baseline rating table, Meets 75℃ ≤ 80℃, ΔT=23.6K satisfies 10K<Δ T ≤ 30K, both correspond to general defects, therefore determined Since the target equipment is an overhead line on the main trunk line, the corresponding equipment criticality weight W=0.3, therefore: . The final defect level is This refers to a general defect.

[0050] S700: Generate defect warning information based on the final defect level.

[0051] Specifically, the final defect level obtained according to S600 Generate defect warning information. Defect warning information may include information such as equipment type, defect location, maximum temperature, defect severity, final defect level, and defect description, to obtain defect details.

[0052] Another embodiment of this application provides an intelligent identification system for abnormal heating defects in overhead power distribution line equipment based on infrared images, which is used to perform the methods of the above embodiments.

[0053] Specifically, the system includes an image acquisition module, a target localization module, a temperature feature extraction module, an anomaly screening module, a basic classification module, a comprehensive classification module, and an early warning generation module.

[0054] The image acquisition module is used to acquire infrared thermal images of the overhead power line equipment and the temperature data corresponding to the infrared thermal images. The target localization module is used to identify targets in infrared thermal images, determine the equipment type of the target device, and locate the key parts to be tested in the target device. The temperature feature extraction module is used to map the location information of the key test part in the infrared thermal image to the temperature data and extract the temperature features of the region of interest corresponding to the key test part. The anomaly screening module is used to perform initial screening for heating anomalies in key test sites based on the temperature characteristics of the region of interest. The basic grading module is used to determine the basic defect grade for key test parts after initial screening, based on the highest temperature and interphase temperature difference in the temperature characteristics of the region of interest. The comprehensive rating module is used to determine the criticality weight of the target equipment based on its equipment type and distribution network topology location, and to determine the final defect level based on the basic defect level and the criticality weight of the equipment. The early warning generation module is used to generate defect early warning information based on the final defect level.

[0055] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0056] The foregoing description is merely an exemplary embodiment of this application and should not be construed as limiting the scope of this application. Any equivalent changes and modifications made in accordance with the teachings of this application shall still fall within the scope of this application. Those skilled in the art will readily conceive of other embodiments of this application upon considering the disclosure of the specification and practice. The foregoing disclosure is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not described in this application. The specification and embodiments are considered exemplary only, and the scope and spirit of this application are defined by the claims.

Claims

1. A method for intelligent identification of abnormal heating defects in overhead power distribution line equipment based on infrared images, characterized in that, It includes the following steps: Obtain the infrared thermal image of the distribution network overhead line equipment and the temperature data corresponding to the infrared thermal image; Perform target recognition on the infrared thermal image to determine the equipment type of the target equipment and locate the key parts to be measured in the target equipment; Map the position information of the key parts to be measured in the infrared thermal image to the temperature data, and extract the temperature characteristics of the region of interest corresponding to the key parts to be measured; Perform a preliminary screening for abnormal heating of the key parts to be measured based on the temperature characteristics of the region of interest; For the key parts to be measured after the preliminary screening, determine the basic defect level according to the highest temperature and the phase - to - phase temperature difference in the temperature characteristics of the region of interest; Determine the equipment criticality weight according to the equipment type of the target equipment and the distribution network topology position, and determine the final defect level according to the basic defect level and the equipment criticality weight; Generate a defect warning message according to the final defect level.

2. The intelligent identification method for abnormal heating defects in overhead power distribution line equipment based on infrared images as described in claim 1, characterized in that, Performing a preliminary screening for abnormal heating of the key parts to be measured based on the temperature characteristics of the region of interest includes: Compare the highest temperature with the basic warning threshold; When the highest temperature is greater than the basic warning threshold, determine the key part to be measured as an abnormal heating point.

3. The intelligent identification method for abnormal heating defects in overhead power distribution line equipment based on infrared images as described in claim 2, characterized in that, The basic warning threshold is a preset fixed threshold or a threshold dynamically adjusted according to the ambient temperature.

4. The intelligent identification method for abnormal heating defects in overhead power distribution line equipment based on infrared images as described in claim 1, characterized in that, Determining the basic defect level according to the highest temperature and the phase - to - phase temperature difference in the temperature characteristics of the region of interest according to the distribution network equipment heating defect diagnosis criterion includes: When 75℃ < Tmax ≤ 80℃ or 10K < ΔT ≤ 30K, determine the corresponding criterion level as a general defect; When 80℃ < Tmax ≤ 90℃ or 30K < ΔT ≤ 40K, determine the corresponding criterion level as a serious defect; When Tmax > 90℃ or ΔT > 40K, determine the corresponding criterion level as a critical defect; Where, Tmax represents the highest temperature of the key part to be measured, and ΔT represents the phase - to - phase temperature difference of the key part to be measured relative to the corresponding part in the same target equipment or the same section of the line.

5. The intelligent identification method for abnormal heating defects in overhead power distribution line equipment based on infrared images as described in claim 4, characterized in that, When the same key part to be measured simultaneously meets the highest temperature criterion and the phase - to - phase temperature difference criterion, determine the criterion level with a higher corresponding defect degree in the highest temperature criterion and the phase - to - phase temperature difference criterion as the basic defect level.

6. The intelligent identification method for abnormal heating defects in overhead power distribution line equipment based on infrared images as described in claim 1, characterized in that, Determining the equipment criticality weight according to the equipment type of the target equipment and the distribution network topology position specifically includes: The equipment criticality weight corresponding to the distribution transformer is 1.0, the equipment criticality weight corresponding to the pole - mounted vacuum switch is 0.8, the equipment criticality weight corresponding to the drop - type fuse on the main line is 0.5, the equipment criticality weight corresponding to the overhead line on the main line is 0.3, and the equipment criticality weight corresponding to the overhead line on the branch line is 0.

7. The intelligent identification method for abnormal heating defects in overhead power distribution line equipment based on infrared images as described in claim 1, characterized in that, Generating a defect warning message specifically includes: Generate a warning message including equipment type, defect location, highest temperature, defect degree, final defect level and defect description, and output the warning message.

8. An intelligent identification system for abnormal heating defects in overhead power distribution line equipment based on infrared images, characterized in that, It includes: An image acquisition module for obtaining the infrared thermal image of the distribution network overhead line equipment and the temperature data corresponding to the infrared thermal image; The target positioning module is used to identify targets in the infrared thermal image, determine the equipment type of the target device, and locate the key parts to be tested in the target device. The temperature feature extraction module is used to map the location information of the key part to be measured in the infrared thermal image to the temperature data, and extract the temperature features of the region of interest corresponding to the key part to be measured. An anomaly screening module is used to perform an initial screening of heating anomalies on the key test parts based on the temperature characteristics of the region of interest. The basic grading module is used to determine the basic defect grade of the key test parts after the initial screening, based on the highest temperature and interphase temperature difference in the temperature characteristics of the region of interest. The comprehensive rating module is used to determine the criticality weight of the target device based on its device type and distribution network topology location, and to determine the final defect level based on the basic defect level and the criticality weight of the device. The early warning generation module is used to generate defect early warning information based on the final defect level.

Images