Insulation monitoring and early warning method and device for high-voltage equipment, equipment and medium

Abstract

The embodiment of the invention discloses an insulation monitoring and early warning method and device for high-voltage equipment, equipment and a medium. A specific embodiment of the method comprises the steps of obtaining a multi-source signal set corresponding to high-voltage equipment in a smart power grid; performing interference separation processing on the partial discharge pulse signal to obtain a processed partial discharge pulse signal; performing first regulation and control processing on the high-voltage equipment based on the processed partial discharge pulse signal and the temperature distribution signal; performing optimization processing on the dielectric loss factor signal based on the temperature distribution signal to obtain an optimized dielectric loss factor signal; performing second regulation and control processing on the high-voltage equipment based on the processed partial discharge pulse signal and the optimized dielectric loss factor signal; and executing early warning processing according to the acquired first identification information and second identification information. According to the embodiment, insulation on-line monitoring and early warning are achieved, and a reliable decision basis is provided for safe operation and maintenance and reliable management of high-voltage equipment in an intelligent power grid.

Description

Technical Field

[0001] The embodiments of this disclosure relate to the field of computer technology, and more specifically to methods, apparatus, devices, and media for insulation monitoring and early warning of high-voltage equipment. Background Technology

[0002] With the rapid development of smart grids, the requirements for the operational reliability of high-voltage power equipment (such as transformers and GIS switchgear) are increasing. Insulation performance, as a key indicator determining the safe operation of equipment, is crucial for effective monitoring and evaluation. Currently, insulation performance testing of high-voltage equipment mainly relies on traditional offline preventative testing and existing online monitoring methods. Traditional offline testing requires scheduled inspections by professionals using specialized instruments after power outages; existing online monitoring methods collect data in real time by installing sensors and primarily rely on fixed threshold criteria and conventional signal processing algorithms for status assessment.

[0003] However, when using the above methods, the following technical problems often arise: Traditional offline testing is not only complex to operate and consumes a lot of manpower and resources, but also leads to excessively long annual power outages, severely restricting the reliability of power grid supply. Existing online monitoring methods suffer severe degradation in the signal-to-noise ratio of key signals such as partial discharge under strong electromagnetic interference environments, making it difficult for conventional filtering algorithms to effectively separate interference; at the same time, fluctuations in ambient temperature easily cause drift in the measured values ​​of parameters such as dielectric loss factor, leading to a decrease in the accuracy of condition assessment and making it difficult to truly reflect the degree of insulation aging.

[0004] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0006] Some embodiments of this disclosure provide methods, apparatus, electronic devices, and computer-readable media for insulation monitoring and early warning of high-voltage equipment to address one or more of the technical problems mentioned in the background section above.

[0007] In a first aspect, some embodiments of this disclosure provide an insulation monitoring and early warning method for high-voltage equipment, comprising: acquiring a multi-source signal set corresponding to the high-voltage equipment in a smart grid, wherein the multi-source signal set includes a partial discharge pulse signal, a temperature distribution signal, and a dielectric loss factor signal; performing interference separation processing on the partial discharge pulse signal to obtain a processed partial discharge pulse signal; performing a first regulation processing on the high-voltage equipment based on the processed partial discharge pulse signal and the temperature distribution signal, wherein the first regulation processing includes adjusting an on-load tap changer; performing optimization processing on the dielectric loss factor signal based on the temperature distribution signal to obtain an optimized dielectric loss factor signal; performing a second regulation processing on the high-voltage equipment based on the processed partial discharge pulse signal and the optimized dielectric loss factor signal, wherein the second regulation processing includes isolating the high-voltage equipment from the power grid; acquiring first identification information corresponding to the first regulation processing and second identification information corresponding to the second regulation processing; and performing early warning processing based on the first identification information and the second identification information.

[0008] Secondly, some embodiments of this disclosure provide an insulation monitoring and early warning device for high-voltage equipment, comprising: an acquisition unit configured to acquire a multi-source signal set corresponding to the high-voltage equipment in a smart grid, wherein the multi-source signal set includes a partial discharge pulse signal, a temperature distribution signal, and a dielectric loss factor signal; an interference separation unit configured to perform interference separation processing on the partial discharge pulse signal to obtain a processed partial discharge pulse signal; and a first control unit configured to perform a first control processing on the high-voltage equipment based on the processed partial discharge pulse signal and the temperature distribution signal, wherein the first control processing includes a loaded... The system includes: a voltage regulator switch adjustment; an optimization unit configured to optimize the dielectric loss factor signal based on the temperature distribution signal to obtain an optimized dielectric loss factor signal; a second control unit configured to perform a second control process on the high-voltage equipment based on the processed partial discharge pulse signal and the optimized dielectric loss factor signal, wherein the second control process includes isolating the high-voltage equipment from the power grid; and an early warning unit configured to acquire first identification information corresponding to the first control process and second identification information corresponding to the second control process, and to perform an early warning process based on the first identification information and the second identification information.

[0009] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0010] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0011] The above embodiments of this application have the following beneficial effects: Through the insulation monitoring and early warning method for high-voltage equipment, this application achieves high-precision and high-reliability online monitoring and early warning of the insulation status of high-voltage equipment under uninterrupted power conditions, effectively improving the reliability of power grid operation and the intelligent level of equipment maintenance. Specifically, traditional insulation performance monitoring relies on offline tests requiring equipment power outages, or online monitoring methods susceptible to electromagnetic interference and temperature drift, which may lead to system power outages, signal distortion, and misjudgments of status, making it difficult to meet the needs of smart grids for continuous power supply and accurate sensing. Based on this, the insulation monitoring and early warning method for high-voltage equipment in this application embodiment: First, by acquiring a multi-source signal set corresponding to the high-voltage equipment (including partial discharge pulse signals, temperature distribution signals, and dielectric loss factor signals), a multi-dimensional information foundation comprehensively reflecting the insulation status is constructed. This step integrates multiple physical quantity signals such as electrical and thermal signals from the data source, providing rich and complementary feature inputs for comprehensive analysis, overcoming the limitations of traditional single-signal monitoring. Then, interference separation processing is performed on the partial discharge pulse signal, significantly improving the signal-to-noise ratio under strong electromagnetic interference environments. This process effectively removes background electromagnetic noise through targeted signal processing techniques, solving the performance degradation problem of conventional filtering algorithms under complex operating conditions and ensuring the authenticity and accuracy of the partial discharge characteristics analyzed subsequently. Next, the dielectric loss factor signal is optimized based on the temperature distribution signal, effectively compensating for measurement drift caused by ambient temperature fluctuations. This mechanism uses the temperature signal as a compensation basis, significantly improving the measurement accuracy of the dielectric loss factor, a key insulation parameter, enabling it to more realistically reflect the aging state of the insulation material and addressing the pain point of inaccurate assessments due to temperature influences in existing methods. Finally, by performing first and second control processing based on the processed signal and integrating two types of identification information for early warning judgment, a multi-level, adaptive insulation state assessment and early warning architecture is constructed. This architecture overcomes the shortcomings of traditional fixed threshold criteria—poor adaptability and susceptibility to false alarms / missed alarms—through multi-dimensional information cross-validation and hierarchical decision-making, achieving more reliable and timely risk warnings. In summary, the embodiments of this application achieve real-time, accurate, and reliable sensing of the insulation status of high-voltage equipment through a collaborative technical approach of "multi-source signal fusion acquisition—interference separation—temperature compensation—graded control and early warning." This method not only avoids system power outages caused by offline testing, ensuring power supply continuity, but also improves the anti-interference capability and measurement accuracy of online monitoring in complex operating environments to a certain extent, providing key technical support for building a highly reliable smart grid. Attached Figure Description

[0012] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0013] Figure 1 This is a flowchart of some embodiments of the insulation monitoring and early warning method for high-voltage equipment according to the present disclosure; Figure 2 These are schematic diagrams of some embodiments of the insulation monitoring and early warning device for high-voltage equipment according to the present disclosure; Figure 3 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0014] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0015] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0016] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0017] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0018] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0019] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0020] Figure 1A flow chart 100 of some embodiments of the insulation monitoring and early warning method for high-voltage equipment according to the present disclosure is shown. The insulation monitoring and early warning method for high-voltage equipment includes the following steps: Step 101: Obtain the set of multi-source signals corresponding to high-voltage equipment in the smart grid.

[0021] In some embodiments, the execution subject (e.g., a computing device) of the insulation monitoring and early warning method for high-voltage equipment can obtain a set of multi-source signals corresponding to high-voltage equipment in a smart grid.

[0022] In some optional implementations of certain embodiments, the aforementioned execution entity can obtain the multi-source signal set corresponding to the high-voltage equipment in the smart grid through the following steps: Step 1: Acquire the partial discharge pulse signal corresponding to the high-voltage equipment in the smart grid. The high-voltage equipment can be a type of power equipment operating at a high voltage level (typically 35kV and above) in the smart grid. For example, the high-voltage equipment can be a transformer or a GIS switchgear. The partial discharge pulse signal can be a sequence of transient electromagnetic pulses generated by the partial breakdown of the insulation material of the high-voltage equipment under the influence of a strong electric field. In practice, the actuator can use a UHF sensor installed on the casing or basin insulator of the high-voltage equipment to continuously acquire the transient electromagnetic pulse sequence arranged in chronological order in real time at a sampling rate of GSps (200MHz-3GHz). Then, the acquired transient electromagnetic pulse sequence is identified as the partial discharge pulse signal corresponding to the high-voltage equipment.

[0023] Step two: Obtain the temperature distribution signal corresponding to the aforementioned high-voltage equipment. This temperature distribution signal can be a set of numerical values ​​including the temperature values ​​at various measuring points on the surface or interior of the high-voltage equipment. In practice, the executing entity can monitor the temperature at each measuring point in real time using an FBG sensor array pre-installed on the surface of the windings, bushings, or housing of the high-voltage equipment. Then, the obtained temperature values ​​at each measuring point are integrated into a numerical set corresponding to these temperature values, and this numerical set is determined as the temperature distribution signal corresponding to the high-voltage equipment.

[0024] Step 3: Obtain the dielectric loss factor signal corresponding to the aforementioned high-voltage equipment. The dielectric loss factor signal can be a macroscopic parameter measuring the degree of energy loss of insulating materials in an alternating electric field; a higher value indicates more severe insulation aging, moisture absorption, or deterioration. In practice, the executing entity can use a dielectric loss tester connected to the capacitor bank or grounding lead of the high-voltage equipment to measure the capacitive current and active current components of the insulating dielectric in real time under the operating voltage of the high-voltage equipment. The ratio of active current to capacitive current is then determined as the dielectric loss factor signal corresponding to the high-voltage equipment.

[0025] Step four involves integrating the aforementioned partial discharge pulse signal, temperature distribution signal, and dielectric loss factor signal into a multi-source signal set. This multi-source signal set includes the partial discharge pulse signal, temperature distribution signal, and dielectric loss factor signal. In practice, the executing entity can integrate these signals into a multi-source signal set corresponding to the high-voltage equipment.

[0026] Step 102: Perform interference separation processing on the partial discharge pulse signal to obtain the processed partial discharge pulse signal.

[0027] In some embodiments, the aforementioned execution entity may perform interference separation processing on the aforementioned partial discharge pulse signal to obtain a processed partial discharge pulse signal.

[0028] In some optional implementations of certain embodiments, the aforementioned execution entity may perform interference separation processing on the aforementioned partial discharge pulse signal through the following steps to obtain the processed partial discharge pulse signal: Step one involves denoising the partial discharge pulse signal to obtain a denoised partial discharge pulse signal. The denoising method can be an adaptive wavelet thresholding approach, which can suppress broadband white noise and random pulse interference in the partial discharge pulse signal. In practice, the execution entity can first perform wavelet packet decomposition on the partial discharge pulse signal to obtain the coefficients of each sub-band. Then, based on the obtained sub-band coefficients, a layer-dependent threshold is used to estimate the noise level, and a soft thresholding method is used to shrink the high-frequency coefficients. Finally, after wavelet packet reconstruction, the denoised partial discharge pulse signal can be obtained.

[0029] Step two involves performing electromagnetic shielding compensation processing on the denoised partial discharge pulse signal to obtain the processed partial discharge pulse signal. The electromagnetic shielding compensation method can be an interference cancellation method based on a reference antenna and an adaptive filter, which can further suppress residual narrowband periodic interference in the denoised partial discharge pulse signal. In practice, the executing entity can synchronously acquire environmental electromagnetic interference signals using a reference antenna mounted on the housing of the high-voltage equipment. Then, using the output of the reference antenna as the desired signal, the Normalized Least Mean Square (NLMS) algorithm is employed to adaptively cancel interference in the time domain on the denoised partial discharge pulse signal. Finally, the output result of the adaptive interference cancellation is determined as the processed partial discharge pulse signal.

[0030] Step 103: Based on the processed partial discharge pulse signal and temperature distribution signal, perform the first regulation process on the high-voltage equipment.

[0031] In some embodiments, the execution entity may perform a first regulation process on the high-voltage equipment based on the processed partial discharge pulse signal and the temperature distribution signal.

[0032] In some optional implementations of certain embodiments, the aforementioned execution entity may perform a first regulation process on the aforementioned high-voltage equipment based on the processed partial discharge pulse signal and the aforementioned temperature distribution signal through the following steps: The first step involves extracting multi-dimensional features from the processed partial discharge pulse signal to obtain multi-dimensional feature information. In practice, the execution entity can extract various feature vectors of the processed partial discharge pulse signal within the current unit time window. These feature vectors include: pulse number, peak amplitude, average amplitude, phase center, energy proportion of 0.3-1 GHz, rising edge, and energy integral. Finally, the extracted feature vectors are integrated into a feature vector sequence, which is then identified as the multi-dimensional feature information.

[0033] The second step involves extracting spatial features from the aforementioned temperature distribution signal to obtain spatial feature information. In practice, the executing entity can first map the temperature values ​​of each measuring point in the temperature distribution signal onto a two-dimensional grid on the device surface, and then generate a temperature distribution heatmap using an interpolation algorithm (such as inverse distance weighted interpolation). Then, various spatial feature vectors are extracted from this temperature distribution heatmap. These spatial feature vectors include: hotspot temperature difference, maximum temperature gradient, and average temperature. Finally, the extracted spatial feature vectors are integrated into a spatial feature vector sequence, and this spatial feature vector sequence is determined as the spatial feature information.

[0034] The third step is to generate a multi-dimensional feature matrix based on the aforementioned multi-dimensional feature information and spatial feature information. In practice, the various feature vectors and spatial feature vectors in the aforementioned multi-dimensional feature information and spatial feature information of the executing entity are concatenated column by column to obtain a matrix containing all the vectors, and this matrix is ​​determined as the multi-dimensional feature matrix.

[0035] The fourth step is to normalize the aforementioned multi-dimensional feature matrix to obtain a normalized multi-dimensional feature matrix. The normalization method can be the standard score method. In practice, the executing entity can normalize the aforementioned multi-dimensional feature matrix and determine the normalized multi-dimensional feature matrix as the normalized multi-dimensional feature matrix.

[0036] The fifth step involves inputting the normalized multi-dimensional feature matrix into a pre-trained physical information neural network model to obtain a preliminary insulation state assessment result. This physical information neural network model can be a known machine learning model that embeds physical law constraints into the forward network loss function, ensuring that the output conforms to the material aging law even with limited data samples. The physical law constraints can be an insulation aging kinetic equation. The material aging law can be that for every 10°C increase in temperature, the insulation life is shortened by 50%. The pre-trained physical information neural network model used in this embodiment has a structure of 3 fully connected layers (128-64-32 nodes) and a single-node Sigmoid output, with an Arrhenius temperature acceleration term added to the loss function. In practice, the execution entity inputs the normalized multi-dimensional feature matrix into the pre-trained physical information neural network model, and after one inference, outputs a scalar parameter (∈[0,1]), which is then used as the preliminary insulation state assessment result.

[0037] Step 6: Perform reliability processing on the preliminary insulation state assessment results to obtain the target insulation state assessment results. The reliability verification method can be an MC-Dropout approach. In practice, the executing entity can re-input the normalized multi-dimensional feature matrix into the pre-trained physical information neural network model and randomly disable 50% of the neurons during the forward pass. After 100 random inferences, 100 parameter samples are obtained. The standard deviation of these 100 parameter samples is then calculated. If the standard deviation is less than 0.05, the uncertainty is sufficiently low, and a reliability verification result that passes the characterization verification is generated; otherwise, a reliability verification result that fails the characterization verification is generated. If the reliability verification result passes the characterization verification, the preliminary insulation state assessment result can be determined as the target insulation state assessment result. If the reliability verification result fails the characterization verification, the preliminary insulation state assessment result is corrected to obtain the target insulation state assessment result. The correction method can be a first-order exponential moving average (EMA) method. Specifically, the aforementioned executing entity can obtain a corrected preliminary insulation state assessment result by calling the most recent historical target insulation state assessment result and weighting and summing it with the aforementioned preliminary insulation state assessment result, and then determine the corrected preliminary insulation state assessment result as the target insulation state assessment result.

[0038] Step 7: In response to the target insulation condition assessment result falling within a preset first range, perform operational optimization processing. This preset first range can be set to [0.7-0.9]. The operational optimization processing can involve cooling the high-voltage equipment. In practice, this operational optimization processing can be performed by starting the auxiliary fan of the high-voltage equipment or increasing the speed of the existing fan, in response to the target insulation condition assessment result falling within the preset first range.

[0039] Step 8: In response to the target insulation condition assessment result falling within the preset second range, adjust the on-load tap changer associated with the high-voltage equipment. The preset second range can be set to [0.5-0.7]. In practice, in response to the target insulation condition assessment result falling within the preset second range, the on-load tap changer associated with the high-voltage equipment is adjusted to the -1 position to slightly reduce the operating voltage and current.

[0040] Step nine: In response to the target insulation condition assessment result falling within a preset third interval, a load transfer process is performed. This preset third interval can be set to [0-0.5]. The load transfer process may involve transferring a portion of the load of the high-voltage equipment to a standby line. In practice, in response to the target insulation condition assessment result falling within a preset third interval, a portion of the equipment's load (e.g., 30%) is transferred to a standby line to perform the load transfer process.

[0041] The steps one through nine described above, as a technical solution of this disclosure embodiment, solve the technical problems of "insufficient utilization of multi-physics information in high-voltage equipment insulation condition assessment, low model reliability under data scarcity conditions, lack of quantification of assessment result uncertainty, and disconnect between condition assessment and operation and maintenance execution." The reasons why existing technologies struggle to construct accurate, automatic, and closed-loop intelligent operation and maintenance systems are as follows: Traditional methods often rely on a single signal (such as partial discharge or temperature alone), severing the coupled influence of electrical and thermal stress on insulation aging, resulting in a one-sided assessment and inability to achieve early warning; assessment models based on pure data drive have poor generalization ability under conditions of scarce equipment fault samples, and the output results lack physical law constraints, potentially leading to misjudgments that violate the common sense of material aging; existing solutions typically provide a single assessment score without quantifying its uncertainty, making it impossible for operation and maintenance personnel to know the confidence level of the assessment results, thus incurring excessive risk when making key decisions such as "voltage reduction" and "load reduction"; furthermore, there are often human decision-making breakpoints between condition assessment results and operation and maintenance instructions, resulting in slow response and susceptibility to errors, making it difficult to achieve an immediate closed loop from perception to execution. If the above factors can be eliminated, a relatively accurate, reliable, and credible assessment of the insulation state can be achieved based on a small number of samples, driving automated and tiered preventative maintenance. To this end, this disclosure includes: First, multi-dimensional feature extraction of partial discharge pulse signals, obtaining a comprehensive electrical feature sequence from pulse intensity and frequency to waveform characteristics, laying a data foundation for in-depth analysis of the nature and activity of insulation defects. Second, interpolation of discrete temperature measurement point signals to generate temperature distribution heatmaps and extraction of their spatial features, achieving a sublimation from "point" temperature to "field" stress, providing an intuitive basis for locating potential overheating hazards. Third, the above-mentioned electrical and thermal multi-dimensional features are concatenated column-wise to generate a unified multi-dimensional feature matrix, achieving for the first time a deep fusion of "electrical-thermal" multi-physics field information at the feature level, enabling the model to learn the coupled aging effect of the two stresses. Fourth, the feature matrix is ​​normalized to eliminate numerical differences between features of different dimensions, ensuring the stability and efficient training of the subsequent model. The fifth step involves inputting the normalized feature matrix into a pre-trained physical information neural network model. By embedding physical constraints such as the Arrhenius aging law into its loss function, the model is forced to maintain its output in accordance with the aging characteristics of insulating materials even when data is scarce, significantly improving the evaluation accuracy and extrapolation reliability under small sample conditions. The sixth step employs the MC-Dropout method to perform multiple random inferences on the preliminary evaluation results to quantify their uncertainty, and then processes them according to their level of uncertainty: when uncertainty is low, the results are directly adopted to ensure a fast response; when uncertainty is high, an exponential moving average method combined with historical data is used for smoothing correction, thereby ensuring the robustness of the final evaluation results and the safety of the decision.Steps seven through nine, based on the final target insulation status assessment results, construct a three-level progressive automatic operation and maintenance response mechanism: When in the first interval, operational optimization is performed (e.g., starting auxiliary fans) to intervene early and delay aging; when in the second interval, adjustments are made to related equipment (e.g., on-load tap changers) to proactively reduce operational stress and control risks; when in the third interval, load transfer is performed to decisively reduce equipment load to prevent the accident from escalating. This allows sparse, multi-source monitoring data to be fused into unified features rich in physical information, and a model enhanced by physical mechanisms can achieve accurate and confident assessments with a small sample size. Finally, the three-level automatic response mechanism seamlessly translates the assessment conclusions into operation and maintenance actions. Furthermore, a reliability handling mechanism based on uncertainty grading eliminates decision-making risks caused by instantaneous model fluctuations. Thus, a complete intelligent operation and maintenance closed loop has been constructed, from "precise perception of multi-physics fields" to "reliability assessment and decision-making" and then to "hierarchical automatic execution". This has realized a fundamental transformation of the operation and maintenance mode of high-voltage equipment from "passive maintenance" to "proactive early warning and precise intervention". While ensuring the accuracy of assessment and the reliability of decision-making, it has improved the operational safety of the power system to a certain extent.

[0042] Step 104: Based on the temperature distribution signal, optimize the dielectric loss factor signal to obtain the optimized dielectric loss factor signal.

[0043] In some embodiments, the execution entity may optimize the dielectric loss factor signal based on the temperature distribution signal to obtain an optimized dielectric loss factor signal.

[0044] In some optional implementations of certain embodiments, the aforementioned execution entity may optimize the aforementioned dielectric loss factor signal based on the aforementioned temperature distribution signal through the following steps to obtain an optimized dielectric loss factor signal: Step one: Generate ambient temperature difference data based on the aforementioned temperature distribution signal. In practice, the executing entity can extract each temperature value from the temperature distribution signal and calculate the arithmetic mean of each temperature value to obtain the average temperature. Then, the average temperature is subtracted from a preset reference temperature, and the absolute value of the difference is determined as the ambient temperature difference data. The preset reference temperature can be set to 20℃.

[0045] Step two: Based on the aforementioned environmental temperature difference data and the aforementioned dielectric loss factor signal, an optimized dielectric loss factor signal is generated. In practice, the aforementioned executing entity can use the aforementioned environmental temperature difference data and the aforementioned dielectric loss factor signal, employing an Arrhenius-type empirical formula, to calculate the dielectric loss factor signal that eliminates temperature drift. Then, the dielectric loss factor signal that eliminates temperature drift is determined as the optimized dielectric loss factor signal.

[0046] Step 105: Based on the processed partial discharge pulse signal and the optimized dielectric loss factor signal, perform a second regulation process on the high-voltage equipment.

[0047] In some embodiments, the execution entity may perform a second regulation process on the high-voltage equipment based on the processed partial discharge pulse signal and the optimized dielectric loss factor signal.

[0048] In some optional implementations of certain embodiments, the aforementioned execution entity may perform a second control process on the aforementioned high-voltage equipment based on the processed partial discharge pulse signal and the optimized dielectric loss factor signal through the following steps: The first step is to generate a frequency feature sequence corresponding to the partially discharge pulse signal based on the processed signal. This frequency feature sequence includes various... Frequency characteristics. The frequency characteristic can be the number of pulses (ppm) within a unit time window. The unit time window can be 1 minute. In practice, the execution entity can use a sliding window to count the partial discharge pulse signal in segments to obtain the number of pulses per unit time.

[0049] Then, the obtained unit time pulse counts are integrated into a unit time pulse count sequence in chronological order, and the integrated unit time pulse count sequence is determined as the frequency feature sequence.

[0050] The second step involves generating a dielectric loss factor (DFD) value sequence corresponding to the optimized DFD signal. In practice, the executing entity can backsample each historical DFD signal within the aforementioned unit time window (1 minute) and optimize each obtained historical DFD signal to obtain optimized historical DFD signals. The optimization process can refer to the steps described above for generating the optimized DFD signal, and will not be repeated here. Next, the optimized historical DFD signals and the optimized DFD signals are integrated into a DFD signal sequence in chronological order, and this integrated DFD signal sequence is determined as the dielectric loss value sequence.

[0051] The third step is to obtain the operating years information of the aforementioned high-voltage equipment. This operating years information can be the cumulative number of years the high-voltage equipment has been in operation from the date of commissioning to the current date. In practice, the implementing entity can obtain the operating years information of the high-voltage equipment from the equipment ledger or the ERP asset module.

[0052] The fourth step involves generating the discharge frequency threshold and the dielectric loss critical threshold based on the aforementioned operating years information. In practice, the executing entity can obtain these thresholds using a linear weighting method. Specifically, for the discharge frequency threshold, the executing entity can use a well-known empirical formula, such as "F=50×(1+0.2Y)", where "F" represents the desired discharge frequency threshold and "Y" represents the acquired operating years information. Substituting the acquired operating years information into this formula yields the discharge frequency threshold. For the dielectric loss critical threshold, the executing entity can use a well-known empirical formula, such as "D=0.015×(1+0.1Y)", where "D" represents the desired dielectric loss critical threshold and "Y" represents the acquired operating years information. Substituting the acquired operating years information into this formula yields the dielectric loss critical threshold.

[0053] The fifth step involves generating a set of slight aging inflection points for insulation based on the aforementioned frequency feature sequence and discharge frequency threshold. This set can be a point set used to integrate various slight aging inflection points. In practice, the executing entity can use the generated discharge frequency threshold to scan each frequency feature in the aforementioned frequency feature sequence point by point. During the scan, if the number of pulses corresponding to three consecutive frequency features is greater than or equal to the aforementioned discharge frequency threshold, the starting time of each window corresponding to these three frequency features is obtained, and the earliest window starting time is determined as the slight aging inflection point. Then, this slight aging inflection point is organized into the set of slight aging inflection points. Following this method, the final set of slight aging inflection points for insulation can be obtained. This set can be empty or may include one or more slight aging inflection points.

[0054] Step 6: Based on the aforementioned dielectric loss numerical sequence and the aforementioned dielectric loss critical threshold, generate an insulation breakdown warning point set. This insulation breakdown warning point set can be a point set used to integrate various insulation breakdown warning points. In practice, the executing entity can use the generated dielectric loss critical threshold to scan each dielectric loss factor signal in the aforementioned dielectric loss numerical sequence point by point. During the scanning process, if three consecutive dielectric loss factor signals are greater than or equal to the aforementioned dielectric loss critical threshold, the starting time of each window corresponding to these three dielectric loss factor signals is obtained, and the earliest window starting time among these window starting times is determined as the insulation breakdown warning point. Then, this insulation breakdown warning point is organized into the insulation breakdown warning point set. Following this method, the final insulation breakdown warning point set can be obtained. This insulation breakdown warning point set can be an empty set or it can include one or more insulation breakdown warning points.

[0055] The seventh step is to reduce the load on the high-voltage equipment to zero and isolate the high-voltage equipment from the power grid in response to the aforementioned insulation breakdown warning point set being a non-empty set.

[0056] Step 8: In response to the fact that the set of slight insulation aging inflection points is a non-empty set and the set of insulation breakdown warning points is an empty set, the maximum load rate of the high-voltage equipment is limited. In practice, the implementing entity can limit the maximum allowable load rate of the equipment to below 80% of its rated capacity.

[0057] The first to eighth steps described above are an inventive point of this disclosure, solving the technical problems of "reliance on a single criterion, static and rigid thresholds, delayed early warning, and lack of a graded control mechanism from early deterioration to emergency failure in the insulation condition assessment of high-voltage equipment." The reasons why existing technologies struggle to achieve early warning and precise graded control are as follows: Existing methods typically use single parameters such as partial discharge or dielectric loss factor in isolation for judgment, failing to comprehensively utilize the characteristics of different features reflecting different aging stages of insulation, resulting in incomplete assessment; fixed thresholds are commonly used, making it impossible to dynamically adjust the warning threshold according to the actual operating years of the equipment. This may be too lenient for older equipment, leading to missed alarms, while being too strict for newer equipment, resulting in false alarms; traditional threshold comparison methods are mostly instantaneous point judgments, highly sensitive to random interference and signal fluctuations, with poor reliability, and only alarm when parameters are severely exceeded, resulting in a significant delay in early warning and missing the opportunity for early intervention; furthermore, the lack of a graded, progressive control strategy matching risk assessment often forces the implementation of extreme measures such as emergency shutdown at the critical point of an accident, failing to achieve refined operation and maintenance of "early detection and early handling." If the above factors can be eliminated, an intelligent early warning system that reflects the progressive aging process of insulation, possesses both sensitivity and reliability, and can automatically implement graded prevention and control can be constructed. To this end, this disclosure includes: First, generating a frequency characteristic sequence of partial discharge pulse signals, transforming instantaneous discharge pulses into a continuous time sequence reflecting changes in the frequency of discharge activity, providing a dynamic data foundation for capturing the initiation and duration of early insulation degradation. Second, generating a dielectric loss factor signal sequence, integrating discrete dielectric loss measurements into a continuous trajectory reflecting the overall aging trend of insulation, preparing for identifying the accelerated degradation stage of insulation performance. Third, acquiring the operating years information of high-voltage equipment, linking the aging patterns of the equipment with the key factor of operating time, providing a core basis for personalized and adaptive adjustment of thresholds. Fourth, based on the operating years information, dynamically generating discharge frequency thresholds and dielectric loss critical thresholds using a linear weighted formula, allowing the evaluation criteria to be relaxed synchronously with the natural aging of the equipment, while ensuring the rigor of evaluation for new equipment and the rationality of evaluation for old equipment, effectively avoiding misjudgments. The fifth step generates a set of inflection points for slight insulation aging by detecting a set of points in the frequency feature sequence that continuously exceed the dynamic threshold. The "three consecutive points" judgment logic effectively filters out random interference, ensuring the reliability of early warning and accurately pinpointing the start of insulation aging. The sixth step generates a set of insulation breakdown warning points by detecting a set of points in the dielectric loss value sequence that continuously exceed the dynamic threshold. This equally robust mechanism captures the critical state of insulation entering accelerated degradation and nearing failure, achieving early warning of serious faults.Steps seven and eight, based on the states of the two point sets mentioned above, construct a differentiated two-level automatic response mechanism: when the insulation breakdown warning point set is not empty, it indicates that the equipment is in an emergency dangerous state, and the ultimate protection measure of reducing the load to zero and isolating it from the power grid is executed to ensure power grid safety with absolute priority; when the only insulation slight aging inflection point set is not empty, it indicates that the equipment is in the early aging stage, and preventive regulation that limits the maximum load rate is executed to delay the insulation aging process by reducing operating stress, thus achieving non-destructive early intervention. Therefore, the "frequency" characteristics of partial discharge and the "degree" characteristics of dielectric loss can be integrated in the time series dimension, and a reliable monitoring of the entire process from "early slight aging" to "late severe degradation" can be achieved using dynamic thresholds and continuous criteria. Furthermore, the adaptive threshold mechanism based on the equipment's service life makes the evaluation criteria more personalized and scientific. Thus, an intelligent early warning and protection closed loop was constructed, covering the insulation aging life cycle, possessing both sensitivity and anti-interference capabilities, and automatically executing graded control from "preventive load limiting" to "emergency isolation". This enabled "early detection, early intervention, and prevention of escalation" of insulation faults in high-voltage equipment, thereby improving the reliability of equipment operation and the level of precision in life management to a certain extent.

[0058] In some optional implementations of certain embodiments, the aforementioned execution entity may reduce the load on the high-voltage equipment to zero and isolate the high-voltage equipment from the power grid by the following steps: The first step involves generating an isolation control command in response to the aforementioned insulation breakdown warning point set being a non-empty set. This isolation control command includes a unique identifier for the aforementioned high-voltage equipment. In practice, upon recognizing that the insulation breakdown warning point set is non-empty, the executing entity immediately generates a structured isolation control command data packet and identifies it as the isolation control command. Specifically, the isolation control command can be encapsulated in JSON format, with key fields including: deviceID (e.g., "TRANSFORMER-BAY1-110kV", consistent with the grid asset management system code), commandType (fixed to "ISOLATION"), targetState (set to "ISOLATED"), and a timestamp based on Coordinated Universal Time (UTC) to ensure the uniqueness, traceability, and precise timing of the command.

[0059] The second step involves sending the isolation control commands to the circuit breaker electrically connected to the high-voltage equipment via an industrial Ethernet or wireless communication network. In practice, the executing entity can obtain the IP address and port number of the circuit breaker electrically connected to the high-voltage equipment. Then, the generated isolation control commands are sent out through the industrial communication interface. Specifically, in the substation's internal LAN environment, transmission is preferentially performed via industrial Ethernet conforming to the IEC 61850 MMS protocol to ensure millisecond-level low latency; for distributed or difficult-to-wire monitoring points, transmission is switched to a 4G / 5G private network with AES-128 encryption or an LTE-230 power wireless private network. In this way, the isolation control commands can be sent to the circuit breaker corresponding to the target high-voltage equipment.

[0060] The third step involves the circuit breaker receiving the isolation control command and driving its electric actuator to perform a tripping operation. In practice, after receiving the isolation control command, the circuit breaker first performs command parsing and security verification, checking the consistency between the deviceID and the devices managed by the system. If the verification passes, it outputs a +24V DC pulse signal with a duration of 200 milliseconds to the circuit breaker's electric actuator (e.g., the spring operating mechanism of a Siemens 3AH series vacuum circuit breaker). This signal excites the tripping coil, releasing the stored energy in the spring, thereby causing the moving contact of the arc-extinguishing chamber to quickly separate, completing the mechanical tripping operation.

[0061] The fourth step involves real-time monitoring of electrical parameters using current and voltage sensors installed on the incoming side of the high-voltage equipment, and confirming whether the load current of the high-voltage equipment has dropped to zero. In practice, the actuator uses Rogowski coil current sensors and capacitive voltage divider sensors installed on the incoming side of the high-voltage equipment to collect waveform data of the three-phase current and voltage in real time at a synchronous sampling rate of 10 kS / s (10,000 samples per second). Then, the RMS (root mean square) value of the three-phase current can be calculated to confirm whether the load current of the high-voltage equipment has dropped to zero. Specifically, when the current values ​​of all three phases remain below the threshold of 0.5 amperes for 100 milliseconds, it can be confirmed that "the load current has dropped to zero," effectively eliminating interference from transient arcs or capacitive leakage currents caused by operational overvoltages.

[0062] The fifth step involves generating an isolation completion signal and sending it to the central server in response to confirmation that the load current of the high-voltage equipment is zero and the circuit breaker electrically connected to the high-voltage equipment is in the open state. In practice, when the executing entity confirms that the load current of the high-voltage equipment has dropped to zero and the circuit breaker electrically connected to the high-voltage equipment is in the open state, a signal indicating that the isolation of the high-voltage equipment is complete can be generated. This signal can then be sent to the central server, causing the server to execute an SQL update statement (e.g., UPDATE device_status SET status = 'ISOLATED', update_time=NOW()WHEREdevice_id='TRANSFORMER-BAY1-110kV') in the device status database (e.g., a real-time asset status table built on MySQL), updating the operating status field of the high-voltage equipment to "isolated".

[0063] The first to fifth steps described above, as a technical solution of this disclosure embodiment, solve the technical problems of "operational dependence on manual processes, response delays, inaccurate status confirmation, and asynchrony between information and physical systems in high-voltage equipment insulation fault isolation." The reasons why existing technologies struggle to achieve rapid, reliable, and fully automated safety isolation are as follows: traditional isolation operations rely on manual identification and early warning, on-site operation, or remote manual control, resulting in slow response speeds and a tendency to miss the optimal isolation opportunity in emergency situations; single communication channels are susceptible to interference in complex electromagnetic environments, leading to lost or delayed control commands; relying solely on circuit breaker auxiliary contacts to determine the isolation status cannot confirm whether the line side is truly energized, posing a safety hazard; and the isolation operation is disconnected from the equipment status management system, resulting in delayed information updates and potential secondary risks such as accidental energization. Eliminating these factors would allow for the construction of a fully automated safety closed loop from intelligent early warning to physical execution and status synchronization. To this end, this disclosure addresses the following: First, in response to the non-empty set of insulation breakdown warning points, structured isolation control commands are generated. These commands are encapsulated in a standardized data format, including device identifiers, operation types, and timestamps, ensuring the uniqueness, traceability, and unambiguous execution of the commands and providing a reliable command source for subsequent automation processes. Second, by adaptively selecting high-reliability communication channels (industrial Ethernet and encrypted wireless private network), real-time, secure, and lossless transmission of control commands in complex industrial environments is ensured, providing communication guarantees for the immediacy of emergency operations. Third, after the circuit breaker control system performs security verification on the commands, it directly drives the electric actuator, achieving seamless conversion from signal to mechanical action with rapid hardware-level response, replacing traditional manual operation and significantly shortening the response time for fault isolation. Fourth, through multi-sensor fusion monitoring and continuous judgment logic, the zero-current state is verified based on high-sampling-rate current and voltage data, achieving accurate and interference-resistant confirmation of the isolation physical effect and ensuring the thoroughness and safety of the isolation operation. The fifth step, by automatically generating an isolation completion signal and updating the central database, achieves real-time synchronization of equipment status in both the information and physical spaces. This provides a unique, accurate, and reliable data source for subsequent operation and maintenance decisions, eliminating the risk of misoperation due to status asynchrony. Thus, the five stages of intelligent early warning, reliable communication, rapid execution, accurate verification, and status synchronization for insulation faults are linked into a complete automated closed loop. Furthermore, the status confirmation mechanism based on multi-sensor verification eliminates operational risks caused by misjudgment of a single signal. Therefore, a complete safety isolation closed loop is constructed, from "intelligent perception and early warning" to "reliable command transmission," then to "rapid hardware execution," and finally to "accurate status synchronization." This represents a fundamental shift in high-voltage equipment fault isolation from "manual decision-making" to "automatic system execution," ensuring operational safety and reliability while improving the power grid's proactive safety defense capabilities and operation and maintenance efficiency to a certain extent.

[0064] Step 106: Obtain the first identification information corresponding to the first control processing and the second identification information corresponding to the second control processing, and perform early warning processing based on the first identification information and the second identification information.

[0065] In some embodiments, the execution entity may obtain first identification information corresponding to the first control process and second identification information corresponding to the second control process, and perform early warning processing based on the first identification information and the second identification information.

[0066] In some optional implementations of certain embodiments, the execution entity may obtain the first identification information corresponding to the first control process and the second identification information corresponding to the second control process through the following steps, and perform a warning process based on the first identification information and the second identification information: Step one: Obtain the first identification information corresponding to the first control process and the second identification information corresponding to the second control process. The first identification information includes the target insulation state assessment result. The second identification information includes a set of slight insulation aging inflection points and a set of insulation breakdown warning points. In practice, the executing entity can obtain the target insulation state assessment result generated in the first control process and determine the obtained target insulation state assessment result as the first identification information. Then, it can obtain the set of slight insulation aging inflection points and the set of insulation breakdown warning points generated in the second control process and determine the obtained set of slight insulation aging inflection points and the set of insulation breakdown warning points as the second identification information.

[0067] Step two: In response to the fact that the above set of slight insulation aging inflection points is not empty and the above target insulation state assessment result is lower than the first threshold, the following first warning processing step is executed: Sub-step one: Generate an equipment status report based on the aforementioned set of minor insulation aging inflection points. The first threshold can be a pre-set value. For example, the first threshold can be set to 0.5. In practice, the executing entity can combine the equipment number of the high-voltage equipment, the corresponding times for each minor insulation aging inflection point in the set of minor insulation aging inflection points, and the target insulation status assessment results into a single set of data. This data is then used to generate the equipment status report.

[0068] Sub-step two involves generating a predicted remaining lifespan for the high-voltage equipment based on the obtained operating age information. In practice, the executing entity can obtain the operating age information of the high-voltage equipment from the equipment ledger or ERP asset module. Then, a linear attenuation formula can be used to generate the predicted remaining lifespan of the high-voltage equipment based on the operating age information. Specifically, the linear attenuation formula can be "T=(1-R) / 0.015×(1+0.2Y)". Where "T" can be the desired predicted remaining lifespan of the high-voltage equipment, "R" can be the target insulation condition assessment result, and "Y" can be the obtained operating age information. Therefore, by substituting the target insulation condition assessment result and the obtained operating age information into the linear attenuation formula, the predicted remaining lifespan of the high-voltage equipment can be obtained.

[0069] Sub-step four: Based on the aforementioned remaining lifespan forecast, generate a maintenance time window. In practice, if the aforementioned remaining lifespan forecast is less than or equal to one year, the next period of lowest electricity consumption (e.g., 00:30–04:30) can be designated as the maintenance time window. If the aforementioned remaining lifespan forecast is greater than or equal to one year or less than three years, the current quarter can be designated as the maintenance time window. If the aforementioned remaining lifespan forecast is greater than or equal to three years, the next year can be designated as the maintenance time window.

[0070] Sub-step five involves sending the aforementioned equipment status report and maintenance time window to the equipment management center. This equipment management center can be the local power supply company's equipment management center. In practice, the implementing entity can send the aforementioned equipment status report and maintenance time window IEC 61850 message to the local equipment management center.

[0071] Step 3: In response to the above insulation breakdown warning point set being non-empty and the above target insulation status assessment result being lower than the second threshold, the following second warning processing steps are executed: Sub-step one: Generate warning level information based on the aforementioned set of insulation breakdown warning points. The second threshold can be a pre-set value. For example, the second threshold can be set to 0.8. In practice, the executing entity can obtain the time corresponding to each insulation breakdown warning point in the set. If all the times corresponding to each insulation breakdown warning point fall within the same time period, the data representing a low level of urgency can be determined as the warning level information. Conversely, if any of the times corresponding to each insulation breakdown warning point does not fall within the same time period, the data representing a high level of urgency can be determined as the warning level information.

[0072] Sub-step two: Based on the aforementioned warning level information, generate a power outage maintenance report corresponding to the warning level. In practice, in one scenario, if the warning level information indicates a low-level emergency, the following text can be integrated into a set of data: "Power outage for 2.5 hours from 02:00 to 04:30 the next morning. The busbar will be maintained by a bypass power supply. Maintenance items include oil chromatography verification and partial discharge location. Load shedding margin must be greater than 20%." This data is then used as the power outage maintenance report corresponding to the aforementioned warning level. In another scenario, if the warning level information indicates a high-level emergency, the following text can be integrated into a set of data: "From 01:00 to 05:00 that night, the main transformer and 110kV busbar will be completely shut down for 4 hours. Load will be shedding via tie lines and mobile generators. The load rate will be temporarily high, requiring advance notification to major customers for peak shifting and on-site command throughout the process." This data is then used as the power outage maintenance report corresponding to the aforementioned warning level.

[0073] Step three involves sending the aforementioned warning level information and power outage maintenance report to the equipment management center. In practice, the implementing entity can send the aforementioned warning level information and power outage maintenance report to the equipment management center and the local power grid dispatch center in real time via the dispatch data network.

[0074] Steps one to three above, as an inventive point of this disclosure, solve the technical problems of "failure to effectively integrate multi-dimensional assessment results of high-voltage equipment insulation status, disconnect between risk assessment and operation and maintenance decisions, and lack of automatic generation and push capability from early warning information to specific maintenance plans." The reasons why existing technologies struggle to achieve precise, personalized, and proactive equipment operation and maintenance are as follows: Existing systems often have multiple independent assessment models or criteria (such as AI-based comprehensive status assessment and threshold-based sequential early warning), whose outputs are isolated, making it difficult for operation and maintenance personnel to cross-verify and comprehensively judge, resulting in insufficient decision-making basis; even if risk assessment results are obtained, maintenance plans usually rely on human experience, resulting in slow response and limitations due to personnel technical levels, making it impossible to quickly generate optimal solutions in emergency situations; traditional life prediction methods are often not strongly correlated with the actual operating status of equipment and real-time fault early warnings, and the prediction results are too macroscopic, unable to support refined maintenance window arrangements, easily leading to over-maintenance or under-maintenance. If the above factors can be eliminated, a decision support closed loop that can automatically integrate multi-source assessment information, intelligently generate executable operation and maintenance strategies, and achieve information push can be constructed. Therefore, this disclosure includes the following steps: Step 1: Obtaining the first identification information (target insulation status assessment result) corresponding to the first control processing and the second identification information (insulation slight aging inflection point set and insulation breakdown early warning point set) corresponding to the second control processing. For the first time, it combines the comprehensive state quantitative assessment based on physical information neural network with the key event point detection results based on dynamic threshold sequence scanning, providing complete and three-dimensional data input for subsequent multi-dimensional and cross-criteria fusion decision-making. Step 2: Setting a composite triggering condition of "insulation slight aging inflection point set is not empty" and "target insulation status assessment result is lower than the first threshold (0.5)", this design effectively avoids false alarms that may be caused by a single criterion. It only starts the first early warning processing when the early electrical characteristics (discharge frequency) are significantly abnormal and the comprehensive insulation status assessment confirms that it is at a poor level, ensuring the accuracy and necessity of the early warning. Its sub-steps construct a complete early warning and planning process: Sub-step 1: Generating an equipment status report, integrating equipment identification, key event time points and comprehensive status values, providing clear and quantitative diagnostic conclusions for operation and maintenance personnel. Sub-step two innovatively combines operational lifespan information with real-time status assessment results using a linear decay formula to generate a predicted remaining lifespan value. This upgrades the model from a static lifespan model to a dynamic lifespan prediction based on the current health status, making the prediction results more personalized and timely. Sub-step four intelligently matches maintenance time windows of varying urgency levels (from precise timing down to a specific day's low load period to more lenient timing up to the next year) based on the dynamically predicted remaining lifespan, enabling adaptive and refined maintenance planning that balances equipment risk and power supply reliability. Sub-step five automatically pushes reports and plans to the management center, completing the entire process of automation from "data analysis" to "decision recommendations" to "information delivery."Step three establishes a more stringent composite triggering condition: "the set of insulation breakdown warning points is not empty" and "the target insulation status assessment result is lower than the second threshold (0.8)". This is used to capture an emergency state where insulation has entered an accelerated deterioration phase and is nearing failure. Its sub-steps aim to generate directly executable emergency plans: Sub-step one intelligently distinguishes between low-level and high-level emergencies based on the time distribution of warning points (whether they all occur on the same day), achieving dynamic and precise classification of warning levels. Sub-step two automatically generates detailed and highly operable power outage maintenance reports based on different warning levels, covering outage time, operating mode, specific maintenance items, and load protection measures, compressing valuable emergency decision-making time from hours to minutes, gaining a head start for rapid and safe handling. Sub-step three simultaneously pushes high-level warning information to both the equipment management center and the power grid dispatch center, achieving cross-departmental collaborative warning and emergency response, ensuring the timeliness of emergency command transmission and the effectiveness of execution. This allows for the deep integration and cross-validation of insulation assessment results from different technical approaches. Based on this, an intelligent triggering and hierarchical early warning mechanism can automatically generate a series of operation and maintenance strategies, ranging from long-term preventative maintenance plans to emergency power outage response schemes. Furthermore, adaptive maintenance windows based on dynamic lifespan prediction and refined emergency plans based on risk levels enhance the scientific rigor and efficiency of operation and maintenance management. Thus, an advanced decision support system integrating "multi-source information fusion, intelligent risk assessment, automatic strategy generation, and precise information delivery" has been constructed, realizing a shift in high-voltage equipment operation and maintenance from "passive response" to "proactive early warning and precise decision-making," thereby improving the lean management level and safe operation assurance capabilities of power grid assets to a certain extent.

[0075] Optionally, the aforementioned implementing entity may also perform the following steps: Step 1: Obtain the set of early warning information corresponding to the aforementioned early warning processing. This set of early warning information can be a data set in a JSON structure. In practice, if both the first and second early warning processing steps are executed, the executing entity can integrate the equipment status report, maintenance time window, early warning level information, and power outage maintenance report into a single data set, and identify this data set as the early warning information set corresponding to the aforementioned early warning processing. If only the first early warning processing step is executed, and the second early warning processing step is not, the executing entity can integrate the equipment status report and maintenance time window into a single data set, and identify this data set as the early warning information set corresponding to the aforementioned early warning processing. If only the second early warning processing step is executed, and the first early warning processing step is not, the executing entity can integrate the first identification information, the early warning level information, and the power outage maintenance report into a single data set, and identify this data set as the early warning information set corresponding to the aforementioned early warning processing. If neither the first nor the second warning processing step described above is executed, the executing entity can determine the first and second identification information as the warning information set corresponding to the warning processing. After determining the warning information set corresponding to the warning processing, the key-value pairs "utcTs" and "deviceCode" are added to the JSON root node of the warning information set corresponding to the warning processing. This allows the current UTC timestamp and the encoding of the high-voltage device to be added, ensuring a globally unique primary key.

[0076] Step two involves generating and storing a status information set corresponding to the high-voltage equipment based on the aforementioned multi-source signal set and early warning information set. This status information set can be a JSON-structured data set. In practice, the executing entity can integrate the multi-source signal set and early warning information set into a single data set, which is then designated as the status information set corresponding to the high-voltage equipment. Subsequently, the time-series database interface (InfluxDB / API) can be called to write data using the "encoding of the high-voltage equipment and the current UTC timestamp" as the primary key, completing local persistence and simultaneously uploading it to the cloud for backup.

[0077] Step three involves format conversion of the aforementioned status information set to obtain a converted status information set. In practice, the executing entity can add two sub-fields, echartsOption and svgCard, to the original JSON format of the status information set, thus forming a chart configuration sub-structure. This completes the format conversion for the visualization engine. Specifically, the echartsOption field is added to store the Echarts chart configuration JSON object, and the svgCard field is added to store the inline SVG string. Finally, the converted status information set is obtained.

[0078] Step four involves visualizing the transformed status information set. This visualization method converts numerical evaluation results into a graphical interface, facilitating rapid decision-making by operators. In practice, the execution entity calls the front-end Echarts engine to directly execute `setOption()` on the `echartsOption` field in the transformed status information set, generating a three-column view of line graphs, scatter plots, and dashboard on the web dashboard. Simultaneously, the inline SVG string of the `svgCard` field is injected into the HTML page, creating a scalable warning card for mobile devices. The entire rendering process achieves both "one-screen overview" and "instant viewing."

[0079] The above embodiments of this application have the following beneficial effects: Through the insulation monitoring and early warning method for high-voltage equipment, this application achieves high-precision and high-reliability online monitoring and early warning of the insulation status of high-voltage equipment under uninterrupted power conditions, effectively improving the reliability of power grid operation and the intelligent level of equipment maintenance. Specifically, traditional insulation performance monitoring relies on offline tests requiring equipment power outages, or online monitoring methods susceptible to electromagnetic interference and temperature drift, which may lead to system power outages, signal distortion, and misjudgments of status, making it difficult to meet the needs of smart grids for continuous power supply and accurate sensing. Based on this, the insulation monitoring and early warning method for high-voltage equipment in this application embodiment: First, by acquiring a multi-source signal set corresponding to the high-voltage equipment (including partial discharge pulse signals, temperature distribution signals, and dielectric loss factor signals), a multi-dimensional information foundation comprehensively reflecting the insulation status is constructed. This step integrates multiple physical quantity signals such as electrical and thermal signals from the data source, providing rich and complementary feature inputs for comprehensive analysis, overcoming the limitations of traditional single-signal monitoring. Then, interference separation processing is performed on the partial discharge pulse signal, significantly improving the signal-to-noise ratio under strong electromagnetic interference environments. This process effectively removes background electromagnetic noise through targeted signal processing techniques, solving the performance degradation problem of conventional filtering algorithms under complex operating conditions and ensuring the authenticity and accuracy of the partial discharge characteristics analyzed subsequently. Next, the dielectric loss factor signal is optimized based on the temperature distribution signal, effectively compensating for measurement drift caused by ambient temperature fluctuations. This mechanism uses the temperature signal as a compensation basis, significantly improving the measurement accuracy of the dielectric loss factor, a key insulation parameter, enabling it to more realistically reflect the aging state of the insulation material and addressing the pain point of inaccurate assessments due to temperature influences in existing methods. Finally, by performing first and second control processing based on the processed signal and integrating two types of identification information for early warning judgment, a multi-level, adaptive insulation state assessment and early warning architecture is constructed. This architecture overcomes the shortcomings of traditional fixed threshold criteria—poor adaptability and susceptibility to false alarms / missed alarms—through multi-dimensional information cross-validation and hierarchical decision-making, achieving more reliable and timely risk warnings. In summary, the embodiments of this application achieve real-time, accurate, and reliable sensing of the insulation status of high-voltage equipment through a collaborative technical approach of "multi-source signal fusion acquisition—interference separation—temperature compensation—graded control and early warning." This method not only avoids system power outages caused by offline testing, ensuring power supply continuity, but also improves the anti-interference capability and measurement accuracy of online monitoring in complex operating environments to a certain extent, providing key technical support for building a highly reliable smart grid.

[0080] Further reference Figure 2 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of an insulation monitoring and early warning device for high-voltage equipment. These device embodiments are similar to... Figure 1Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0081] like Figure 2 As shown, an insulation monitoring and early warning device 200 for high-voltage equipment in some embodiments includes: an acquisition unit 201, an interference separation unit 202, a first control unit 203, an optimization unit 204, a second control unit 205, and an early warning unit 206. The acquisition unit 201 is configured to acquire a multi-source signal set corresponding to the high-voltage equipment in the smart grid, wherein the multi-source signal set includes a partial discharge pulse signal, a temperature distribution signal, and a dielectric loss factor signal; the interference separation unit 202 is configured to perform interference separation processing on the partial discharge pulse signal to obtain a processed partial discharge pulse signal; the first control unit 203 is configured to perform a first control processing on the high-voltage equipment based on the processed partial discharge pulse signal and the temperature distribution signal, wherein the first control processing includes on-load tap changer adjustment; the optimization unit 204 is configured to... Based on the aforementioned temperature distribution signal, the aforementioned dielectric loss factor signal is optimized to obtain an optimized dielectric loss factor signal; the second control unit 205 is configured to perform a second control process on the aforementioned high-voltage equipment based on the aforementioned processed partial discharge pulse signal and the aforementioned optimized dielectric loss factor signal, wherein the aforementioned second control process includes isolating the aforementioned high-voltage equipment from the power grid; the early warning unit 206 is configured to acquire the first identification information corresponding to the aforementioned first control process and the second identification information corresponding to the aforementioned second control process, and to perform an early warning process based on the aforementioned first identification information and the aforementioned second identification information.

[0082] It is understandable that the units described in the device 200 are related to the reference. Figure 1 The steps in the described method correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method also apply to the device 200 and the units contained therein, and will not be repeated here.

[0083] The following is for reference. Figure 3 It shows a schematic diagram of the structure of an electronic device 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0084] like Figure 3As shown, the electronic device 300 may include a processing unit 301 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0085] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0086] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of some embodiments of this disclosure.

[0087] It should be noted that, in some embodiments of this disclosure, the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0088] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0089] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs. When the electronic device executes the aforementioned one or more programs, the electronic device causes the following actions: It acquires a set of multi-source signals corresponding to high-voltage equipment in a smart grid, wherein the set of multi-source signals includes a partial discharge pulse signal, a temperature distribution signal, and a dielectric loss factor signal; it performs interference separation processing on the aforementioned partial discharge pulse signal to obtain a processed partial discharge pulse signal; it performs a first regulation processing on the aforementioned high-voltage equipment based on the processed partial discharge pulse signal and the aforementioned temperature distribution signal, wherein the first regulation processing includes adjusting an on-load tap changer; it performs optimization processing on the aforementioned dielectric loss factor signal based on the aforementioned temperature distribution signal to obtain an optimized dielectric loss factor signal; it performs a second regulation processing on the aforementioned high-voltage equipment based on the processed partial discharge pulse signal and the aforementioned optimized dielectric loss factor signal, wherein the second regulation processing includes isolating the aforementioned high-voltage equipment from the power grid; it acquires first identification information corresponding to the first regulation processing and second identification information corresponding to the second regulation processing; and it performs an early warning processing based on the first identification information and the second identification information.

[0090] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0091] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0092] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including an acquisition unit, an interference separation unit, a first control unit, an optimization unit, a second control unit, and an early warning unit. The names of these units do not necessarily limit the specific unit; for example, the acquisition unit may also be described as "a unit that acquires a set of multi-source signals corresponding to high-voltage equipment in a smart grid."

[0093] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0094] Some embodiments of this disclosure also provide a computer program product, including a computer program that, when executed by a processor, implements any of the above-described insulation monitoring and early warning methods for high-voltage equipment.

[0095] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure 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 above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A method for insulation monitoring and early warning of high-voltage equipment, comprising: Obtain a set of multi-source signals corresponding to high-voltage equipment in a smart grid, wherein the set of multi-source signals includes partial discharge pulse signals, temperature distribution signals, and dielectric loss factor signals; The partial discharge pulse signal is subjected to interference separation processing to obtain the processed partial discharge pulse signal; Based on the processed partial discharge pulse signal and the temperature distribution signal, the high-voltage equipment is subjected to a first regulation process, wherein the first regulation process includes on-load tap changer adjustment; Based on the temperature distribution signal, the dielectric loss factor signal is optimized to obtain an optimized dielectric loss factor signal. Based on the processed partial discharge pulse signal and the optimized dielectric loss factor signal, a second regulation process is performed on the high-voltage equipment, wherein the second regulation process includes isolating the high-voltage equipment from the power grid; Obtain first identification information corresponding to the first control process and second identification information corresponding to the second control process, and perform early warning processing based on the first identification information and the second identification information.

2. The method according to claim 1, wherein, The acquisition of the multi-source signal set corresponding to high-voltage equipment in the smart grid includes: Acquire partial discharge pulse signals corresponding to high-voltage equipment in the smart grid; Obtain the temperature distribution signal corresponding to the high-voltage equipment; Obtain the dielectric loss factor signal corresponding to the high-voltage equipment; The partial discharge pulse signal, the temperature distribution signal, and the dielectric loss factor signal are integrated into a multi-source signal set.

3. The method according to claim 1, wherein, The interference separation processing of the partial discharge pulse signal to obtain the processed partial discharge pulse signal includes: The partial discharge pulse signal is denoised to obtain a denoised partial discharge pulse signal. The noise-reduced partial discharge pulse signal is subjected to electromagnetic shielding compensation processing to obtain the processed partial discharge pulse signal.

4. The method according to claim 1, wherein, The optimization processing of the dielectric loss factor signal based on the temperature distribution signal to obtain an optimized dielectric loss factor signal includes: Based on the temperature distribution signal, generate ambient temperature difference data; Based on the ambient temperature difference data and the dielectric loss factor signal, an optimized dielectric loss factor signal is generated.

5. The method according to claim 1, wherein, The step of acquiring the first identification information corresponding to the first control processing and the second identification information corresponding to the second control processing, and performing the early warning processing based on the first identification information and the second identification information, includes: Obtain first identification information corresponding to the first control process and second identification information corresponding to the second control process, wherein the first identification information includes the target insulation state assessment result, and the second identification information includes a set of insulation slight aging inflection points and a set of insulation breakdown warning points; In response to the fact that the set of slight aging inflection points of the insulation is not empty and the target insulation state assessment result is lower than the first threshold, the following first early warning processing step is executed: Based on the set of slight insulation aging inflection points, generate an equipment status report; Based on the obtained information on the operating years of the high-voltage equipment, a predicted value for the remaining lifespan of the high-voltage equipment is generated; Based on the predicted remaining lifespan, a maintenance time window is generated; The equipment status report and the maintenance time window are pushed to the equipment management center; In response to the insulation breakdown warning point set being non-empty and the target insulation state assessment result being lower than the second threshold, the following second warning processing step is executed: Based on the insulation breakdown early warning point set, generate early warning level information; Based on the warning level information, a power outage maintenance report corresponding to the warning level information is generated; The warning level information and the power outage maintenance report are pushed to the equipment management center.

6. The method according to claim 1, wherein, The method further includes: Obtain the set of early warning information corresponding to the early warning processing; Based on the multi-source signal set and the early warning information set, a status information set corresponding to the high-voltage equipment is generated, and the status information set is stored. The state information set is format-converted to obtain the converted state information set; The transformed set of state information is then visualized.

7. An insulation monitoring and early warning device for high-voltage equipment, comprising: The acquisition unit is configured to acquire a set of multi-source signals corresponding to high-voltage equipment in the smart grid, wherein the set of multi-source signals includes a partial discharge pulse signal, a temperature distribution signal, and a dielectric loss factor signal; An interference separation unit is configured to perform interference separation processing on the partial discharge pulse signal to obtain a processed partial discharge pulse signal. The first control unit is configured to perform a first control process on the high-voltage equipment based on the processed partial discharge pulse signal and the temperature distribution signal, wherein the first control process includes on-load tap changer adjustment. The optimization unit is configured to optimize the dielectric loss factor signal based on the temperature distribution signal to obtain an optimized dielectric loss factor signal. The second control unit is configured to perform a second control process on the high-voltage equipment based on the processed partial discharge pulse signal and the optimized dielectric loss factor signal, wherein the second control process includes isolating the high-voltage equipment from the power grid; The early warning unit is configured to acquire first identification information corresponding to the first control process and second identification information corresponding to the second control process, and to perform early warning processing based on the first identification information and the second identification information.

8. An electronic device, comprising: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 6.

9. A computer-readable medium having a computer program stored thereon, wherein, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 6.

Images