Standardized ring main unit intelligent safety protection and early warning system

Abstract

The invention relates to the technical field of power grid safety guarantee, and particularly discloses a standardized ring main unit intelligent safety protection and early warning system, which comprises a data acquisition layer, a central processing layer and an execution control layer, and is characterized in that the data acquisition layer is responsible for real-time acquisition of operating parameters of a ring main unit; the central processing layer comprises a data preprocessing sub-module, a risk assessment sub-module and a decision optimization sub-module, and realizes data cleaning, feature extraction, risk assessment and strategy generation. Through hierarchical design, efficient and accurate ring main unit state monitoring and fault prevention and control are realized. The data acquisition layer comprehensively acquires electrical, insulating and state parameters in real time by means of various sensors, and provides an accurate and rich data basis for the system; and a data preprocessing, risk assessment and decision optimization sub-module of the central processing layer performs deep processing on the acquired data, realizes a complete process from data cleaning, feature extraction to risk assessment and strategy generation, and ensures that the risk judgment is accurate and the strategy is reasonable.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid security, and in particular to a standardized ring main unit intelligent safety protection and early warning system. Background Art

[0002] With the development of intelligent power systems, the safe operation of ring main units, as key equipment in distribution networks, is crucial to ensuring power supply reliability.

[0003] There are still many shortcomings in the current ring network cabinet operation monitoring and fault warning. On the one hand, traditional monitoring methods rely on a single sensor to collect parameters, which cannot fully reflect the operating status of the ring network cabinet. For example, it is difficult to capture potential faults such as partial discharge and insulation degradation by only monitoring current and voltage; on the other hand, risk assessment methods mostly use fixed threshold judgments, which cannot adapt to the complex and changeable operating conditions of the ring network cabinet, and are prone to misjudgment or missed judgment, making it difficult to discover and deal with potential fault hazards in a timely manner.

[0004] Existing ring main unit monitoring systems often lack a systematic data processing mechanism. The data collected by some systems have not been effectively pre-processed, and there are noise interference and outliers, which affect the accuracy of the data; the data format is not unified, and it is difficult to integrate and analyze data from different sensors, which reduces the efficiency of data utilization. In the risk assessment link, the impact of operating environment factors (such as load rate and ambient temperature) on equipment status is not fully considered, the weight coefficient is fixed, and the fault risk cannot be accurately assessed, resulting in a lack of scientific operation and maintenance decisions. Summary of the Invention

[0005] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides a standardized ring network cabinet intelligent safety protection and early warning system to solve the above-mentioned technical defects.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a standardized ring main unit intelligent safety protection and early warning system, including: a data acquisition layer, a central processing layer and an execution control layer, wherein the data acquisition layer is responsible for the real-time collection of the ring main unit operating parameters; the central processing layer includes a data preprocessing submodule, a risk assessment submodule and a decision optimization submodule to implement data cleaning, feature extraction, risk assessment and strategy generation; the execution control layer includes an early warning notification subsystem, a fault handling subsystem and a log storage subsystem, and performs corresponding early warning, fault handling and log storage operations according to the evaluation results;

[0007] The data acquisition layer is connected to the central processing layer through a built-in sensor network. At the same time, a communication transmission layer is also provided in the ring network cabinet intelligent safety protection and early warning system, and the communication transmission layer is connected to the central processing layer through a built-in communication protocol stack.

[0008] Furthermore, the operating parameters of the ring network cabinet include electrical parameters, insulation parameters and state parameters. The electrical parameters are jointly composed of the amplitude, frequency and phase of the partial discharge signal of the ring network cabinet in each detection cycle; the insulation parameters are jointly composed of the sulfur dioxide concentration value, hydrogen sulfide concentration value and tetrafluoromethane concentration value of the ring network cabinet in each detection cycle; and the state parameters are jointly composed of the load rate and ambient temperature of the ring network cabinet in each detection cycle.

[0009] Furthermore, the data preprocessing submodule is used to perform data preprocessing on the ring main unit operating parameters, including: data cleaning, data integration and data transformation processing.

[0010] Furthermore, the ring main unit operating parameter data preprocessing method is as follows:

[0011] The noise of each data in the ring main unit operating parameters is removed by filtering methods. At the same time, the normal value range of each parameter is determined, and abnormal values ​​outside the range are directly deleted. The data collection time is aligned and the output signals of different sensors are converted into a standard numerical format. Finally, the parameter data of different magnitudes and ranges are normalized so that all data are within the same range.

[0012] The risk assessment submodule is used to calculate and analyze the operating parameters of the ring network cabinet in each detection cycle, and obtain the partial discharge severity assessment function, insulation fault comprehensive index and mechanical failure risk index of the ring network cabinet in each detection cycle respectively; then, by comprehensively calculating and analyzing the partial discharge severity assessment function, insulation fault comprehensive index and mechanical failure risk index, the comprehensive fault risk parameters of the ring network cabinet in each detection cycle are obtained.

[0013] Furthermore, the calculation and analysis method of the partial discharge severity evaluation function of the ring main unit in each detection cycle is as follows:

[0014] The rated load rate and standard ambient temperature of the ring main unit are obtained from the execution control layer. The dynamic weight coefficients of the electrical parameters are calculated based on the load rate and ambient temperature of the ring main unit in each detection cycle. The dynamic weight coefficients of the amplitude of the partial discharge signal of the ring main unit in each detection cycle are obtained as α′, the dynamic weight coefficients of the frequency of the partial discharge signal of the ring main unit in each detection cycle are obtained as β′, and the dynamic weight coefficients of the phase of the partial discharge signal of the ring main unit in each detection cycle are obtained as γ′.

[0015] The amplitude, frequency and phase of the partial discharge signal of the ring main unit in each detection cycle are respectively denoted as A i 、f i and At the same time, obtain the maximum signal amplitude A of the ring network cabinet during normal operation max and minimum value A minThe characteristic frequency f0 of the ring main unit during normal operation and the maximum frequency f during normal operation max and the minimum value f min , the characteristic phase of the ring network cabinet during normal operation Wherein, i=1, 2, ..., n, i represents the number of each detection cycle, and n represents the total number of detection cycle numbers;

[0016] According to the formula Calculate the partial discharge severity evaluation function FD of the ring main cabinet in each detection cycle i .

[0017] Furthermore, the calculation and analysis method of the insulation fault comprehensive index of the ring main unit in each detection cycle is as follows:

[0018] The reference operating time t0 and operating time t of the ring main unit are obtained from the execution control layer. The dynamic weight coefficient of each data in the insulation parameter is calculated based on the ambient temperature of the ring main unit in each detection cycle. The dynamic weight coefficient of the sulfur dioxide concentration value of the ring main unit in each detection cycle is obtained as w1′, the dynamic weight coefficient of the hydrogen sulfide concentration value of the ring main unit in each detection cycle is obtained as w2′, and the dynamic weight coefficient of the tetrafluoromethane concentration value of the ring main unit in each detection cycle is obtained as w3′.

[0019] Assume that the gas content vector The corresponding normal operation minimum vector Maximum value vector Dynamic weight coefficient vector

[0020] Define the gas content normalization function The calculation method is to vector Each element in , and obtain the normalized vector; according to the formula Calculate the comprehensive insulation fault index JG of the ring main unit in each detection cycle i .

[0021] Furthermore, the risk assessment submodule is used to compare and analyze the partial discharge severity assessment function and the insulation fault comprehensive index of the ring main unit in each detection cycle with the corresponding adaptive threshold value to obtain the corresponding risk assessment level;

[0022] Introduce a historical data sliding window W, which contains the most recent N detection cycle data; calculate the partial discharge severity evaluation function FD within the historical data sliding window W i The mean of ′ and standard deviation σFD i ′, according to the formula Calculate the adaptive threshold YT′ for partial discharge severity assessment, where a1 is the safety factor, determined based on historical fault data and the acceptable false alarm rate;

[0023] The calculated partial discharge severity evaluation function FD i The discharge severity level is divided by comparing it with the adaptive threshold YT′.

[0024] Furthermore, by calculating the comprehensive insulation fault index JG within the historical data sliding window W i The mean of ′ and standard deviation σJG i ′, according to the formula Calculate the adaptive threshold JT′ for insulation fault severity assessment, where a2 is the safety factor, determined based on historical fault data and acceptable false alarm rate;

[0025] The calculated insulation fault severity evaluation function JG i ′ is compared with the adaptive threshold JT′ to classify the severity level of the insulation fault.

[0026] Furthermore, the decision optimization submodule establishes a risk assessment model and introduces a feedback correction coefficient to optimize and update the dynamic weight coefficient, thereby improving the risk assessment accuracy of the ring main unit in each detection cycle;

[0027] Combine the pre-processed ring main unit operating parameters into a feature vector X i , in, are the normalized partial discharge amplitude and discharge frequency, is the measured concentration of sulfur dioxide and hydrogen sulfide gas; by the eigenvector X i Each parameter in is assigned a corresponding weight coefficient w i , and perform weighted summation to calculate the risk index S, the calculation formula is:

[0028] If the risk index S is less than 0.3, the risk level is judged to be normal, and the treatment measure is routine monitoring; if the risk index is 0.3≤S≤0.6, the risk level is judged to be early warning, and the treatment measure is to strengthen monitoring and shorten the inspection cycle; if the risk index is 0.6≤S≤0.8, the risk level is judged to be alarm, and the treatment measure is to start automatic inspection and prepare for maintenance; if the risk index S≥0.8, the risk level is judged to be emergency, and the treatment measure is to immediately alarm and trigger the emergency shutdown mechanism.

[0029] Furthermore, by calculating the characteristic parameter X i and the covariance Cov(X i,S) and the variance Var(S) of the risk index S to obtain the feedback correction coefficient δ i , the specific calculation formula is: According to the feedback correction coefficient δ i For the weight coefficient w i To update, the specific calculation formula is: w i ′=w i +κ·(δ i -w i ), where κ = 0.05 is the learning rate, which is used to control the step size of weight update, w i ′ is the updated weight coefficient; when δ i >w i When the characteristic parameter X i The correlation with the risk index S is strong, and its weight needs to be increased; when δ i <w i , then reduce its weight appropriately.

[0030] Beneficial effects of the present invention:

[0031] 1. The present invention realizes efficient and accurate ring network cabinet status monitoring and fault prevention and control through layered design; the data acquisition layer uses a variety of sensors (ultra-high frequency, gas concentration, current, thermocouple temperature sensor, etc.) to comprehensively and in real time collect electrical, insulation, and status parameters, providing an accurate and rich data foundation for the system; the data preprocessing, risk assessment and decision optimization submodules of the central processing layer deeply process the collected data, realizing a complete process from data cleaning, feature extraction to risk assessment and strategy generation, ensuring accurate risk judgment and reasonable strategy; the setting of the communication transmission layer ensures stable and efficient data transmission; the execution control layer performs early warning, fault handling and log storage operations in a timely manner according to the evaluation results, forming a monitoring-assessment-disposal closed loop. The overall system can timely detect potential faults in the ring network cabinet, give early warning and take effective measures to reduce the probability of faults, reduce equipment damage and power outages, improve the reliability and safety of the ring network cabinet operation, and at the same time accumulate operation data to provide a basis for subsequent optimization, improve the intelligent level of operation and maintenance management, and reduce operation and maintenance costs.

[0032] 2. In the present invention, the operating parameters of the ring network cabinet are comprehensively processed through the data preprocessing submodule, and filtering, noise removal and outlier processing are used to ensure data accuracy. Data integration realizes time alignment and format unification, and normalization processing facilitates data comparison and analysis, laying a solid and reliable data foundation for subsequent risk assessment. The risk assessment submodule conducts in-depth calculation and analysis, and dynamically adjusts the weight coefficients of each data in the partial discharge and insulation parameters in combination with factors such as the ring network cabinet load rate, ambient temperature, and operating time, so that the assessment is more in line with the actual operating conditions, accurately obtains the partial discharge severity assessment function, the insulation fault comprehensive index, etc., and then calculates the comprehensive fault risk parameters, which can effectively identify the potential fault risks of the ring network cabinet, provide early warnings, and help operation and maintenance personnel take timely measures to reduce the probability of faults, ensure the stable and reliable operation of the ring network cabinet, and improve the safety and continuity of power supply.

[0033] 3. The risk assessment submodule in the present invention introduces a sliding window of historical data and calculates an adaptive threshold value in combination with the mean, standard deviation and safety factor, so that the threshold setting fits the actual operation of the ring main unit and can be dynamically adjusted according to the equipment characteristics and historical fault data; the partial discharge severity assessment function and the insulation fault comprehensive index are compared with the corresponding adaptive threshold value and divided into levels, which can accurately judge the severity of partial discharge and insulation fault, and distinguish between mild, moderate and severe levels of partial discharge, which can clearly reflect the discharge development stage and the potential impact on the equipment; judge low risk and high risk of insulation fault, and clarify the critical situation of insulation status risk, which helps operation and maintenance personnel to quickly and accurately grasp the fault risk level of the ring main unit, and take reasonable measures in advance for different levels of risk, such as strengthening monitoring when it is mild and emergency maintenance when it is severe, etc., to effectively prevent faults, reduce accident losses, ensure the safe and stable operation of the ring main unit, and improve the reliability and operation and maintenance efficiency of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The present invention will be further described below with reference to the accompanying drawings.

[0035] Figure 1 This is a functional block diagram of the standardized ring main unit intelligent safety protection and early warning system according to an embodiment of the present invention;

[0036] Figure 2 This is a principle block diagram of the data acquisition layer, central processing layer and execution control layer of the present invention. DETAILED DESCRIPTION

[0037] Below, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described herein.

[0038] Example 1

[0039] See also Figure 1 and Figure 2 As shown in the figure, the standardized ring network cabinet intelligent safety protection and early warning system includes: a data acquisition layer, a central processing layer and an execution control layer. Among them, the data acquisition layer is responsible for the real-time collection of the ring network cabinet operating parameters, which include electrical parameters, insulation parameters and status parameters; the central processing layer includes a data preprocessing submodule, a risk assessment submodule and a decision optimization submodule to realize data cleaning, feature extraction, risk assessment and strategy generation; the execution control layer includes an early warning notification subsystem, a fault handling subsystem and a log storage subsystem, and performs corresponding early warning, fault handling and log storage operations according to the evaluation results.

[0040] Specifically, the data acquisition layer is connected to the central processing layer through the built-in sensor network. At the same time, the ring network cabinet intelligent safety protection and early warning system is also equipped with a communication transmission layer, which is connected to the central processing layer through the built-in communication protocol stack.

[0041] As a further explanation of the solution in this embodiment, the real-time collection method of the ring main unit operating parameters is as follows:

[0042] The partial discharge pulse information of the ring main unit in each detection cycle is collected by an ultra-high frequency sensor installed inside the ring main unit, and the partial discharge signal amplitude, frequency and phase are extracted from the partial discharge pulse information of the ring main unit in each detection cycle. The electrical parameters are jointly composed of the partial discharge signal amplitude, frequency and phase of the ring main unit in each detection cycle.

[0043] The gas composition information of the ring network cabinet in each detection cycle is collected by a gas concentration sensor installed inside the ring network cabinet, and the sulfur dioxide concentration value, hydrogen sulfide concentration value and tetrafluoromethane concentration value are extracted from the gas composition information of the ring network cabinet in each detection cycle. The sulfur dioxide concentration value, hydrogen sulfide concentration value and tetrafluoromethane concentration value of the ring network cabinet in each detection cycle together constitute the insulation parameters.

[0044] A current sensor installed inside the RMU measures the current in the circuit in real time during each test cycle. Combined with the rated current of the RMU, the load factor of the RMU during each test cycle is calculated. The load factor is calculated by dividing the real-time current by the rated current. A thermocouple temperature sensor installed inside the RMU measures the internal temperature of the RMU during each test cycle to obtain the ambient temperature of the RMU during each test cycle. The load factor and ambient temperature of the RMU during each test cycle together constitute the status parameter.

[0045] In summary, the present invention realizes efficient and accurate ring network cabinet status monitoring and fault prevention and control through layered design; the data acquisition layer uses a variety of sensors (ultra-high frequency, gas concentration, current, thermocouple temperature sensor, etc.) to comprehensively and in real time collect electrical, insulation, and status parameters, providing an accurate and rich data foundation for the system; the data preprocessing, risk assessment and decision optimization submodules of the central processing layer deeply process the collected data, realizing a complete process from data cleaning, feature extraction to risk assessment and strategy generation, ensuring accurate risk judgment and reasonable strategy; the setting of the communication transmission layer ensures stable and efficient data transmission; the execution control layer promptly performs early warning, fault handling and log storage operations based on the evaluation results, forming a monitoring-assessment-disposal closed loop. The overall system can timely detect potential faults in the ring network cabinet, issue early warnings and take effective measures to reduce the probability of faults, reduce equipment damage and power outages, improve the reliability and safety of the ring network cabinet operation, and at the same time accumulate operation data to provide a basis for subsequent optimization, improve the intelligent level of operation and maintenance management, and reduce operation and maintenance costs.

[0046] As a further explanation of the scheme in this embodiment, the data preprocessing submodule is used to perform data preprocessing on the ring main unit operating parameters, including: data cleaning, data integration and data transformation processing; the specific ring main unit operating parameter data preprocessing method is as follows:

[0047] The noise of each data in the ring network cabinet operating parameters is removed by filtering methods, and the normal value range of each parameter is determined. Abnormal values ​​outside the range are directly deleted; the data are aligned according to the collection time, and the signals output by different sensors are converted into a standard numerical format; finally, the parameter data of different magnitudes and ranges are normalized so that all data are within the same range; the normalization methods can be minimum-maximum normalization and Z-score normalization.

[0048] The risk assessment submodule is used to calculate and analyze the operating parameters of the ring main unit in each detection cycle, and obtain the partial discharge severity assessment function, insulation fault comprehensive index and mechanical failure risk index of the ring main unit in each detection cycle; then, by comprehensively calculating and analyzing the partial discharge severity assessment function, insulation fault comprehensive index and mechanical failure risk index, the comprehensive fault risk parameters of the ring main unit in each detection cycle are obtained.

[0049] Furthermore, the calculation and analysis method of the partial discharge severity evaluation function of the ring main unit in each detection cycle is as follows:

[0050] The rated load rate and standard ambient temperature of the ring main unit are obtained from the execution control layer, and the dynamic weight coefficient of each data in the electrical parameters is calculated based on the load rate and ambient temperature of the ring main unit in each detection cycle.

[0051] Specifically, the dynamic weight coefficient of the amplitude of the partial discharge signal of the ring main unit in each detection cycle is α′, α′=α+k1×(L-L0)+k2×(T-T0), the dynamic weight coefficient of the frequency of the partial discharge signal of the ring main unit in each detection cycle is β′, β′=β+k3×(L-L0)+k4×(T-T0), and the dynamic weight coefficient of the phase of the partial discharge signal of the ring main unit in each detection cycle is γ′, γ′=1-α′-β′; among them, α and β are fixed weight coefficients determined according to actual experience; L and T are load rate and ambient temperature, respectively, L0 and T0 are rated load rate and standard ambient temperature, respectively; k1, k2, k3, and k4 are adjustment coefficients determined according to experimental data.

[0052] The amplitude, frequency and phase of the partial discharge signal of the ring main unit in each detection cycle are respectively denoted as A i 、f i and At the same time, obtain the maximum signal amplitude A of the ring network cabinet during normal operation max and minimum value A min The characteristic frequency f0 of the ring main unit during normal operation and the maximum frequency f during normal operation max and the minimum value f min , the characteristic phase of the ring network cabinet during normal operation Wherein, i=1, 2, ..., n, i represents the number of each detection cycle, and n represents the total number of detection cycle numbers.

[0053] According to the formula Calculate the partial discharge severity evaluation function FD of the ring main cabinet in each detection cycle i .

[0054] The calculation and analysis method of the comprehensive insulation fault index of the ring main unit in each detection cycle is as follows:

[0055] The reference operating time t0 and operating time t of the ring main unit are obtained from the execution control layer, and the dynamic weight coefficient of each data in the insulation parameter is calculated based on the ambient temperature of the ring main unit in each detection cycle.

[0056] Specifically, the dynamic weight coefficient of the sulfur dioxide concentration value of the ring network cabinet in each detection cycle is w1′, w1′=w1+b1×(T-T0)+b2×(t-t0), the dynamic weight coefficient of the hydrogen sulfide concentration value of the ring network cabinet in each detection cycle is w2′, w2′=w2+b3×(T-T0)+b4×(t-t0), and the dynamic weight coefficient of the tetrafluoromethane concentration value of the ring network cabinet in each detection cycle is w3′, w3′=1-w1′-w2′; among them, w1 and w2 are fixed weight coefficients determined based on actual experience; b1, b2, b3, and b4 are adjustment coefficients determined through experimental data and actual operation experience.

[0057] Assume that the gas content vector The corresponding normal operation minimum vector Maximum value vector Dynamic weight coefficient vector

[0058] Define the gas content normalization function The calculation method is to vector Each element in , and obtain the normalized vector; according to the formula Calculate the comprehensive insulation fault index JG of the ring main unit in each detection cycle i .

[0059] In summary, the present invention uses a data preprocessing submodule to comprehensively process the operating parameters of the ring network cabinet, filtering and noise removal and outlier processing to ensure data accuracy, data integration to achieve time alignment and format unification, and normalization processing to facilitate data comparison and analysis, laying a solid and reliable data foundation for subsequent risk assessment. The risk assessment submodule conducts in-depth calculation and analysis, combining factors such as the ring network cabinet load rate, ambient temperature, and operating time, and dynamically adjusts the weight coefficients of each data in the partial discharge and insulation parameters to make the assessment more in line with the actual operating conditions, accurately obtain the partial discharge severity assessment function, the insulation fault comprehensive index, etc., and then calculate the comprehensive fault risk parameters, which can effectively identify the potential fault risks of the ring network cabinet, provide early warnings, and help operation and maintenance personnel take timely measures to reduce the probability of faults, ensure the stable and reliable operation of the ring network cabinet, and improve the safety and continuity of power supply.

[0060] The risk assessment submodule is used to compare and analyze the partial discharge severity evaluation function and insulation fault comprehensive index of the ring main unit in each detection cycle with the corresponding adaptive thresholds to obtain the corresponding risk assessment level.

[0061] Introduce a historical data sliding window W, which contains the most recent N detection cycle data; calculate the partial discharge severity evaluation function FD within the historical data sliding window W i The mean of ′ and standard deviation σFD i ′, according to the formula The adaptive threshold YT′ for partial discharge severity assessment is calculated, and a1 is the safety factor, which is determined based on historical fault data and the acceptable false alarm rate.

[0062] The calculated partial discharge severity evaluation function FD i The discharge severity level is divided into different levels by comparing with the adaptive threshold YT′. The specific level division method is as follows:

[0063] When FD i When <YT′, it is judged as a mild partial discharge level. At this time, the partial discharge is in a relatively early or weak stage and has little impact on the insulation performance of the equipment.

[0064] When YT′≤FD i When YT′<YT′+ΔYT′, it is judged as a moderate partial discharge level, indicating that the partial discharge phenomenon is relatively obvious and may cause a certain degree of damage to the equipment insulation; among them, ΔYT′ is the moderate discharge increment threshold, which is determined based on equipment characteristics and operating experience.

[0065] When FD i When ≥YT′+ΔYT′, it is judged as a severe partial discharge level, which means that the partial discharge situation is serious and the equipment insulation may have been severely damaged, which may cause equipment failure or even accidents at any time.

[0066] Calculate the comprehensive insulation fault index JG within the historical data sliding window W i The mean of ′ and standard deviation σJG i ′, according to the formula The adaptive threshold JT′ for insulation fault severity assessment is calculated, and a2 is the safety factor, which is determined based on historical fault data and the acceptable false alarm rate.

[0067] The calculated insulation fault severity evaluation function JG i ' is compared with the adaptive threshold JT' to classify the severity of the insulation fault. The specific classification method is as follows:

[0068] When JG i When <JT′, it is judged as a low-risk insulation fault. At this time, the current insulation status has not yet reached the risk criticality.

[0069] When JG i When ≥JT′, it is judged as a high-risk insulation fault, which means that the insulation fault risk of the ring main unit has reached or exceeded the set critical value.

[0070] In summary, the risk assessment submodule in the present invention introduces a sliding window of historical data and calculates an adaptive threshold value in combination with the mean, standard deviation and safety factor, so that the threshold setting fits the actual operation of the ring main unit and can be dynamically adjusted according to the equipment characteristics and historical fault data; the local discharge severity evaluation function and the insulation fault comprehensive index are compared with the corresponding adaptive threshold value and divided into levels, which can accurately judge the severity of local discharge and insulation fault, and distinguish between mild, moderate and severe levels of local discharge, which can clearly reflect the discharge development stage and the potential impact on the equipment; judge low risk and high risk of insulation fault, and clarify the critical situation of insulation status risk, which helps operation and maintenance personnel to quickly and accurately grasp the risk level of ring main unit failure, and take reasonable measures in advance for different levels of risk, such as strengthening monitoring when it is mild and emergency maintenance when it is severe, etc., to effectively prevent faults from occurring, reduce accident losses, ensure the safe and stable operation of the ring main unit, and improve the reliability and operation and maintenance efficiency of the power system.

[0071] Furthermore, the decision optimization submodule establishes a risk assessment model and introduces a feedback correction coefficient to optimize and update the dynamic weight coefficient, thereby improving the risk assessment accuracy of the ring network cabinet in each detection cycle.

[0072] Combine the pre-processed ring main unit operating parameters into a feature vector X i , in, are the normalized partial discharge amplitude and discharge frequency, is the measured concentration of sulfur dioxide and hydrogen sulfide gas; by the eigenvector X i Each parameter in is assigned a corresponding weight coefficient w i , and perform weighted summation to calculate the risk index S, the calculation formula is:

[0073] If the risk index S is less than 0.3, the risk level is judged to be normal, and the treatment measure is routine monitoring; if the risk index is 0.3≤S≤0.6, the risk level is judged to be early warning, and the treatment measure is to strengthen monitoring and shorten the inspection cycle; if the risk index is 0.6≤S≤0.8, the risk level is judged to be alarm, and the treatment measure is to start automatic inspection and prepare for maintenance; if the risk index S≥0.8, the risk level is judged to be emergency, and the treatment measure is to immediately alarm and trigger the emergency shutdown mechanism.

[0074] By calculating the characteristic parameter X i and the covariance Cov(X i ,S) and the variance Var(S) of the risk index S to obtain the feedback correction coefficient δ i , the specific calculation formula is: According to the feedback correction coefficient δ i For the weight coefficient w iTo update, the specific calculation formula is: w i ′=w i +κ·(δ i -w i ), where κ = 0.05 is the learning rate, which is used to control the step size of weight update, w i ′ is the updated weight coefficient; when δ i >w i When the characteristic parameter X i The correlation with the risk index S is strong, and its weight needs to be increased; when δ i <w i , then reduce its weight appropriately.

[0075] In summary, the decision optimization submodule in the present invention constructs a risk assessment model, integrates the pre-processed ring network cabinet operating parameters into a feature vector, and assigns a weight coefficient to calculate the risk index. It divides the risk level based on a clear threshold, and provides a step-by-step treatment measure from routine monitoring to emergency shutdown, making risk management more targeted and standardized; at the same time, a feedback correction coefficient mechanism is introduced to dynamically optimize the weight coefficient based on the covariance and variance of the feature parameters and the risk index. When the correlation between the two is high, the corresponding parameter weight is enhanced, and vice versa, the adaptability of the model to the complex operating state of the ring network cabinet is effectively improved; using such a dynamic adjustment method, the risk assessment deviation can be calibrated in real time, misjudgment and missed judgment can be reduced, and the risk assessment can be ensured to fit the actual operating conditions, helping operation and maintenance personnel to accurately grasp equipment risks, scientifically plan operation and maintenance strategies, reduce the probability of equipment failure, improve the operating safety and operation and maintenance efficiency of the ring network cabinet, and realize the continuous optimization and upgrading of the intelligent safety protection and early warning system.

[0076] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The size of the coefficient is a specific value obtained by quantifying each parameter. Regarding the size of the coefficient, as long as it does not affect the proportional relationship between the parameter and the quantified value, it is acceptable.

[0077] In addition, it will be understood by those skilled in the art that various aspects of the present invention may be illustrated and described by a number of patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvements thereto. Accordingly, various aspects of the present invention may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of the present invention may be represented as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0078] Unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology and should not be interpreted in an idealized or highly formal sense, unless expressly defined as such herein.

[0079] The above is an illustration of the present invention and should not be considered as limiting thereof. Although several exemplary embodiments of the present invention have been described, it will be readily understood by those skilled in the art that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present invention. Therefore, all such modifications are intended to be included within the scope of the present invention as defined by the claims. It should be understood that the above is an illustration of the present invention and should not be considered as being limited to the specific embodiments disclosed, and modifications to the disclosed embodiments and other embodiments are intended to be included within the scope of the appended claims. The present invention is defined by the claims and their equivalents.

Claims

1. Standardized ring main unit intelligent safety protection and early warning system, characterized by: include: The data acquisition layer, central processing layer, and execution control layer are responsible for real-time collection of ring network cabinet operating parameters. The central processing layer includes a data preprocessing submodule, a risk assessment submodule, and a decision optimization submodule to implement data cleaning, feature extraction, risk assessment, and strategy generation. The execution control layer includes an early warning notification subsystem, a fault handling subsystem, and a log storage subsystem to perform corresponding early warning, fault handling, and log storage operations based on the assessment results. The data acquisition layer is connected to the central processing layer through a built-in sensor network. At the same time, a communication transmission layer is also provided in the ring network cabinet intelligent safety protection and early warning system, and the communication transmission layer is connected to the central processing layer through a built-in communication protocol stack.

2. The standardized ring main unit intelligent safety protection and early warning system according to claim 1 is characterized in that: The operating parameters of the ring network cabinet include electrical parameters, insulation parameters and state parameters. The electrical parameters are jointly composed of the amplitude, frequency and phase of the partial discharge signal of the ring network cabinet in each detection cycle; the insulation parameters are jointly composed of the sulfur dioxide concentration value, hydrogen sulfide concentration value and tetrafluoromethane concentration value of the ring network cabinet in each detection cycle; and the state parameters are jointly composed of the load rate and ambient temperature of the ring network cabinet in each detection cycle.

3. The standardized ring main unit intelligent safety protection and early warning system according to claim 1 is characterized in that: The data preprocessing submodule is used to perform data preprocessing on the ring network cabinet operating parameters, including: data cleaning, data integration and data transformation processing.

4. The standardized ring main unit intelligent safety protection and early warning system according to claim 1 is characterized in that: The ring main unit operating parameter data preprocessing method is as follows: The noise of each data in the ring main unit operating parameters is removed by filtering methods. At the same time, the normal value range of each parameter is determined, and abnormal values ​​outside the range are directly deleted. The data collection time is aligned and the output signals of different sensors are converted into a standard numerical format. Finally, the parameter data of different magnitudes and ranges are normalized so that all data are within the same range. The risk assessment submodule is used to calculate and analyze the operating parameters of the ring main unit in each detection cycle, and obtain the partial discharge severity evaluation function, insulation fault comprehensive index and mechanical failure risk index of the ring main unit in each detection cycle; Then, by comprehensively calculating and analyzing the partial discharge severity evaluation function, insulation fault comprehensive index and mechanical failure risk index, the comprehensive fault risk parameters of the ring main unit in each detection cycle are obtained.

5. The standardized ring main unit intelligent safety protection and early warning system according to claim 1 is characterized in that: The calculation and analysis method of the partial discharge severity evaluation function of the ring main unit in each detection cycle is as follows: The rated load rate and standard ambient temperature of the ring main unit are obtained from the execution control layer. The dynamic weight coefficients of the electrical parameters are calculated based on the load rate and ambient temperature of the ring main unit in each detection cycle. The dynamic weight coefficients of the amplitude of the partial discharge signal of the ring main unit in each detection cycle are obtained as α′, the dynamic weight coefficients of the frequency of the partial discharge signal of the ring main unit in each detection cycle are obtained as β′, and the dynamic weight coefficients of the phase of the partial discharge signal of the ring main unit in each detection cycle are obtained as γ′. The amplitude, frequency and phase of the partial discharge signal of the ring main unit in each detection cycle are respectively denoted as A i 、f i and At the same time, obtain the maximum signal amplitude A of the ring network cabinet during normal operation max and minimum value A min The characteristic frequency f0 of the ring main unit during normal operation and the maximum frequency f during normal operation max and the minimum value f min , the characteristic phase of the ring network cabinet during normal operation Wherein, i=1, 2, ..., n, i represents the number of each detection cycle, and n represents the total number of detection cycle numbers; According to the formula Calculate the partial discharge severity evaluation function FD of the ring main cabinet in each detection cycle i .

6. The standardized ring main unit intelligent safety protection and early warning system according to claim 1 is characterized in that: The calculation and analysis method of the insulation fault comprehensive index of the ring main unit in each detection cycle is as follows: The reference operating time t0 and operating time t of the ring main unit are obtained from the execution control layer. The dynamic weight coefficient of each data in the insulation parameter is calculated based on the ambient temperature of the ring main unit in each detection cycle. The dynamic weight coefficient of the sulfur dioxide concentration value of the ring main unit in each detection cycle is obtained as w1′, the dynamic weight coefficient of the hydrogen sulfide concentration value of the ring main unit in each detection cycle is obtained as w2′, and the dynamic weight coefficient of the tetrafluoromethane concentration value of the ring main unit in each detection cycle is obtained as w3′. Assume that the gas content vector The corresponding normal operation minimum vector Maximum value vector Dynamic weight coefficient vector Define the gas content normalization function The calculation method is to vector Each element in , and obtain the normalized vector; according to the formula Calculate the comprehensive insulation fault index JG of the ring main unit in each detection cycle i .

7. The standardized ring main unit intelligent safety protection and early warning system according to claim 5 is characterized in that: The risk assessment submodule is used to compare and analyze the partial discharge severity evaluation function and the insulation fault comprehensive index of the ring main unit in each detection cycle with the corresponding adaptive threshold value to obtain the corresponding risk assessment level; Introduce a historical data sliding window W, which contains the data of the most recent N detection cycles; Calculate the partial discharge severity evaluation function FD within the historical data sliding window W i The mean of ′ and standard deviation σFD i ′, according to the formula Calculate the adaptive threshold YT′ for partial discharge severity assessment, where a1 is the safety factor, determined based on historical fault data and the acceptable false alarm rate; The calculated partial discharge severity evaluation function FD i Compared with the adaptive threshold YT′, Classify the severity of discharge.

8. The standardized ring main unit intelligent safety protection and early warning system according to claim 6 is characterized in that: By calculating the comprehensive insulation fault index JG within the historical data sliding window W i The mean of ′ and standard deviation σJG i ′, according to the formula Calculate the adaptive threshold JT′ for insulation fault severity assessment, where a2 is the safety factor, determined based on historical fault data and acceptable false alarm rate; The calculated insulation fault severity evaluation function JG i ′ is compared with the adaptive threshold JT′ to classify the severity level of the insulation fault.

9. The standardized ring main unit intelligent safety protection and early warning system according to claim 1 is characterized in that: The decision optimization submodule establishes a risk assessment model and introduces a feedback correction coefficient to optimize and update the dynamic weight coefficient, thereby improving the risk assessment accuracy of the ring network cabinet in each detection cycle; Combine the pre-processed ring main unit operating parameters into a feature vector X i , in, are the normalized partial discharge amplitude and discharge frequency, is the measured concentration of sulfur dioxide and hydrogen sulfide gas; by the eigenvector X i Each parameter in is assigned a corresponding weight coefficient w i , and perform weighted summation to calculate the risk index S, the calculation formula is: If the risk index S is less than 0.3, the risk level is judged to be normal, and the treatment measure is routine monitoring; if the risk index is 0.3≤S≤0.6, the risk level is judged to be early warning, and the treatment measure is to strengthen monitoring and shorten the inspection cycle; if the risk index is 0.6≤S≤0.8, the risk level is judged to be alarm, and the treatment measure is to start automatic inspection and prepare for maintenance; if the risk index S≥0.8, the risk level is judged to be emergency, and the treatment measure is to immediately alarm and trigger the emergency shutdown mechanism.

10. The standardized ring main unit intelligent safety protection and early warning system according to claim 9 is characterized in that: By calculating the characteristic parameter X i and the covariance Cov(X i ,S) and the variance Var(S) of the risk index S to obtain the feedback correction coefficient δ i , the specific calculation formula is: According to the feedback correction coefficient δ i For the weight coefficient w i To update, the specific calculation formula is: w i ′=w i +κ·(δ i -w i ), where κ = 0.05 is the learning rate, which is used to control the step size of weight update, w i ′ is the updated weight coefficient; when δ i >w i When the characteristic parameter X i The correlation with the risk index S is strong, and its weight needs to be increased; when δ i <w i , then reduce its weight appropriately.

Images