Transformer risk assessment and emergency equipment scheduling system

Abstract

The invention relates to the technical field of power grid emergency management, and discloses a transformer risk assessment and emergency equipment scheduling system, which comprises a data access module used for accessing original transformer multi-source data from a power grid resource business middle station and a data middle station through a preset data interface, the material management platform accesses the original emergency equipment internet-of-things data; and the data management module is used for receiving the original transformer multi-source data and the original emergency equipment internet-of-things data. A data collection and treatment technology is adopted, standardized treatment is performed based on multi-source heterogeneous data, and the treated data constructs a risk quantitative evaluation model, so that the technical effect of comprehensively and objectively quantitatively analyzing the short-circuit risk of the transformer is achieved. The defect that a final risk assessment result cannot comprehensively and objectively reveal the health condition of the transformer, and the risk early warning accuracy is affected is overcome.

Description

Technical Field

[0001] This invention relates to the field of power grid emergency management technology, specifically a transformer risk assessment and emergency equipment dispatching system. Background Technology

[0002] As a core component of the power system, the stability of transformer operation directly impacts the safety and reliability of the power grid. During grid operation, transformers are subjected to a combination of electrical, thermal, and mechanical stresses over extended periods, particularly the impact of short-circuit currents, which can lead to internal structural damage, decreased insulation performance, and even sudden failures. Therefore, conducting accurate risk assessments of operating transformers and establishing rapid and efficient emergency response and equipment deployment mechanisms are crucial for ensuring the safe operation of the power grid, shortening fault repair time, and minimizing economic losses.

[0003] However, the invention of a transformer risk assessment and emergency equipment dispatch system has the following shortcomings in the existing technology:

[0004] Current technologies struggle to generate consistent quantitative analysis results when assessing transformer short-circuit risks. This problem stems from the fact that assessment models fail to fully integrate heterogeneous data from multiple sources, resulting in risk assessments that cannot comprehensively and objectively reveal the transformer's actual health condition and load-bearing capacity, thus affecting the accuracy of risk warnings.

[0005] In existing technologies, it is difficult to achieve optimal resource allocation and efficient utilization during the deployment of emergency equipment. This problem stems from the lack of real-time information sensing channels for the management of emergency equipment, making it impossible to dynamically obtain the specific location and availability status of the equipment. As a result, decision-makers rely on manual communication and coordination when formulating deployment plans due to information gaps and delays. This leads to slow issuance of deployment orders and insufficient rationality of the plans, ultimately reducing the overall efficiency of emergency repairs.

[0006] To address these issues, this invention proposes a transformer risk assessment and emergency equipment dispatching system. Summary of the Invention

[0007] To address the shortcomings of existing technologies, this invention provides a transformer risk assessment and emergency equipment dispatching system to solve the problems mentioned in the background section.

[0008] To achieve the above objectives, the present invention provides the following technical solution: a transformer risk assessment and emergency equipment dispatching system, wherein the transformer risk assessment and emergency equipment dispatching system comprises:

[0009] The data access module is used to access the original multi-source data of transformers through the power grid resource business platform and the data platform through a preset data interface, and to access the original IoT data of emergency equipment through the property management platform.

[0010] The data governance module is used to receive the original transformer multi-source data and the original emergency equipment IoT data, and to clean, transform and standardize the received data to generate standardized transformer multi-source data and standardized emergency equipment real-time IoT data.

[0011] The risk quantification assessment module is used to receive multi-source data of the standardized transformer, calculate it through the built-in risk coefficient analysis model, and generate a quantitative risk score that can characterize the health level of the transformer.

[0012] The risk intelligent early warning module is used to acquire the quantitative risk score in real time, and automatically generate a high-risk early warning signal when it is determined that the score exceeds a preset safety threshold.

[0013] The emergency optimization and allocation module is used to immediately call up real-time IoT data of standardized emergency equipment after receiving a high-risk warning signal, and generate an optimal allocation plan that includes specific equipment and optimal routes through the built-in optimization algorithm.

[0014] The emergency optimization and allocation module further includes:

[0015] The emergency task requirement analysis unit is used to immediately parse the accident location coordinates and the type and specifications of the required emergency equipment embedded in the signal after receiving the high-risk warning signal, so as to generate structured task requirements.

[0016] The candidate equipment screening unit is used to receive the structured task requirements and the real-time IoT data of the standardized emergency equipment, and to screen all emergency equipment. When the operating status parameters of the emergency equipment are available and its type and specifications match the task requirements, the equipment is included in the candidate equipment set.

[0017] The selection criteria are as follows:

[0018] ,

[0019] in, For emergency equipment The current running status parameters, This is a preset available status indicator. For emergency equipment Types and specifications, The type specification specified in the task requirements;

[0020] The scheduling cost function calculation unit is used to receive the candidate equipment set and calculate the comprehensive scheduling cost for each candidate equipment in the set through a weighted cost function.

[0021] The formula for calculating the weighted cost function is as follows:

[0022] ,

[0023] in, For candidate equipment The overall scheduling cost The preset time cost weighting coefficient, The fixed cost weighting coefficient is preset, and and The sum of ; To calculate the results from candidate equipment by calling geographic information services and taking into account real-time traffic conditions. Current location Drive to the coordinates of the accident location The shortest time required In order to be compatible with candidate equipment The basic deployment cost associated with the type and specification;

[0024] The optimal solution determination and scheme generation unit is used to select the candidate equipment with the lowest comprehensive scheduling cost from the candidate equipment set as the optimal allocation target, integrate the information of the optimal allocation target with the optimal path corresponding to the shortest time, generate the optimal allocation scheme and forward it to the scheduling closed-loop execution module.

[0025] The scheduling closed-loop execution module is used to issue the optimal allocation plan to the target emergency equipment, and during the execution of the allocation task, it tracks the trajectory and task operation status of the target emergency equipment in real time until the task is completed.

[0026] Preferably, the risk intelligent early warning module generates a visualized risk assessment profile while generating a high-risk early warning signal, and highlights the specific location of the corresponding transformer on a geographic information map using a bright color.

[0027] Preferably, the optimization algorithm built into the emergency optimization and allocation module takes the shortest total response time or the lowest comprehensive handling cost as the optimization objective, and performs calculations by comprehensively considering task requirements, equipment availability and real-time traffic information.

[0028] The optimal allocation plan specifically includes the unique identification number of the allocated equipment, the contact information of the person in charge of the target, the planned and generated digital optimal driving route, and the estimated arrival time calculated by the system.

[0029] Preferably, the scheduling closed-loop execution module tracks the task operation status in real time by receiving status feedback signals. The status feedback signals are used to identify progress nodes such as task start, task arrival, task in operation, and task completion.

[0030] Preferably, the transformer risk assessment and emergency equipment dispatch system constructs a layered security protection system covering the network layer, host layer, application layer, and data layer. The security protection system includes the deployment of network firewalls, web application firewalls, intrusion prevention systems, and data transmission encryption technology.

[0031] Preferably, the data access module further includes:

[0032] The transformer data timing acquisition unit has a built-in periodic synchronization timing trigger mechanism. This mechanism determines whether to generate a data acquisition request based on a preset synchronization time interval. The condition for this determination is that the time difference between the current system time and the last successful acquisition time is greater than or equal to the synchronization time interval. When the determination condition is met, the unit actively sends the data acquisition request to the power grid resource business platform and the data platform to receive the original transformer data packet containing the check code.

[0033] The determination condition for the timed triggering mechanism is expressed as follows:

[0034] ≥ ,

[0035] in, The current system time. The timestamp of the last successful data retrieval. This is the preset synchronization time interval;

[0036] The emergency equipment IoT real-time subscription unit subscribes to the original emergency equipment data stream with timestamps pushed by the property management platform in real time by establishing a persistent communication link.

[0037] The data integrity verification unit is used to perform cyclic redundancy verification on the received original transformer data packet and to perform data freshness verification on the original emergency equipment data stream. When both verification and validation pass, verified original transformer multi-source data and verified original emergency equipment IoT data are generated.

[0038] The passing condition for the cyclic redundancy check is as follows:

[0039] ,

[0040] in, The checksum is calculated by the data integrity verification unit using the cyclic redundancy check algorithm on the data payload portion of the original transformer data packet. This is the checksum included in the original transformer data packet;

[0041] The conditions for passing the data freshness verification are as follows:

[0042] ≤ ,

[0043] in, The current system time. The timestamp is embedded within a single data frame in the original emergency equipment data stream. This is the maximum data latency threshold allowed by the system.

[0044] The data routing and forwarding unit is used to forward the verified original transformer multi-source data and the verified original emergency equipment IoT data to the data governance module after receiving them.

[0045] Preferably, the data governance module further includes:

[0046] The raw data parsing and cleaning unit is used to receive raw transformer multi-source data and raw emergency equipment IoT data, and to perform validity verification on the numerical fields in the data. If the field value of the numerical field does not meet the preset validity judgment conditions, the unit calls the preset mean interpolation algorithm to calculate the interpolation value to replace the field value and generate a cleaned dataset.

[0047] The validity determination criteria are as follows: :

[0048] ≥ ≤ ,

[0049] in, This is the current value of the numeric field. It is an empty value. The minimum valid value preset for this field. The maximum valid value preset for this field;

[0050] The calculation formula for the mean interpolation algorithm is as follows:

[0051] ,

[0052] in, The calculated interpolation value, To sum the values ​​of all fields in the dataset that satisfy the validity criteria for this field, This represents the total number of field values ​​in the dataset that satisfy the validity criteria.

[0053] The numerical data normalization unit receives the cleaned dataset and applies a minimum-maximum normalization algorithm to all numerical fields in the dataset to generate a normalized numerical dataset. ;

[0054] The calculation formula for the minimum-maximum normalization algorithm is as follows:

[0055] ,

[0056] in, The result after normalizing the field values. This is the original value of the field. To find the minimum value among all values ​​of this field in the cleaned dataset. This represents the maximum value of this field among all values ​​in the cleaned dataset.

[0057] The standardized data structure generation unit is used to receive the normalized numerical dataset, integrate the dataset with the data of non-numerical fields, and then assemble and generate the standardized transformer multi-source data and the standardized emergency equipment real-time IoT data according to the predefined unified data model, and forward them to the risk quantification assessment module and the emergency optimization and allocation module.

[0058] Preferably, the risk quantification and assessment module further includes:

[0059] The factor weight determination unit is used to construct a multi-level evaluation factor structure based on the analytic hierarchy process (AHP) and to perform a consistency test on the evaluation factor structure to generate a set of effective factor weight coefficients. The condition for passing the consistency test is that the calculated consistency ratio is less than a preset consistency threshold.

[0060] The formula for calculating the consistency ratio is as follows:

[0061] ,

[0062] in, The consistency ratio, The consistency index is determined by looking up a table in advance based on the matrix order. As a general consistency indicator, the calculation formula is:

[0063] ,

[0064] in, To evaluate the largest eigenvalue of the judgment matrix corresponding to the factor structure, Determine the order of a matrix;

[0065] The risk scoring weighting calculation unit is used to receive the effective factor weight coefficients and the standardized transformer multi-source data, and to perform mathematical operations using a weighted summation algorithm to generate the quantified risk score.

[0066] The calculation formula for the weighted summation algorithm is as follows:

[0067] ,

[0068] in, For quantitative risk scoring, For the first The weighting coefficients of the evaluation factors For the first Normalized values ​​of the evaluation factors;

[0069] The evaluation result forwarding unit is used to forward the quantified risk score as the final output of the risk quantification evaluation module to the risk intelligent early warning module for subsequent threshold determination after receiving the quantified risk score.

[0070] Preferably, the risk intelligent early warning module further includes:

[0071] The risk score time series generation unit is used to acquire and store the quantified risk score in real time, and construct a risk score time series containing the current risk score and historical risk scores based on a preset time window length.

[0072] The risk trend quantification analysis unit is used to receive the risk score time series and calculate the risk change rate by performing linear regression analysis on the data points in the series. The risk change rate is used to characterize the trend of risk score changes over time.

[0073] The formula for calculating the rate of change of risk is as follows:

[0074] / ,

[0075] in, For the rate of change of risk, This represents the total number of data points in the risk scoring time series. For the first The time coordinates of the data points For the first The quantitative risk score corresponding to each data point;

[0076] The multi-dimensional early warning level determination unit is used to acquire the quantified risk score and the risk change rate, and determine the specific early warning level according to a set of logical determination rules including preset risk thresholds and risk change rate thresholds.

[0077] An example of the logical determination rule is as follows:

[0078] When the quantified risk score is greater than the first risk threshold, or when the quantified risk score is greater than the second risk threshold and the risk change rate is greater than the first change rate threshold, the warning level is determined to be the highest level.

[0079] The early warning signal encapsulation and forwarding unit is used to encapsulate the quantified risk score, the risk change rate and the early warning level into a structured high-risk early warning signal when the early warning level is not in a normal state, and forward the signal to the emergency optimization and allocation module.

[0080] Preferably, the scheduling closed-loop execution module further includes:

[0081] The dispatch instruction issuance and confirmation unit is used to receive the optimal allocation plan and send the plan to the vehicle terminal of the target emergency equipment through a secure communication protocol. After receiving the unique confirmation acknowledgment signal returned by the vehicle terminal, the unit generates a confirmed dispatch task.

[0082] The path deviation monitoring unit is used to obtain the current position coordinates of the target emergency equipment in real time after the confirmed scheduling task is generated, and calculate the shortest vertical distance between the coordinates and the preset optimal path in the optimal allocation scheme. If the shortest vertical distance exceeds the preset path deviation threshold, a path deviation alarm is generated.

[0083] The criteria for determining path deviation are as follows:

[0084] > ,

[0085] in, The shortest perpendicular distance between the current position coordinates and the optimal path. This is the preset maximum allowed path deviation threshold;

[0086] The task status automatic determination unit is used to continuously acquire the current location coordinates, calculate the geographical distance between the coordinates and the target location in the optimal allocation scheme, and when the geographical distance is less than the preset arrival radius and the continuous stay within the radius exceeds the preset minimum stay time, the unit automatically updates the task status to "arrived".

[0087] The condition for automatically updating the task status to "completed" is as follows:

[0088] ≤ ≥ ,

[0089] in, This is a function used to calculate the geographical distance between points. The coordinates of the current position. For the target location, The preset arrival radius, The time that has been spent within the arrival radius. This is the preset minimum stay duration;

[0090] The task closed-loop termination unit is used to receive a task completion signal reported by the vehicle terminal of the target emergency equipment. After receiving the signal, the unit determines the final task status as closed and generates a task closed-loop instruction for data archiving.

[0091] This invention provides a transformer risk assessment and emergency equipment dispatch system. It has the following beneficial effects:

[0092] 1. This invention employs data collection and governance technology, performs standardized governance based on multi-source heterogeneous data, and constructs a risk quantification assessment model using the governed data. This achieves the technical effect of comprehensively and objectively quantifying and analyzing transformer short-circuit risks. Compared with existing technologies where the assessment model fails to effectively integrate multi-source heterogeneous data, this invention addresses the deficiency that the final risk assessment results cannot comprehensively and objectively reveal the transformer's health status, thus affecting the accuracy of risk warnings.

[0093] 2. This invention employs real-time access to IoT data for emergency equipment and emergency optimization and allocation technology. Upon receiving a high-risk early warning signal, the system automatically acquires the location and availability status of emergency equipment and generates the optimal allocation plan through a built-in optimization algorithm. This achieves the technical effects of dynamically sensing emergency resources, intelligently optimizing scheduling paths, and executing allocation instructions in a closed loop. Compared to existing technologies that rely on manual communication to coordinate emergency equipment, this invention addresses the shortcomings of slow allocation decisions and insufficient plan rationality caused by information gaps and delays, ultimately reducing the overall efficiency of emergency repairs. Attached Figure Description

[0094] Figure 1 This is a system framework diagram of the present invention. Detailed Implementation

[0095] To enable those skilled in the art to understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort should fall within the scope of protection of the present invention.

[0096] The present invention will now be described in detail with reference to the accompanying drawings:

[0097] Example 1:

[0098] Please see the appendix Figure 1 This invention provides a transformer risk assessment and emergency equipment dispatching system, which includes:

[0099] The data access module is used to access the original multi-source data of transformers through the power grid resource business platform and the data platform through a preset data interface, and to access the original IoT data of emergency equipment through the property management platform.

[0100] The data access module further includes:

[0101] The transformer data timed acquisition unit has a built-in periodic synchronization timed triggering mechanism. This mechanism determines whether to generate a data acquisition request based on a preset synchronization time interval. The condition for this determination is that the time difference between the current system time and the last successful acquisition time is greater than or equal to the synchronization time interval. When the determination condition is met, the unit actively sends a data acquisition request to the power grid resource business platform and the data platform to receive the original transformer data packet containing the check code.

[0102] The determination condition for the timed trigger mechanism is expressed as follows:

[0103] ≥ ,

[0104] in, The current system time. The timestamp of the last successful data retrieval. This is the preset synchronization time interval;

[0105] The emergency equipment IoT real-time subscription unit subscribes to the original emergency equipment data stream with timestamps pushed by the property management platform in real time by establishing a persistent communication link.

[0106] The data integrity verification unit is used to perform cyclic redundancy verification on the received original transformer data packets and to perform data freshness verification on the original emergency equipment data stream. When both verification and validation pass, it generates verified original transformer multi-source data and verified original emergency equipment IoT data.

[0107] The passing condition for cyclic redundancy check is:

[0108] ,

[0109] in, The checksum is calculated by the data integrity verification unit using the cyclic redundancy check algorithm on the data payload portion of the original transformer data packet. This is the checksum included in the original transformer data packet;

[0110] The conditions for passing the data freshness verification are:

[0111] ≤ ,

[0112] in, The current system time. The timestamp is embedded within a single data frame in the original emergency equipment data stream. This is the maximum data latency threshold allowed by the system.

[0113] The data routing and forwarding unit is used to forward the verified original transformer multi-source data and the verified original emergency equipment IoT data to the data governance module after receiving them.

[0114] The data governance module is used to receive raw transformer multi-source data and raw emergency equipment IoT data, and to clean, transform and standardize the received data to generate standardized transformer multi-source data and standardized emergency equipment real-time IoT data.

[0115] The data governance module further includes:

[0116] The raw data parsing and cleaning unit is used to receive raw transformer multi-source data and raw emergency equipment IoT data, and to perform validity verification on the numerical fields in the data. If the field value of the numerical field does not meet the preset validity judgment conditions, the unit calls the preset mean interpolation algorithm to calculate the interpolation value to replace the field value and generate a cleaned dataset.

[0117] Among them, the validity determination criteria are: :

[0118] ≥ ≤ ,

[0119] in, This is the current value of the numeric field. It is an empty value. The minimum valid value preset for this field. The maximum valid value preset for this field;

[0120] The formula for the mean interpolation algorithm is:

[0121] ,

[0122] in, The calculated interpolation value, To sum the values ​​of all fields in the dataset that satisfy the validity criteria for this field, This represents the total number of field values ​​in the dataset that satisfy the validity criteria.

[0123] The numerical data normalization unit receives the cleaned dataset and applies a minimum-maximum normalization algorithm to all numerical fields in the dataset to generate a normalized numerical dataset. ;

[0124] The calculation formula for the minimum-maximum normalization algorithm is as follows:

[0125] ,

[0126] in, The result after normalizing the field values. This is the original value of the field. To find the minimum value among all values ​​of this field in the cleaned dataset. This represents the maximum value of this field among all values ​​in the cleaned dataset.

[0127] The standardized data structure generation unit is used to receive the normalized numerical dataset, integrate the dataset with the data of non-numerical fields, and then assemble and generate standardized transformer multi-source data and standardized emergency equipment real-time IoT data according to the predefined unified data model, and forward them to the risk quantification assessment module and the emergency optimization and allocation module.

[0128] The risk quantification assessment module is used to receive standardized multi-source transformer data, calculate it through the built-in risk coefficient analysis model, and generate a quantitative risk score that can characterize the health level of the transformer.

[0129] The risk quantification assessment module further includes:

[0130] The factor weight determination unit is used to construct a multi-level evaluation factor structure based on the analytic hierarchy process and to perform a consistency test on the evaluation factor structure to generate a set of effective factor weight coefficients. The condition for passing the consistency test is that the calculated consistency ratio is less than the preset consistency threshold.

[0131] The formula for calculating the consistency ratio is as follows:

[0132] ,

[0133] in, The consistency ratio, The consistency index is determined by looking up a table in advance based on the matrix order. As a general consistency indicator, the calculation formula is:

[0134] ,

[0135] in, To evaluate the largest eigenvalue of the judgment matrix corresponding to the factor structure, Determine the order of a matrix;

[0136] The risk scoring weighting unit receives valid factor weight coefficients and standardized transformer multi-source data, and performs mathematical operations using a weighted summation algorithm to generate a quantitative risk score.

[0137] The formula for the weighted summation algorithm is as follows:

[0138] ,

[0139] in, For quantitative risk scoring, For the first The weighting coefficients of the evaluation factors For the first Normalized values ​​of the evaluation factors;

[0140] The assessment result forwarding unit is used to forward the quantified risk score as the final output of the risk quantification assessment module to the risk intelligent early warning module for subsequent threshold determination after receiving the quantified risk score.

[0141] The risk intelligent early warning module is used to obtain quantitative risk scores in real time, and automatically generate high-risk warning signals when the score exceeds the preset safety threshold.

[0142] The risk intelligent early warning module further includes:

[0143] The risk score time series generation unit is used to acquire and store quantified risk scores in real time. Based on a preset time window length, it constructs a risk score time series that includes the current risk score and historical risk scores from continuous quantified risk scores.

[0144] The risk trend quantitative analysis unit is used to receive the risk score time series and calculate the risk change rate by performing linear regression analysis on the data points in the series. The risk change rate is used to characterize the trend of risk score changes over time.

[0145] The formula for calculating the rate of change of risk is as follows:

[0146] / ,

[0147] in, For the rate of change of risk, This represents the total number of data points in the risk scoring time series. For the first The time coordinates of the data points For the first The quantitative risk score corresponding to each data point;

[0148] The multi-dimensional early warning level determination unit is used to obtain a quantitative risk score and risk change rate, and determines the specific early warning level based on a set of logical determination rules that include preset risk thresholds and risk change rate thresholds.

[0149] Examples of logical decision rules are as follows:

[0150] When the quantified risk score is greater than the first risk threshold, or when the quantified risk score is greater than the second risk threshold and the risk change rate is greater than the first change rate threshold, the warning level is determined to be the highest level.

[0151] The early warning signal encapsulation and forwarding unit is used to encapsulate the quantified risk score, risk change rate and early warning level into a structured high-risk early warning signal when the early warning level is not in a normal state, and forward the signal to the emergency optimization and allocation module.

[0152] The emergency optimization and allocation module is used to immediately call up real-time IoT data of standardized emergency equipment after receiving a high-risk warning signal, and generate an optimal allocation plan that includes specific equipment and optimal routes through the built-in optimization algorithm.

[0153] The emergency optimization and allocation module further includes:

[0154] The emergency mission requirement analysis unit is used to immediately analyze the accident location coordinates and the type and specifications of the required emergency equipment embedded in the high-risk warning signal after receiving it, so as to generate structured mission requirements.

[0155] The candidate equipment screening unit is used to receive structured task requirements and real-time IoT data of standardized emergency equipment, and to screen all emergency equipment. When the operating status parameters of the emergency equipment are available and its type and specifications match the task requirements, the equipment is included in the candidate equipment set.

[0156] The selection criteria are as follows:

[0157] ,

[0158] in, For emergency equipment The current running status parameters, This is a preset available status indicator. For emergency equipment Types and specifications, The type specification specified in the task requirements;

[0159] The scheduling cost function calculation unit is used to receive the candidate equipment set and calculate the comprehensive scheduling cost for each candidate equipment in the set through a weighted cost function.

[0160] The formula for calculating the weighted cost function is as follows:

[0161] ,

[0162] in, For candidate equipment The overall scheduling cost, The preset time cost weighting coefficient, The fixed cost weighting coefficient is preset, and and The sum of ; To calculate the results from candidate equipment by calling geographic information services and taking into account real-time traffic conditions. Current location Drive to the coordinates of the accident location The shortest time required In order to be compatible with candidate equipment The basic deployment cost associated with the type and specification;

[0163] The optimal solution determination and scheme generation unit is used to select the candidate equipment with the minimum overall scheduling cost from the candidate equipment set as the optimal allocation target, integrate the information of the optimal allocation target with the optimal path corresponding to the shortest time, generate the optimal allocation scheme and forward it to the scheduling closed-loop execution module.

[0164] The scheduling closed-loop execution module is used to issue the optimal allocation plan to the target emergency equipment, and during the allocation task execution, it tracks the movement trajectory and task operation status of the target emergency equipment in real time until the task is completed.

[0165] The scheduling closed-loop execution module further includes:

[0166] The dispatch instruction issuance and confirmation unit is used to receive the optimal allocation plan and send the plan to the vehicle terminal of the target emergency equipment through a secure communication protocol. After receiving the unique confirmation acknowledgment signal returned by the vehicle terminal, the unit generates a confirmed dispatch task.

[0167] The path deviation monitoring unit is used to obtain the current position coordinates of the target emergency equipment in real time after the confirmed dispatch task is generated, and calculate the shortest vertical distance between the coordinates and the preset optimal path in the optimal dispatch plan. If the shortest vertical distance exceeds the preset path deviation threshold, a path deviation alarm is generated.

[0168] The criteria for determining path deviation are as follows:

[0169] > ,

[0170] in, This represents the shortest perpendicular distance between the current location coordinates and the optimal path. This is the preset maximum allowed path deviation threshold;

[0171] The task status automatic determination unit is used to continuously acquire the current location coordinates, calculate the geographical distance between the coordinates and the target location in the optimal allocation plan, and when the geographical distance is less than the preset arrival radius and the continuous stay within the radius exceeds the preset minimum stay time, the unit automatically updates the task status to "arrived".

[0172] The condition for automatically updating the task status to "completed" is as follows:

[0173] ≤ ≥ ,

[0174] in, This is a function used to calculate the geographical distance between points. The coordinates of the current position. For the target location, The preset arrival radius, The time that has been spent within the arrival radius. This is the preset minimum stay duration;

[0175] The task closed-loop termination unit is used to receive a task completion signal reported by the vehicle terminal of the target emergency equipment. After receiving the signal, the unit determines the final task status as closed and generates a task closed-loop instruction for data archiving.

[0176] The advantage of the data access module is that it establishes a stable and reliable multi-source heterogeneous information input channel. By taking into account both timed batch retrieval and real-time subscription push, it ensures that the system can continuously and comprehensively acquire static device information and dynamic IoT information from different business platforms. Through the built-in verification mechanism, it guarantees the integrity and timeliness of the input data from the source, providing a high-quality data foundation for all subsequent analysis and decision-making.

[0177] The advantage of the data governance module is that it acts as a data standardization processing center, which can automatically clean, transform and align raw data from diverse sources and with different formats. By handling missing and outlier values ​​and normalizing values ​​with different physical meanings, it eliminates inconsistencies and incomparability at the data level, and finally outputs a unified, clean, high-quality dataset that can be directly used for model calculations, which significantly improves the accuracy and reliability of subsequent analysis.

[0178] The advantage of the risk quantification assessment module is that it combines complex expert experience with objective data. By constructing a hierarchical analysis structure and using mathematical methods to determine the importance of each risk factor, it transforms the multi-dimensional and ambiguous manual judgment of transformer health status into a precise, objective, and quantifiable single risk score. This enables a unified measurement and intuitive comparison of the risk levels of different transformers, making risk identification scientific and accurate.

[0179] The advantage of the intelligent risk warning module is that it realizes an intelligent upgrade from static threshold alarms to dynamic trend prediction. The system focuses on whether the current risk score exceeds the standard, and by analyzing the trend of risk score changes over time, it can detect potential signs of risk deterioration in advance. Combining the absolute level of risk and the rate of change of risk, it makes a multi-dimensional comprehensive judgment and can issue a forward-looking and differentiated warning signal, thus gaining valuable time for emergency preparation.

[0180] The advantage of the emergency optimization and allocation module is that it transforms the traditional emergency response scheduling and decision-making process, which relies on human experience, into an automated intelligent decision-making process based on real-time data and optimization algorithms. After receiving an early warning signal, the system can instantly match and filter among all available equipment, comprehensively consider various factors, and calculate the optimal allocation plan, which greatly improves the speed of emergency response and the rationality of resource allocation.

[0181] The advantage of the scheduling closed-loop execution module is that it constructs a fully visualized monitoring and management closed loop from the issuance of instructions to the completion of tasks. By tracking the movement trajectory and operation status of the dispatched equipment in real time, it ensures that the optimized dispatch plan can be executed accurately, and can provide immediate alarms for deviations and abnormal states during the execution process. At the same time, it automatically records key task nodes, realizes refined and automated management of the entire life cycle of emergency tasks, and ensures the final implementation of dispatch instructions.

[0182] Example 2:

[0183] This embodiment aims to overcome the problems in existing technologies where transformer risk assessment relies on manual experience and fragmented data for qualitative judgment, and where emergency equipment deployment is inefficient due to poor information flow. Therefore, this embodiment provides a transformer risk assessment and emergency equipment dispatch system.

[0184] This embodiment deploys the system using container services at the infrastructure layer and utilizes file services to store unstructured documents and reports. At the Platform as a Service (PaaS) layer, the system employs Kafka message queues as the core middleware for high-frequency data exchange and asynchronous communication, uses a distributed storage system to manage massive amounts of historical data, and selects a caching database like Redis to store frequently accessed hot data. At the public service layer, a consistency service is deployed to ensure the synchronization of the states of each node in the distributed environment, and a power monitoring center is provided to monitor the operation of the system infrastructure. At the service layer, Nginx is used as the service gateway, and Nacos is used as the configuration center and service registration and discovery center. The front-end interface is built based on Vue, Element-UI, and jQuery technologies to provide users with an interactive interface.

[0185] The core business logic layer of the system includes a business pressure monitoring and assessment center and a large-scale data processing center. These two work together to implement the six functional modules defined in the claims. The specific implementation of this embodiment will be described in detail below, following the data flow:

[0186] First, the data access module starts working. This module, through a collection service deployed in the business logic layer, uses a Kafka message queue producer client to subscribe to and receive raw emergency equipment IoT data streams pushed by the property management platform, containing real-time location and status information of emergency equipment. Simultaneously, this module uses the Nginx service gateway to call the preset data interfaces of the power grid resource business platform and data platform to periodically retrieve raw multi-source transformer data, including static transformer ledgers, historical maintenance records, real-time load current, and winding temperature. All the accessed raw data is uniformly sent to a specific Kafka topic, forming a data source to be processed.

[0187] Next, the data flows into the data governance module, which is primarily handled by the large-scale data processing center. As a Kafka consumer, the large-scale data processing center obtains the raw data from the main data source. First, the data is parsed and cleaned, such as determining the validity range of numeric fields and using algorithms like mean interpolation to fill in missing values. Then, a min-maximum normalization algorithm is used to convert numeric data of different dimensions into standardized values ​​within a unified range. Finally, based on a predefined unified data model, the large-scale data processing center integrates and encapsulates the cleaned and transformed data into structured, standardized transformer multi-source data and standardized emergency equipment real-time IoT data. Both are stored in a Redis cache database for high-speed querying and simultaneously persisted to a distributed storage system.

[0188] The subsequent risk quantification assessment module then begins operation; this function is implemented by the Business Stress Monitoring and Assessment Center. This center periodically reads the latest standardized multi-source transformer data from Redis and invokes a built-in risk coefficient analysis model based on the Analytic Hierarchy Process (AHP). The model performs weighted calculations based on preset factor weight coefficients and the standardized data to calculate a quantitative risk score that characterizes the health level of each transformer.

[0189] Next, the intelligent risk warning module intervenes, a function also executed by the business stress monitoring and assessment center. This center acquires the generated quantitative risk score in real time and combines it with historical scores to form a time series, calculating the risk trend through algorithms such as linear regression analysis. When the absolute value of the risk score or its trend exceeds a preset safety threshold, the module immediately generates a high-risk warning signal containing transformer information, risk score, warning level, and geographical coordinates. This signal is broadcast through a new Kafka topic, and simultaneously, the front-end interface is invoked to highlight the high-risk transformer on a visual geographic information map built with Vue.

[0190] Upon receiving a high-risk warning signal, the emergency optimization and deployment module is triggered. A dedicated scheduling service, acting as a Kafka consumer, starts immediately after detecting the warning signal. First, it parses the accident location and task requirements from the warning signal. Then, it quickly retrieves standardized real-time IoT data for all emergency equipment from the Redis cache, filtering out candidate equipment that is available and matches the equipment type. Next, the module invokes a built-in optimization algorithm. This algorithm aims to minimize the total response time or overall cost, comprehensively considering the current location of each candidate piece of equipment, real-time traffic conditions, and basic deployment costs to calculate the optimal deployment plan. This plan specifies the unique identification number of the deployed equipment, the optimal travel route, and the estimated arrival time.

[0191] Finally, the scheduling closed-loop execution module is responsible for implementing the plan. The scheduling service sends the generated optimal allocation plan to the vehicle-mounted terminal of the target emergency equipment via a secure API interface or a specific Kafka command topic. During mission execution, this module continuously receives and processes real-time location and mission status signals reported by the vehicle-mounted terminal via Kafka. The scheduling service updates the status to the system in real time, allowing for full-process visual tracking through the front-end interface. If the monitored trajectory deviates significantly from the preset path, the system automatically generates a deviation alarm until a mission completion signal is received. This completes the closed-loop management of the scheduling process, and the process data is archived.

[0192] Compared with the prior art, this embodiment produces significant beneficial effects:

[0193] First, this invention enables precise quantitative assessment of transformer short-circuit risks, improving the targeting and effectiveness of equipment operation and maintenance. This beneficial effect stems from the fact that this invention no longer relies on scattered data and subjective experience for vague qualitative judgments. Instead, it constructs a large-scale data processing center to systematically collect and standardize multi-source heterogeneous data. Utilizing a quantitative assessment model embedded in the business pressure monitoring and assessment center, it performs scientific calculations, comprehensively and objectively revealing the true health status of the transformer, thus ensuring accurate and reliable risk identification results.

[0194] Next, the invention addresses the information silo problem in the emergency equipment deployment process, significantly improving emergency response speed and equipment utilization efficiency. This beneficial effect stems from the fact that the invention, through real-time access to IoT data from emergency equipment and combined with an intelligent emergency optimization and deployment module, changes the inefficient model that previously relied on manual communication and coordination. When a risk occurs, the system can automatically generate and issue optimal dispatch instructions within seconds based on a global, real-time resource view, realizing a shift from passive response to proactive early warning, and from manual decision-making to intelligent optimization. This ensures that emergency resources are deployed to the most needed locations at the most needed time, greatly shortening repair response time.

[0195] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A transformer risk assessment and emergency equipment dispatching system, characterized in that, The transformer risk assessment and emergency equipment dispatch system includes: The data access module is used to access the original multi-source data of transformers through the power grid resource business platform and the data platform through a preset data interface, and to access the original IoT data of emergency equipment through the property management platform. The data governance module is used to receive the original transformer multi-source data and the original emergency equipment IoT data, and to clean, transform and standardize the received data to generate standardized transformer multi-source data and standardized emergency equipment real-time IoT data. The risk quantification assessment module is used to receive multi-source data of the standardized transformer, calculate it through the built-in risk coefficient analysis model, and generate a quantitative risk score that can characterize the health level of the transformer. The risk intelligent early warning module is used to acquire the quantitative risk score in real time, and automatically generate a high-risk early warning signal when the score exceeds a preset safety threshold. The emergency optimization and allocation module is used to immediately call up real-time IoT data of standardized emergency equipment after receiving a high-risk warning signal, and generate an optimal allocation plan that includes specific equipment and optimal routes through the built-in optimization algorithm. The emergency optimization and allocation module further includes: The emergency task requirement analysis unit is used to immediately parse the accident location coordinates and the type and specifications of the required emergency equipment embedded in the signal after receiving the high-risk warning signal, so as to generate structured task requirements. The candidate equipment screening unit is used to receive the structured task requirements and the real-time IoT data of the standardized emergency equipment, and to screen all emergency equipment. When the operating status parameters of the emergency equipment are available and its type and specifications match the task requirements, the equipment is included in the candidate equipment set. The selection criteria are as follows: ， in, For emergency equipment The current running status parameters, This is a preset available status indicator. For emergency equipment Types and specifications, The type specification specified in the task requirements; The scheduling cost function calculation unit is used to receive the candidate equipment set and calculate the comprehensive scheduling cost for each candidate equipment in the set through a weighted cost function. The formula for calculating the weighted cost function is as follows: ， in, For candidate equipment The overall scheduling cost, The preset time cost weighting coefficient, The fixed cost weighting coefficient is preset, and and The sum of ; To calculate the results from candidate equipment by calling geographic information services and taking into account real-time traffic conditions. Current location Drive to the coordinates of the accident location The shortest time required In order to be compatible with candidate equipment The basic deployment cost associated with the type and specification; The optimal solution determination and scheme generation unit is used to select the candidate equipment with the lowest comprehensive scheduling cost from the candidate equipment set as the optimal allocation target, integrate the information of the optimal allocation target with the optimal path corresponding to the shortest time, generate the optimal allocation scheme and forward it to the scheduling closed-loop execution module. The scheduling closed-loop execution module is used to issue the optimal allocation plan to the target emergency equipment, and during the execution of the allocation task, it tracks the trajectory and task operation status of the target emergency equipment in real time until the task is completed.

2. The transformer risk assessment and emergency equipment dispatching system according to claim 1, characterized in that, The intelligent risk warning module generates a visual risk assessment profile while generating a high-risk warning signal, and highlights the specific location of the corresponding transformer on a geographic information map.

3. The transformer risk assessment and emergency equipment dispatching system according to claim 1, characterized in that, The optimization algorithm built into the emergency optimization and allocation module takes the shortest total response time or the lowest comprehensive handling cost as the optimization objective, and performs calculations by comprehensively considering task requirements, equipment availability and real-time traffic information. The optimal allocation plan specifically includes the unique identification number of the allocated equipment, the contact information of the person in charge of the target, the planned and generated digital optimal driving route, and the estimated arrival time calculated by the system.

4. The transformer risk assessment and emergency equipment dispatching system according to claim 1, characterized in that, The scheduling closed-loop execution module tracks the task status in real time by receiving status feedback signals. The status feedback signals are used to identify progress nodes such as task start, task arrival, task in progress, and task completion.

5. The transformer risk assessment and emergency equipment dispatching system according to claim 1, characterized in that, The transformer risk assessment and emergency equipment dispatch system constructs a layered security protection system covering the network layer, host layer, application layer, and data layer. The security protection system includes the deployment of network firewalls, web application firewalls, intrusion prevention systems, and data transmission encryption technology.

6. The transformer risk assessment and emergency equipment dispatching system according to claim 1, characterized in that, The data access module further includes: The transformer data timing acquisition unit has a built-in periodic synchronization timing trigger mechanism. This mechanism determines whether to generate a data acquisition request based on a preset synchronization time interval. The condition for this determination is that the time difference between the current system time and the last successful acquisition time is greater than or equal to the synchronization time interval. When the determination condition is met, the unit actively sends the data acquisition request to the power grid resource business platform and the data platform to receive the original transformer data packet containing the check code. The determination condition for the timed triggering mechanism is expressed as follows: ≥ ， in, The current system time. The timestamp of the last successful data retrieval. This is the preset synchronization time interval; The emergency equipment IoT real-time subscription unit subscribes to the original emergency equipment data stream with timestamps pushed by the property management platform in real time by establishing a persistent communication link. The data integrity verification unit is used to perform cyclic redundancy verification on the received original transformer data packet and to perform data freshness verification on the original emergency equipment data stream. When both verification and validation pass, verified original transformer multi-source data and verified original emergency equipment IoT data are generated. The passing condition for the cyclic redundancy check is as follows: ， in, The checksum is calculated by the data integrity verification unit using the cyclic redundancy check algorithm on the data payload portion of the original transformer data packet. This is the checksum included in the original transformer data packet; The conditions for passing the data freshness verification are as follows: ≤ ， in, The current system time. The timestamp is embedded within a single data frame in the original emergency equipment data stream. This is the maximum data latency threshold allowed by the system. The data routing and forwarding unit is used to forward the verified original transformer multi-source data and the verified original emergency equipment IoT data to the data governance module after receiving them.

7. The transformer risk assessment and emergency equipment dispatching system according to claim 1, characterized in that, The data governance module further includes: The raw data parsing and cleaning unit is used to receive raw transformer multi-source data and raw emergency equipment IoT data, and to perform validity verification on the numerical fields in the data. If the field value of the numerical field does not meet the preset validity judgment conditions, the unit calls the preset mean interpolation algorithm to calculate the interpolation value to replace the field value and generate a cleaned dataset. The validity determination criteria are as follows: : ≥ ≤ ， in, This is the current value of the numeric field. It is an empty value. The minimum valid value preset for this field. The maximum valid value preset for this field; The calculation formula for the mean interpolation algorithm is as follows: ， in, The calculated interpolation value, To sum the values ​​of all fields in the dataset that satisfy the validity criteria for this field, This represents the total number of field values ​​in the dataset that satisfy the validity criteria. The numerical data normalization unit receives the cleaned dataset and applies a minimum-maximum normalization algorithm to all numerical fields in the dataset to generate a normalized numerical dataset. ; The calculation formula for the minimum-maximum normalization algorithm is as follows: ， in, The result after normalizing the field values. This is the original value of the field. To find the minimum value among all values ​​of this field in the cleaned dataset. This represents the maximum value of this field among all values ​​in the cleaned dataset. The standardized data structure generation unit is used to receive the normalized numerical dataset, integrate the dataset with the data of non-numerical fields, and then assemble and generate the standardized transformer multi-source data and the standardized emergency equipment real-time IoT data according to the predefined unified data model, and forward them to the risk quantification assessment module and the emergency optimization and allocation module.

8. The transformer risk assessment and emergency equipment dispatching system according to claim 1, characterized in that, The risk quantification assessment module further includes: The factor weight determination unit is used to construct a multi-level evaluation factor structure based on the analytic hierarchy process (AHP) and to perform a consistency test on the evaluation factor structure to generate a set of effective factor weight coefficients. The condition for passing the consistency test is that the calculated consistency ratio is less than a preset consistency threshold. The formula for calculating the consistency ratio is as follows: ， in, The consistency ratio, The consistency index is determined by looking up a table in advance based on the matrix order. As a general consistency indicator, the calculation formula is: ， in, To evaluate the largest eigenvalue of the judgment matrix corresponding to the factor structure, Determine the order of a matrix; The risk scoring weighting calculation unit is used to receive the effective factor weight coefficients and the standardized transformer multi-source data, and to perform mathematical operations using a weighted summation algorithm to generate the quantified risk score. The calculation formula for the weighted summation algorithm is as follows: ， in, For quantitative risk scoring, For the first The weighting coefficients of the evaluation factors For the first Normalized values ​​of the evaluation factors; The evaluation result forwarding unit is used to forward the quantified risk score as the final output of the risk quantification evaluation module to the risk intelligent early warning module for subsequent threshold determination after receiving the quantified risk score.

9. The transformer risk assessment and emergency equipment dispatching system according to claim 1, characterized in that, The aforementioned intelligent risk warning module further includes: The risk score time series generation unit is used to acquire and store the quantified risk score in real time, and construct a risk score time series containing the current risk score and historical risk scores based on a preset time window length. The risk trend quantification analysis unit is used to receive the risk score time series and calculate the risk change rate by performing linear regression analysis on the data points in the series. The risk change rate is used to characterize the trend of risk score changes over time. The formula for calculating the rate of change of risk is as follows: / ， in, For the rate of change of risk, This represents the total number of data points in the risk scoring time series. For the first The time coordinates of the data points For the first The quantitative risk score corresponding to each data point; The multi-dimensional early warning level determination unit is used to acquire the quantified risk score and the risk change rate, and determine the specific early warning level according to a set of logical determination rules including preset risk thresholds and risk change rate thresholds. An example of the logical determination rule is as follows: When the quantified risk score is greater than the first risk threshold, or when the quantified risk score is greater than the second risk threshold and the risk change rate is greater than the first change rate threshold, the warning level is determined to be the highest level. The early warning signal encapsulation and forwarding unit is used to encapsulate the quantified risk score, the risk change rate and the early warning level into a structured high-risk early warning signal when the early warning level is not in a normal state, and forward the signal to the emergency optimization and allocation module.

10. A transformer risk assessment and emergency equipment dispatching system according to claim 1, characterized in that, The scheduling closed-loop execution module further includes: The dispatch instruction issuance and confirmation unit is used to receive the optimal allocation plan and send the plan to the vehicle terminal of the target emergency equipment through a secure communication protocol. After receiving the unique confirmation acknowledgment signal returned by the vehicle terminal, the unit generates a confirmed dispatch task. The path deviation monitoring unit is used to obtain the current position coordinates of the target emergency equipment in real time after the confirmed scheduling task is generated, and calculate the shortest vertical distance between the coordinates and the preset optimal path in the optimal allocation scheme. If the shortest vertical distance exceeds the preset path deviation threshold, a path deviation alarm is generated. The criteria for determining path deviation are as follows: ＞ ， in, The shortest perpendicular distance between the current position coordinates and the optimal path. This is the preset maximum allowed path deviation threshold; The task status automatic determination unit is used to continuously acquire the current location coordinates, calculate the geographical distance between the coordinates and the target location in the optimal allocation scheme, and when the geographical distance is less than the preset arrival radius and the continuous stay within the radius exceeds the preset minimum stay time, the unit automatically updates the task status to "arrived". The condition for automatically updating the task status to "completed" is as follows: ≤ ≥ ， in, This is a function used to calculate the geographical distance between points. The coordinates of the current position. For the target location, The preset arrival radius, The time that has been spent within the arrival radius. This is the preset minimum stay duration; The task closed-loop termination unit is used to receive a task completion signal reported by the vehicle terminal of the target emergency equipment. After receiving the signal, the unit determines the final task status as closed and generates a task closed-loop instruction for data archiving.

Images