Dynamic area infrared temperature measurement interaction method for intelligent patrol of transformer substation

Abstract

The invention relates to the field of intelligent substation inspection, and discloses a dynamic region infrared temperature measurement interaction method for intelligent substation inspection, which comprises the following steps of: S1, dividing an inspection region according to equipment distribution, equipment grade, historical temperature anomaly records and environmental data in a substation, generating historical temperature anomaly indexes through the historical temperature anomaly records, generating a region weight of each patrol region; and S2, determining the temperature measurement frequency and the temperature measurement angle of each patrol area according to the area weight, and obtaining a temperature measurement result. Through a dynamic area division and priority weight generation method, accurate division of a substation equipment area is realized, and the temperature measurement frequency and the scanning angle are dynamically adjusted according to equipment importance, historical abnormal records and environmental factors. Through preferential temperature measurement of a high-risk area and key equipment, the coverage rate and the temperature measurement precision of infrared temperature measurement are remarkably improved, the temperature measurement redundancy of a low-risk area is effectively reduced, and the utilization efficiency of temperature measurement resources is improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent substation inspection technology, specifically to a dynamic area infrared temperature measurement interactive method for intelligent substation inspection. Background Technology

[0002] With the continuous expansion of modern substations and the increasing variety of equipment, traditional manual inspection methods can no longer meet the needs of real-time monitoring and maintenance of substation equipment operation. Especially during inspections of critical equipment or high-risk areas, manual inspections suffer from limited coverage, low efficiency, and difficulty in timely response. These shortcomings not only reduce the efficiency of equipment fault detection but also increase the operational risks of substations, leading to higher energy consumption and equipment maintenance costs.

[0003] Currently, infrared thermography is widely used in substation equipment inspection systems for temperature monitoring to promptly detect overheating or abnormal conditions. However, existing infrared thermography methods primarily rely on fixed, periodic inspection patterns, which often fail to flexibly address the dynamic changes and complex environments of substation equipment in practical applications. Existing infrared thermography systems typically employ fixed measurement frequencies and scanning angles, unable to dynamically adjust based on the actual risk level of the equipment and the importance of the area. This leads to over-measurement in low-risk areas and under-measurement in high-risk areas, thus affecting measurement efficiency and the accuracy of risk identification. Furthermore, while existing multi-source data fusion technologies can perform some risk assessment by collecting information such as equipment status, electrical parameters, and environmental data, the simplicity of the data fusion methods and the lack of dynamic feedback mechanisms typically prevent real-time risk assessment and dynamic optimization. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a dynamic area infrared temperature measurement interactive method for intelligent inspection of substations. The aim is to achieve intelligent inspection of substation equipment by dynamically dividing the inspection area and rationally allocating the temperature measurement frequency and scanning angle, thereby improving the accuracy and efficiency of equipment monitoring.

[0005] This method dynamically divides inspection areas based on factors such as the spatial distribution of equipment within the substation, equipment level, historical temperature anomaly records, and environmental data, and assigns corresponding weights to each area. By rationally calculating and adjusting area weights, important equipment and high-risk areas are prioritized for inspection, thereby ensuring comprehensive monitoring of critical equipment during the inspection process. The method further includes generating historical temperature anomaly indicators based on historical temperature anomaly records, and dynamically adjusting the temperature measurement frequency and angle of each inspection area in conjunction with information such as equipment level and environmental factors to optimize inspection efficiency. To achieve the above objectives, the present invention provides a dynamic area infrared temperature measurement interaction method for intelligent inspection of substations, characterized by the following steps: S1. Based on the equipment distribution, equipment level, historical temperature anomaly records, and environmental data within the substation, the inspection area is divided. Historical temperature anomaly indicators are generated through historical temperature anomaly records, and the regional weight of each inspection area is generated. S2. Adjust the acquisition parameters of the infrared temperature measurement acquisition unit for each patrol area according to the area weight; S3. Collect electrical parameters and perform standardized processing and weighted fusion with historical temperature anomaly indicators and environmental data to generate a comprehensive risk score for each inspection area; S4. A comprehensive risk score threshold is preset and compared with the comprehensive risk score. When the comprehensive risk score is greater than the comprehensive risk score threshold, an abnormal warning is triggered, and the patrol path is adjusted according to the comprehensive risk score and the current patrol progress. S5. Collect the temperature coverage rate, anomaly detection rate and risk score change rate of each patrol area in different patrol cycles, calculate the optimization coefficient of each patrol area, and adjust the patrol path for the next round based on the optimization coefficient.

[0006] Preferably, in step S1, the region weight is calculated as follows: The sum of the equipment level values ​​and the sum of historical temperature anomaly indicators of all equipment in the inspection area are calculated separately. The sum of the equipment level values, the sum of the historical temperature anomaly indicators, and the environmental factor indicators of the area are then weighted and summed to obtain the regional weight of the inspection area.

[0007] Preferably, the specific process of dividing the inspection area in S1 includes: Obtain the spatial coordinates and importance level of all equipment in the substation, divide the substation space into equidistant grid cells, and ensure that each grid cell contains at least one piece of equipment. Identify the equipment level within a grid cell and merge grid cells with a high density of high-level equipment into separate key inspection areas; Merge low-level or scattered grid cells based on spatial proximity; Obtain historical temperature anomaly indicators from the equipment, and prioritize merging grid cells with historical anomaly frequency or amplitude higher than the preset standard to form high-risk inspection areas.

[0008] Preferably, in step S2, the calculation method of the acquisition parameters includes: Calculate the difference between the regional weight of the inspected area and the minimum weight among all regions; The difference is multiplied by the frequency adjustment coefficient to obtain the frequency increment, and the minimum sampling frequency is added to the frequency increment to obtain the infrared temperature measurement sampling frequency of the inspection area. The difference is multiplied by the angle adjustment coefficient to obtain the angle increment, and the minimum scanning angle is added to the angle increment to obtain the optimized scanning angle of the inspection area.

[0009] Preferably, in step S3, the comprehensive risk score is calculated as follows: Calculate the average value of the normalized infrared thermometer values ​​and the average value of the comprehensive electrical parameters of all equipment in the inspection area. The average value of the normalized infrared thermometry value, the average value of the comprehensive electrical parameter index, and the comprehensive regional environmental factor index are weighted and summed to obtain the comprehensive risk score of the patrol area.

[0010] Preferably, in step S4, the setting standard for the preset comprehensive risk scoring threshold is dynamically adjusted based on the statistical distribution of historical data from the substation, specifically including: Calculate the mean and standard deviation of the comprehensive risk score for all inspected areas; The sum of the multiples of the mean and the standard deviation is set as the threshold for the comprehensive risk score, wherein the multiples of the standard deviation are determined by an adjustment factor; The adjustment factor is dynamically corrected based on real-time environmental data. When the ambient temperature is higher than the set value, the adjustment factor is lowered.

[0011] Preferably, in step S4, the calculation method for adjusting the inspection path based on the comprehensive risk score and the current inspection progress is as follows: Calculate the distance between the current inspection unit and the center point of the inspection area, and use the sum of the distance and non-zero constants as the distance factor; Calculate the ratio of the comprehensive risk score of the inspection area to the distance factor, and use this ratio as the path priority for the inspection area; The patrol queue is dynamically adjusted according to the path priority from highest to lowest, so that high-risk and nearby areas are patrolled first.

[0012] Preferably, in step S5, the optimization coefficient is calculated as follows: Calculate the regional temperature measurement coverage rate index, which is determined based on the ratio of the actual number of temperature measurements to the theoretical number of measurements required; Calculate the regional anomaly detection rate index, which is the ratio of the number of abnormal devices in the region to the total number of devices; Calculate the regional risk score change rate, which is the ratio of the change in the regional risk score relative to the previous inspection cycle. The optimization coefficient of the patrol area is obtained by weighted summing of the area temperature coverage rate index, the area anomaly detection rate index, and the area risk score change rate.

[0013] Preferably, the strategy for adjusting based on the optimization coefficient feedback in S5 includes: Calculate the statistical distribution of optimization coefficients for all areas in the current inspection round; When the optimization coefficient of a certain region is in the high distribution range, the path priority of that region will be increased in the next round of dynamic region division, and the infrared temperature measurement strategy control module will be instructed to increase the temperature measurement frequency and temperature measurement scanning angle of that region. When the optimization coefficient of a certain area is in a low distribution range, the temperature measurement intensity of that area should be maintained or appropriately reduced in the next round of inspection.

[0014] Preferably, the determination is made based on the relative magnitude of the optimization coefficient across all inspection areas: Regions with high optimization coefficients: This indicates that the overall risk, anomaly rate, and coverage efficiency are all relatively high. Region with low optimization coefficient: This indicates that the overall indicators are low, and the intensity of the patrols should be appropriately reduced. in To optimize the coefficients, This is the average of the optimization coefficients for all areas in the current inspection round. The standard deviation is the statistical standard deviation of the optimization coefficients for all inspected areas in the current inspection round. This is an adjustable coefficient.

[0015] This invention provides a dynamic area infrared temperature measurement interaction method for intelligent substation inspection. It has the following beneficial effects: 1. This invention achieves precise division of substation equipment areas through dynamic area partitioning and priority weight generation methods, and dynamically adjusts the temperature measurement frequency and scanning angle based on equipment importance, historical anomaly records, and environmental factors. By prioritizing temperature measurement of high-risk areas and critical equipment, this invention significantly improves the coverage and accuracy of infrared thermography, effectively reduces temperature measurement redundancy in low-risk areas, and enhances the utilization efficiency of temperature measurement resources.

[0016] 2. This invention utilizes a multi-source data fusion and risk assessment module, combining infrared temperature measurement data, electrical parameters, environmental data, and equipment historical records to achieve real-time risk assessment of each inspection area. Based on real-time data feedback, the system can dynamically adjust its temperature measurement strategy, prioritizing inspections of high-risk areas. This real-time feedback mechanism can promptly identify potential fault points, effectively reducing the risk of equipment failure and downtime.

[0017] 3. This invention introduces a closed-loop feedback optimization mechanism, which dynamically adjusts the inspection path and temperature measurement strategy based on inspection data and temperature measurement results. By calculating the regional optimization coefficient, the system can adaptively optimize the inspection path and temperature measurement frequency, ensuring that high-risk areas are inspected in a timely manner, while improving the overall inspection efficiency. This adaptive closed-loop feedback mechanism enables the system to flexibly respond to changes in the substation environment, further enhancing the reliability and intelligence level of the substation intelligent inspection system. Attached Figure Description

[0018] Figure 1 This is a system flowchart of the present invention; Figure 2 This is a system framework diagram of the present invention. Detailed Implementation

[0019] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Example: Please see the appendix Figure 1 - Appendix Figure 2 This invention provides a dynamic area infrared temperature measurement interactive system for intelligent substation inspection, including an infrared temperature measurement acquisition unit, a dynamic area division module, an infrared temperature measurement strategy control module, a multi-source data fusion analysis module, an interactive anomaly early warning module, and a closed-loop feedback optimization module. These modules form a cohesive system according to predetermined logical relationships to achieve accurate monitoring, risk assessment, and inspection optimization of the temperature of key substation equipment.

[0021] The infrared temperature acquisition unit is used to collect temperature data from key equipment within the substation. This unit may include a mobile infrared sensor and a fixed infrared monitoring camera, with a spatial resolution of 0.05~0.2m / pixel, a temperature accuracy of ±0.5, and a typical temperature measurement range of -20℃ to 200℃, covering the operating temperature range of substation equipment. It can acquire equipment surface temperature data from different heights and angles, and then digitize the collected data before transmitting it to the infrared temperature measurement strategy control module. The output data of the infrared temperature acquisition unit serves as the basis for subsequent area division, temperature measurement strategy adjustment, and risk assessment.

[0022] The dynamic zone division module generates dynamic inspection zones and zone weights based on equipment distribution information, equipment level, historical temperature anomaly records, and environmental data. The module determines the importance level of each zone through comprehensive analysis of various factors and outputs the dynamic zone division results to the infrared temperature measurement strategy control module to guide temperature measurement frequency, acquisition angle, and path priority. This module can update the zone division in real time to reflect environmental changes and historical inspection information.

[0023] The infrared temperature measurement strategy control module adjusts the acquisition parameters of the infrared temperature measurement acquisition unit based on the area weights and patrol path information provided by the dynamic area division module. The module controls the sensor scanning angle, sampling frequency, and data acquisition method to achieve high-frequency acquisition in key areas and routine acquisition in ordinary areas. The execution results of the infrared temperature measurement strategy control module are transmitted in real time to the multi-source data fusion analysis module for risk assessment and anomaly identification.

[0024] The multi-source data fusion and analysis module receives data output from the infrared temperature measurement strategy control module and combines it with equipment electrical parameters, environmental monitoring data, and historical inspection records for fusion processing and risk assessment. The module calculates a comprehensive risk score for each dynamic area according to a preset algorithm and sends the score results to the interactive anomaly early warning module. This module's function ensures a high degree of correlation between temperature measurement data and other key data, thereby supporting accurate anomaly identification and path optimization within the system.

[0025] The interactive anomaly early warning module triggers warnings based on the risk score provided by the multi-source data fusion analysis module and dynamically adjusts the patrol path according to the score results. The module can generate visual anomaly alerts to guide operators to focus on high-risk areas, while simultaneously feeding back the path adjustment and operational results to the closed-loop feedback optimization module. This module enables real-time response and collaborative control during the patrol process.

[0026] The closed-loop feedback optimization module receives output information from each module, including infrared temperature measurement data, risk scores, and path adjustment records. It analyzes patrol efficiency, coverage, and anomaly detection effectiveness, and optimizes and adjusts dynamic area division and infrared temperature measurement strategies.

[0027] Based on the above system, a dynamic area infrared temperature measurement interactive method for intelligent substation inspection is implemented, including the following steps: S1. Dynamic Area Division and Priority Weight Generation: The dynamic area division module is used to generate inspection areas and area weights based on the distribution of equipment in the substation, equipment level, historical temperature anomaly records, and environmental data, in order to support the dynamic adjustment of subsequent infrared temperature measurement strategies. Equipment distribution includes identifying various key equipment within the substation, such as main transformers, circuit breakers, current transformers, and voltage transformers; Equipment classification includes classifying equipment into importance levels (such as high, medium, and low) based on its impact on the safe and stable operation of the power system, and assigning numerical values ​​for regional weighting calculations. Historical temperature anomaly records include abnormal temperature data, anomaly occurrence time, anomaly amplitude, and anomaly frequency, and are normalized or standardized.

[0028] The dynamic area partitioning module first acquires the spatial distribution information of substation equipment, including equipment coordinates, equipment type, and importance level. Specifically, it obtains the spatial coordinates of all equipment within the substation, including key equipment such as main transformers, circuit breakers, and instrument transformers. The entire substation space is then divided into equidistant two-dimensional or three-dimensional grid cells, with each grid cell ensuring it contains at least one piece of equipment. This provides a foundation for subsequent area merging and optimization. Each piece of equipment is assigned a weight based on its criticality and fault impact level. In the initial grid, cells with a high density of high-level equipment are merged into separate inspection areas to improve the temperature measurement coverage of key equipment. Grids containing low-level or scattered equipment can be merged based on spatial proximity to reduce temperature measurement redundancy. And obtain historical temperature anomaly indicators of system equipment. Grid cells with frequent or high historical anomalies are prioritized for merging to form high-risk inspection areas, thereby increasing the frequency and accuracy of inspections. In conjunction with historical temperature anomaly data, a device state vector is established, which can be represented as: in, Indicates the first The state vector of the device. Indicates equipment level, Indicates the height of the equipment's location. This indicates historical temperature anomalies in the equipment.

[0029] Subsequently, the dynamic area division module divides the inspection area into weighted areas based on the equipment status vector and environmental data. The formula for calculating the area weight is as follows: in, Indicates the first The weight of the inspection area Represents the set of devices within the area. These are weighting coefficients, used to adjust for equipment level, historical anomaly indicators, and environmental factors, respectively. Impact on regional weights. Environmental factors. Environmental factors, including ventilation conditions, heat dissipation, or areas with locally high temperatures, are incorporated into the regional weighting calculation to optimize regional boundaries and ensure that high-risk areas are centrally identified; specifically: Ventilation conditions: Average wind speed can be obtained by deploying wind speed sensors in each grid area or by utilizing existing environmental data. Heat dissipation status: can be calculated based on the temperature gradient around the equipment or the heat dissipation rate of the thermal imaging measurement area; Local temperature is obtained by thermal infrared thermometry, and the difference between the local temperature and the regional average temperature is used as a quantitative indicator. The dynamic region segmentation module generates an initial dynamic region list by calculating the weights of all candidate regions and sorts them according to their weights, providing a reference for the infrared temperature measurement strategy module. During the inspection process, the module can update the region weights based on real-time environmental data and inspection results, achieving dynamic adjustment. Real-time updates can be achieved by recalculating new region weights through weighted calculation of equipment state vectors and environmental data, prioritizing the inspection and temperature measurement of high-risk or key areas. The dynamic region segmentation module outputs region weights. These outputs provide input to the infrared temperature measurement strategy control module to determine the temperature measurement frequency, scanning angle, and patrol path priority for each region.

[0030] S2. Dynamic adjustment of infrared temperature measurement strategy; The infrared temperature measurement strategy control module is used to dynamically adjust the acquisition parameters of the infrared temperature measurement acquisition unit according to the regional weight data output by the dynamic region division module, so as to achieve coordinated coverage of high-frequency temperature measurement in key areas and conventional temperature measurement in ordinary areas. The infrared temperature measurement strategy control module first receives the weights of each region from the dynamic region division module. The module also includes a list of devices within the corresponding area. It calculates the temperature measurement frequency for each area based on weighted values. and temperature measurement angle optimization parameters The formula for calculating the temperature measurement frequency is as follows: in, Indicates the first Infrared temperature sampling frequency of the patrol area Indicates the minimum sampling frequency. This indicates the weight of the region. This represents the minimum weight of all regions. This is the frequency adjustment coefficient, used to adjust the influence of the region weight on the sampling frequency.

[0031] The temperature measurement angle optimization parameter is used to control the scanning angle and temperature measurement resolution of the infrared sensor to ensure full coverage of the surface of critical equipment. The angle optimization can be expressed as: This indicates the optimized scanning angle. Indicates the minimum scanning angle. Indicates the angle adjustment coefficient. Indicates the region weight; This represents the minimum weight across all regions.

[0032] The infrared temperature measurement strategy control module instructs the infrared temperature measurement acquisition unit to execute temperature measurement tasks based on frequency and angle parameters calculated by the formula, and transmits the temperature measurement results and execution records to the multi-source data fusion and analysis module in real time. Simultaneously, the infrared temperature measurement strategy control module adjusts the temperature measurement strategy in real time based on the inspection progress and temperature measurement results. When the abnormal temperature index of equipment in the area exceeds the preset threshold, the infrared temperature measurement strategy control module automatically increases the temperature measurement frequency and scanning angle in that area, achieving priority temperature measurement in key areas. S3. Multi-source data fusion and risk assessment; The multi-source data fusion and analysis module is used to fuse the data output by the infrared temperature measurement acquisition unit with the equipment electrical parameters, environmental monitoring data and historical inspection records, and calculate the comprehensive risk score of each dynamic area to support anomaly early warning and inspection path optimization. The multi-source data fusion and analysis module first receives temperature data from the infrared temperature measurement strategy control module, including equipment temperature values, measurement timestamps, and measurement angle information within the area. Simultaneously, the module collects equipment electrical parameter data, including indicators such as equipment load, current, voltage, and power factor, and acquires environmental monitoring data, such as substation ambient temperature, humidity, and wind speed information. Historical inspection records include historical temperature anomalies and historical inspection path data. Comprehensive Risk Score The calculation formula is as follows: in, Indicates the first The comprehensive risk score of the inspected area Indicates the number of devices in the area. Indicates the first Infrared temperature measurement value of the device. Indicates the first Comprehensive electrical parameters of the equipment This represents a comprehensive index of regional environmental factors. These are the weighting coefficients for temperature measurement data, electrical parameters, and environmental factors, respectively. The risk score for each patrol area is calculated using a formula, and the scores are sorted by area and output to the interactive anomaly warning module. Areas with high risk scores are prioritized for patrol during route optimization, and adjustments to the temperature measurement strategy for key areas can be triggered. During the calculation process, indicators from different data sources are standardized to ensure that the data are weighted and fused under a unified dimension. The output of the multi-source data fusion analysis module forms a closed-loop feedback with the infrared temperature measurement strategy control module. The temperature measurement data affects the risk score, and the risk score, in turn, adjusts the temperature measurement frequency and scanning angle.

[0033] S4. Interactive anomaly warning and path optimization; The interactive anomaly warning module is used to trigger anomaly warnings based on the comprehensive risk score provided by the multi-source data fusion analysis module, and dynamically optimize the inspection path to achieve priority inspection of high-risk areas and key equipment; The interactive anomaly warning module first receives a comprehensive risk score for each patrol area. The module compares the risk score with a preset threshold. When comparing, When the system triggers an anomaly warning, the warning information includes the anomaly area number, a list of high-risk equipment within the area, and the risk level. The module outputs the warning information to the operator interface and also uses it as input parameters for patrol route optimization. The criteria for setting comprehensive risk scoring thresholds are typically determined based on the actual operating environment of the substation, the working status of the equipment, and historical anomaly data. The aim is to effectively distinguish between high-risk and low-risk areas, trigger timely anomaly warnings, and ensure the rational allocation of inspection resources. Specific criteria can be set based on the following aspects: Historical data analysis: Based on historical inspection data and equipment operation status of the substation, the historical risk performance of each area is analyzed to determine a baseline risk score. For example, if historical data indicates that the risk score of a certain area is higher than a specific value, it usually means that the area is in a high-risk state. By combining historical temperature anomaly data, equipment failure rate, equipment downtime records, etc., with abnormal performance of the equipment in past inspection cycles, a reasonable preliminary threshold can be derived.

[0034] Equipment level and risk correlation: High-risk equipment (such as main transformers and important transformers) has a greater impact on the stability and security of the overall system than low-risk equipment. Therefore, the comprehensive risk score threshold for areas where high-risk equipment is located can be set appropriately lower to ensure that these areas are prioritized for inspection. For low-risk equipment, a relatively higher threshold can be set, as the failure of these devices has a smaller impact on the overall system security.

[0035] Distribution analysis of risk scores: By statistically analyzing the comprehensive risk scores of each inspection area of ​​the substation, an appropriate distribution range is established. The mean and standard deviation of the risk scores for all areas can be calculated, and a standard value can be set for each score. For example, the high-risk threshold can be set by adding 1-2 standard deviations to the mean, and the low-risk threshold can be set by subtracting the standard deviation. This method ensures that most high-risk areas are effectively screened out while avoiding the false triggering of low-risk areas.

[0036] Real-time data dynamic adjustment: The comprehensive risk scoring threshold can also be dynamically adjusted based on real-time data. For example, in certain special circumstances, such as seasonal changes, equipment aging, or sudden environmental changes, the risk scoring threshold can be appropriately lowered or raised. This dynamic adjustment helps the system maintain a good early warning mechanism under different operating conditions.

[0037] The impact of environmental factors: Environmental data, such as temperature, humidity, and wind speed, also affect equipment operating status and safety. Therefore, threshold settings must consider not only the equipment's condition but also changes in real-time environmental data. For example, if the ambient temperature in a certain area is significantly higher than normal, it may increase the risk of equipment failure. In this case, the threshold can be appropriately lowered to increase the frequency of inspections.

[0038] Expert experience and system feedback: Based on the actual operation of the substation and equipment management experience, experts can set initial risk scoring thresholds. Furthermore, as the system operates, the threshold settings can be continuously adjusted and optimized based on actual inspection results and equipment feedback.

[0039] The inspection route optimization calculates route priority based on the risk score of each area and the current inspection progress. Route optimization can be expressed as: in, Indicates the first Path priority for the inspection area Indicates the regional risk score. This represents the total number of areas inspected. Indicates the current inspection unit and area Distance from the center point. This calculation result is used to adjust the inspection sequence, prioritizing the inspection of high-risk areas that are close to the inspection unit. During the patrol, the system continuously receives real-time data from the infrared temperature measurement acquisition unit and the infrared temperature measurement strategy control module, dynamically adjusting the path priority. When the temperature measurement results show that the temperature index in a certain area is rising rapidly, the path optimization module will immediately increase the patrol priority of that area and feed back to the infrared temperature measurement strategy control module to increase the temperature measurement frequency and scanning angle.

[0040] S5. Closed-loop feedback optimization; The closed-loop feedback optimization module collects output information from the infrared temperature measurement acquisition unit, the dynamic area division module, the multi-source data fusion analysis module, and the interactive anomaly early warning module. It then comprehensively analyzes and optimizes the system inspection strategy to form adaptive closed-loop control, specifically including: The closed-loop feedback optimization module receives temperature data from the infrared temperature acquisition unit, temperature execution records from the infrared temperature measurement strategy control module, regional weights from the dynamic region division module, and path adjustment records from the interactive anomaly early warning module. The module then aggregates this information according to time series and regional series to construct a patrol data matrix. Its elements represent the temperature measurement coverage, anomaly detection, and risk score of each area during different inspection cycles.

[0041] Based on the inspection data matrix The closed-loop feedback optimization module calculates the regional optimization coefficient. in, Indicates the first The urgency coefficient of the inspection needs in the inspection area This indicates the regional temperature monitoring coverage rate. This represents the regional anomaly detection rate index. Indicates the rate of change in regional risk scores. The weighting coefficients are used to optimize the influence of each indicator in the overall optimization process. The regional temperature measurement coverage rate index represents the actual coverage of infrared temperature measurement in the inspected area during the inspection cycle. It compares the number of times all equipment or grid units in the area are measured during the current inspection cycle with the theoretical number of measurements that should be taken (such as the total number of measurements calculated according to the regional weight and temperature measurement frequency plan).

[0042] The formula can be expressed as: in, Indicates the first Temperature measurement coverage of each patrol area.

[0043] The regional anomaly detection rate index represents the proportion of abnormal equipment successfully detected in the patrol area during the patrol cycle; it is the ratio of the number of abnormal devices in the area to the total number of devices in the area.

[0044] The formula can be expressed as: in, Indicates the first The anomaly detection rate of each patrol area.

[0045] The rate of change of regional risk score indicates the change in the risk level of the inspected area relative to the previous inspection cycle, and is used to reflect the dynamics of risk. The difference between the regional comprehensive risk score in the current inspection cycle and the score in the previous inspection cycle is taken and then divided by the score in the previous inspection cycle for normalization.

[0046] Optimization coefficient This comprehensively reflects the temperature measurement coverage, anomaly detection, and risk changes in each region, and calculates path priority based on the optimization coefficient for each region. , The larger the value, the more likely the area is to have insufficient coverage, numerous anomalies, or increased risk; therefore, it will be given a higher path priority in route planning. This ensures that high-risk or critical equipment areas are inspected and tested in a timely manner, specifically: in The function represents the distance between the patrol unit and the center of the region. By combining optimization coefficients with distance, the inspection sequence is dynamically generated.

[0047] Simultaneously, optimization coefficients are used to control parameters of the infrared temperature measurement strategy, such as the measurement frequency and scanning angle: a high optimization coefficient region can improve the measurement frequency and scanning accuracy, while a low optimization coefficient region can moderately reduce the measurement intensity, saving inspection resources. Specifically: The system makes its judgment based on the relative magnitude of the optimization coefficient across all inspection areas: Regions with high optimization coefficients: Or before sorting A region indicates a high level of overall risk, anomaly rate, and coverage efficiency.

[0048] Region with low optimization coefficient: Or after sorting The area indicates a lower overall index, and the intensity of patrols can be appropriately reduced.

[0049] in This is the average of the optimization coefficients for all areas in the current inspection round. The standard deviation is the statistical standard deviation of the optimization coefficients for all inspected areas in the current inspection round. This is an adjustable coefficient used to flexibly control high and low threshold values; The optimization coefficient is the result of closed-loop calculation for each round of inspections and will be dynamically updated according to changes in temperature measurement coverage, anomaly detection, and risk.

[0050] The closed-loop feedback optimization module adjusts the dynamic area division and infrared temperature measurement strategy for the next round based on the optimization coefficient. Areas with high optimization coefficients will have their temperature measurement frequency and path priority increased in the next round of inspections, while the inspection frequency of areas with low optimization coefficients can be appropriately reduced, thereby improving the overall inspection efficiency of the system while ensuring coverage of critical equipment and high-risk areas.

[0051] This invention quantifies equipment level, historical anomalies, and environmental factors into operable regional weights through dynamic region division and priority weight generation. This enables refined management of critical equipment and high-risk areas, allowing for centralized utilization of infrared thermography resources while avoiding blind spots and resource waste inherent in traditional inspection methods. Secondly, the multi-source data fusion and risk assessment module employs standardized processing and weighted fusion methods to uniformly quantify different types of data, achieving a comprehensive assessment of the overall risk of the substation and making anomaly warnings more accurate and reliable. Furthermore, the interactive anomaly warning and path optimization module dynamically adjusts the inspection sequence and temperature measurement strategy through optimization coefficients, achieving a synergistic improvement in inspection efficiency and anomaly detection rate, ensuring the system adaptively updates and optimizes during multiple rounds of inspections.

[0052] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A dynamic area infrared temperature measurement interactive method for intelligent inspection of substations, characterized in that: Includes the following steps: S1. Based on the equipment distribution, equipment level, historical temperature anomaly records, and environmental data within the substation, the inspection area is divided. Historical temperature anomaly indicators are generated through historical temperature anomaly records, and the regional weight of each inspection area is generated. S2. Adjust the acquisition parameters of the infrared temperature measurement acquisition unit for each patrol area according to the area weight; S3. Collect electrical parameters and perform standardized processing and weighted fusion with historical temperature anomaly indicators and environmental data to generate a comprehensive risk score for each inspection area; S4. A comprehensive risk score threshold is preset and compared with the comprehensive risk score. When the comprehensive risk score is greater than the comprehensive risk score threshold, an abnormal warning is triggered, and the patrol path is adjusted according to the comprehensive risk score and the current patrol progress. S5. Collect the temperature coverage rate, anomaly detection rate and risk score change rate of each patrol area in different patrol cycles, calculate the optimization coefficient of each patrol area, and adjust the patrol path for the next round based on the optimization coefficient.

2. The dynamic area infrared temperature measurement interactive method for intelligent substation inspection according to claim 1, characterized in that: In step S1, the region weight is calculated as follows: The sum of the equipment level values ​​and the sum of historical temperature anomaly indicators of all equipment in the inspection area are calculated separately. The sum of the equipment level values, the sum of the historical temperature anomaly indicators, and the environmental factor indicators of the area are then weighted and summed to obtain the regional weight of the inspection area.

3. The dynamic area infrared temperature measurement interactive method for intelligent substation inspection according to claim 1, characterized in that: The specific process of dividing the inspection area in S1 includes: Obtain the spatial coordinates and importance level of all equipment in the substation, divide the substation space into equidistant grid cells, and ensure that each grid cell contains at least one piece of equipment. Identify the equipment level within a grid cell and merge grid cells with a high density of high-level equipment into separate key inspection areas; Merge low-level or scattered grid cells based on spatial proximity; Obtain historical temperature anomaly indicators from the equipment, and prioritize merging grid cells with historical anomaly frequency or amplitude higher than the preset standard to form high-risk inspection areas.

4. The dynamic area infrared temperature measurement interactive method for intelligent substation inspection according to claim 1, characterized in that: In step S2, the calculation method for the acquisition parameters includes: Calculate the difference between the regional weight of the inspected area and the minimum weight among all regions; The difference is multiplied by the frequency adjustment coefficient to obtain the frequency increment, and the minimum sampling frequency is added to the frequency increment to obtain the infrared temperature measurement sampling frequency of the inspection area. The difference is multiplied by the angle adjustment coefficient to obtain the angle increment, and the minimum scanning angle is added to the angle increment to obtain the optimized scanning angle of the inspection area.

5. The dynamic area infrared temperature measurement interactive method for intelligent substation inspection according to claim 1, characterized in that: In step S3, the comprehensive risk score is calculated as follows: Calculate the average value of the normalized infrared thermometer values ​​and the average value of the comprehensive electrical parameters of all equipment in the inspection area. The average value of the normalized infrared thermometry value, the average value of the comprehensive electrical parameter index, and the comprehensive regional environmental factor index are weighted and summed to obtain the comprehensive risk score of the patrol area.

6. The dynamic area infrared temperature measurement interactive method for intelligent substation inspection according to claim 1, characterized in that: In step S4, the setting standard for the preset comprehensive risk scoring threshold is dynamically adjusted based on the statistical distribution of historical data from the substation, specifically including: Calculate the mean and standard deviation of the comprehensive risk score for all inspected areas; The sum of the multiples of the mean and the standard deviation is set as the threshold for the comprehensive risk score, wherein the multiples of the standard deviation are determined by an adjustment factor; The adjustment factor is dynamically corrected based on real-time environmental data. When the ambient temperature is higher than the set value, the adjustment factor is lowered.

7. The dynamic area infrared temperature measurement interactive method for intelligent substation inspection according to claim 1, characterized in that: In S4, the calculation method for adjusting the inspection path based on the comprehensive risk score and the current inspection progress is as follows: Calculate the distance between the current inspection unit and the center point of the inspection area, and use the sum of the distance and non-zero constants as the distance factor; Calculate the ratio of the comprehensive risk score of the inspection area to the distance factor, and use this ratio as the path priority for the inspection area; The patrol queue is dynamically adjusted according to the path priority from highest to lowest, so that high-risk and nearby areas are patrolled first.

8. The dynamic area infrared temperature measurement interactive method for intelligent substation inspection according to claim 1, characterized in that: In step S5, the optimization coefficient is calculated as follows: Calculate the regional temperature measurement coverage rate index, which is determined based on the ratio of the actual number of temperature measurements to the theoretical number of measurements required; Calculate the regional anomaly detection rate index, which is the ratio of the number of abnormal devices in the region to the total number of devices; Calculate the regional risk score change rate, which is the ratio of the change in the regional risk score relative to the previous inspection cycle. The optimization coefficient of the patrol area is obtained by weighted summing of the area temperature coverage rate index, the area anomaly detection rate index, and the area risk score change rate.

9. The dynamic area infrared temperature measurement interactive method for intelligent substation inspection according to claim 1, characterized in that: The strategy in S5 that adjusts based on the optimization coefficient feedback includes: Calculate the statistical distribution of optimization coefficients for all areas in the current inspection round; When the optimization coefficient of a certain region is in the high distribution range, the path priority of that region will be increased in the next round of dynamic region division, and the infrared temperature measurement strategy control module will be instructed to increase the temperature measurement frequency and temperature measurement scanning angle of that region. When the optimization coefficient of a certain area is in a low distribution range, the temperature measurement intensity of that area should be maintained or appropriately reduced in the next round of inspection.

10. The dynamic area infrared temperature measurement interactive method for intelligent substation inspection according to claim 1, characterized in that: The judgment is made based on the relative magnitude of the optimization coefficient across all inspection areas: Regions with high optimization coefficients: This indicates that the overall risk, anomaly rate, and coverage efficiency are all relatively high. Region with low optimization coefficient: This indicates that the overall indicators are low, and the intensity of the patrols should be appropriately reduced. in To optimize the coefficients, This is the average of the optimization coefficients for all areas in the current inspection round. This represents the statistical standard deviation of the optimization coefficients for all inspected areas in the current inspection round. This is an adjustable coefficient.

Images