Electrical fire early warning method, device and equipment based on leakage current temperature detection

Abstract

The invention relates to the technical field of fire early warning, in particular to an electrical fire early warning method, device and equipment based on leakage current temperature detection. The method comprises the following steps: acquiring information data of electrical equipment; performing electrical equipment power line position positioning on the electrical equipment information data to generate electrical equipment power line position information data; performing leakage current sensor data acquisition on the electrical equipment power line position information data to obtain standard electrical equipment leakage current monitoring data; and performing maximum fluctuation curve segment confirmation on the leakage current monitoring data of the standard electrical equipment to obtain a maximum fluctuation curve of the leakage current of the electrical equipment. According to the invention, by introducing leakage current fluctuation mode identification, accurate power line positioning, intelligent anomaly detection and heat map analysis, the accuracy, response speed and positioning capability of the electrical fire early warning system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fire warning, and in particular to an electrical fire warning method, device and equipment based on leakage current temperature detection. Background Art

[0002] As a common type of fire, electrical fire is highly concealed and destructive. Traditional fire warning methods mostly rely on sensors such as smoke and temperature. However, in recent years, leakage current temperature detection technology has gradually attracted the attention of researchers and has become an important direction in the field of electrical fire warning. Leakage current is usually caused by insulation failure or aging of electrical equipment. When leakage current flows through electrical equipment, local temperature rise will occur. By detecting the temperature change caused by leakage current, early warning of electrical fire can be achieved. Initially, leakage current detection mainly relied on traditional current sensors, but these methods have the disadvantages of slow response and inability to accurately capture subtle changes. With the development of smart sensors and wireless communication technology, leakage current temperature detection technology has gradually combined high-precision temperature sensors with leakage current sensors, which can monitor the leakage current and temperature changes of equipment in real time, and perform abnormality detection through data analysis. In recent years, fire warning systems based on leakage current temperature have been gradually applied to smart homes, power facilities, industrial equipment and other fields, and have achieved certain results. However, the existing technologies currently rely on a single temperature threshold or current threshold to judge leakage current anomalies, and rely on fixed temperature thresholds for judgment, which cannot provide multi-level temperature analysis and dynamic warning feedback, resulting in low accuracy of electrical fire warning. Summary of the invention

[0003] Based on this, it is necessary to provide an electrical fire warning method, device and equipment based on leakage current temperature detection to solve at least one of the above technical problems.

[0004] To achieve the above object, an electrical fire early warning method based on leakage current temperature detection is provided, the method comprising the following steps: Step S1: Acquire electrical equipment information data; locate the power line of the electrical equipment according to the electrical equipment information data to generate the power line position information data of the electrical equipment; collect leakage current sensor data of the power line position information data of the electrical equipment to obtain standard electrical equipment leakage current monitoring data; Step S2: Confirm the maximum fluctuation curve segment of the leakage current monitoring data of the standard electrical equipment to obtain the maximum fluctuation curve of the leakage current of the electrical equipment; divide the standard electrical equipment leakage current monitoring data into suspicious line modes based on the maximum fluctuation curve of the leakage current of the electrical equipment to generate suspicious line mode data, wherein the suspicious line mode data includes a gradual change mode and a sudden increase mode; mark the suspicious line segment of the power line location information data of the electrical equipment based on the suspicious line mode data to generate the suspicious power line segment location information data of the electrical equipment; Step S3: Based on the gradual change mode, the position information data of the suspected power line segment of the electrical equipment is used to detect the long-term abnormal change of the power insulation layer, and generate the long-term abnormal temperature change data of the power line segment; based on the position information data of the suspected power line segment of the electrical equipment in the sudden increase mode, the instantaneous abnormal change of the power input is detected, and the instantaneous abnormal temperature change data of the line segment is generated; based on the long-term abnormal temperature change data of the power line segment and the instantaneous abnormal temperature change data of the line segment, the temperature level of the thermal map is marked to generate the abnormal temperature change level data; Step S4: Perform early warning response feedback on the electrical equipment information data according to the abnormal temperature change level data, generate electrical equipment abnormal early warning response feedback data, and perform electrical fire early warning operations.

[0005] The present invention can ensure the accuracy of subsequent leakage current monitoring by obtaining detailed information of electrical equipment and accurately locating the position of the power line. The clear calibration of the power line position enables the leakage current sensor to monitor key areas in a targeted manner, avoiding the problem of inaccurate or incomplete installation of the leakage current sensor in the traditional method. By performing fluctuation curve analysis on the leakage current monitoring data, potential fault signals in the electrical equipment can be identified earlier. The maximum fluctuation of the leakage current usually means an abnormal state of the electrical equipment (such as aging of the insulation layer, poor contact, etc.). Dividing the leakage current fluctuation mode into a gradual change mode and a sudden increase mode helps to distinguish different types of faults: the gradual change mode indicates a long-term accumulated hidden danger, and the sudden increase mode is usually related to sudden electrical faults, which enables the system to take different early warning and processing measures according to different modes, thereby improving the accuracy of the early warning and the response speed. By combining the gradual change mode and the sudden increase mode, the long-term abnormality detection and instantaneous abnormality detection of the power line segment are performed respectively, so that the long-term accumulated temperature changes and sudden changes can be distinguished, which helps to accurately distinguish the hidden fire risks in electrical equipment (such as temperature changes caused by long-term aging or wear of the power insulation layer) from sudden electrical faults (such as instantaneous temperature rise caused by a sudden increase in current). By marking the abnormal temperature changes of the power line segment with the temperature level of the heat map and generating the corresponding abnormal temperature change level data, the fire risk of the electrical equipment can be intuitively displayed. The marking of the temperature change level can more accurately reflect the severity of the fire risk, thereby providing a more scientific basis for the subsequent early warning response. Based on these data, the system can issue early warnings in time and formulate targeted response measures according to the temperature change level. For example, when the temperature change reaches a certain threshold, the system can automatically cut off the power supply, start the fire fighting equipment or notify the relevant personnel to handle it. In this way, it not only improves the early warning capability of fire, but also takes preventive measures before the fire occurs to reduce the incidence of electrical fires. Therefore, the present invention improves the accuracy, response speed and positioning capability of the electrical fire warning system by introducing leakage current fluctuation pattern recognition, precise power line positioning, intelligent anomaly detection and thermal map analysis.

[0006] Preferably, step S1 comprises the following steps: Step S11: Acquire electrical equipment information data; Step S12: performing electrical equipment topology analysis on the electrical equipment information data to generate electrical equipment topology data; locating the electrical equipment power line position of the electrical equipment information data based on the electrical equipment topology data to generate electrical equipment power line position information data; Step S13: deploying leakage current sensors on the power line location information data of the electrical equipment based on a preset distance interval to obtain leakage current sensor deployment data; performing wireless data collection on the leakage current sensor deployment data to obtain leakage current monitoring data of the electrical equipment; Step S14: preprocess the electrical equipment leakage current monitoring data to generate standard electrical equipment leakage current monitoring data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization.

[0007] The present invention helps to clarify the layout and working principle of electrical equipment by acquiring and topologically analyzing the information of electrical equipment, and provides systematic and accurate information on the location of power lines of electrical equipment, which provides key basic data support for subsequent leakage current monitoring and equipment maintenance. The leakage current sensor is deployed on the power line at a preset distance interval to ensure the comprehensiveness and accuracy of leakage current monitoring. The wireless collection of deployment data makes the monitoring data real-time and easy to transmit, which improves the response speed and flexibility of the system. Data preprocessing (including cleaning, denoising, filling missing values ​​and standardization) ensures the high quality of the data and provides a reliable basis for subsequent leakage current analysis, which not only improves the accuracy of the analysis results, but also can effectively reduce noise interference in subsequent machine learning or model optimization. Through precise leakage current monitoring and analysis, the system can timely identify potential safety hazards of electrical equipment, thereby reducing the risk of leakage accidents and improving the safety of electrical equipment. At the same time, the standardization and processing of data make the management and maintenance of equipment more efficient and controllable.

[0008] Preferably, step S2 comprises the following steps: Step S21: converting the standard electrical equipment leakage current monitoring data into a time-series leakage current monitoring curve to generate an electrical equipment leakage current curve; extracting the peak current of the electrical equipment leakage current curve to obtain the peak leakage current data of the electrical equipment; calculating the variation amplitude of the electrical equipment leakage current curve based on the peak leakage current of the electrical equipment to obtain the peak variation amplitude data of the electrical equipment; Step S22: confirming the maximum fluctuation curve segment of the standard electrical equipment leakage current monitoring data according to the electrical equipment peak leakage current data and the electrical equipment peak change amplitude data, and obtaining the maximum fluctuation curve of the electrical equipment leakage current; Step S23: dividing the standard electrical equipment leakage current monitoring data into suspicious line modes based on the maximum fluctuation curve of the electrical equipment leakage current, and generating suspicious line mode data, wherein the suspicious line mode data includes a gradual change mode and a sudden increase mode; Step S24: marking the suspicious line segments of the power line location information data of the electrical equipment based on the suspicious line pattern data to generate the suspicious power line segment location information data of the electrical equipment.

[0009] The present invention can clearly identify the leakage current change trend and prominent abnormal points of the electrical equipment by converting the leakage current curve of the electrical equipment and extracting the peak current. By calculating the peak change amplitude, the degree of leakage current change can be further quantified to help analyze whether there is a potential danger or equipment failure. By confirming the maximum fluctuation curve segment, the most critical fluctuation part in the leakage current data of the electrical equipment can be more accurately identified. This process can calibrate the potential risk points of the electrical equipment in the system and provide more specific monitoring data for subsequent detection and analysis. By dividing the maximum fluctuation curve of the leakage current into modes, the gradual change mode and the sudden increase mode can be automatically distinguished, which provides a specific mode reference for different types of leakage current problems. The gradual change is usually related to problems such as equipment aging and poor line contact, while the sudden increase mode indicates a more serious fault or short circuit risk. The suspicious line segment is marked based on the suspicious line mode data, and the power line segment with problems in the electrical equipment can be accurately identified. Through these data, the operation and maintenance personnel can accurately locate the fault point, avoid the false alarm or missed alarm in the traditional detection method, and improve the efficiency and accuracy of fault detection. Through this process, the system can not only monitor the leakage current changes of electrical equipment in real time, but also automatically identify and locate potential fault risks, greatly improving the predictability and efficiency of equipment maintenance. It further reduces the risk of equipment damage and safety accidents, and helps managers take measures to repair them in advance.

[0010] Preferably, step S23 includes the following steps: Step S231: extracting the maximum fluctuation point and the minimum fluctuation point based on the maximum fluctuation curve of the leakage current of the electrical equipment, and obtaining the maximum fluctuation point data and the minimum fluctuation point data of the leakage current of the electrical equipment; Step S232: performing a time domain analysis on the maximum fluctuation point data of the leakage current of the electrical equipment and the minimum fluctuation point data of the leakage current of the electrical equipment to generate fluctuation change time domain data; comparing the fluctuation change time domain data with a preset standard fluctuation time domain threshold, and when the fluctuation change time domain data is greater than or equal to the preset standard fluctuation time domain threshold, marking the corresponding fluctuation change time domain data as progressive change time domain data; Step S233: when the fluctuation change time domain data is less than the preset standard fluctuation time domain threshold, the corresponding fluctuation change time domain data is marked as sudden increase change time domain data; based on the gradual change time domain data, the standard electrical equipment leakage current monitoring data is divided into a first suspicious mode to generate a gradual change mode; Step S234: performing a second suspicious pattern classification on the standard electrical equipment leakage current monitoring data based on the sudden increase change time domain data to generate a sudden increase type change pattern.

[0011] The present invention can accurately capture the most important change nodes in the leakage current curve by extracting the maximum fluctuation point and the minimum fluctuation point of the leakage current of the electrical equipment, which helps to further analyze the operating status of the electrical equipment, especially the cause of abnormal fluctuations, and provides preliminary clues to potential faults of the electrical equipment. By performing a time domain analysis on the fluctuation point data, generating fluctuation change time domain data, and comparing it with the standard fluctuation time domain threshold, the fluctuation trend of the electrical equipment in a specific time period can be identified, especially when the fluctuation change exceeds the standard threshold, it can be marked as gradual change time domain data. This analysis method can monitor the health status of the equipment in real time and discover safety hazards in advance. Based on the comparison of the fluctuation change time domain data with the preset threshold, the fluctuation data is intelligently marked as gradual change or sudden change. This process classifies the data according to the actual fluctuation type, so that gradual faults (such as equipment aging, poor connection) and sudden faults (such as short circuit, rapid equipment damage) are effectively distinguished, providing a clearer direction for subsequent fault location. By dividing suspicious patterns based on gradual change time domain data and sudden change time domain data, gradual change patterns and sudden change patterns are generated respectively. Through this pattern recognition, the system can more accurately identify different types of failure risks and provide reliable data support for fault prediction and timely maintenance of electrical equipment. By distinguishing between gradual and sudden change patterns, managers can take different preventive and maintenance measures according to the nature of different patterns. For example, for gradual change patterns, regular inspections or preventive maintenance can be carried out; while for sudden change patterns, immediate processing is required to prevent equipment damage or safety accidents. This precise pattern classification greatly improves the fault prediction and management capabilities of electrical equipment.

[0012] Preferably, step S24 includes the following steps: Step S241: performing power line wiring path analysis on the power line location information data of the electrical equipment to generate power line wiring path data; Step S242: using the power line wiring path data to segment the power line position information data of the electrical equipment to generate power line segmentation data, wherein the power line segmentation includes power main line segmentation and power branch line segmentation; Step S243: Mapping the power line segmentation data to the actual position information of the abnormal power line segments based on the suspicious line pattern data, and generating the suspicious power line segment position information data of the electrical equipment.

[0013] The present invention generates power line wiring path data by analyzing the path of the power line position information of the electrical equipment. This process helps the system to deeply understand the power line layout of the electrical equipment and provides basic data support for the subsequent power line segmentation and fault location. Through accurate path analysis, the system can accurately identify the overall layout of the power line and provide more comprehensive background information for further diagnosis. The power line is segmented by the power line wiring path data, and the power line is subdivided into a power main line and a power branch line. Through the detailed segmentation of the power line, the potential problems on the power line can be more clearly located. The distinction between the power main line and the branch line makes the troubleshooting more specific, and the source of the fault can be located according to different power line segments. By mapping the power line segmentation data to abnormal power line segments based on the suspicious line pattern data, the position of the suspicious power line segment is clearly marked. This process combines the abnormal mode identified in the leakage current monitoring, ensures that only the potential fault area is monitored, and improves the accuracy of the detection. Through this method, the system can quickly identify the suspicious sections on the power line, reducing the misjudgment and omission caused by the wide range in the traditional method. Through accurate power line segmentation and suspicious power line segment location, the system can quickly determine the fault location when leakage or other electrical faults occur, which greatly improves the efficiency of fault location, shortens downtime and maintenance time, and helps operation and maintenance personnel to perform repairs or replacements faster, reducing equipment downtime. By combining suspicious line patterns with power line segment mapping, the system can accurately focus on the line segment with problems, avoiding unnecessary false alarms and missed alarms. This method ensures high accuracy and efficiency of system monitoring, especially in large-scale electrical equipment networks, which can effectively avoid excessive alarms and improve operational efficiency.

[0014] Preferably, step S3 comprises the following steps: Step S31: Based on the gradual change mode, the temperature sensor is used to monitor the insulation layer temperature of the suspected power line segment of the electrical equipment using the location information data of the suspected power line segment, and the suspected power line segment insulation layer temperature monitoring data is generated; based on the sudden change mode, the temperature sensor is used to monitor the power inlet temperature of the suspected power line segment of the electrical equipment using the location information data of the suspected power line segment, and the suspected power line segment inlet temperature monitoring data is generated; Step S32: performing temperature long-term change anomaly detection on the suspected power line segment insulation layer temperature monitoring data to generate the power line segment long-term temperature anomaly change data; performing temperature instantaneous change anomaly detection on the suspected power line segment inlet temperature monitoring data to generate the line segment instantaneous temperature anomaly change data; Step S33: converting the power line segment long-term temperature abnormal change data and the line segment instantaneous temperature abnormal change data into an abnormal temperature heat map to generate an abnormal temperature change heat map; Step S34: performing temperature gradient analysis on the abnormal temperature change heat map to generate abnormal temperature change gradient data; and marking the abnormal temperature change heat map with abnormal temperature levels according to the abnormal temperature change gradient data to generate abnormal temperature change level data.

[0015] The present invention uses temperature sensors to monitor the temperature of different parts according to the gradual change mode and the sudden change mode. By monitoring the insulation layer temperature and the power inlet temperature of the suspected power line segment of the electrical equipment, the heat change in the operation of the equipment can be accurately identified under different fault modes. This mode-divided monitoring method enables temperature monitoring to adapt to different fault types, thereby improving the accuracy of fault diagnosis. By performing long-term and instantaneous abnormal detection on the insulation layer and the power inlet temperature respectively, the electrical equipment can be monitored from multiple angles from different time dimensions. Long-term temperature changes can detect temperature fluctuations caused by factors such as aging and long-term load of the equipment, while instantaneous temperature changes can timely capture high temperature fluctuations caused by sudden faults such as short circuits and overloads. This dual detection strategy enhances the early warning capability of the system and improves the reaction speed to potential dangers. By converting the long-term temperature abnormal change data and the instantaneous temperature abnormal change data into abnormal temperature change heat maps, the abnormal part of the temperature data is made more intuitive and clear. Through the display in the form of heat maps, operation and maintenance personnel can quickly identify the problem area without manually analyzing a large amount of temperature data, thereby greatly improving the efficiency of problem identification. By performing temperature gradient analysis on the abnormal temperature change heat map, the monitoring of the thermal status of the equipment is further refined. Changes in temperature gradients can reveal local hot spots in power line segments or equipment, which are often harbingers of potential failures. By generating abnormal temperature change gradient data, the system can more accurately locate specific fault points or high-risk areas, providing more accurate fault location information for operation and maintenance personnel. By marking the temperature level of the abnormal temperature change heat map, step S34 can automatically label different degrees of temperature changes, allowing managers to quickly identify which areas are at higher risk. This process can reasonably arrange inspection and maintenance priorities according to the severity of the temperature, ensure timely handling of high-risk areas, and reduce the occurrence of equipment failures and safety accidents.

[0016] Preferably, performing temperature gradient analysis on the abnormal temperature change thermal map includes: Perform color mapping on the abnormal temperature change heat map to generate abnormal temperature change color mapping data; extract pixel RGB values ​​of the abnormal temperature change heat map based on the abnormal temperature change color mapping data to obtain heat map pixel chromaticity information data; perform chromaticity color difference extreme value screening on the heat map pixel chromaticity information data to obtain pixel chromaticity color difference maximum value data and pixel chromaticity color difference minimum value data; The chromaticity difference of adjacent pixels is calculated for the chromaticity information data of the heat map pixels to obtain the difference chromaticity values ​​of adjacent pixels; the temperature gradient of the chromaticity information data of the heat map pixels is calculated by the difference chromaticity values ​​of adjacent pixels to generate the chromaticity gradient data of abnormal temperature change; The abnormal temperature change chromaticity gradient data is averaged over the gradient range using the pixel point chromaticity color difference maximum value data and the pixel point chromaticity color difference minimum value data to generate the abnormal temperature change gradient data.

[0017] The present invention can show the temperature change through different levels and depths of colors by color mapping the abnormal temperature change heat map. The color change intuitively reflects the temperature difference, so that the system can more clearly capture the spatial distribution of temperature change, laying the foundation for subsequent gradient analysis. By extracting the RGB values ​​of the heat map pixels and screening according to the extreme values ​​of chromaticity and color difference, the system can accurately identify the key areas of temperature change from complex image data. Large chromaticity differences usually correspond to parts of the equipment with large temperature fluctuations, which are at risk of failure. By screening the maximum and minimum color difference data, potential high-risk areas can be given priority, thereby effectively reducing the false alarm rate. By screening out extremely large and extremely small chromaticity and color difference data, the system can filter out areas with small or insignificant temperature changes, and focus on analyzing those parts with large temperature fluctuations, which not only improves the efficiency of analysis, but also helps locate the key points of failure. By calculating the chromaticity difference of adjacent pixels, the gradient information of temperature changes in different areas in the heat map can be revealed. The size of the temperature gradient directly reflects the drastic degree of temperature change, especially when a fault or abnormal state occurs, the temperature change is often drastic and local. By calculating the difference in chromaticity values ​​between adjacent pixels, the temperature gradient can be quantified more accurately, providing a basis for subsequent fault location and risk prediction. This process can clearly identify areas in the equipment where temperature changes are more prominent by calculating the temperature gradient in the thermal map. This is particularly important for monitoring electrical equipment, because areas with large gradients indicate overheating or failure of a part of the equipment, which requires more stringent monitoring or maintenance.

[0018] Preferably, step S4 comprises the following steps: Step S41: performing equipment abnormal line segment temperature warning on the electrical equipment information data according to the abnormal temperature change level data, and generating equipment abnormal line segment temperature warning data; Step S42: Upload the equipment abnormal line segment temperature warning data to the cloud platform for warning response feedback, generate electrical equipment abnormal warning response feedback data, and perform electrical fire warning operations.

[0019] The present invention can accurately identify the parts of the equipment with abnormal temperature changes by performing temperature warning on the electrical equipment based on the abnormal temperature change level data. This warning mechanism can timely discover the problems of overheating, short circuit, insulation damage, etc. in the equipment, so as to issue a warning in advance to avoid further equipment damage or safety accidents. Through the graded warning of the temperature change level, the severity of the temperature anomaly can be accurately judged, and the anomalies of different levels can be handled accordingly. Dangerous areas such as high temperature and overheating will be able to obtain effective responses at the earliest stage, thereby reducing the probability of catastrophic failures such as fire. The temperature warning data of the abnormal line segment of the equipment is uploaded to the cloud platform, and the powerful processing power and distributed characteristics of cloud computing are used to realize real-time processing of data and full network monitoring. Once the abnormal temperature change is detected, the system can immediately start the early warning response mechanism of the cloud platform to provide timely feedback for the on-site personnel. Through the feedback mechanism of the cloud platform, the system can automatically generate abnormal early warning response data of electrical equipment, including real-time fault location, temperature level, risk assessment and other key information. This automated response process not only improves the speed of emergency response, but also reduces the tediousness of manual operation, and improves the accuracy and timeliness of the early warning.

[0020] In this specification, an electrical fire warning device based on leakage current temperature detection is provided, which is used to execute the above-mentioned electrical fire warning method based on leakage current temperature detection. The electrical fire warning device based on leakage current temperature detection includes: The data acquisition module is used to obtain electrical equipment information data; locate the power line of the electrical equipment based on the electrical equipment information data to generate the power line position information data of the electrical equipment; collect leakage current sensor data on the power line position information data of the electrical equipment to obtain the leakage current monitoring data of the standard electrical equipment; The line segment pattern classification module is used to confirm the maximum fluctuation curve segment of the leakage current monitoring data of the standard electrical equipment to obtain the maximum fluctuation curve of the leakage current of the electrical equipment; divide the standard electrical equipment leakage current monitoring data into suspicious line patterns based on the maximum fluctuation curve of the leakage current of the electrical equipment to generate suspicious line pattern data, wherein the suspicious line pattern data includes a gradual change pattern and a sudden increase pattern; mark the suspicious line segment of the power line location information data of the electrical equipment based on the suspicious line pattern data to generate the suspicious power line segment location information data of the electrical equipment; The abnormal temperature detection module is used to perform long-term abnormal change detection of the power insulation layer based on the location information data of the suspected power line segment of the electrical equipment in a gradual change mode, and generate the long-term abnormal temperature change data of the power line segment; perform instantaneous abnormal change detection of the power input based on the location information data of the suspected power line segment of the electrical equipment in a sudden increase mode, and generate the instantaneous abnormal temperature change data of the line segment; perform thermal map temperature level annotation based on the long-term abnormal temperature change data of the power line segment and the instantaneous abnormal temperature change data of the line segment, and generate the abnormal temperature change level data; The early warning response module is used to provide early warning response feedback to the electrical equipment information data based on the abnormal temperature change level data, generate electrical equipment abnormal early warning response feedback data, and perform electrical fire early warning operations.

[0021] An electrical fire warning device based on leakage current temperature detection comprises a processor, a memory and a computer program stored in the memory and executable on the processor, and is used to execute the electrical fire warning method based on leakage current temperature detection.

[0022] The beneficial effect of the present invention is that by accurately acquiring the information data of the electrical equipment and locating the position of the power line, a foundation is laid for subsequent leakage current monitoring and fault detection. This process ensures the accuracy and relevance of the leakage current monitoring data, so that abnormal conditions in the electrical equipment can be effectively detected. By confirming the maximum fluctuation curve segment of the leakage current monitoring data of the standard electrical equipment, the fluctuation range in the leakage current data can be accurately identified, providing an accurate basis for further analyzing the state of the electrical equipment. Based on the maximum fluctuation curve segment, the leakage current monitoring data is divided into modes, and the abnormal mode of the leakage current is divided into a gradual change mode and a sudden increase mode. This can further refine the abnormal type of the equipment, so that the monitoring system can analyze and identify different types of potential faults in a targeted manner. Based on the gradual change mode, the long-term change abnormality detection of the power insulation layer is carried out, and the abnormal fluctuation of the temperature over a long period of time can be detected, so that the temperature change problem caused by aging or damage of the power line can be discovered early, thereby reducing the risk of fire. Based on the sudden increase change mode, the instantaneous temperature change of the power inlet is detected, which can capture sudden temperature anomalies in time, especially changes related to the instantaneous load or fault of the electrical equipment, ensuring that potential dangers can be responded to quickly. By marking the temperature level of the thermal map, a different temperature level is assigned to each abnormal temperature change area, so that the severity and potential risks of the temperature anomaly can be quantified, further improving the accuracy of fault warning. According to the generated abnormal temperature change level data, the electrical equipment is given an immediate early warning response feedback. This process can help managers to detect abnormalities in time and take corresponding disposal measures to prevent temperature anomalies from further developing into serious accidents such as electrical fires. Therefore, the present invention improves the accuracy, response speed and positioning capability of the electrical fire early warning system by introducing leakage current fluctuation pattern recognition, precise power line positioning, intelligent anomaly detection and thermal map analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram of the steps of an electrical fire warning method based on leakage current temperature detection; Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart; Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG. The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0024] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0025] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0026] It should be understood that although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, and the term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0027] To achieve this, please refer to Figures 1 to 3 , an electrical fire early warning method based on leakage current temperature detection, the method comprising the following steps: Step S1: Acquire electrical equipment information data; locate the power line of the electrical equipment according to the electrical equipment information data to generate the power line position information data of the electrical equipment; collect leakage current sensor data of the power line position information data of the electrical equipment to obtain standard electrical equipment leakage current monitoring data; Step S2: Confirm the maximum fluctuation curve segment of the leakage current monitoring data of the standard electrical equipment to obtain the maximum fluctuation curve of the leakage current of the electrical equipment; divide the standard electrical equipment leakage current monitoring data into suspicious line modes based on the maximum fluctuation curve of the leakage current of the electrical equipment to generate suspicious line mode data, wherein the suspicious line mode data includes a gradual change mode and a sudden increase mode; mark the suspicious line segment of the power line location information data of the electrical equipment based on the suspicious line mode data to generate the suspicious power line segment location information data of the electrical equipment; Step S3: Based on the gradual change mode, the position information data of the suspected power line segment of the electrical equipment is used to detect the long-term abnormal change of the power insulation layer, and generate the long-term abnormal temperature change data of the power line segment; based on the position information data of the suspected power line segment of the electrical equipment in the sudden increase mode, the instantaneous abnormal change of the power input is detected, and the instantaneous abnormal temperature change data of the line segment is generated; based on the long-term abnormal temperature change data of the power line segment and the instantaneous abnormal temperature change data of the line segment, the temperature level of the thermal map is marked to generate the abnormal temperature change level data; Step S4: Perform early warning response feedback on the electrical equipment information data according to the abnormal temperature change level data, generate electrical equipment abnormal early warning response feedback data, and perform electrical fire early warning operations.

[0028] The present invention can ensure the accuracy of subsequent leakage current monitoring by obtaining detailed information of electrical equipment and accurately locating the position of the power line. The clear calibration of the power line position enables the leakage current sensor to monitor key areas in a targeted manner, avoiding the problem of inaccurate or incomplete installation of the leakage current sensor in the traditional method. By performing fluctuation curve analysis on the leakage current monitoring data, potential fault signals in the electrical equipment can be identified earlier. The maximum fluctuation of the leakage current usually means an abnormal state of the electrical equipment (such as aging of the insulation layer, poor contact, etc.). Dividing the leakage current fluctuation mode into a gradual change mode and a sudden increase mode helps to distinguish different types of faults: the gradual change mode indicates a long-term accumulated hidden danger, and the sudden increase mode is usually related to sudden electrical faults, which enables the system to take different early warning and processing measures according to different modes, thereby improving the accuracy of the early warning and the response speed. By combining the gradual change mode and the sudden increase mode, the long-term abnormality detection and instantaneous abnormality detection of the power line segment are performed respectively, so that the long-term accumulated temperature changes and sudden changes can be distinguished, which helps to accurately distinguish the hidden fire risks in electrical equipment (such as temperature changes caused by long-term aging or wear of the power insulation layer) from sudden electrical faults (such as instantaneous temperature rise caused by a sudden increase in current). By marking the abnormal temperature changes of the power line segment with the temperature level of the heat map and generating the corresponding abnormal temperature change level data, the fire risk of the electrical equipment can be intuitively displayed. The marking of the temperature change level can more accurately reflect the severity of the fire risk, thereby providing a more scientific basis for the subsequent early warning response. Based on these data, the system can issue early warnings in time and formulate targeted response measures according to the temperature change level. For example, when the temperature change reaches a certain threshold, the system can automatically cut off the power supply, start the fire fighting equipment or notify the relevant personnel to handle it. In this way, it not only improves the early warning capability of fire, but also takes preventive measures before the fire occurs to reduce the incidence of electrical fires. Therefore, the present invention improves the accuracy, response speed and positioning capability of the electrical fire warning system by introducing leakage current fluctuation pattern recognition, precise power line positioning, intelligent anomaly detection and thermal map analysis.

[0029] In the embodiment of the present invention, reference Figure 1 FIG. 1 is a schematic diagram of a step flow of an electrical fire early warning method based on leakage current temperature detection of the present invention. In this example, the electrical fire early warning method based on leakage current temperature detection includes the following steps: Step S1: Acquire electrical equipment information data; locate the power line of the electrical equipment according to the electrical equipment information data to generate the power line position information data of the electrical equipment; collect leakage current sensor data of the power line position information data of the electrical equipment to obtain standard electrical equipment leakage current monitoring data; In an embodiment of the present invention, the electrical equipment information data includes information such as the model, usage parameters, working status, and installation location of the equipment, which can usually be obtained through the equipment management system, documents provided by the manufacturer, or automated configuration tools during the installation process. Detailed information of the equipment is automatically obtained by scanning a QR code, RFID, or through an intelligent management interface of the electrical equipment (such as Modbus, BACnet, etc.). In the absence of automated equipment, electrical equipment information data such as equipment model, installation location, voltage rating, etc. can be manually input. According to the installation location of the electrical equipment and the electrical wiring diagram, the path and location of the power cord are determined through the equipment topology diagram (such as CAD drawings, electronic wiring diagrams, etc.). The topology diagram provides information such as the equipment, terminals, and connection paths connected to the power cord. If there is no ready-made electrical wiring diagram, the position of the power cord can be manually calibrated through on-site surveys, handheld GPS devices, or laser rangefinders. Use sensors with positioning functions (such as radio frequency identification technology, fiber optic sensors, etc.) to determine the precise location of the power cord. Use geographic information system (GIS) tools or three-dimensional modeling software (such as AutoCAD, Revit, etc.) to digitize the location information of the power cord to generate precise location information data of the power cord of the electrical equipment. The power line location information data includes: the starting point, end point, path, laying location (ground, inside the wall, underground pipeline, etc.), and installation method (through pipes, open wires, underground laying, etc.) of each power line. Select leakage current sensors suitable for electrical equipment. Common leakage current sensors include residual current sensors (RCD) and Hall effect sensors, which can detect whether there is leakage current in the power line and provide real-time data. According to the power line location information, select the location to install the leakage current sensor. The sensor is usually installed at the incoming end of the power line, or in key distribution boxes, distribution cabinets, sockets, etc. Through the principle of electromagnetic induction, the leakage current sensor detects any imbalance when the current flows through the power line (such as the current difference between the phase line and the neutral line), so as to determine whether leakage occurs. After installation, the leakage current sensor transmits the monitored leakage current data to the data acquisition module (such as PLC, smart sensor hub, etc.) by wireless or wired means, and further uploads it to the cloud platform or local monitoring system. Set the accuracy and frequency of data acquisition according to actual needs. Usually, leakage current data is collected once per second, every minute or every hour, and stored as time series data. Based on the collected leakage current data, preprocessing and standardization are performed to generate standard electrical equipment leakage current monitoring data, which includes: leakage current value of each electrical equipment, monitoring time, sensor location, equipment status and other information.

[0030] Step S2: Confirm the maximum fluctuation curve segment of the leakage current monitoring data of the standard electrical equipment to obtain the maximum fluctuation curve of the leakage current of the electrical equipment; divide the standard electrical equipment leakage current monitoring data into suspicious line modes based on the maximum fluctuation curve of the leakage current of the electrical equipment to generate suspicious line mode data, wherein the suspicious line mode data includes a gradual change mode and a sudden increase mode; mark the suspicious line segment of the power line location information data of the electrical equipment based on the suspicious line mode data to generate the suspicious power line segment location information data of the electrical equipment; In an embodiment of the present invention, the original leakage current monitoring data is preprocessed. Data preprocessing includes denoising, filling missing values, smoothing signals, etc., to ensure that the data quality is high enough to accurately analyze the fluctuation curve. Signal smoothing technology (such as sliding average filter, low-pass filter) is used to remove high-frequency noise. Using the processed leakage current monitoring data, a fluctuation curve of the leakage current over time is drawn. This curve reflects the time series change of the leakage current. By calculating the change amplitude of the fluctuation curve, the maximum fluctuation section, that is, the area where the leakage current fluctuates greatly, is identified. A peak detection algorithm can be used to identify the maximum and minimum values ​​of the fluctuation. By calculating the peak and valley values ​​of the curve, the interval of the maximum fluctuation is determined, which is caused by power load fluctuations, equipment startup / shutdown, etc. The identified fluctuation segments are standardized to eliminate the influence of factors such as equipment and time intervals, so that the identification of the fluctuation segments is more consistent and accurate. Set a fluctuation amplitude threshold (such as a significant fluctuation if the leakage current changes by more than 0.5A within 5 seconds) to confirm the maximum fluctuation section. The fluctuation segment greater than this threshold is the "maximum fluctuation segment". As the basis for subsequent analysis, the maximum fluctuation curve of the leakage current of the electrical equipment is generated. The curve identifies the time period and the corresponding leakage current value when the large fluctuation occurs. The gradually increasing or decreasing leakage current fluctuation mode is usually related to the gradual aging of electrical equipment, the increase of load or the early stage of failure. The fluctuation of this mode has a slow and stable change trend and a low fluctuation rate. The sudden and drastic leakage current change in a short period of time is usually caused by equipment failure, short circuit, grounding fault or other emergencies. The fluctuation of this mode is very short in time and the change amplitude is large. Analyze each fluctuation segment on the maximum fluctuation curve, and combine the preset fluctuation amplitude threshold and change rate to determine whether it belongs to the gradual change mode or the sudden increase mode. Gradual change mode: The change rate of the fluctuation is less than a certain threshold and the duration is long. Sudden increase mode: The change rate of the fluctuation is greater than a certain threshold and the duration is short. Use statistical methods (such as standard deviation, mean value, etc.) to analyze the characteristics of the frequency, duration, amplitude and other characteristics of the fluctuation, and automatically divide the fluctuation curve segments into two types of modes. On the basis of pattern recognition, suspicious line pattern data is generated, including the identification, occurrence time, fluctuation amplitude and other information of the gradual change pattern and the sudden increase pattern. By analyzing the location information of the power line of the electrical equipment, determine which power line segments are related to the suspicious line pattern (gradual change pattern or sudden increase pattern). The specific method includes: comparing the workload, historical fault records and location (such as high-load area, vulnerable area, etc.) of the power line, and inferring which power line segments have abnormal fluctuations. Use the equipment topology map and power line location data, combined with the monitoring data of the leakage current sensor, to associate the relationship between the specific power line segment and the suspicious pattern. Based on the above analysis results, mark the location information data of the power line of the electrical equipment to determine the power line segment where the fault occurs.In the power line location data, a "suspicious" mark field is added to indicate which power line segments have problems. A unique identifier can be generated for each suspicious segment to facilitate subsequent tracking and analysis. Finally, a set of suspicious power line segment location information data for electrical equipment is generated, including the specific location of the suspicious power line segment, the type of fluctuation pattern (gradual change or sudden increase), the time interval of occurrence, the equipment involved, etc.

[0031] Step S3: Based on the gradual change mode, the position information data of the suspected power line segment of the electrical equipment is used to detect the long-term abnormal change of the power insulation layer, and generate the long-term abnormal temperature change data of the power line segment; based on the position information data of the suspected power line segment of the electrical equipment in the sudden increase mode, the instantaneous abnormal change of the power input is detected, and the instantaneous abnormal temperature change data of the line segment is generated; based on the long-term abnormal temperature change data of the power line segment and the instantaneous abnormal temperature change data of the line segment, the temperature level of the thermal map is marked to generate the abnormal temperature change level data; In the embodiment of the present invention, the suspicious power line segment has been determined by the progressive change pattern of the leakage current data. Long-term temperature monitoring is performed based on these suspicious line segments, mainly detecting the temperature change of the insulation layer of the power line segment. A temperature sensor is installed on the insulation layer of the power line segment to monitor the temperature change of this part. The data collected by the sensor is used to analyze the long-term change of temperature. The time series data analysis method is used to observe the change trend of temperature over time, especially the temperature change amplitude. The set temperature threshold is used for abnormal detection. If the temperature change amplitude exceeds the preset threshold, it is determined to be temperature abnormal. The long-term abnormal temperature change data will contain information such as the peak value, duration, and change amplitude of the temperature. According to the temperature change curve, the long-term abnormal temperature change data is extracted, including the temperature fluctuation amplitude, duration, change trend, etc. Through these data, it can be judged whether the power line segment has abnormal temperature rise caused by reasons such as long-term excessive load or aging of insulation materials. The sudden increase mode usually means that the current or load of the electrical equipment suddenly increases, causing the instantaneous temperature of the power line segment to rise sharply, which is caused by sudden situations such as short circuit, ground fault or equipment failure. According to the sudden increase fluctuation pattern identified in step S2, further temperature anomaly detection is performed on these suspicious line segments. A temperature sensor is installed at the entrance of the power line segment to monitor the temperature change at the entrance of the power line. The instantaneous temperature data of the power entrance is collected, with special attention to the sharp fluctuation of temperature when the power load changes or equipment failure occurs. The temperature data is analyzed, and a fast change detection algorithm (such as fast Fourier transform, mutation detection algorithm, etc.) is used to identify sudden increase fluctuations. If the temperature change rate exceeds the preset sudden increase threshold, it is determined to be an instantaneous temperature anomaly. Output the instantaneous temperature abnormal change data of the line segment, which contains information such as the occurrence time, change rate, and maximum value of the abnormal temperature. Combine the long-term temperature abnormal change data of the power line segment and the instantaneous temperature abnormal change data of the line segment to generate a temperature abnormal change heat map. The heat map will show the temperature abnormal changes in different areas of the power line segment in different time periods. Different colors in the heat map represent different degrees of temperature change. Common color mappings are: blue for low temperature, yellow for medium temperature, and red for high temperature. The generated abnormal temperature change heat map is analyzed, and the temperature gradient analysis (as mentioned in step S2) is used to calibrate the temperature levels of different areas. According to the actual temperature value and the set threshold, the temperature range in the heat map is divided into different levels. For example: Low temperature (normal): The temperature change is less than the set normal working range. Moderate abnormality: The temperature change is within the set warning range. High temperature (dangerous): The temperature change exceeds the set alarm threshold and there is a fire risk. Based on the results of the heat map annotation, abnormal temperature change level data is generated, including the temperature change level of each power line segment (normal, warning, dangerous) and the time period and location of occurrence.The output abnormal temperature change level data will serve as the basic data for subsequent alarm, maintenance, inspection and other decisions. This data can not only help detect potential fire risks, but also provide a basis for equipment maintenance.

[0032] Step S4: Perform early warning response feedback on the electrical equipment information data according to the abnormal temperature change level data, generate electrical equipment abnormal early warning response feedback data, and perform electrical fire early warning operations.

[0033] In the embodiment of the present invention, the warning threshold is set according to actual needs. For example, when the temperature change level is "dangerous", a high priority warning is triggered; when the level is "warning", a medium priority warning is triggered. Normal levels are not processed. Temperature warnings can be based on different temperature change amplitudes (such as changes above 5°C are warnings, and changes above 10°C are dangerous), as well as change times (such as continuous high temperatures for more than a certain period of time are warnings). The temperature warning model is used to respond to abnormal temperature change level data to generate abnormal line segment temperature warning data for electrical equipment. According to the above analysis, the generated abnormal line segment temperature warning data of the equipment can be used as a system feedback and decision-making basis to further determine whether it is necessary to manually inspect the equipment or take other preventive measures. The generated abnormal line segment temperature warning data of the electrical equipment is uploaded to the cloud platform, and the cloud platform will serve as a centralized monitoring and feedback management system. The existing Internet of Things (IoT) or big data platform can be used for data collection and transmission. After receiving the data, the cloud platform performs subsequent automated processing and feedback according to preset business rules and response strategies. On the cloud platform, an alarm response mechanism is set. When the temperature abnormality level reaches the warning or danger level, the system will: automatically generate a warning notification and send it to relevant personnel (such as electrical engineers, safety officers or equipment maintenance personnel). Start the real-time monitoring mechanism, conduct more intensive monitoring and data collection on abnormal power line segments, generate accident investigation processes and emergency response processes, provide support for subsequent operations, and generate abnormal warning response feedback data for electrical equipment.

[0034] Preferably, step S1 comprises the following steps: Step S11: Acquire electrical equipment information data; Step S12: performing electrical equipment topology analysis on the electrical equipment information data to generate electrical equipment topology data; locating the electrical equipment power line position of the electrical equipment information data based on the electrical equipment topology data to generate electrical equipment power line position information data; Step S13: deploying leakage current sensors on the power line location information data of the electrical equipment based on a preset distance interval to obtain leakage current sensor deployment data; performing wireless data collection on the leakage current sensor deployment data to obtain leakage current monitoring data of the electrical equipment; Step S14: preprocess the electrical equipment leakage current monitoring data to generate standard electrical equipment leakage current monitoring data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization.

[0035] In an embodiment of the present invention, basic information of electrical equipment, including equipment type, voltage, current, load status, working time, etc., is collected through an Internet of Things (IoT) sensor network. Equipment information is integrated from different data sources (such as SCADA system, equipment management system, sensor equipment, etc.) into a unified data platform to ensure the comprehensiveness and accuracy of the data. Topological modeling of electrical equipment is performed using graph theory methods. By analyzing the connection relationship, load distribution, power flow direction, etc. between devices, the electrical connection structure (i.e., topological structure) between devices is generated, and a topological diagram of the electrical equipment is generated, including device nodes, connecting lines, power supply paths, etc. The topological diagram can effectively represent the layout and mutual relationship of electrical equipment, which is convenient for subsequent monitoring and fault location. Based on the topological data, the power line of the equipment is accurately identified, and the position data of the power line of the electrical equipment is generated through a graphic positioning algorithm. According to the topological data of the power line and the preset distance interval, the deployment position of each power line segment is calculated. Generally, the deployment interval of the sensor should be set according to factors such as the length of the power line and the current load to ensure that the entire electrical equipment network can be covered and the leakage current monitoring requirements are met. Select a leakage current sensor suitable for the electrical equipment to ensure that the sensor can monitor the leakage current in real time and has high accuracy and stability. The sensor type can be a Hall sensor, current transformer, etc., to generate deployment data of the leakage current sensor, including sensor location, deployment plan, device number, etc. Wireless communication technology (such as Wi-Fi, LoRa, Zigbee, etc.) is used for data collection, and the sensor data is sent to the central processing system or cloud platform through the wireless network. Ensure that the collected leakage current monitoring data can be uploaded in real time, and verify the integrity of time synchronization and data transmission. Remove outliers, duplicate values, or incomplete data points in the data. Use statistical methods (such as mean, median filtering, etc.) for repair. Use digital filtering technology (such as low-pass filter, Kalman filter, etc.) to remove noise in the collection process to ensure the accuracy of monitoring data. For missing values ​​caused by signal loss or equipment failure, interpolation methods (such as linear interpolation, Lagrange interpolation, etc.) are used to fill in missing data. Standardize the data so that the monitoring data of different devices and different time periods have consistent dimensions, which is convenient for subsequent analysis and modeling. Common methods include z-score standardization or min-max normalization.

[0036] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes: Step S21: converting the standard electrical equipment leakage current monitoring data into a time-series leakage current monitoring curve to generate an electrical equipment leakage current curve; extracting the peak current of the electrical equipment leakage current curve to obtain the peak leakage current data of the electrical equipment; calculating the variation amplitude of the electrical equipment leakage current curve based on the peak leakage current of the electrical equipment to obtain the peak variation amplitude data of the electrical equipment; Step S22: confirming the maximum fluctuation curve segment of the standard electrical equipment leakage current monitoring data according to the electrical equipment peak leakage current data and the electrical equipment peak variation amplitude data, and obtaining the electrical equipment leakage current maximum fluctuation curve; Step S23: dividing the standard electrical equipment leakage current monitoring data into suspicious line modes based on the maximum fluctuation curve of the electrical equipment leakage current, and generating suspicious line mode data, wherein the suspicious line mode data includes a gradual change mode and a sudden increase mode; Step S24: marking the suspicious line segments of the power line location information data of the electrical equipment based on the suspicious line pattern data to generate the suspicious power line segment location information data of the electrical equipment.

[0037] In an embodiment of the present invention, the leakage current monitoring data of standard electrical equipment is converted into a leakage current monitoring curve according to a time series. Each data point corresponds to a leakage current value at a specific time, and the data is sorted by a timestamp to generate a curve graph of leakage current changing over time. In the leakage current monitoring curve, a peak detection algorithm (such as a local maximum algorithm) is used to extract the peak current in the curve. Usually, the peak current represents a key indicator of abnormal load or electrical state of the electrical equipment, and the peak value can be extracted by mathematical methods such as a moving window or a threshold-based method. The maximum leakage current value of each time period is calculated, and these values ​​are recorded as "electrical equipment peak leakage current data". Based on the extracted peak leakage current data, the change amplitude between each time period is calculated. The change amplitude is the change value of the peak current, and a simple difference calculation formula can be used: change amplitude = peak current at the current moment - peak current at the previous moment; generate electrical equipment peak change amplitude data as a quantitative description of the fluctuation of the equipment state. According to the peak leakage current data and the peak change amplitude data of the electrical equipment, the part with a larger fluctuation amplitude in the leakage current curve is identified. By setting a threshold value for the fluctuation amplitude, the time period whose fluctuation exceeds the set standard is screened out to form a "maximum fluctuation curve segment". The specific operation can be performed by calculating the peak current and change amplitude in each time period, and selecting the part with a change amplitude greater than a certain critical value as the maximum fluctuation segment. For each detected fluctuation segment, its starting point and end point can be extracted, marked as the "maximum fluctuation curve segment", and the reasons behind it can be further analyzed. The gradual change mode is usually manifested as a trend of gradual increase in leakage current. By analyzing the rising part of the leakage current curve, the fluctuation segments with relatively gentle changes and longer duration are identified. These segments can be regarded as gradual change patterns. For each gradually increasing fluctuation segment, the rate of change of the leakage current over time (such as the slope) is calculated to determine whether it conforms to the gradual pattern. The sudden increase mode is manifested as a sudden increase in leakage current in a short period of time. By analyzing the peak change amplitude data, the segments where the leakage current suddenly changes in a very short period of time are identified. These segments are sudden increase modes. The detection of sudden increase modes can be based on the "jumping" fluctuation characteristics, looking for sudden large fluctuations and marking them. Use classification algorithms (such as threshold judgment, cluster analysis, etc.) to divide the maximum fluctuation curve into patterns. Finally, suspicious line pattern data is generated, indicating whether each segment is a gradual change pattern or a sudden increase pattern. The identified suspicious line pattern (gradual change pattern or sudden increase pattern) is combined with the power line topology data of the electrical equipment to mark the line segment with abnormal leakage current. By combining with the topological relationship of the power line, the specific line segment position can be accurately located. For example, if the leakage current curve of a certain power line segment shows a gradual increase pattern, the power line segment is marked as a "suspicious power line segment".All suspicious line segments are numbered and recorded, including their specific location in the electrical equipment, the power line they belong to, the type of pattern detected (gradual or sudden), and the location information data of the suspicious power line segment is generated. This data can be used for subsequent maintenance and fault diagnosis.

[0038] Preferably, step S23 includes the following steps: Step S231: extracting the maximum fluctuation point and the minimum fluctuation point based on the maximum fluctuation curve of the leakage current of the electrical equipment, and obtaining the maximum fluctuation point data and the minimum fluctuation point data of the leakage current of the electrical equipment; Step S232: performing a time domain analysis on the maximum fluctuation point data of the leakage current of the electrical equipment and the minimum fluctuation point data of the leakage current of the electrical equipment to generate fluctuation change time domain data; comparing the fluctuation change time domain data with a preset standard fluctuation time domain threshold, and when the fluctuation change time domain data is greater than or equal to the preset standard fluctuation time domain threshold, marking the corresponding fluctuation change time domain data as progressive change time domain data; Step S233: when the fluctuation change time domain data is less than the preset standard fluctuation time domain threshold, the corresponding fluctuation change time domain data is marked as sudden increase change time domain data; based on the gradual change time domain data, the standard electrical equipment leakage current monitoring data is divided into a first suspicious mode to generate a gradual change mode; Step S234: performing a second suspicious pattern classification on the standard electrical equipment leakage current monitoring data based on the sudden increase change time domain data to generate a sudden increase type change pattern.

[0039] In an embodiment of the present invention, by analyzing the leakage current monitoring curve of the electrical equipment, a peak detection algorithm (such as a local maximum algorithm) is used to extract the maximum fluctuation point. The maximum fluctuation point indicates that the leakage current value reaches the highest peak within a certain period of time. The maximum fluctuation value of each time period is calculated and marked as the "maximum fluctuation point". These points can be captured and extracted by a sliding window method or an algorithm based on the amplitude of fluctuations. Similarly, the minimum fluctuation point in the curve is extracted by a local minimum detection method. The minimum fluctuation point indicates the lowest point of the leakage current value within a certain period of time. The minimum fluctuation point is determined and recorded by the reverse operation of the peak extraction algorithm (local minimum detection). The extracted maximum fluctuation point and minimum fluctuation point respectively form two data sets: the maximum fluctuation point data of the leakage current of the electrical equipment and the minimum fluctuation point data of the leakage current of the electrical equipment, which provide a basis for subsequent time domain analysis. The extracted maximum fluctuation point and minimum fluctuation point data are analyzed in the time domain. The specific method is to calculate the time interval between each fluctuation point and analyze the current change rate between the fluctuation points, usually using the difference method: the change amount = the fluctuation point current at the current moment - the fluctuation point current at the previous moment. The current change rate between each pair of maximum and minimum fluctuation points is arranged in chronological order to form a complete set of "fluctuation change time domain data". The generated fluctuation change time domain data is compared with the preset standard fluctuation time domain threshold. The standard fluctuation time domain threshold can be determined by historical data or empirical model, indicating the acceptable range of fluctuation under normal circumstances. When the fluctuation change time domain data is greater than or equal to the threshold, it means that the fluctuation has a trend of gradual change. For the fluctuation data that meets the conditions, it is marked as "gradual change time domain data", indicating that the leakage current has a trend of gradual increase, indicating potential equipment aging, load increase or other gradual faults. When the fluctuation change time domain data is less than the standard fluctuation time domain threshold, it means that the leakage current has a sudden increase in a short period of time, which belongs to the sudden increase type change mode. These fluctuation data are marked as "sudden increase change time domain data". According to the part marked as gradual change time domain data, the first round of suspicious pattern division is carried out. The specific manifestation of the gradual change mode is determined using a preset pattern recognition algorithm (such as based on the characteristics of fluctuation amplitude, fluctuation duration, etc.). For fluctuations that appear to increase gradually, a "progressive change pattern" can be generated, and the cause of the fault can be further analyzed, such as electrical equipment overload, poor contact, etc. Based on the sudden change time domain data, a second round of suspicious pattern division is performed. This pattern indicates that the leakage current fluctuates violently in a very short period of time, usually indicating a sudden electrical fault (such as electrical short circuit, poor contact, etc.). The sudden change pattern can be confirmed by methods based on the change amplitude and mutation point detection, and a "sudden change pattern" can be generated. By calculating and analyzing the sudden change data, the "sudden change pattern" is generated and marked to provide a basis for subsequent fault diagnosis.

[0040] Preferably, step S24 includes the following steps: Step S241: performing power line wiring path analysis on the power line location information data of the electrical equipment to generate power line wiring path data; Step S242: using the power line wiring path data to segment the power line position information data of the electrical equipment to generate power line segmentation data, wherein the power line segmentation includes power main line segmentation and power branch line segmentation; Step S243: Mapping the power line segmentation data to the actual position information of the abnormal power line segments based on the suspicious line pattern data, and generating the suspicious power line segment position information data of the electrical equipment.

[0041] In an embodiment of the present invention, the actual wiring path of the power line is analyzed according to the power line location information data of the electrical equipment. The wiring path analysis usually needs to be combined with the topological structure of the electrical equipment, the device connection method and the actual installed power line location. The overall layout path of the power line is analyzed by a geographic information system (GIS) or other path analysis algorithms (such as Dijkstra algorithm, etc.), and these path data may include the layout of the main power line and its branch lines, as well as the connection relationship of the power line. Through the wiring path analysis, a detailed power line wiring path data set is generated, which includes the starting point, end point, each key node, branch point, connection point and other information of the power line. The path data can be represented by a grid or a coordinate system, and specifically may include the direction, distance, and paragraph information of the power line. According to the power line wiring path data, the power line location information data of the electrical equipment is accurately segmented into power line segments. The basis for segmentation is usually the connection point, branch point and specific section of the power line. The segmentation can be based on the key nodes on the path (such as joints, electrical equipment access points, branch locations, etc.), and these key nodes serve as natural breakpoints for segmentation, so that the power line can be divided into several segments. The main power line is segmented to identify the various sections in the main power line. In this segmentation process, the main power line segment is the main line from the power input end to the device distribution point. The segmented main line segment may include information such as the connection part where the power enters the device, the access point between the main lines, etc. Identify and segment the branch lines of the power supply. Branch lines are usually lines extending from the main power line to connect electrical equipment. Each branch line has different loads and failure risks. Separate segmentation of these branch lines can help subsequent detection to locate the specific location of the fault more accurately. Through the above analysis and segmentation, power line segmentation data is generated. Each segmented power line segment will include its starting and ending nodes, length, path and other information for use in subsequent analysis. According to the suspicious line pattern data obtained in step S23, combined with the power line segmentation data, each power line segment is mapped to an abnormal position. The suspicious line pattern data includes a gradual change mode and a sudden increase change mode, which can help identify power line segments with abnormal current fluctuations. According to the identified suspicious line mode, it is determined whether each power line segment has current abnormality. If the current anomaly manifests as a gradual change or a sudden increase, mark these power line segments as "suspicious power line segments". When mapping, the location information in the power line wiring path data can be combined to associate the suspicious power line segments with specific physical locations. Based on the mapping of abnormal power line segments, generate suspicious power line segment location information data. This data set will include the location, segment information, and fault type (such as gradual change or sudden change) of all power line segments where abnormal fluctuations are detected. The suspicious power line segment location information data will be helpful for subsequent equipment maintenance and fault location, and provide maintenance personnel with accurate inspection and analysis guidance.

[0042] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes: Step S31: Based on the gradual change mode, the temperature sensor is used to monitor the insulation layer temperature of the suspected power line segment of the electrical equipment using the location information data of the suspected power line segment, and the suspected power line segment insulation layer temperature monitoring data is generated; based on the sudden change mode, the temperature sensor is used to monitor the power inlet temperature of the suspected power line segment of the electrical equipment using the location information data of the suspected power line segment, and the suspected power line segment inlet temperature monitoring data is generated; Step S32: performing temperature long-term change anomaly detection on the suspected power line segment insulation layer temperature monitoring data to generate the power line segment long-term temperature anomaly change data; performing temperature instantaneous change anomaly detection on the suspected power line segment inlet temperature monitoring data to generate the line segment instantaneous temperature anomaly change data; Step S33: converting the power line segment long-term temperature abnormal change data and the line segment instantaneous temperature abnormal change data into an abnormal temperature heat map to generate an abnormal temperature change heat map; Step S34: performing temperature gradient analysis on the abnormal temperature change heat map to generate abnormal temperature change gradient data; and marking the abnormal temperature change heat map with abnormal temperature levels according to the abnormal temperature change gradient data to generate abnormal temperature change level data.

[0043] In an embodiment of the present invention, after a progressive change pattern is detected, a temperature sensor is used to perform continuous temperature monitoring on the insulation layer of a suspected power line segment of an electrical device. The sensor should be installed at key locations of the power line segment, such as joints, bends, or areas with heavy current loads, to monitor the temperature changes of the insulation layer of the power line in real time. The generated insulation layer temperature monitoring data of the suspected power line segment includes real-time temperature changes, temperature trends, and temperature change rates. For a sudden increase type change pattern detected, the temperature sensor is installed at the entrance of the power line segment, such as the power access port of the electrical device. Monitor the temperature fluctuations at the power input end, especially the temperature rise caused by a sudden increase in current. The generated entrance temperature monitoring data of the suspected power line segment includes the temperature changes at the input end, with special attention paid to the sudden increase in temperature and its duration. Perform long-term temperature change anomaly detection on the insulation layer temperature monitoring data of the suspected power line segment to check whether there is a temperature increase trend beyond the normal range. Sliding windows and anomaly detection algorithms (such as Z-score-based methods) can be used to identify whether the temperature changes abnormally over a long period of time. For example, if the temperature continues to rise above a certain threshold, the generated long-term abnormal temperature change data of the power line segment will record the detected long-term abnormal temperature fluctuations, including the temperature increase amplitude, duration, and temperature change trend. Instantaneous temperature anomaly detection is performed on the temperature monitoring data at the entrance of the power line segment. In the sudden increase change mode, the temperature sudden rise phenomenon is detected. An algorithm based on the instantaneous change rate can be used to identify drastic changes in temperature in a short period of time, especially a short temperature jump at the power entrance. The generated line segment instantaneous temperature abnormal change data records all instantaneous abnormal temperature events, highlighting the instantaneous temperature change amplitude and duration. The long-term temperature abnormal change data is combined with the instantaneous temperature abnormal change data to perform abnormal temperature heat map conversion. This heat map can visualize the temperature change trend on the power line segment and mark the degree of temperature abnormality at each location. The temperature data of each monitoring point of the power line segment is mapped to the heat map through a coordinate system (such as a two-dimensional or three-dimensional coordinate). Different temperature change amplitudes and rates will be marked with different colors to indicate different temperature abnormality levels. The abnormal temperature change heat map will show temperature hot spots, especially those areas with long-term high temperatures or sudden temperature increases. These areas need special attention. The heat map can be color-coded according to the spatial location of the monitoring point and the size of the abnormal temperature change, using a heat map style (such as red for high temperature anomalies and blue for normal areas) to represent temperature changes. Perform temperature gradient analysis on the abnormal temperature change heat map to detect the intensity and range of temperature changes. Gradient analysis can use gradient operators (such as the Sobel operator) or smoothing and then perform differential calculations to find the areas with the fastest temperature changes. The temperature gradient indicates the rate and direction of temperature change from low to high. The abnormal temperature change gradient data will record the areas with the most dramatic temperature changes, which are usually associated with potential fault points or power line damage.According to the temperature gradient data, the abnormal temperature heat map is graded and the different degrees of temperature anomalies are graded. Common temperature anomaly grades can include: normal (green), mild anomaly (yellow), moderate anomaly (orange), severe anomaly (red). The abnormal temperature change grade data will include the temperature anomaly grade of each location, which can help maintenance personnel quickly identify the most dangerous power line segments.

[0044] Preferably, performing temperature gradient analysis on the abnormal temperature change thermal map includes: Perform color mapping on the abnormal temperature change heat map to generate abnormal temperature change color mapping data; extract pixel RGB values ​​of the abnormal temperature change heat map based on the abnormal temperature change color mapping data to obtain heat map pixel chromaticity information data; perform chromaticity color difference extreme value screening on the heat map pixel chromaticity information data to obtain pixel chromaticity color difference maximum value data and pixel chromaticity color difference minimum value data; The chromaticity difference of adjacent pixels is calculated for the chromaticity information data of the heat map pixels to obtain the difference chromaticity values ​​of adjacent pixels; the temperature gradient of the chromaticity information data of the heat map pixels is calculated by the difference chromaticity values ​​of adjacent pixels to generate the chromaticity gradient data of abnormal temperature change; The abnormal temperature change chromaticity gradient data is averaged over the gradient range using the pixel point chromaticity color difference maximum value data and the pixel point chromaticity color difference minimum value data to generate the abnormal temperature change gradient data.

[0045] In an embodiment of the present invention, by color mapping the abnormal temperature change heat map, different temperature values ​​are corresponded to specific colors. For example, the low temperature area is represented by blue, the medium temperature is represented by yellow, and the high temperature is represented by red. Color mapping is usually based on the temperature interval setting, and the temperature value range is divided into several levels, each level corresponds to a color. Common color mapping methods include linear mapping or nonlinear mapping. According to the temperature change range, the temperature data of the heat map is mapped to the corresponding color value. For example, if the temperature change range is 0°C to 100°C, it is mapped to green when the temperature is 20°C and mapped to red when the temperature is 80°C. The generated abnormal temperature change color mapping data will include the color information of each pixel and the corresponding temperature value. The color mapping value of each heat map pixel is extracted and converted into three components in the RGB (red, green, blue) color mode. The RGB value consists of three integer values ​​(R, G, B), which represent the intensity of red, green and blue. For example, red represents RGB (255, 0, 0) and blue represents RGB (0, 0, 255). The extracted RGB value of each pixel will form a chromaticity information data set, and the RGB value of each pixel corresponds to the temperature information of the point. The thermal map pixel chromaticity information data contains the RGB chromaticity value of each pixel, which is used for subsequent color difference calculation and temperature gradient analysis. In the RGB data of the entire thermal map, the chromaticity difference between each pixel and the surrounding pixels is calculated. The chromaticity difference can be measured by calculating the Euclidean distance between the RGB values. The formula is as follows: Chromaticity difference = in, , , and , , are the RGB values ​​of two pixels respectively. According to the calculation results of the chromaticity difference, find the maximum chromaticity difference and the minimum chromaticity difference values. The maximum chromaticity difference indicates the area with the largest temperature change, while the minimum chromaticity difference indicates the area with the smallest temperature change. Generate pixel chromaticity color difference maximum value data and pixel chromaticity color difference minimum value data. These two data sets represent the areas with the most drastic and the most stable temperature changes in the heat map, respectively. For each pair of adjacent pixels in the heat map, calculate the chromaticity difference between them. Adjacent pixels are usually adjacent pixels up and down, left and right, or diagonally. Calculate the chromaticity difference of each pair of adjacent pixels and record the difference value. The generated adjacent pixel difference chromaticity value will reflect the degree of temperature change in the heat map. A larger difference value indicates a larger temperature change. Using the chromaticity difference between adjacent pixels, calculate the temperature gradient of each pixel. Generally, the temperature gradient can be expressed by calculating the average or maximum value of the difference chromaticity values ​​of adjacent pixels to represent the rate of temperature change. The calculation formula of the temperature gradient can be expressed as: Temperature gradient = ;in, is the number of adjacent pixels, and the chromaticity difference is the chromaticity difference between each pair of adjacent pixels. The calculated temperature gradient data will be used to identify areas in the heat map where the temperature changes more dramatically. Higher gradient values ​​usually indicate areas with larger temperature changes, which are potential areas of faults or anomalies. Determine the maximum and minimum values ​​of the temperature gradient based on the maximum and minimum chromaticity difference data of the pixel points. Divide the temperature gradient range into several intervals, and map the temperature gradient value of each pixel point to the corresponding interval. The gradient range can usually be divided into different levels (for example: low, medium, and high). Group the temperature gradients according to the gradient intervals to generate abnormal temperature change gradient data. Each gradient interval corresponds to a temperature change level, so that the temperature changes in the heat map can be divided into levels to help identify the existing fault areas.

[0046] Preferably, step S4 comprises the following steps: Step S41: performing equipment abnormal line segment temperature warning on the electrical equipment information data according to the abnormal temperature change level data, and generating equipment abnormal line segment temperature warning data; Step S42: Upload the equipment abnormal line segment temperature warning data to the cloud platform for warning response feedback, generate electrical equipment abnormal warning response feedback data, and perform electrical fire warning operations.

[0047] In the embodiment of the present invention, the temperature change area of ​​each electrical device is included through the abnormal temperature change level data, and the severity level of the temperature change is indicated. The temperature change level includes the following categories: low-level abnormality (slight temperature fluctuation, which will not directly cause a fire, but indicates a potential fault); medium-level abnormality (obvious temperature fluctuation, which requires monitoring and further analysis); high-level abnormality (serious temperature fluctuation, resulting in a fire risk). According to the abnormal temperature change level data, a specific warning rule is set. For example, it is set that when the temperature change level of a certain electrical device reaches the medium level or above, a temperature warning is triggered. According to the rated temperature of the electrical device, a temperature change threshold is defined. If the temperature change amplitude or absolute temperature of the device exceeds the threshold, a warning is triggered. If the temperature of the device changes by more than a certain rate in a short time, a warning can also be triggered. Through the electrical equipment information data and the abnormal temperature change level data, the power cord, terminal block, socket and other parts of the electrical equipment are subjected to temperature warning analysis. If the temperature of a power line segment, connection point or other key parts reaches the preset warning standard, the abnormal line segment temperature warning data of the device is generated, and the generated warning data includes: the name of the warning device, the temperature change level, the location of the warning line segment, the temperature fluctuation information, the warning level, the timestamp, etc. The generated device abnormal line segment temperature warning data is uploaded to the cloud platform in real time through the Internet of Things (IoT) device or network interface to ensure real-time and high efficiency. The uploaded data can be transmitted in lightweight data formats such as JSON format, XML format or Protobuf to reduce bandwidth consumption and improve transmission efficiency. Encrypted communication (such as TLS / SSL) is used to ensure data security and avoid data leakage or tampering. After receiving the device temperature warning data, the cloud platform automatically analyzes and processes it. The specific steps include: the warning response engine built into the cloud platform determines whether further processing is required based on the warning level, warning area, device usage and other information of the device. For example, if the device warning level is "high", the platform will generate an emergency response notification. The cloud platform sends relevant feedback based on the warning level, including the following situations: If the device temperature exceeds the high threshold, the platform will issue an emergency alarm to the designated maintenance personnel, device administrator or security personnel. The cloud platform can provide warning response suggestions, such as "check the device immediately" or "reduce the load and lower the temperature". The abnormal status of the device will be updated in real time, and all relevant personnel can monitor it in real time.

[0048] In this specification, an electrical fire warning device based on leakage current temperature detection is provided, which is used to execute the above-mentioned electrical fire warning method based on leakage current temperature detection. The electrical fire warning device based on leakage current temperature detection includes: The data acquisition module is used to obtain electrical equipment information data; locate the power line of the electrical equipment based on the electrical equipment information data to generate the power line position information data of the electrical equipment; collect leakage current sensor data on the power line position information data of the electrical equipment to obtain the leakage current monitoring data of the standard electrical equipment; The line segment pattern classification module is used to confirm the maximum fluctuation curve segment of the leakage current monitoring data of the standard electrical equipment to obtain the maximum fluctuation curve of the leakage current of the electrical equipment; divide the standard electrical equipment leakage current monitoring data into suspicious line patterns based on the maximum fluctuation curve of the leakage current of the electrical equipment to generate suspicious line pattern data, wherein the suspicious line pattern data includes a gradual change pattern and a sudden increase pattern; mark the suspicious line segment of the power line location information data of the electrical equipment based on the suspicious line pattern data to generate the suspicious power line segment location information data of the electrical equipment; The abnormal temperature detection module is used to perform long-term abnormal change detection of the power insulation layer based on the location information data of the suspected power line segment of the electrical equipment in a gradual change mode, and generate the long-term abnormal temperature change data of the power line segment; perform instantaneous abnormal change detection of the power input based on the location information data of the suspected power line segment of the electrical equipment in a sudden increase mode, and generate the instantaneous abnormal temperature change data of the line segment; perform thermal map temperature level annotation based on the long-term abnormal temperature change data of the power line segment and the instantaneous abnormal temperature change data of the line segment, and generate the abnormal temperature change level data; The early warning response module is used to provide early warning response feedback to the electrical equipment information data based on the abnormal temperature change level data, generate electrical equipment abnormal early warning response feedback data, and perform electrical fire early warning operations.

[0049] An electrical fire warning device based on leakage current temperature detection comprises a processor, a memory and a computer program stored in the memory and executable on the processor, and is used to execute the electrical fire warning method based on leakage current temperature detection.

[0050] The beneficial effect of the present invention is that by accurately acquiring the information data of the electrical equipment and locating the position of the power line, a foundation is laid for subsequent leakage current monitoring and fault detection. This process ensures the accuracy and relevance of the leakage current monitoring data, so that abnormal conditions in the electrical equipment can be effectively detected. By confirming the maximum fluctuation curve segment of the leakage current monitoring data of the standard electrical equipment, the fluctuation range in the leakage current data can be accurately identified, providing an accurate basis for further analyzing the state of the electrical equipment. Based on the maximum fluctuation curve segment, the leakage current monitoring data is divided into modes, and the abnormal mode of the leakage current is divided into a gradual change mode and a sudden increase mode. This can further refine the abnormal type of the equipment, so that the monitoring system can analyze and identify different types of potential faults in a targeted manner. Based on the gradual change mode, the long-term change abnormality detection of the power insulation layer is carried out, and the abnormal fluctuation of the temperature over a long period of time can be detected, so that the temperature change problem caused by aging or damage of the power line can be discovered early, thereby reducing the risk of fire. Based on the sudden increase change mode, the instantaneous temperature change of the power inlet is detected, which can capture sudden temperature anomalies in time, especially changes related to the instantaneous load or fault of the electrical equipment, ensuring that potential dangers can be responded to quickly. By marking the temperature level of the thermal map, a different temperature level is assigned to each abnormal temperature change area, so that the severity and potential risks of the temperature anomaly can be quantified, further improving the accuracy of fault warning. According to the generated abnormal temperature change level data, the electrical equipment is given an immediate early warning response feedback. This process can help managers to detect abnormalities in time and take corresponding disposal measures to prevent temperature anomalies from further developing into serious accidents such as electrical fires. Therefore, the present invention improves the accuracy, response speed and positioning capability of the electrical fire early warning system by introducing leakage current fluctuation pattern recognition, precise power line positioning, intelligent anomaly detection and thermal map analysis.

[0051] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0052] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An electrical fire early warning method based on leakage current temperature detection, characterized in that: The following steps are involved: Step S1: Acquire electrical equipment information data; locate the power line of the electrical equipment according to the electrical equipment information data to generate the power line position information data of the electrical equipment; collect leakage current sensor data of the power line position information data of the electrical equipment to obtain standard electrical equipment leakage current monitoring data; Step S2: Confirm the maximum fluctuation curve segment of the leakage current monitoring data of the standard electrical equipment to obtain the maximum fluctuation curve of the leakage current of the electrical equipment; divide the standard electrical equipment leakage current monitoring data into suspicious line modes based on the maximum fluctuation curve of the leakage current of the electrical equipment to generate suspicious line mode data, wherein the suspicious line mode data includes a gradual change mode and a sudden increase mode; mark the suspicious line segment of the power line location information data of the electrical equipment based on the suspicious line mode data to generate the suspicious power line segment location information data of the electrical equipment; Step S3: Based on the progressive change mode, the position information data of the suspected power line segment of the electrical equipment is subjected to long-term abnormal change detection of the power insulation layer, and long-term abnormal temperature change data of the power line segment is generated; Based on the location information data of the suspected power line segment of the electrical equipment in the sudden increase mode, the power inlet instantaneous change abnormality detection is performed to generate the line segment instantaneous temperature abnormal change data; based on the power line segment long-term temperature abnormal change data and the line segment instantaneous temperature abnormal change data, the thermal map temperature level is marked to generate abnormal temperature change level data; Step S4: Perform early warning response feedback on the electrical equipment information data according to the abnormal temperature change level data, generate electrical equipment abnormal early warning response feedback data, and perform electrical fire early warning operations.

2. The electrical fire early warning method based on leakage current temperature detection according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Acquire electrical equipment information data; Step S12: performing electrical equipment topology analysis on the electrical equipment information data to generate electrical equipment topology data; locating the electrical equipment power line position of the electrical equipment information data based on the electrical equipment topology data to generate electrical equipment power line position information data; Step S13: deploying leakage current sensors on the power line location information data of the electrical equipment based on a preset distance interval to obtain leakage current sensor deployment data; performing wireless data collection on the leakage current sensor deployment data to obtain leakage current monitoring data of the electrical equipment; Step S14: preprocess the electrical equipment leakage current monitoring data to generate standard electrical equipment leakage current monitoring data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization.

3. The electrical fire early warning method based on leakage current temperature detection according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: converting the standard electrical equipment leakage current monitoring data into a time-series leakage current monitoring curve to generate an electrical equipment leakage current curve; extracting the peak current of the electrical equipment leakage current curve to obtain the peak leakage current data of the electrical equipment; calculating the variation amplitude of the electrical equipment leakage current curve based on the peak leakage current of the electrical equipment to obtain the peak variation amplitude data of the electrical equipment; Step S22: confirming the maximum fluctuation curve segment of the standard electrical equipment leakage current monitoring data according to the electrical equipment peak leakage current data and the electrical equipment peak variation amplitude data, and obtaining the electrical equipment leakage current maximum fluctuation curve; Step S23: dividing the standard electrical equipment leakage current monitoring data into suspicious line modes based on the maximum fluctuation curve of the electrical equipment leakage current, and generating suspicious line mode data, wherein the suspicious line mode data includes a gradual change mode and a sudden increase mode; Step S24: marking the suspicious line segments of the power line location information data of the electrical equipment based on the suspicious line pattern data to generate the suspicious power line segment location information data of the electrical equipment.

4. The electrical fire early warning method based on leakage current temperature detection according to claim 3 is characterized in that: Step S23 includes the following steps: Step S231: extracting the maximum fluctuation point and the minimum fluctuation point based on the maximum fluctuation curve of the leakage current of the electrical equipment, and obtaining the maximum fluctuation point data and the minimum fluctuation point data of the leakage current of the electrical equipment; Step S232: performing a time domain analysis on the maximum fluctuation point data of the leakage current of the electrical equipment and the minimum fluctuation point data of the leakage current of the electrical equipment to generate fluctuation change time domain data; comparing the fluctuation change time domain data with a preset standard fluctuation time domain threshold, and when the fluctuation change time domain data is greater than or equal to the preset standard fluctuation time domain threshold, marking the corresponding fluctuation change time domain data as progressive change time domain data; Step S233: when the fluctuation change time domain data is less than the preset standard fluctuation time domain threshold, the corresponding fluctuation change time domain data is marked as sudden increase change time domain data; based on the gradual change time domain data, the standard electrical equipment leakage current monitoring data is divided into a first suspicious mode to generate a gradual change mode; Step S234: performing a second suspicious pattern classification on the standard electrical equipment leakage current monitoring data based on the sudden increase change time domain data to generate a sudden increase type change pattern.

5. The electrical fire early warning method based on leakage current temperature detection according to claim 3 is characterized in that: Step S24 includes the following steps: Step S241: performing power line wiring path analysis on the power line location information data of the electrical equipment to generate power line wiring path data; Step S242: using the power line wiring path data to segment the power line position information data of the electrical equipment to generate power line segmentation data, wherein the power line segmentation includes power main line segmentation and power branch line segmentation; Step S243: Mapping the power line segmentation data to the actual position information of the abnormal power line segments based on the suspicious line pattern data, and generating the suspicious power line segment position information data of the electrical equipment.

6. The electrical fire early warning method based on leakage current temperature detection according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: Based on the gradual change mode, the temperature sensor is used to monitor the insulation layer temperature of the suspected power line segment of the electrical equipment using the location information data of the suspected power line segment, and the suspected power line segment insulation layer temperature monitoring data is generated; based on the sudden change mode, the temperature sensor is used to monitor the power inlet temperature of the suspected power line segment of the electrical equipment using the location information data of the suspected power line segment, and the suspected power line segment inlet temperature monitoring data is generated; Step S32: performing temperature long-term change anomaly detection on the suspected power line segment insulation layer temperature monitoring data to generate the power line segment long-term temperature anomaly change data; performing temperature instantaneous change anomaly detection on the suspected power line segment inlet temperature monitoring data to generate the line segment instantaneous temperature anomaly change data; Step S33: converting the power line segment long-term temperature abnormal change data and the line segment instantaneous temperature abnormal change data into an abnormal temperature heat map to generate an abnormal temperature change heat map; Step S34: performing temperature gradient analysis on the abnormal temperature change heat map to generate abnormal temperature change gradient data; and marking the abnormal temperature change heat map with abnormal temperature levels according to the abnormal temperature change gradient data to generate abnormal temperature change level data.

7. The electrical fire early warning method based on leakage current temperature detection according to claim 6, characterized in that: Temperature gradient analysis of abnormal temperature change heat maps includes: Perform color mapping on the abnormal temperature change heat map to generate abnormal temperature change color mapping data; extract pixel RGB values ​​of the abnormal temperature change heat map based on the abnormal temperature change color mapping data to obtain heat map pixel chromaticity information data; perform chromaticity color difference extreme value screening on the heat map pixel chromaticity information data to obtain pixel chromaticity color difference maximum value data and pixel chromaticity color difference minimum value data; The chromaticity difference of adjacent pixels is calculated for the chromaticity information data of the heat map pixels to obtain the difference chromaticity values ​​of adjacent pixels; the temperature gradient of the chromaticity information data of the heat map pixels is calculated by the difference chromaticity values ​​of adjacent pixels to generate the chromaticity gradient data of abnormal temperature change; The abnormal temperature change chromaticity gradient data is averaged over the gradient range using the pixel point chromaticity color difference maximum value data and the pixel point chromaticity color difference minimum value data to generate the abnormal temperature change gradient data.

8. The electrical fire early warning method based on leakage current temperature detection according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing equipment abnormal line segment temperature warning on the electrical equipment information data according to the abnormal temperature change level data, and generating equipment abnormal line segment temperature warning data; Step S42: Upload the equipment abnormal line segment temperature warning data to the cloud platform for warning response feedback, generate electrical equipment abnormal warning response feedback data, and perform electrical fire warning operations.

9. An electrical fire warning device based on leakage current temperature detection, characterized in that: Used to execute the electrical fire early warning method based on leakage current temperature detection as claimed in claim 1, the electrical fire early warning device based on leakage current temperature detection comprises: The data acquisition module is used to obtain electrical equipment information data; locate the power line position of the electrical equipment based on the electrical equipment information data to generate the power line position information data of the electrical equipment; collect leakage current sensor data on the power line position information data of the electrical equipment to obtain standard electrical equipment leakage current monitoring data; The line segment pattern classification module is used to confirm the maximum fluctuation curve segment of the leakage current monitoring data of the standard electrical equipment to obtain the maximum fluctuation curve of the leakage current of the electrical equipment; divide the standard electrical equipment leakage current monitoring data into suspicious line patterns based on the maximum fluctuation curve of the leakage current of the electrical equipment to generate suspicious line pattern data, wherein the suspicious line pattern data includes a gradual change pattern and a sudden increase pattern; mark the suspicious line segment of the power line location information data of the electrical equipment based on the suspicious line pattern data to generate the suspicious power line segment location information data of the electrical equipment; The abnormal temperature detection module is used to perform long-term abnormal change detection of the power insulation layer based on the location information data of the suspected power line segment of the electrical equipment in a gradual change mode, and generate the long-term abnormal temperature change data of the power line segment; perform instantaneous abnormal change detection of the power input based on the location information data of the suspected power line segment of the electrical equipment in a sudden increase mode, and generate the instantaneous abnormal temperature change data of the line segment; perform thermal map temperature level annotation based on the long-term abnormal temperature change data of the power line segment and the instantaneous abnormal temperature change data of the line segment, and generate the abnormal temperature change level data; The early warning response module is used to provide early warning response feedback to the electrical equipment information data based on the abnormal temperature change level data, generate electrical equipment abnormal early warning response feedback data, and perform electrical fire early warning operations.

10. An electrical fire warning device based on leakage current temperature detection, characterized in that: The invention comprises a processor, a memory and a computer program stored in the memory and executable on the processor, and is used to execute the electrical fire early warning method based on leakage current temperature detection as described in any one of claims 1 to 8.

Images