EVA insulation blanket online performance detection method based on infrared imaging and temperature sensing

Abstract

The invention discloses an EVA insulation blanket online performance detection method based on infrared imaging and temperature sensing. The EVA insulation blanket online performance detection method comprises the following steps that monitoring equipment is adopted to collect images of an insulation blanket in real time; the temperature distribution on the surface of the insulation blanket is monitored in real time through an infrared thermal imaging sensor integrated on monitoring equipment; the surface temperature of the insulation blanket is analyzed in real time, and an early warning signal is automatically sent out before the temperature reaches a preset safety threshold value. Compared with a traditional manual detection mode, the safety condition of a working site can be mastered more rapidly and comprehensively through real-time monitoring, the penetrating power of safety management is greatly improved, and potential safety hazards are reduced.

Description

[Technical field]

[0001] The invention belongs to the technical field of electric power engineering, and in particular relates to a method for detecting the performance of an EVA insulation blanket. [Background technology]

[0002] Distribution network non-stop operation has been widely used in power grids because it can improve power supply reliability economically and effectively. Due to the complex structure and small gap distance of distribution network equipment, insulation shielding is an important means to ensure the safety of personnel and equipment. Ethylene-vinyl acetate copolymer (EVA) insulation blanket has been widely used in distribution network non-stop operation.

[0003] However, under high temperature and high load conditions in summer, ethylene-vinyl acetate copolymer (EVA) insulation blankets often experience adverse conditions such as hot melting, which leads to the deterioration of the mechanical and insulation properties of the EVA insulation blankets, seriously affecting their normal use, and even causing them to be scrapped due to overheating. In addition, compared with rubber-type insulation shielding devices, the surface flashover voltage of the EVA insulation blanket under high temperature conditions is smaller, and the leakage current amplitude increases more, increasing the probability of surface flashover and reducing its insulation performance. Compared with live working, the interlayer breakdown of the EVA insulation blanket is very harmful, which will bring serious threats to live working personnel. Therefore, studying the influence of the mechanical and electrical properties of the EVA insulation blanket under high temperature, clarifying the degradation mechanism of the EVA insulation blanket and taking reasonable protective measures can effectively extend the service life and avoid the reduction of electromechanical performance caused by overheating, which is of great significance to ensure the safety of personnel and equipment.

[0004] Currently, the performance testing of EVA insulation blankets on the market mostly relies on manual regular inspections or simple tests, which fail to fully consider the real-time changes in insulation performance under high temperature environments. In addition, the existing testing methods are insufficient in testing efficiency and accuracy, and cannot detect local overheating, mechanical damage, etc. in a timely manner. [Summary of the invention]

[0005] In view of the shortcomings of the prior art, the technical problem to be solved by the present invention is to provide an online performance detection method for EVA insulation blanket based on infrared imaging and temperature sensing, so as to solve the shortcomings of the existing detection means in detection efficiency and accuracy, and to monitor in real time the most suitable temperature of the EVA insulation blanket when working, so as to ensure the insulation performance of the insulation blanket and avoid operational accidents.

[0006] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0007] The online performance detection method of EVA insulation blanket based on infrared imaging and temperature sensing includes the following steps:

[0008] Use monitoring equipment to collect images of insulation blankets in real time;

[0009] The temperature distribution on the surface of the insulation blanket is monitored in real time through the infrared thermal imaging sensor integrated in the monitoring equipment;

[0010] The surface temperature of the insulation blanket is analyzed in real time, and a warning signal is automatically issued before the temperature reaches the preset safety threshold.

[0011] Preferably, the monitoring device is a ball monitoring device; or, the monitoring device is carried on a drone.

[0012] Preferably, the monitoring device is provided with an automatic tracking module, and the automatic tracking module controls the monitoring device to automatically adjust the viewing angle to achieve tracking of the insulation blanket.

[0013] Preferably, the monitoring device firstly automatically identifies and locks the position of the insulation blanket using a target detection algorithm; and then continuously tracks the position of the insulation blanket using a target tracking algorithm, so that the insulation blanket is always within the monitoring range.

[0014] Preferably, the target detection algorithm is a YOLO target detection algorithm.

[0015] Preferably, the target tracking algorithm is a KCF target tracking algorithm, and a video behavior recognition model is constructed by combining the YOLO target detection algorithm and the KCF target tracking algorithm.

[0016] Preferably, for the video behavior recognition model, sample pictures in the working environment are collected, the position of the insulation blanket is marked using the LabelImg tool, and the YOLO and KCF algorithms are trained to improve the recognition accuracy.

[0017] Preferably, a pixel value mapping algorithm is used to convert the thermal image of the insulation blanket acquired by the infrared thermal imaging sensor into temperature distribution data, and the temperature information of each area on the surface of the insulation blanket is extracted.

[0018] Preferably, the temperature gradient and change rate of different areas of the insulation blanket are calculated by a distributed algorithm; the temperature rise of each area of ​​the insulation blanket is predicted by an LSTM time series prediction model to predict possible breakdown points.

[0019] Preferably, after the warning signal is issued, if the temperature continues to rise, an alarm is triggered to prompt the operator to take necessary protective measures.

[0020] The present invention adopts the above technical solution and has the following beneficial effects:

[0021] (1) Real-time detection improves the penetration of safety monitoring: Through the combination of infrared thermal imaging sensors and video monitoring equipment, the system can perform real-time temperature detection on the insulation blanket during operation and accurately monitor its surface temperature changes. Even in complex operating environments, the system can effectively and quickly detect temperature anomalies. Compared with traditional manual detection methods, real-time monitoring can more quickly and comprehensively grasp the safety status of the work site, greatly improving the penetration of safety management and reducing potential safety hazards.

[0022] (2) Unaffected by height and light exposure, all-weather monitoring: The system uses infrared thermal imaging technology and is carried out through equipment such as drones. It can work stably at different heights, ensuring all-weather monitoring effects. When facing higher poles and towers, the system can clearly obtain temperature data and video images to ensure that the temperature changes of the insulation blanket are monitored in real time, solving the limitations that traditional monitoring equipment may encounter in complex environments.

[0023] (3) Early warning, trend warning: Through real-time analysis of temperature signals, the system can automatically issue a warning signal before the temperature reaches the preset critical value, helping operators take protective measures before dangerous situations occur. This early warning function not only improves the safety of operations, but also effectively prevents accidents and avoids problems such as insulation failure and equipment damage caused by excessive temperature of the insulation blanket.

[0024] (4) Greatly improve economic benefits: The system has high economic benefits. On the one hand, through precise monitoring and early warning, the service life of equipment such as insulation blankets is extended, and the loss caused by equipment overheating or failure is reduced. On the other hand, real-time monitoring and early warning can effectively avoid sudden accidents, reduce operation downtime, and reduce the cost of repair and replacement of equipment. In addition, the reduction of safety accidents also means the reduction of manpower and material costs, which greatly improves the overall operational efficiency and brings significant economic returns.

[0025] These features and advantages of the present invention will be disclosed in detail in the following specific embodiments and drawings.

Brief Description of the Drawings

[0026] The invention will be further described below in conjunction with the accompanying drawings:

[0027] Figure 1 It is the operation flow chart of the present invention;

[0028] Figure 2 This is a flowchart of the multi-point temperature difference analysis and breakdown point prediction algorithm based on infrared camera;

[0029] Figure 3The test result diagram is obtained by taking the average value of the first, second and third interlayer breakdown voltages of the insulation blanket specimens at different temperatures. [Specific implementation method]

[0030] The technical solutions of the embodiments of the present invention are explained and described below in conjunction with the drawings of the embodiments of the present invention, but the following embodiments are only preferred embodiments of the present invention, not all. Based on the embodiments in the implementation mode, other embodiments obtained by those skilled in the art without creative work are all within the protection scope of the present invention.

[0031] Study the influence of high temperature on the mechanical and electrical properties of EVA insulation blanket:

[0032] As the temperature of the EVA insulation blanket rises, the molecules in the EVA structure will break and oxidize to produce small molecules, causing cracks, pores and other defects on the surface of the EVA film. Secondly, the instantaneous current generated by the application of voltage will produce higher temperatures locally. The thermal shock caused by the local high temperature will have a certain impact on the structure of the EVA insulation blanket, further promoting the thermal aging degradation of the EVA, and the generated heat will diffuse in space.

[0033] As a closed area, it is obviously a heat accumulation area. Therefore, as the heat accumulates, the local temperature of the edge area of ​​the film rises, causing the resistance of the material to decrease. Under the condition of constant voltage, the current increases, generating more heat, causing more and more heat to accumulate in the center area, thus creating a vicious cycle, and eventually causing interlayer breakdown in this area. The EVA insulation blanket breaks down prematurely due to the thermal effect. The heat accumulates at one point during the transfer process, and the large amount of heat accumulated at one point causes thermal breakdown.

[0034] Setting up an EVA insulation blanket temperature test experiment: The present invention provides an experimental method for detecting the performance of an EVA insulation blanket at different temperatures and combining X-ray diffraction (XRD) and differential scanning calorimetry (DSC) techniques. The main function of the X-ray diffraction experiment is to use the diffraction phenomenon of X-rays in the crystals in the material structure to obtain the characteristics of the X-ray signal after diffraction, and obtain the diffraction spectrum through software processing. The diffraction spectrum information can not only be used to determine the physical phase using a conventional microscope, but also to analyze whether there are defects or lattice defects inside the crystal structure of the material. It has a wide range of applications and is usually used to measure materials such as powders, single crystals or polycrystals, polymers, etc. Analyze the changes in the aggregation structure of the EVA insulation blanket after pretreatment at different temperatures.

[0035] The EVA insulation blanket was heated to different temperature ranges (25℃ to 120℃) by an infrared heating device, and the changes in dielectric constant, dielectric loss and interlayer breakdown voltage were monitored in real time. The results show that with the increase of temperature, the dielectric constant and dielectric loss of the EVA insulation blanket show a significant upward trend, especially at 120℃, the dielectric constant increases by 33.9% and the dielectric loss increases by 93.1%. In addition, the interlayer breakdown voltage decreases significantly above 80℃, indicating that high temperature has a significant effect on the insulation performance. Due to the different temperatures of the polymer, the grain size and dimensions in its structure cause uneven strain in the structure. At high temperatures, some grains or grains between grains in the internal structure of the EVA insulation blanket produce corresponding microscopic strain under stress. For this, the influence of high temperature on the mechanical properties of the EVA insulation blanket can be analyzed by microscopic strain.

[0036] The relationship between microscopic strain and diffraction broadening is:

[0037]

[0038] Where: δs is microscopic strain, generally expressed as a percentage; FW is the half-height width of the diffraction peak; θ is the Bragg angle. The influence of microscopic strain in the XRD diffraction spectra of EVA insulation blankets at different temperatures was analyzed by Origin software. The degradation of the microstructure of the material by high temperature was further verified, providing important data support for ensuring the safety of uninterrupted power supply operation of the distribution network.

[0039] The following is the technical solution of the present invention:

[0040] The online performance detection method of EVA insulation blanket based on infrared imaging and temperature sensing includes the following steps:

[0041] Use monitoring equipment to collect images of insulation blankets in real time;

[0042] The temperature distribution on the surface of the insulation blanket is monitored in real time through the infrared thermal imaging sensor integrated in the monitoring equipment;

[0043] The surface temperature of the insulation blanket is analyzed in real time, and a warning signal is automatically issued before the temperature reaches the preset safety threshold.

[0044] Wherein, the monitoring device is a ball monitoring device; or, the monitoring device is mounted on a drone. The monitoring device is provided with an automatic tracking module, and the automatic tracking module controls the monitoring device to automatically adjust the viewing angle to track the insulation blanket. Specifically, the monitoring device first uses a target detection algorithm to automatically identify and lock the position of the insulation blanket; then, the position of the insulation blanket is continuously tracked through a target tracking algorithm, so that the insulation blanket is always within the monitoring range. The above technical solution monitors the non-stop operation of the distribution network, and uses a tracking model to enable the camera to track the insulation blanket, so that the position of the insulation blanket is always within the monitoring screen and occupies the main content, which is convenient for subsequent infrared processing.

[0045] In this embodiment, the target detection algorithm is the YOLO target detection algorithm, and the target tracking algorithm is the KCF target tracking algorithm. By combining the YOLO target detection algorithm and the KCF target tracking algorithm, a video behavior recognition model is constructed to achieve real-time detection and tracking of operators and insulation blankets. First, the YOLO algorithm is used to detect the position of the operator, and the KCF algorithm is used to achieve continuous tracking of the personnel. At the same time, for the video behavior recognition model, sample images in the working environment are collected, the position of the insulation blanket is marked using the LabelImg tool, and the YOLO and KCF algorithms are trained to improve the recognition accuracy.

[0046] Then, based on the temperature signal model, by collecting the temperature data of the insulation blanket under different temperature conditions, the temperature prediction model is trained using a machine learning algorithm to achieve early warning of temperature anomalies. The temperature data obtained by the sensor is transmitted to the background system wirelessly to analyze temperature changes in real time. Combined with the video screen, the temperature data is dynamically associated with the position of the insulation blanket. By collecting the temperature trends of each part and combining it with a distributed prediction algorithm, the system can detect temperature anomalies in a timely manner. When the temperature exceeds the preset safety threshold, it will automatically issue a warning or alarm signal to ensure operational safety.

[0047] Specifically, the thermal image of the insulation blanket obtained by the infrared thermal imaging sensor is converted into temperature distribution data using a pixel value mapping algorithm, and the temperature information of each area on the surface of the insulation blanket is extracted. The temperature gradient and change rate of different areas of the insulation blanket are calculated using a distributed algorithm; the temperature rise of each area of ​​the insulation blanket is predicted using an LSTM time series prediction model to predict possible breakdown points.

[0048] Finally, information fusion and decision-making: The real-time video detection results and temperature signal detection results are integrated and decided on the ground information terminal. When the temperature signal detection results are abnormal, it indicates that the insulation performance of the insulation blanket has been irreversibly damaged, and there may be dangerous situations such as insulation breakdown. The operation process needs to be suspended and the ground safety inspectors intervene immediately.

[0049] Furthermore, after the warning signal is issued, if the temperature continues to rise, an alarm is triggered to prompt the operator to take necessary protective measures.

[0050] like Figure 1 As shown in the figure: When the operation starts, the system is started. First, the working environment is monitored in real time through the YOLO target detection algorithm, and the positions of the operators and insulation blankets are automatically detected and identified. Subsequently, the detected personnel and insulation blankets are continuously tracked using the KCF target tracking algorithm to ensure that the targets are always within the visible range in the monitoring screen. At the same time, the system will automatically determine whether the information of the insulator is successfully collected in the screen. If it is confirmed that the insulator has been accurately identified and located, the system will automatically switch to the temperature acquisition module and start real-time collection of temperature data for the insulation blanket and insulator. Through dynamic monitoring of temperature changes, the system can promptly warn of abnormal temperature conditions to ensure the safety and accuracy of the operation.

[0051] Figure 2 The flowchart shows the complete process of the multi-point temperature difference analysis and breakdown point prediction algorithm based on infrared cameras. First, the system starts and monitors the insulation blanket in real time through an infrared camera, capturing thermal images and converting them into temperature data. Next, the system uses a distributed algorithm to calculate the temperature gradient and change rate of different areas of the insulation blanket and identify areas with abnormal temperature rise. Subsequently, the temperature of each area is predicted through the LSTM time series prediction model to predict future temperature rise trends and potential breakdown points. When the temperature forecast of a certain area approaches or exceeds the safety threshold, the system will issue a warning signal; if the temperature continues to rise, an alarm will be triggered to prompt the operator to take necessary protective measures. Through this process, the system can achieve accurate monitoring and early warning of the insulation blanket to ensure operational safety.

[0052] The average value of the first, second and third interlayer breakdown voltages of the insulation blanket samples at different temperatures was obtained, and the test results were as follows: Figure 3 As shown, through Figure 3 It can be seen that with the increase of temperature, the interlayer breakdown voltage of the EVA insulation blanket first increases slightly, and then shows a rapid decline. Taking the temperature of 20℃ as a reference, when the temperature is 40℃ and 60℃ during the test, the interlayer breakdown voltage of the EVA insulation blanket does not change significantly, but when the temperature is 80℃, the interlayer breakdown voltage of the insulation blanket decreases by 9.7%, and when the temperature is 100℃, the interlayer breakdown voltage of the insulation blanket decreases by 18.4%. When the temperature rises from 20℃ to 60℃, the interlayer breakdown voltage of the insulation blanket gradually increases, and when the temperature rises from 80℃ to 100℃, the interlayer breakdown voltage shows a downward trend. The threshold temperature for the interlayer breakdown voltage of the EVA insulation blanket to decrease is about 80℃, based on which the relevant warning threshold is proposed.

[0053] The above is only a specific embodiment of the invention, but the protection scope of the invention is not limited thereto. Those skilled in the art should understand that the invention includes but is not limited to the contents described in the drawings and the above specific embodiments. Any modification that does not deviate from the functional and structural principles of the invention will be included in the scope of the claims.

Claims

1. An online performance detection method for EVA insulation blanket based on infrared imaging and temperature sensing, characterized in that: The steps include: Use monitoring equipment to collect images of insulation blankets in real time; The infrared thermal imaging sensor integrated in the monitoring equipment can monitor the temperature distribution on the surface of the insulation blanket in real time. The surface temperature of the insulation blanket is analyzed in real time, and a warning signal is automatically issued before the temperature reaches the preset safety threshold.

2. The online performance detection method of EVA insulation blanket according to claim 1, characterized in that: The monitoring device is a ball monitoring device; or, the monitoring device is carried on a drone.

3. The online performance detection method of EVA insulation blanket according to claim 2 is characterized in that: The monitoring device is provided with an automatic tracking module, and the automatic tracking module controls the monitoring device to automatically adjust the viewing angle to achieve tracking of the insulation blanket.

4. The online performance detection method of EVA insulation blanket according to claim 3 is characterized in that: The monitoring device firstly automatically identifies and locks the position of the insulation blanket using a target detection algorithm; then continuously tracks the position of the insulation blanket using a target tracking algorithm, so that the insulation blanket is always within the monitoring range.

5. The online performance detection method of EVA insulation blanket according to claim 4 is characterized in that: The target detection algorithm is the YOLO target detection algorithm.

6. The online performance detection method of EVA insulation blanket according to claim 5, characterized in that: The target tracking algorithm is a KCF target tracking algorithm, which builds a video behavior recognition model by combining the YOLO target detection algorithm and the KCF target tracking algorithm.

7. The online performance detection method of EVA insulation blanket according to claim 6, characterized in that: For the video behavior recognition model, sample pictures in the working environment are collected, the location of the insulation blanket is marked using the LabelImg tool, and the YOLO and KCF algorithms are trained to improve the recognition accuracy.

8. The online performance detection method of EVA insulation blanket according to claim 1, characterized in that: The thermal image of the insulation blanket obtained by the infrared thermal imaging sensor is converted into temperature distribution data using a pixel value mapping algorithm, and the temperature information of each area on the surface of the insulation blanket is extracted.

9. The online performance detection method of EVA insulation blanket according to claim 8, characterized in that: The temperature gradient and change rate of different areas of the insulation blanket are calculated through a distributed algorithm. The temperature rise of each area of ​​the insulation blanket is predicted through the LSTM time series prediction model to predict possible breakdown points.

10. The online performance detection method of EVA insulation blanket according to claim 1, characterized in that: After the early warning signal is issued, if the temperature continues to rise, an alarm will be triggered to prompt the operator to take necessary protective measures.

Images