Power grid monitoring management system

Abstract

The invention belongs to the technical field of power grids, and particularly relates to a power grid monitoring management system, which is characterized in that a multi-source data integration module is used for collecting and integrating transformer equipment parameters, working parameters and environmental parameters of a transformer in a power grid jurisdiction to form a comprehensive data set reflecting the running state of the transformer; and establishing a transformer aging analysis model by using the comprehensive data set, and performing fine tuning training on the comprehensive data set of the transformer. According to the invention, the aging analysis model of the transformer is established in the power grid, the risk assessment model is established for the aging state of the transformer in the jurisdiction, the risk assessment model is set, the aging state of the transformer in the power grid jurisdiction is supervised, and early warning signals are made in combination with various data. The aging state can be formed according to the working data and the environment data of the transformer so as to update the maintenance plan of the transformer, the aging of the transformer can be early warned, and the transformer can be maintained in time.

Description

Technical Field

[0001] The present invention relates to the technical field of power grids, and in particular to a power grid monitoring and management system. Background Art

[0002] The power grid monitoring and management system is an indispensable part of the power system, which ensures the safe, reliable and efficient operation of the power system through real-time monitoring, data collection, analysis and control.

[0003] Existing patent (Publication No.: CN110635572B) and a power grid monitoring and management system;

[0004] Existing patent (Publication No.: CN112305338B) and a method and system for detecting the aging degree of a dry-type transformer;

[0005] Problems raised against Comparative Document 1:

[0006] Since the voltage stability and coordinated control of the power grid are inseparable from the transformer, and there is no effective supervision of the transformer, when the transformer fails, there is a high possibility of a chain reaction leading to a regional power grid failure;

[0007] Problems raised against Comparative Document 2: In Comparative Document 2, the characteristic quantities of thermal aging of various insulating materials at different temperatures are proposed, and the thermal aging index is judged by analyzing the change in the concentration of decomposed gas. However, for a transformer, the factors affecting the aging of the transformer are relatively complex. Even if the insulating material has not reached the aging degree, the transformer needs to be regularly overhauled and maintained. At the same time, the aging of the transformer also has a greater impact on the stability of the power grid. If the aging transformer cannot be maintained in time, once a transformer in the area fails, it may lead to a regional power outage and even damage to other transformers.

[0008] Therefore, it is necessary to provide a power grid monitoring and management system to solve the above technical problems. Summary of the Invention

[0009] To solve the above technical problems, the present invention provides a power grid monitoring and management system, which incorporates the aging situation of transformers into the power grid monitoring and management system.

[0010] A power grid monitoring and management system provided by the present invention collects and integrates the transformer equipment parameters, working parameters and environmental parameters of transformers within the power grid jurisdiction through a multi-source data integration module to form a comprehensive data set reflecting the operating state of the transformers;

[0011] Using the comprehensive data set to establish a transformer aging analysis model, fine-tuning and training the transformer comprehensive data set, and learning the common characteristics of transformer aging data through transfer learning and deep learning models;

[0012] Based on the common characteristics of the transformer aging data output by the transformer aging analysis model, combined with information such as the rated capacity, load rate, operating time of the transformer, and the topological structure of the power grid where it is located, an evaluation is carried out, and a risk assessment model is established;

[0013] The risk assessment module issues a first-level warning, a second-level warning, or a third-level warning for the risk level of the transformer aging status;

[0014] Supervise the status of the transformer based on the evaluation results and risk levels of the risk assessment module;

[0015] The transformer maintenance evaluation module issues a high-risk warning and a low-risk warning according to the replaced components and maintenance status of the transformer;

[0016] Retrieve the comprehensive dataset of transformers with high-risk warnings, and the transformer matching module marks the risks for other transformers with common characteristics within the power grid jurisdiction.

[0017] Preferably, the method for calculating the transformer aging index A based on equipment parameters and working parameters is as follows:

[0018]

[0019] Among them, the transformer working parameters, working voltage U, working current I, power factor PF, and transformer equipment parameters include rated power S, rated voltage U, turns ratio T, and efficiency E;

[0020] is: the square of the load rate;

[0021] is: the voltage deviation;

[0022] is: the attenuation of efficiency and power factor.

[0023] Preferably, the influence of environmental parameters on transformer aging:

[0024] Among them, temperature C, humidity R, altitude H;

[0025] Temperature acceleration term:

[0026] exp(λ·ΔC), ΔC = C - C ref

[0027] Cref: reference temperature;

[0028] λ: material-related coefficient;

[0029] Humidity acceleration term:

[0030] 1 + α·max(R - R crit , 0)

[0031] Rcrit: Humidity threshold;

[0032] α: Humidity sensitivity coefficient;

[0033] Altitude correction term:

[0034]

[0035] Href: Reference altitude;

[0036] β: Altitude coefficient.

[0037] Preferably, the method for calculating the transformer aging index A by adding environmental parameters based on device parameters and working parameters is as follows:

[0038]

[0039] Wherein, temperature C, humidity R, altitude H;

[0040] exp(λ·ΔC) is: Humidity acceleration term;

[0041] (1 + α·max(R - R crit , 0)) is: Humidity acceleration term;

[0042] is: Altitude correction term.

[0043] Preferably, the multi-source data integration module: working parameters include voltage, current, and power factor; transformer device parameters include rated power, rated voltage, turns ratio, and efficiency; environmental data includes temperature, humidity, and altitude, and integrates them to form a comprehensive data set reflecting the operating state of the transformer;

[0044] Transformer aging analysis model: Use the deep learning model pre-trained on the comprehensive data set of transformers in the power grid jurisdiction as the basic model, and then perform fine-tuning training on the transformer comprehensive data set;

[0045] Risk assessment model: According to the aging prediction results output by the transformer aging analysis model, combined with the rated capacity, load rate, operating time of the transformer, and the topological structure information of the power grid where it is located, when the risk level exceeds the preset threshold, the system immediately issues three levels of warning signals. The first-level warning is a red alert, indicating high risk, the second-level warning is an orange alert, indicating medium risk, and the third-level warning is a yellow alert, indicating low risk;

[0046] Monitoring and maintenance module: Based on the risk assessment results and the aging prediction information of the transformer, the system generates a monitoring and maintenance plan;

[0047] Transformer maintenance evaluation module: After the transformer is maintained, the replaced components and the maintenance status are uploaded to the transformer maintenance evaluation module to evaluate the aging status of the maintained transformer. The evaluation is divided into high-risk warning and low-risk warning;

[0048] Transformer matching module: When a high-risk warning appears in the transformer maintenance evaluation module, search for transformers of the same model within the jurisdiction, and make an analogy by combining the environmental data, working parameters, and sensor data of the transformers of the same model to mark the transformers under the same working conditions.

[0049] Preferably, the method for calculating the risk assessment model based on the transformer aging index A in combination with the rated capacity, load factor, operating time, and topological structure information of the power grid where the transformer is located is as follows:

[0050]

[0051] Aging index A: Normalized to Amax (assuming the maximum value is 10), that is;

[0052] Load factor L: The ratio of the actual load to the rated capacity. The reference load factor Lbase = 0.8, and the index k = 2 strengthens the high-load risk;

[0053] Operating time T: Normalized to the design life Tdesign = 30 years;

[0054] Topological structure factor C: Reflects the importance of the transformer in the power grid, and the value is {1, 2, 3} (low, medium, high);

[0055] First-level warning (high risk): R≥3;

[0056] Second-level warning (medium risk): 1≤R<3;

[0057] Third-level warning (low risk): R<1.

[0058] Preferably, the transformer maintenance evaluation module: For the transformer to be maintained in the transformer maintenance evaluation module, the importance of the replaced components is classified:

[0059] Key components: Wi = 3;

[0060] Important components: Wi = 2;

[0061] General components: Wi = 1;

[0062] Classify the transformer maintenance status level:

[0063] Completely repaired: Si = 1.0;

[0064] Partially repaired: Si = 0.5;

[0065] Unrepaired or major defects remaining: Si = 0;

[0066] The formula for calculating the aging state of the transformer after maintenance by combining the scoring of replaced components and the scoring of the transformer maintenance status is as follows:

[0067]

[0068] High-risk warning: R ≥ 3;

[0069] Low-risk warning: R < 3.

[0070] Compared with the related technologies, a power grid monitoring and management system provided by the present invention has the following beneficial effects:

[0071] 1. The present invention establishes an aging analysis model of transformers in the power grid, establishes a risk assessment model for the aging state of transformers in the jurisdiction, and sets a risk assessment model to form supervision over the aging state of transformers in the power grid jurisdiction, and issues a warning signal by combining various data, which is beneficial to forming an aging state based on the working data and environmental data of the transformers and then updating the maintenance plan of the transformers, is beneficial to warning against the aging of the transformers, and is beneficial to timely repairing the transformers.

[0072] 2. After the transformer of the present invention is repaired, through the transformer detection and evaluation module, combined with the components that need to be replaced for the repaired transformer and the transformer maintenance status, the aging state of the repaired transformer is evaluated, and it is divided into high-risk warning and low-risk warning. For the transformer with a high-risk warning, the transformer matching module is started. For the data of the transformer with a high-risk warning and the transformers of the same model in the jurisdiction, by comparing the environmental data, working parameters and sensor data of the transformers of the same model, the transformers under the same working conditions are marked, which is beneficial to quickly eliminate possible risks after a high-risk warning is found. Description of the Drawings

[0073] Figure 1 It is a schematic diagram of the overall control process of a power grid monitoring and management system provided by the present invention;

[0074] Figure 2 It is a schematic diagram of the process of Embodiment 1 of a power grid monitoring and management system provided by the present invention;

[0075] Figure 3 It is a schematic diagram of the process of Embodiment 2 of a power grid monitoring and management system provided by the present invention. Detailed Embodiments

[0076] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the protection scope of the present invention.

[0077] A power grid monitoring and management system:

[0078] Multi-source data integration module: Working parameters include voltage, current, power factor, and transformer equipment parameters including rated power, rated voltage, transformation ratio, and efficiency. Environmental data includes temperature, humidity, and altitude.

[0079] It also includes: historical operation and maintenance records, maintenance time, fault types, and handling situations.

[0080] Through data cleaning, feature extraction, and standardization processing, these data from different sources and in different formats are fused into a comprehensive dataset that comprehensively reflects the operating status of the transformer.

[0081] Transformer aging analysis model: Using a pre-trained deep learning model (such as a convolutional neural network or a recurrent neural network) on the comprehensive dataset of transformers in the power grid jurisdiction as the basic model, and then performing fine-tuning training on the transformer comprehensive dataset. Through transfer learning, the deep learning model can quickly learn the common features of transformer data.

[0082] On this basis, refined adjustments are made according to the characteristics of the transformer itself, so as to effectively improve the accuracy and generalization ability of the transformer aging analysis model, and reliable assessment of the transformer aging status can be achieved even in the case of small samples.

[0083] According to the aging prediction results output by the transformer aging analysis model, combined with information such as the rated capacity, load rate, operating time of the transformer, and the topological structure of the power grid where it is located, a risk assessment model is established.

[0084] This model comprehensively considers various factors and uses the analytic hierarchy process or the fuzzy comprehensive evaluation method, etc. to calculate the operating risk level of the transformer. When the risk level exceeds the preset threshold, the system immediately issues three levels of warning signals. The first-level warning is a red alert, indicating high risk;

[0085] The second-level warning is an orange alert, indicating medium risk;

[0086] The third-level warning is a yellow alert, indicating low risk, and the warning information is sent to relevant operation and maintenance personnel and the power grid dispatching center to remind them to pay attention to the operating status of the transformer in a timely manner.

[0087] Monitoring and maintenance module

[0088] Based on the risk assessment results and the aging prediction information of the transformer, the system automatically generates a personalized monitoring and maintenance plan.

[0089] For transformers with a low risk level, the monitoring period is appropriately extended, and a regular inspection and data collection are carried out once a week.

[0090] For transformers with a medium risk level, the monitoring period is shortened to every 3 - 5 days, and the detection items of some key parameters are increased.

[0091] For transformers with a high risk level, 24 - hour real - time monitoring is implemented, a detailed inspection and data analysis are carried out every day, and a comprehensive maintenance plan in the near future is arranged.

[0092] At the same time, predict the remaining life of the transformer according to its aging trend, plan the procurement of spare parts and equipment replacement plan in advance to ensure the safe and stable operation of the power grid.

[0093] Transformer maintenance evaluation module: Upload the replaced parts and maintenance status of the transformer after maintenance to the transformer maintenance evaluation module to evaluate the aging status of the transformer after maintenance. The evaluation is divided into high - risk warning and low - risk warning.

[0094] The method for calculating the transformer aging index A based on equipment parameters and working parameters is as follows:

[0095]

[0096] Among them, the transformer working parameters include working voltage U, working current I, power factor PF, and the transformer equipment parameters include rated power S, rated voltage U, transformation ratio T, and efficiency E.

[0097] is: the square of the load rate;

[0098] is: the voltage deviation;

[0099] is: the attenuation of efficiency and power factor.

[0100] Preferably, the influence of environmental parameters on transformer aging:

[0101] Among them, temperature C, humidity R, altitude H;

[0102] Temperature acceleration term:

[0103] exp(λ·ΔC), ΔC = C - C ref

[0104] Physical meaning: For every 1℃ increase in temperature, the aging rate increases exponentially (simplified form of the Arrhenius model).

[0105] Cref: Reference temperature (such as 20 °C);

[0106] λ: Material - related coefficient (such as λ = 0.08, corresponding to every 10 °C increase in temperature, the aging rate doubles);

[0107] Humidity acceleration term:

[0108] 1 + α·max(R - R crit , 0)

[0109] Physical meaning: When the humidity exceeds the critical value Rcrit (such as 70%), the moisture absorption of the insulating material accelerates aging.

[0110] Rcrit: Humidity threshold;

[0111] α: Humidity - sensitive coefficient (such as α = 0.02, for every 10% increase in humidity, the aging rate increases by 20%);

[0112] Altitude correction term:

[0113]

[0114] Physical meaning: At high altitudes, the air is thin and the heat - dissipation ability decreases, which is equivalent to an amplified temperature rise.

[0115] Href: Reference altitude (such as 1000 m);

[0116] β: Altitude coefficient (such as β = 0.03, for every 1000 m increase in altitude, the aging rate increases by 3%).

[0117] Among them, the above three kinds of data are calibrated according to actual needs, and the parameter calibration method can be referred to;

[0118] Temperature coefficient λ: Fitted through accelerated aging experiments or historical failure data.

[0119] Humidity threshold R: Refer to the moisture - absorption characteristics of the insulating material (such as for oil - immersed paper insulation, Rcrit = 65%).

[0120] Altitude coefficient β: Based on the altitude - temperature rise correction table in IEEE Std C57.12.00.

[0121] For example: If a certain transformer operates under the following conditions:

[0122] Sactual / Srated = 0.9, Uactual / Urated = 1.05, E = 0.98, PF = 0.92;

[0123] C = 50 °C, R = 80%, H = 2000 m, λ = 0.08, Cref = 20 °C, α = 0.02, Rcrit = 70%, β = 0.03, Href = 1000 m;

[0124]

[0125] Environmental factors increase the aging rate to 3.96 times the base value, and maintenance needs to be prioritized.

[0126] Based on equipment parameters, operating parameters, and environmental parameters, the method for calculating the transformer aging index A is as follows:

[0127]

[0128] Among them, temperature C, humidity R, altitude H;

[0129] exp(λ·ΔC) is: humidity acceleration term;

[0130] (1 + α·max(R - R crit , 0)) is: humidity acceleration term;

[0131] is: altitude correction term.

[0132] Multi-source data integration module: operating parameters, including voltage, current, and power factor; transformer equipment parameters, including rated power, rated voltage, turns ratio, and efficiency; environmental data, including temperature, humidity, and altitude;

[0133] Transformer aging analysis model: Using a deep learning model pre-trained on the comprehensive dataset of transformers in the power grid jurisdiction as the basic model, and then performing fine-tuning training on the transformer comprehensive dataset;

[0134] Risk assessment model: According to the aging prediction results output by the transformer aging analysis model, combined with the rated capacity, load rate, operating time of the transformer, and the topological structure information of the power grid where it is located, when the risk level exceeds the preset threshold, the system immediately issues three levels of warning signals. The first-level warning is a red alert, indicating high risk, the second-level warning is an orange alert, indicating medium risk, and the third-level warning is a yellow alert, indicating low risk;

[0135] Monitoring and maintenance module: Based on the risk assessment results and the aging prediction information of the transformer, the system generates a monitoring and maintenance plan;

[0136] Transformer overhaul evaluation module: Upload the replaced components and maintenance status of the transformer after overhaul to the transformer overhaul evaluation module to evaluate the aging status of the transformer after overhaul. The evaluation is divided into high-risk warning and low-risk warning;

[0137] Transformer matching module: When a high-risk warning appears in the transformer maintenance evaluation module, search for transformers of the same model within the jurisdiction, and make an analogy by combining the environmental data, working parameters, and sensor data of the transformers of the same model, and mark the transformers under the same working conditions.

[0138] The method for calculating the risk assessment model based on the transformer aging index A in combination with the rated capacity, load rate, operating time of the transformer, and the topological structure information of the power grid where it is located is as follows:

[0139]

[0140] Aging index (A): Normalized to Amax (assuming the maximum value is 10), that is.

[0141] Load rate (L): The ratio of the actual load to the rated capacity, the reference load rate Lbase = 0.8, and the exponent k = 2 strengthens the high-load risk.

[0142] Operating time (T): Normalized to the design life Tdesign = 30 years.

[0143] Topological structure factor (C): Reflects the importance of the transformer in the power grid, and the values are {1, 2, 3} (low, medium, high);

[0144] First-level warning (high risk): R ≥ 3;

[0145] Severe aging, extremely high load, long-term operation, and located at a critical node.

[0146] Second-level warning (medium risk): 1 ≤ R < 3;

[0147] There is aging or high load, but not both reaching extreme values.

[0148] Third-level warning (low risk): R < 1;

[0149] Less aging, moderate load, or short operating time.

[0150] Transformer maintenance evaluation module: For the transformers maintained in the transformer maintenance evaluation module that need to replace components, classify the importance of the replaced components:

[0151] Key components (such as windings, iron cores): Wi = 3;

[0152] Important components (such as bushings, tap changers): Wi = 2;

[0153] General components (such as radiators, oil conservators): Wi = 1;

[0154] Classify the maintenance status level of the transformer:

[0155] Full repair: Si = 1.0;

[0156] Partial repair: Si = 0.5;

[0157] Unrepaired or major defects remaining: Si = 0;

[0158] The formula for calculating the aging state of the transformer after maintenance by combining the scoring of replaced components and the scoring of transformer maintenance status is as follows:

[0159]

[0160] High-risk warning: R ≥ 3;

[0161] Low-risk warning: R < 3.

[0162] Illustrative example:

[0163] Importance and maintenance status of coupling components: The risk weight is the highest when key components are unrepaired (Wi = 3), and the risk value is amplified by superimposing maintenance defects (1 - Si).

[0164] Dynamic threshold division: If any key component is unrepaired (R ≥ 3) during a single maintenance, a first-level warning is directly triggered; other cases are classified as second-level.

[0165] Case 1: Replace 1 key component (winding), and the maintenance status is partial repair (S = 0.5)

[0166] R = 3×(1 - 0.5) = 1.5

[0167] Second-level warning.

[0168] Case 2: Replace 1 key component (iron core) unrepaired (S = 0) + 1 important component (bushing) fully repaired (S = 1)

[0169] R = 3×(1 - 0) + 2×(1 - 1) = 3

[0170] First-level warning.

[0171] Example 1

[0172] The multi-source data integration module collects and integrates the transformer equipment parameters, working parameters, and environmental parameters of the transformers within the power grid jurisdiction to form a comprehensive dataset reflecting the operating state of the transformers;

[0173] Using the comprehensive dataset, a transformer aging analysis model is established, and the transformer comprehensive dataset is fine-tuned and trained to learn the common characteristics of transformer aging data through transfer learning and deep learning models;

[0174] Based on the common characteristics of the transformer aging data output by the transformer aging analysis model, combined with information such as the rated capacity, load rate, operating time of the transformer, and the topological structure of the power grid where it is located, an assessment is carried out. Furthermore, the transformer aging index is calculated through the transformer aging analysis model based on the equipment parameters and working parameters to estimate the aging degree of the transformer.

[0175] Establish a risk assessment model, issue a first-level warning, second-level warning, or third-level warning according to the risk assessment, and send the warning information to the relevant operation and maintenance personnel;

[0176] Supervise the status of the transformer through the monitoring and maintenance module based on the assessment results and risk levels of the risk assessment module;

[0177] For transformers with a low risk level, appropriately extend the monitoring period and conduct a regular inspection and data collection once a week;

[0178] For transformers with a medium risk level, shorten the monitoring period to every 3 - 5 days and increase the detection items for some key parameters;

[0179] For transformers with a high risk level, implement 24-hour real-time monitoring, conduct a detailed inspection and data analysis every day, and arrange a comprehensive maintenance plan in the near future;

[0180] Personnel repair the transformer with a first-level warning. At the same time, through the transformer repair evaluation module, evaluate the actual aging status of the repaired transformer;

[0181] Classify the importance of the transformer components replaced during the repair and the transformer repair status level, and then calculate the transformer aging status (actual aging status).

[0182] The transformer repair evaluation module issues a high-risk warning and a low-risk warning based on the replaced components and repair status of the transformer. If it is determined to be a low-risk warning, correction is required, that is, it is matched with the aging degree of the transformer in the transformer aging analysis model.

[0183] Example 2

[0184] Collect and integrate the transformer equipment parameters, working parameters, and environmental parameters of the transformers in the power grid jurisdiction through the multi-source data integration module to form a comprehensive data set reflecting the operating status of the transformers;

[0185] Use the comprehensive data set to establish a transformer aging analysis model, fine-tune and train the transformer comprehensive data set, and learn the common characteristics of the transformer aging data through transfer learning and deep learning models;

[0186] Based on the common characteristics of the transformer aging data output by the transformer aging analysis model, combined with information such as the rated capacity, load rate, operating time of the transformer, and the topological structure of the power grid where it is located, an assessment is carried out. Furthermore, the transformer aging index is calculated through the transformer aging analysis model based on equipment parameters and working parameters to estimate the aging degree of the transformer.

[0187] Due to different regions, external environmental parameters also need to be considered. According to the regional characteristics of the jurisdiction where the power grid is located, factors related to temperature, humidity, and altitude need to be added, and then the aging degree of the transformer is estimated (estimating the aging degree of the transformer).

[0188] Establish a risk assessment model. According to the first-level warning, second-level warning, or third-level warning evaluated by the risk assessment, the first-level warning is a high-risk warning, the second-level warning is a medium-risk warning, and the third-level warning is a low-risk warning, and send this warning information to relevant operation and maintenance personnel;

[0189] Supervise the status of the transformer through the monitoring and maintenance module based on the evaluation results and risk levels of the risk assessment module;

[0190] For transformers with a first-level warning, that is, a high-risk level, implement 24-hour real-time monitoring, conduct detailed inspections and data analysis every day, and arrange a comprehensive maintenance plan in the near future.

[0191] Personnel repair the transformers with a first-level warning. At the same time, through the transformer maintenance evaluation module, evaluate the actual aging status of the repaired transformers;

[0192] Classify the importance of the transformer components replaced during the repair, as well as the classification of the transformer maintenance status level, and then calculate the transformer aging status (actual aging status).

[0193] The transformer maintenance evaluation module issues high-risk warnings and low-risk warnings based on the replaced components and maintenance status of the transformer. If it is determined as a high-risk warning, it is consistent with the estimated situation of the aging degree of the transformer in the transformer aging analysis model;

[0194] Retrieve the comprehensive data set of the transformers with high-risk warnings, and through the transformer matching module, further match other transformers with common characteristics in the power grid jurisdiction to make risk markings.

[0195] Advance the maintenance plans of other transformers marked with risks.

[0196] The above are only embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structural or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A power grid monitoring and management system, characterized in that, The multi-source data integration module collects and integrates the transformer equipment parameters, operating parameters, and environmental parameters of the transformers within the power grid jurisdiction to form a comprehensive dataset reflecting the operating status of the transformers; The transformer aging analysis model is established using the comprehensive dataset. The transformer comprehensive dataset is fine-tuned and trained, and the common characteristics of the transformer aging data are learned through transfer learning and deep learning models; Based on the common characteristics of the transformer aging data output by the transformer aging analysis model, combined with information such as the rated capacity, load rate, operating time of the transformer, and the topological structure of the power grid where it is located, the transformer aging index is evaluated, and a risk assessment model is established; The risk assessment module issues a first-level warning, a second-level warning, or a third-level warning for the risk level of the transformer aging status; The status of the transformer is supervised based on the evaluation results and risk levels of the risk assessment module; The transformer maintenance evaluation module issues high-risk warnings and low-risk warnings based on the replaced components and maintenance status of the transformer; The comprehensive dataset of the transformer with a high-risk warning is retrieved, and the transformer matching module marks the risks of other transformers with common characteristics within the power grid jurisdiction; 2. The power grid monitoring and management system according to claim 1, wherein, The method for calculating the transformer aging index A based on equipment parameters and operating parameters is as follows: Among them, the transformer operating parameters include operating voltage U, operating current I, power factor PF, and the transformer equipment parameters include rated power S, rated voltage U, transformation ratio T, and efficiency E; is: the square of the load factor; Namely: voltage deviation; Namely: efficiency and power factor attenuation.

3. A power grid monitoring and management system according to claim 2, characterized in that, The influence of environmental parameters on transformer aging: Among them, temperature C, humidity R, altitude H; Temperature acceleration term: exp(λ·ΔC), where ΔC = C - C ref Cref: reference temperature; λ: material-related coefficient; Humidity acceleration term: 1 + α·max(R - R crit , 0) Rcrit: humidity threshold; α: humidity sensitivity coefficient; Altitude correction term: Href: reference altitude; β: altitude coefficient.

4. A power grid monitoring and management system according to claim 3, characterized in that, The method for calculating the transformer aging index A by adding environmental parameters based on equipment parameters and operating parameters is as follows: Among them, temperature C, humidity R, altitude H; exp(λ, ΔC) is: humidity acceleration term; (1 + α·max(R - R crit , 0)) is the humidity acceleration term; is: altitude correction term.

5. A power grid monitoring and management system according to claim 1, characterized in that, Multi-source data integration module: The operating parameters include voltage, current, and power factor; the transformer equipment parameters include rated power, rated voltage, transformation ratio, and efficiency; the environmental data includes temperature, humidity, and altitude, and they are integrated to form a comprehensive dataset reflecting the operating status of the transformer; Transformer aging analysis model: Using a pre-trained deep learning model on the comprehensive dataset of transformers within the power grid jurisdiction as the basic model, and then fine-tuning and training on the transformer comprehensive dataset; Risk assessment model: According to the aging prediction results output by the transformer aging analysis model, combined with the rated capacity, load rate, operating time of the transformer, and the topological structure information of the power grid where it is located, when the risk level exceeds the preset threshold, the system immediately issues three levels of warning signals. The first-level warning is a red alert, indicating high risk, the second-level warning is an orange alert, indicating medium risk, and the third-level warning is a yellow alert, indicating low risk; Monitoring and maintenance module: Based on the risk assessment results and the aging prediction information of the transformer, the system generates a monitoring and maintenance plan; Transformer maintenance evaluation module: Upload the replaced components and maintenance status of the transformer after maintenance to the transformer maintenance evaluation module to evaluate the aging status of the transformer after maintenance. The evaluation is divided into high-risk warning and low-risk warning; Transformer matching module: When a high-risk warning appears in the transformer maintenance evaluation module, search for transformers of the same model in the jurisdiction, and make an analogy by combining the environmental data, working parameters and sensor data of the transformers of the same model, and mark the transformers under the same working conditions.

6. A power grid monitoring and management system according to claim 5, characterized in that, The method for calculating the risk assessment model R based on the transformer aging index A in combination with the rated capacity, load rate, operating time of the transformer and the topological structure information of the power grid where it is located is as follows: Aging index A: Normalized to Amax (assuming the maximum value is 10), that is; Load rate L: The ratio of the actual load to the rated capacity, the reference load rate Lbase = 0.8, and the exponent k = 2 to strengthen the high-load risk; Operating time T: Normalized to the design life Tdesign = 30 years; Topological structure factor C: Reflects the importance of the transformer in the power grid, with values {1, 2, 3} (low, medium, high); First-level warning (high risk): R ≥ 3; Second-level warning (medium risk): 1 ≤ R < 3; Third-level warning (low risk): R < 1.

7. A power grid monitoring and management system according to claim 5, characterized in that: Transformer maintenance evaluation module: For the transformers maintained in the transformer maintenance evaluation module that need to replace components, classify the importance of the replaced components: Key components: Wi = 3; Important components: Wi = 2; General components: Wi = 1; Classify the transformer maintenance status level: Completely repaired: Si = 1.0; Partially repaired: Si = 0.5; Not repaired or major defects remaining: Si = 0; The formula for calculating the aging status of the transformer after maintenance by combining the score of the replaced components and the score of the transformer maintenance status is as follows: High-risk warning: R ≥ 3; Low-risk warning: R < 3.

Images