Intelligent sensor-based live detection method and system for zero-value insulator

Abstract

The application relates to the technical field of live detection, in particular to a live detection method and system for zero-value insulators based on intelligent sensors, which realizes the intelligentization of the whole process of the operation state of insulators by integrating the dynamic correlation of power load fluctuation, environmental erosion effect and the health state of the body, can not only accurately evaluate the current health degree, but also can predict the performance evolution trend in the future, finally converts passive maintenance into active protection through the early warning module, significantly improves the preventive maintenance ability and safety and reliability of power grid operation, and effectively avoids the cascading failure risk caused by the failure of insulators.

Description

Technical Field

[0001] This application relates to the field of live-line detection technology, and in particular to a live-line detection method and system for zero-value insulators based on intelligent sensors. Background Technology

[0002] Insulators, as key equipment in transmission lines and substations, play a dual role of mechanical support and electrical insulation. Their operational reliability directly affects the safety and stability of the entire power grid. However, insulators are exposed to complex and changing natural and electrical environments for a long time, and their performance will gradually deteriorate due to aging, pollution, cracks and other factors, which may lead to serious accidents such as breakdown, flashover or even string breakage.

[0003] Currently, insulator condition assessment technology mainly relies on various online monitoring methods, such as leakage current monitoring, electric field measurement, ultrasonic detection, and infrared thermography analysis. These technologies can acquire physical quantities reflecting the current health status of insulators (such as equivalent salt density, peak leakage current, etc.), and issue alarms based on these real-time or near-real-time data, combined with preset static thresholds. However, with the increasing scale of power grids and the growing complexity of load structures, especially the integration of a large number of highly volatile renewable energy sources and the switching on and off of large industrial loads, traditional assessment methods have revealed the following significant limitations: Existing methods are based on historical or current operational data, which cannot predict power flow changes caused by planned future events (such as the commissioning of new industrial parks, the start of large-scale municipal projects, or seasonal load surges). When the load suddenly increases in the future, even if the insulators are currently in good condition, they may face risks such as overheating and accelerated insulation degradation due to their inability to withstand the expected current surge. In summary, existing insulator condition assessment technologies are insufficient to meet the high-level requirements of modern power grids for forward-looking risk warnings, comprehensive assessment dimensions, and intelligent decision support. Summary of the Invention

[0004] To overcome the shortcomings and deficiencies of existing technologies, this application provides a method and system for detecting zero-value insulators based on intelligent sensors. This solution integrates the dynamic correlation between power load fluctuations, environmental erosion effects, and the insulator's health status, realizing full-process intelligent monitoring of the insulator's operating status. It can not only accurately assess the current health status but also predict future performance evolution trends. Ultimately, through the early warning module, it transforms passive maintenance into active protection, significantly improving the preventive maintenance capabilities and safety and reliability of the power grid, and effectively avoiding the risk of cascading failures caused by insulator failure.

[0005] To achieve the above objectives, this application adopts the following technical solution: In a first aspect, this application provides a zero-value insulator live-line detection system based on intelligent sensors, comprising the following modules: The system includes an insulator condition acquisition module, a power condition analysis module, an environmental analysis module, an insulator analysis module, a future operation prediction module, and an early warning module. The insulator condition acquisition module acquires the appearance and operational data of the insulators. The power condition analysis module analyzes the power demand fluctuations and power load conditions of the corresponding loads and assesses future power impact. The environmental analysis module analyzes the environmental impact of the area where the insulators are located. The insulator analysis module performs health analysis on the insulators based on their appearance and operational data. The future operation prediction module predicts the future operational performance of the insulators based on the future power impact assessment results, environmental impact results, and insulator health analysis results. The early warning module issues early warnings based on the predicted future operational performance of the insulators.

[0006] In one implementation of this application, the acquisition of the appearance and operation data of the insulators includes the following specific content: using a drone equipped with a high-definition visible light camera, infrared thermal imager, ultraviolet imager and other equipment to perform a full-range, multi-spectral scan of the insulator string from the air to acquire the appearance image and heating status of the insulators of the high-altitude line; and acquiring the leakage current and electric field distribution of the corresponding insulator equipment through a fixedly installed online monitoring device.

[0007] In one implementation of this application, the future power impact assessment includes the following specific steps: The first step is to obtain the future power consumption plan of the load. This can be obtained from the load plan, such as for large-scale projects. If there is no plan, it is necessary to make an estimate. The estimation process can be obtained through historical power data and environmental data. The power consumption changes in different time periods are obtained. Traditional insulator condition assessment is mostly based on historical or current data and is a passive response. However, this step actively obtains or predicts future load changes and incorporates future power demand into the assessment system. This allows the system to detect the potential current impact caused by the commissioning of large-scale projects or seasonal load changes in advance, providing key data input for subsequent assessment of the pressure that power equipment will bear under future real operating conditions. The second step involves obtaining the electricity consumption and fluctuations for each future time period. The current anomaly for each time period is obtained by dividing the current for each future time period by the current safe current of the insulator. The current anomaly for the future period is then obtained by integrating the current anomalies for each time period over time and dividing by the period duration. The current safe current of the insulator is determined by multiplying the current insulator's health status by a health influence coefficient. This health influence is then multiplied by the insulator's factory safe current to obtain the current safe current. This approach does not simply compare the future current with a fixed safety threshold; instead, it introduces the dynamic concept of the current safe current. This current value is dynamically corrected based on the insulator's real-time health status, ensuring that the safety benchmark accurately reflects the current aging or contamination status of the equipment. This results in a more objective and reliable assessment. Finally, by integrating and averaging the current anomalies for each future time period over time, the resulting future period current anomaly is a scalar value that comprehensively reflects the average overload pressure level throughout the entire assessment period. The third step is to obtain the power consumption fluctuation situation for each time period in the future. The current fluctuation impact anomaly at the corresponding time is obtained by subtracting the current situation at the next time from the current situation at the previous time within the cycle and dividing the absolute value by the current situation at the next time by the current current of the insulator. The current fluctuation anomaly in the future cycle is obtained by obtaining the average value of the current fluctuation impact anomaly within the cycle. In the power system, many faults are not caused by stable overloads, but by violent load fluctuations. Such fluctuations will generate huge electrodynamic forces and thermal stresses, accelerating equipment aging. This step defines the current fluctuation impact anomaly by calculating the ratio of the absolute value of the current change at adjacent time moments to the current safe current, effectively measuring the intensity of such instantaneous impacts. The fourth step is to obtain the future power impact assessment result by weighted summation of the future cycle current anomaly and the future cycle current fluctuation anomaly. This step integrates the two key indicators calculated in the first two steps, which represent the steady-state risk of the future cycle current anomaly and the future cycle current fluctuation anomaly of the future cycle, which represent the dynamic risk, by weighted summation.

[0008] In one implementation of this application, the environmental impact specifically includes the following: The first step involves obtaining the size and density of airborne particulate matter for future periods through weather forecast terminals, along with air wind speed and humidity, as well as the flatness and surface area-to-volume ratio of the corresponding insulator's outer surface. After obtaining a 3D digital model through 3D scanning, the accompanying 3D software can estimate the precise surface area-to-volume ratio of the model. The flatness of the corresponding insulator's outer surface is represented by the arithmetic mean of the absolute values ​​of the height deviations of each point on the surface from the reference plane. Introducing 3D scanning technology to obtain a true model of the insulator and calculating the precise surface area-to-volume ratio provides a reliable geometric basis for subsequent analysis of pollutant adhesion and aggregation trends. Obtaining future meteorological and particulate matter data makes the entire assessment model forward-looking, capable of predicting rather than merely responding to environmental changes. The second step is to obtain the flatness of the outer surface of the insulator and the surface area-to-volume ratio. The data are divided by the maximum safe range of the corresponding data type, and the resulting ratios are weighted and summed to obtain the surface aggregation anomaly of the insulator. This achieves a quantitative assessment and comprehensive evaluation of the insulator's susceptibility to contamination. By normalizing different physical quantities, the influence of dimensions is eliminated, allowing data that were originally incomparable to be calculated under the same standard. The third step involves obtaining the average wind speed and humidity at the corresponding location, dividing the data by the maximum safe range for each data type, and then weighting and summing the resulting ratios to obtain weather impact anomalies. The average diameter of airborne particles and the average diameter of pits on the insulator surface are then obtained. The difference between the average diameter of airborne particles and the average diameter of pits on the insulator surface is calculated and divided by the sum of the average diameters of airborne particles and pits on the insulator surface to obtain similarity anomalies in their diameters. The greater the similarity, the more difficult it is for particles to be removed after entering the pit. The particle density is divided by the safe density to obtain density anomalies. The density anomalies and diameter similarity anomalies are then weighted and summed to obtain pollutant anomalies. The impact of weather conditions on pollutant transport and adhesion, and the impact of the pollutant's own characteristics on adhesion firmness are processed in a hierarchical manner. The fourth step involves weighted summation of pollutant anomalies and weather impact anomalies, followed by multiplication with insulator surface aggregation anomalies to obtain the environmental impact assessment. This achieves a comprehensive, non-linear assessment of environmental risk. The intermediate indicators obtained in the previous steps are fused at a higher order, and any low anomaly value in any step will significantly reduce the final environmental impact risk value.

[0009] In one implementation of this application, the health analysis of the insulator includes the following specific aspects: The first step is to obtain images of the insulator's appearance, heating status, and leakage current. The second step is to obtain the surface damage condition of the insulation value and the average distance from the damage point to the circuit connection point. The damage anomaly is obtained by dividing the surface damage volume by the safe damage volume, the distance anomaly is obtained by dividing the safe distance by the average distance from the damage point to the circuit connection point, and the damage anomaly is obtained by multiplying the distance anomaly by the damage anomaly. The third step is to obtain the temperature anomaly by dividing the temperature at the insulator connection by the maximum safe temperature, and the current anomaly by dividing the leakage current of the insulator by the maximum safe current. The health of the insulator is obtained by taking the weighted sum of the damage anomaly, temperature anomaly, and current anomaly and then taking the reciprocal. In the process of taking the reciprocal, a very small positive number needs to be added to the denominator to avoid the denominator being 0 and the fraction being meaningless.

[0010] In one implementation of this application, the prediction of the future operating performance of the insulator includes the following specific details: The system obtains the current cycle insulator health status, environmental impact status, and future power impact assessment results. It then calculates the future scenario anomaly by weighted summation of these results. Subtracting the future scenario anomaly from the current value yields the scenario impact residual coefficient. Multiplying the current cycle insulator health status by this residual coefficient yields the predicted operational performance of the insulator in the future cycle. Weighted fusion of the environmental impact status and future power impact assessment results generates a quantitative index of future scenario anomalies that comprehensively reflects external environmental stress and system operational requirements. Furthermore, subtracting the future scenario anomaly from the current value defines the scenario impact residual coefficient, which directly represents the proportion of residual capacity that the insulator can maintain under multiple adverse external factors. Finally, multiplying the current cycle insulator health status by this residual coefficient enables accurate and dynamic prediction of the equipment's performance evolution in future cycles.

[0011] In one implementation of this application, the early warning based on the predicted future operating performance of the insulator includes the following specific details: The system obtains the predicted operating performance of insulators for future cycles and compares it with the set safety threshold. If the predicted operating performance is greater than or equal to the set safety threshold, it means that the insulation value for the future cycle can meet the requirements and no replacement is needed. If the predicted operating performance is less than the set safety threshold, it means that the insulation value for the future cycle cannot meet the requirements and replacement is needed. A replacement alarm is then sent to the staff.

[0012] Secondly, this application also provides a method for detecting the liveness of zero-value insulators based on smart sensors, including the following specific steps: Obtain information on the appearance and operational data of the insulators; Analyze the fluctuations in power demand and power load of the corresponding load to assess the future impact on power. Analyze the environmental impact of the area where the insulator is located; Health analysis of insulators is conducted based on their appearance and operational data. Based on the future power impact assessment results, environmental impact situation, and insulator health analysis results, the future operating performance of insulators is predicted; Early warnings are issued based on predictions of the future operating performance of insulators.

[0013] Thirdly, this application provides an electronic device comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes a method for detecting the liveness of a zero-value insulator based on a smart sensor by calling the computer program stored in the memory.

[0014] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform a method for detecting the liveness of zero-value insulators based on intelligent sensors.

[0015] Compared with the prior art, this application has the following advantages and beneficial effects: This solution integrates the dynamic correlation between power load fluctuations, environmental erosion effects, and the insulator's health status to achieve intelligent monitoring of the entire insulator operation process. It can not only accurately assess the current health status but also predict future performance evolution trends. Ultimately, through the early warning module, it transforms passive maintenance into proactive protection, significantly improving the preventive maintenance capabilities and safety and reliability of the power grid operation, and effectively avoiding the risk of cascading failures caused by insulator failure. Attached Figure Description

[0016] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a schematic diagram of the overall process structure of an embodiment of the method of this application; Figure 2 This is a schematic diagram of the steps involved in the insulator health analysis according to an embodiment of the method of this application; Figure 3 This is a schematic diagram of the module composition structure of an embodiment of the system in this application. Detailed Implementation

[0017] The technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments and specific features in the embodiments are detailed descriptions of the technical solution of this application, rather than limitations thereof. In the absence of conflict, the embodiments and technical features in the embodiments can be combined with each other.

[0018] Please see Figures 1 to 2 , Figure 1 This is a schematic diagram of the overall process of the zero-value insulator live-line detection method based on smart sensors provided in the embodiments of this application, which specifically includes the following steps: Obtain information on the appearance and operational data of the insulators; In this embodiment, obtaining the appearance and operation data of the insulators includes the following specific content: using a drone equipped with a high-definition visible light camera, infrared thermal imager, ultraviolet imager and other equipment, the insulator string is scanned from the air in all directions and multiple spectrums to obtain the appearance image and heating status of the insulators of the high-altitude line; and the leakage current and electric field distribution of the corresponding insulator equipment are obtained through fixedly installed online monitoring devices (such as leakage current sensor and electric field distribution sensor). Analyze the fluctuations in power demand and power load of the corresponding load to assess the future impact on power. In this embodiment, the future power impact assessment includes the following specific steps: The first step is to obtain the future power consumption plan of the load. This can be obtained from the load plan, such as for large-scale projects. If there is no plan, it needs to be estimated. The estimation process can be obtained through historical power data and environmental data. This estimation method is described in detail in existing technologies such as "Residential Power Consumption Forecasting Technology and Application Based on Neural Network Model" and "Research on Residential Power Consumption Load Optimization Based on Hybrid Long Short-Term Memory Neural Network". This is not the main improvement point, so it will not be described in detail here. The next step is to obtain the power consumption change situation in each time period. Traditional insulator condition assessment is mostly based on historical or current data and is a passive response. However, this step actively obtains or predicts future load changes and incorporates future power demand into the assessment system. This allows the system to perceive the potential current impact caused by the commissioning of large-scale projects or seasonal load changes in advance, providing key data input for subsequent assessment of the pressure that power equipment will bear under future real operating conditions. In this example, the period is set by the staff and can be set to one day or one week, etc. The second step involves obtaining the electricity consumption and fluctuations for each future time period. The current anomaly for each future time period is obtained by dividing the current for that period by the current safety current of the insulator. The current anomaly for the future period is then obtained by integrating the current anomalies for each time period within the future cycle and dividing by the cycle length. The current safety current of the insulator is determined as follows: the current insulator health level is multiplied by a health influence coefficient to obtain the health influence. This health influence is then multiplied by the insulator's factory-set safety current (manufacturer test settings) to obtain the current safety current. This is not a simple comparison of future currents with a fixed safety threshold, but rather the introduction of a dynamic concept: the current safety current. This current value is determined by the insulator's actual... The health status is dynamically corrected in real time, so that the safety benchmark can truly reflect the current aging or pollution status of the equipment, and the assessment results are more objective and reliable. Furthermore, by integrating and averaging the current anomalies of each time period in the future over the time dimension, the final future cycle current anomaly is a scalar value that can comprehensively reflect the average overload pressure level within the entire assessment cycle. The factory safety current is corrected by real-time health status and influence coefficient, so that the safety threshold is adaptively adjusted with the aging and pollution status of the insulator, and more accurately reflects the current tolerance of the equipment. The current anomalies of each time period in the cycle are weighted by time length and averaged to obtain a scalar value that reflects the average overload pressure of the entire cycle, avoiding misjudgment caused by instantaneous peak values. The third step is to obtain the power consumption fluctuation situation for each future time period. The current fluctuation impact anomaly at the corresponding time is obtained by subtracting the current situation at the next time from the current situation at the previous time within the cycle and dividing the absolute value by the current situation at the current situation at the next time by the current situation at the current situation of the insulator. The current fluctuation anomaly in the future cycle is obtained by obtaining the average value of the current fluctuation impact anomaly within the cycle. In the power system, many faults are not caused by stable overloads, but by drastic load fluctuations (such as the start and stop of large motors). Such fluctuations will generate huge electrodynamic forces and thermal stresses, accelerating equipment aging. This step defines the current fluctuation impact anomaly by calculating the ratio of the absolute value of the current change at adjacent time moments to the current safe current, effectively measuring the intensity of this instantaneous impact. The ratio of the absolute value of the current change at adjacent time moments to the current safe current directly measures the electrodynamic and thermal stress impacts generated by drastic load fluctuations (such as the start and stop of large motors). Such instantaneous stresses are an important cause of mechanical fatigue and thermal aging of insulators. The fourth step is to obtain the future power impact assessment result by weighted summation of the future cycle current anomaly and the future cycle current fluctuation anomaly. This step integrates the two key indicators calculated in the first two steps, which represent the steady-state risk of the future cycle current anomaly and the future cycle current fluctuation anomaly of the future cycle, which represent the dynamic risk, by weighted summation. Analyze the environmental impact of the area where the insulator is located; In this embodiment, the environmental impact includes the following specific details: The first step involves obtaining the size and density of airborne particulate matter for future periods through weather forecast terminals, along with air wind speed and humidity, as well as the flatness and surface area-to-volume ratio of the corresponding insulator's outer surface. After obtaining a 3D digital model through 3D scanning, the accompanying 3D software can estimate the precise surface area-to-volume ratio of the model. The flatness of the corresponding insulator's outer surface is represented by the arithmetic mean of the absolute values ​​of the height deviations of each point on the surface from the reference plane. Introducing 3D scanning technology to obtain a true model of the insulator and calculating the precise surface area-to-volume ratio provides a reliable geometric basis for subsequent analysis of pollutant adhesion and aggregation trends. Obtaining future meteorological and particulate matter data makes the entire assessment model forward-looking, capable of predicting rather than merely responding to environmental changes. The second step involves obtaining the flatness of the insulator's outer surface and its surface area to volume ratio. The data is then divided by the maximum safe range for the corresponding data type, and the resulting ratios are weighted and summed to obtain the surface aggregation anomaly of the insulator. This achieves a quantitative assessment and comprehensive evaluation of the insulator's susceptibility to contamination. By normalizing different physical quantities, the influence of dimensions is eliminated, allowing previously incomparable data to be calculated under the same standard. Surface roughness (flatness) and complex geometric structure (surface area to volume ratio) directly affect the ability to capture and adhere to pollutants. Normalization eliminates dimensional differences and enables a comprehensive evaluation of multiple physical quantities. The third step involves obtaining the average wind speed and humidity at the corresponding location. The data is divided by the maximum safe range for each data type, and the resulting ratios are weighted and summed to obtain weather impact anomalies. The average diameter of airborne particles and the average diameter of pits on the insulator surface are obtained. The difference between the average diameter of airborne particles and the average diameter of pits on the insulator surface is calculated and divided by the sum of their diameters to obtain similarity anomalies. Larger similarities indicate greater difficulty in removing particles once they enter the pit. The particle density is divided by the safe density to obtain density anomalies. The density anomalies and diameter similarity anomalies are weighted and summed to obtain pollutant anomalies. The influence of weather conditions (wind speed, humidity) on pollutant transport and adhesion, and the influence of pollutant characteristics (particle density, particle size matching) on ​​adhesion strength are processed hierarchically. When the particle diameter is similar to the surface pit size, pollutants are easily embedded and difficult to remove by wind and rain. Diameter similarity anomalies quantify this mechanical locking effect. The effects of meteorological conditions (wind speed, humidity) on pollutant transport and the influence of pollutant characteristics (density, particle size) on adhesion stability are evaluated separately and then fused. The fourth step involves weighted summation of pollutant anomalies and weather impact anomalies, followed by multiplication with insulator surface aggregation anomalies to obtain the environmental impact assessment. This achieves a comprehensive, non-linear assessment of environmental risk. The intermediate indicators obtained in the previous steps (insulator surface aggregation anomalies, weather impact anomalies, and pollutant anomalies) are fused in a higher order. If the anomaly value of any one of these factors is low (for example, the insulator surface is smooth and does not easily accumulate pollutants, or the weather conditions are conducive to dispersing pollutants), the final environmental impact risk value will be significantly reduced. Health analysis of insulators is conducted based on their appearance and operational data. In this embodiment, the health analysis of the insulator includes the following specific contents: The first step is to obtain images of the insulator's appearance, heating status, and leakage current. The second step is to obtain the surface damage condition of the insulation value and the average distance from the damage point to the circuit connection point. The damage anomaly is obtained by dividing the surface damage volume by the safe damage volume, and the distance anomaly is obtained by dividing the safe distance by the average distance from the damage point to the circuit connection point. The damage anomaly is obtained by multiplying the distance anomaly and the damage anomaly. The closer the damage is to the circuit connection point, the more significant the impact on electric field distortion and leakage current. The product relationship between the distance anomaly and the damage anomaly reflects the spatial amplification effect. The third step is to obtain the temperature anomaly by dividing the temperature at the insulator connection by the maximum safe temperature, and the current anomaly by dividing the leakage current of the insulator by the maximum safe current. The health of the insulator is obtained by taking the weighted sum of the damage anomaly, temperature anomaly, and current anomaly and then taking the reciprocal. In the process of taking the reciprocal, a very small positive number needs to be added to the denominator to avoid the denominator being 0 and the fraction being meaningless. Based on the future power impact assessment results, environmental impact situation, and insulator health analysis results, the future operating performance of insulators is predicted; In this embodiment, the prediction of the future operating performance of the insulator includes the following specific details: The system obtains the current cycle insulator health status, environmental impact status, and future power impact assessment results. It then calculates the future scenario anomaly by weighted summation of these results. Subtracting the future scenario anomaly from the current value yields the scenario impact residual coefficient. Multiplying the current cycle insulator health status by this residual coefficient yields the predicted operational performance of the insulator in the future cycle. Weighted fusion of the environmental impact status and future power impact assessment results generates a quantitative index of future scenario anomalies that comprehensively reflects external environmental stress and system operational requirements. Furthermore, subtracting the future scenario anomaly from the current value defines the scenario impact residual coefficient, which directly represents the proportion of residual capacity that the insulator can maintain under multiple adverse external factors. Finally, multiplying the current cycle insulator health status by this residual coefficient enables accurate and dynamic prediction of the equipment's performance evolution in future cycles. Early warning is issued based on the predicted future operating performance of the insulators; In this embodiment, the early warning based on the predicted future operating performance of the insulator includes the following specific aspects: The system obtains the predicted operating performance of insulators for future cycles and compares it with the set safety threshold. If the predicted operating performance is greater than or equal to the set safety threshold, it means that the insulation value for the future cycle can meet the requirements and does not need to be replaced. If the predicted operating performance is less than the set safety threshold, it means that the insulation value for the future cycle cannot meet the requirements and needs to be replaced. A replacement alarm is then sent to the staff. The advantages of the above embodiments are as follows: by integrating the dynamic correlation between power load fluctuations, environmental erosion effects and the physical health status of the insulator, the entire process of intelligent management of the insulator's operating status is realized. It can not only accurately assess the current health status, but also predict future performance evolution trends. Finally, through the early warning module, passive maintenance is transformed into active protection, which significantly improves the preventive maintenance capability and safety and reliability of the power grid operation, and effectively avoids the risk of chain failures caused by insulator failure.

[0019] This section requires a detailed explanation of the specific value selection method for the parameters (such as thresholds and weighting weights) in this embodiment. At least 500 sets of historical data related to the insulator condition assessment in this example are obtained, along with the judgment result regarding whether the insulator can operate normally in the next cycle. The insulator condition assessment data is imported into each step of this embodiment for calculation to obtain the operational performance prediction result. The calculated operational performance prediction result and the judgment result regarding whether the insulator can operate normally in the next cycle are simultaneously imported into MATLAB fitting software for data fitting iteration. An example of the set parameters that satisfy the judgment result accuracy exceeding the set threshold is output. Specific fitting steps are as follows: First, collect and organize at least 500 sets of complete historical data. Each set of data should include all input variables of the model (e.g., future load power consumption planning data, 3D scan data of insulator appearance, leakage current, infrared temperature, ambient wind speed, humidity, particulate matter data, etc.) and the corresponding "standard answer," that is, the objective judgment result of whether the insulator will operate normally in the next cycle (e.g., 1 represents normal, 0 represents fault or needs replacement). In MATLAB, these input variables are constructed into feature vectors according to the model's calculation process (health analysis, future power impact assessment, environmental impact assessment), and the judgment results are constructed into label vectors. The entire assessment and prediction process described is implemented in MATLAB as a parameterized function. The input of this function is the historical data feature vector and a set of parameters to be determined (including but not limited to: health impact coefficient, weights of current anomalies and current fluctuation anomalies in the future power impact assessment, weights of each sub-item in the environmental impact assessment (such as surface aggregation anomalies, weather impact anomalies, pollutant anomalies) and their internal calculation of the maximum safe range and safety threshold, etc.), and the output is the future operation of the insulator. The performance prediction results are then analyzed. An objective function is defined to calculate the consistency between the model's predictions (typically converted to binary classification after comparison with a threshold) and historical true labels, for example, using accuracy as the optimization objective. In MATLAB, a global optimization algorithm, such as a genetic algorithm or particle swarm optimization, is chosen to solve this optimization problem. The optimization algorithm runs multiple iterations. In each generation, it calculates the prediction accuracy of the entire model on 500 sets of historical data using a set of candidate parameter solutions. Based on the accuracy, the algorithm retains the best parameter combinations and generates new, potentially better parameter combinations by simulating natural evolution (genetic algorithm) or swarm intelligence (particle swarm optimization). This process continues until a preset number of iterations is reached or the accuracy improvement is no longer significant. After the optimization process is complete, the algorithm outputs a set of parameter combinations that achieve the highest prediction accuracy on historical data (ideally exceeding a certain threshold, such as 95%). This set of parameters is the optimal parameter set obtained through data-driven fitting. Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of the zero-value insulator live-line detection system based on intelligent sensors provided in an embodiment of this application, including: The system comprises an insulator condition acquisition module, a power condition analysis module, an environmental analysis module, an insulator analysis module, a future operation prediction module, and an early warning module. The insulator condition acquisition module acquires the appearance and operational data of the insulators. The power condition analysis module analyzes the power demand fluctuations and power load conditions of the corresponding loads and conducts future power impact assessments. The environmental analysis module analyzes the environmental impact of the area where the insulators are located. The insulator analysis module performs health analysis on the insulators based on their appearance and operational data. The future operation prediction module predicts the future operational performance of the insulators based on the future power impact assessment results, environmental impact results, and insulator health analysis results. The early warning module issues early warnings based on the predicted future operational performance of the insulators.

[0020] The parameters and steps for implementing the corresponding functions of each unit module in the zero-value insulator live-line detection system based on intelligent sensors described above can be referred to the parameters and steps in the embodiments of the zero-value insulator live-line detection method based on intelligent sensors described above, and will not be repeated here.

[0021] Embodiments of this application also provide an electronic device, including a memory, a processor, and a communication bus; the memory and the processor are connected via the communication bus. The memory stores a method for detecting the liveness of zero-value insulators based on smart sensors, which can be loaded by the processor and executed as provided in the above embodiments.

[0022] The memory can be used to store instructions, programs, code, code sets, or instruction sets. The memory may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing the zero-value insulator live-line detection method based on intelligent sensors provided in the above embodiments. The data storage area may store data involved in the zero-value insulator live-line detection method based on intelligent sensors provided in the above embodiments.

[0023] A processor may include one or more processing cores. The processor executes instructions, programs, code sets, or instruction sets stored in memory, and calls data stored in memory to perform various functions and process data as described in this application. The processor may be at least one of a specific application-specific integrated circuit, a digital signal processor, a digital signal processing device, a programmable logic device, a field-programmable gate array, a central processing unit, a controller, a microcontroller, and a microprocessor. It is understood that, for different devices, the electronic devices used to implement the above-described processor functions may also be other types, and the embodiments of this application do not specifically limit this.

[0024] A communication bus may include a pathway for transmitting information between the aforementioned components. The communication bus can be a PCI bus or an EISA bus, etc. Communication buses can be categorized into address buses, data buses, control buses, etc.

[0025] This application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as described in the above embodiments for the method of detecting live zero-value insulators based on smart sensors.

[0026] In this embodiment, a computer-readable storage medium can be a tangible device that holds and stores instructions used by an instruction execution device. The computer-readable storage medium can be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, the computer-readable storage medium can be a portable computer disk, a hard disk, a USB flash drive, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), spoofing random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory stick, floppy disk, optical disk, magnetic disk, mechanical encoding device, or any combination thereof.

[0027] The terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0028] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing application concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions claimed in this application.

Claims

1. A method for detecting liveness of zero-value insulators based on intelligent sensors, characterized in that, The specific steps include the following: Obtain information on the appearance and operational data of the insulators; Analyze the fluctuations in power demand and power load of the corresponding load to assess the future impact on power. Analyze the environmental impact of the area where the insulator is located; Health analysis of insulators is conducted based on their appearance and operational data. Based on the future power impact assessment results, environmental impact situation, and insulator health analysis results, the future operating performance of insulators is predicted; Early warnings are issued based on predictions of the future operating performance of insulators.

2. The method for detecting liveness of zero-value insulators based on intelligent sensors according to claim 1, characterized in that, The future power impact assessment includes the following specific steps: The first step is to obtain the future power consumption plan of the load and the power consumption changes in different time periods; The second step is to obtain the electricity consumption and fluctuations for each future time period. The current anomaly for the corresponding time period is obtained by dividing the current for each future time period by the current safe current of the insulator. The current anomaly for each time period in the future cycle is obtained by integrating the current anomaly over the time length and dividing it by the cycle length. The current safe current of the insulator is obtained by multiplying the current health status of the insulator by the health status influence coefficient. The current safe current is obtained by multiplying the health status influence by the factory safe current of the insulator. The third step is to obtain the power consumption fluctuations in future time periods. The current fluctuation impact anomaly at the corresponding time is obtained by subtracting the absolute value of the current situation at the previous time from the current situation at the next time within the cycle and dividing it by the current safe current of the insulator. The current fluctuation anomaly in future cycles is obtained by obtaining the average value of the current fluctuation impact anomalies within the cycle. The fourth step is to obtain the future power impact assessment result by weighted summation of the current anomalies and current fluctuation anomalies in future cycles.

3. The method for detecting liveness of zero-value insulators based on intelligent sensors according to claim 1, characterized in that, The environmental impact details include the following: The first step is to obtain the size and density of airborne particles for the future period through the weather forecast terminal, as well as the air wind speed and humidity, and the flatness and surface area-to-volume ratio of the corresponding insulator's outer surface. The second step is to obtain the flatness of the outer surface of the insulator and the surface area-to-volume ratio. Divide the data by the maximum safe range of the corresponding data type, and then sum the weighted ratios to obtain the surface aggregation anomaly of the insulator. The third step is to obtain the average wind speed and humidity at the corresponding location, divide the data by the maximum safe range for the corresponding data type, and then sum the weighted ratios to obtain the weather impact anomaly; obtain the average diameter of airborne particulate matter and the average diameter of insulator surface pits, calculate the difference between the average diameter of airborne particulate matter and the average diameter of insulator surface pits, divide the difference by the sum of the average diameter of airborne particulate matter and the average diameter of insulator surface pits to obtain the similarity anomaly of the two diameters, divide the particulate matter density by the safe density to obtain the density anomaly, and then sum the density anomaly and the diameter similarity anomaly by weight to obtain the pollutant anomaly; The fourth step is to weight and sum the pollutant anomalies and weather impact anomalies, and then multiply this sum with the insulator surface accumulation anomalies to obtain the environmental impact information.

4. The method for detecting liveness of zero-value insulators based on intelligent sensors according to claim 1, characterized in that, The health analysis of the insulator includes the following specific contents: The first step is to obtain images of the insulator's appearance, heating status, and leakage current. The second step is to obtain the surface damage condition of the insulation value and the average distance from the damage point to the circuit connection point. The damage anomaly is obtained by dividing the surface damage volume by the safe damage volume, the distance anomaly is obtained by dividing the safe distance by the average distance from the damage point to the circuit connection point, and the damage anomaly is obtained by multiplying the distance anomaly by the damage anomaly. The third step is to obtain the temperature anomaly by dividing the temperature at the insulator connection by the maximum safe temperature, and the current anomaly by dividing the leakage current of the insulator by the maximum safe current. The health of the insulator is obtained by taking the reciprocal of the weighted sum of the damage anomaly, temperature anomaly, and current anomaly.

5. The method for detecting liveness of zero-value insulators based on intelligent sensors according to claim 1, characterized in that, The prediction of the future operating performance of the insulator includes the following specific details: The current cycle insulator's health status, environmental impact status, and future power impact assessment results are obtained. The future scenario anomaly is obtained by weighted summation of the environmental impact status and future power impact assessment results. The scenario impact residual coefficient is obtained by subtracting the future scenario anomaly from the numerical value. The future cycle insulator's operational performance prediction result is obtained by multiplying the current cycle insulator's health status by the scenario impact residual coefficient.

6. The method for detecting liveness of zero-value insulators based on intelligent sensors according to claim 1, characterized in that, The early warning based on the prediction results of the future operating performance of insulators includes the following specific contents: The system obtains the predicted operating performance of insulators for future cycles and compares it with the set safety threshold. If the predicted operating performance is greater than or equal to the set safety threshold, it means that the insulation value for the future cycle can meet the requirements and no replacement is needed. If the predicted operating performance is less than the set safety threshold, it means that the insulation value for the future cycle cannot meet the requirements and replacement is needed. A replacement alarm is then sent to the staff.

7. The method for detecting liveness of zero-value insulators based on intelligent sensors according to claim 1, characterized in that, The acquisition of insulator appearance and insulator operation data includes the following specific content: using a drone equipped with a high-definition visible light camera, infrared thermal imager and ultraviolet imager to perform all-round, multi-spectral scanning of insulator strings from the air to acquire images of the appearance and heating status of insulators on high-altitude lines; and acquiring leakage current and electric field distribution of the corresponding insulator equipment through a fixedly installed online monitoring device.

8. A zero-value insulator live-line detection system based on intelligent sensors, used to implement the zero-value insulator live-line detection method based on intelligent sensors according to any one of claims 1-7, characterized in that, Includes the following modules: The system includes an insulator condition acquisition module, a power condition analysis module, an environmental analysis module, an insulator analysis module, a future operation prediction module, and an early warning module. The insulator condition acquisition module acquires the appearance and operational data of the insulators. The power condition analysis module analyzes the power demand fluctuations and power load conditions of the corresponding loads and assesses future power impact. The environmental analysis module analyzes the environmental impact of the area where the insulators are located. The insulator analysis module performs health analysis on the insulators based on their appearance and operational data. The future operation prediction module predicts the future operational performance of the insulators based on the future power impact assessment results, environmental impact results, and insulator health analysis results. The early warning module issues early warnings based on the predicted future operational performance of the insulators.

9. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; characterized in that the processor executes the zero-value insulator live detection method based on a smart sensor as described in any one of claims 1-7 by calling the computer program stored in the memory.

Images