Power distribution automation terminal operation and maintenance method based on 104 protocol

Abstract

The invention discloses a power distribution automation terminal operation and maintenance method based on a 104 protocol, and belongs to the field of electric power automation, and the method specifically comprises the steps: employing the IEC 104 protocol to collect the state data of power grid equipment through a power distribution automation terminal, and transmitting the state data to a main station system in real time; the master station system processes the received data by using an intelligent fault diagnosis model to realize accurate classification and grading of faults; once a fault or abnormity is detected, an early warning mechanism is triggered immediately, and a customized fault notification is generated and sent to operation and maintenance personnel; and operation and maintenance personnel perform remote operation by using the intelligent operation and maintenance APP, quickly respond and process faults, and then feed back a processing result to the master station system, so that instant updating and closed-loop management of the state of the power grid equipment are realized, and the operation and maintenance efficiency and safety of the power grid are improved.

Description

Technical Field

[0001] The present invention belongs to the field of electric power automation, and more specifically relates to a distribution automation terminal operation and maintenance method based on 104 protocol. Background Art

[0002] The IEC 104 protocol, which is a communication protocol for power automation developed by the International Electrotechnical Commission (IEC), is an important basis for realizing real-time monitoring, data collection, equipment control and protection of power systems. This protocol is widely used in the power industry, especially in power scenarios such as substations and power plants, providing important support for the safe and stable operation of power systems.

[0003] With the development of smart grid, distribution automation terminals, as an important part of smart grid, gradually occupy an important position in distribution network. These terminals integrate multiple functions, including data collection, status monitoring, fault alarm, etc., providing strong support for the operation and maintenance management of distribution network. However, with the continuous expansion of distribution network scale and the continuous increase of equipment, traditional operation and maintenance methods can no longer meet current needs.

[0004] At present, the existing distribution automation terminal operation and maintenance methods based on the 104 protocol have the following main limitations: traditional operation and maintenance methods mostly rely on manual inspections and on-site operations, which are time-consuming, labor-intensive and inefficient; when equipment fails, it often takes a long time to discover and handle it, affecting the safe and stable operation of the power grid; during the data transmission process, if effective security measures are not taken, it is vulnerable to network attacks and data leakage risks; distribution automation terminals from different manufacturers may have inconsistent communication protocols, which increases the difficulty of operation and maintenance.

[0005] For example, the patent with publication number CN105656729A discloses a method for detecting errors in the underlying message of the IEC104 protocol, including: based on the TCP and IP protocols, by setting a network mirror port on the front switch to realize the copy monitoring of the interactive message between the dispatching automation master station system and the substation system, and calculate the parameter variables of the protocol, complete the analysis of the original communication message, compare the calculated parameter variables with the master station system parameter variables, and send relevant alarm information according to the comparison result. The present invention performs protocol detection on the underlying message of the IEC60870-5-104 protocol, reports message errors, and provides timely detection basis for the daily operation and maintenance of the dispatching master station system, ensuring the stability and correctness of the operation of the dispatching automation system.

[0006] The above existing technologies all have the following problems: they focus on error detection of the underlying messages of the IEC104 protocol, but do not involve further processing and analysis of the data, such as fault diagnosis or equipment status evaluation, and are relatively simple in function; the application scenarios are limited; it is necessary to set a network mirror port on the front-end switch, which requires the system to have corresponding hardware support. If the hardware conditions are not met or the upgrade is difficult, the implementation of this method will be limited; it is not directly related to the rapid processing of faults and lacks real-time performance; it lacks intelligence in error handling. Summary of the invention

[0007] In view of the shortcomings of the prior art, the present invention proposes a distribution automation terminal operation and maintenance method based on the 104 protocol. The distribution automation terminal regularly uses the IEC 104 protocol to collect power grid equipment status data and transmits it to the master station system in real time; the master station system uses an intelligent fault diagnosis model to process the received data to achieve accurate classification and grading of faults; once a fault or abnormality is detected, an early warning mechanism is immediately triggered, and a customized fault notification is generated and sent to the operation and maintenance personnel; the operation and maintenance personnel use the intelligent operation and maintenance APP to perform remote operations, quickly respond to and handle faults, and then feed back the processing results to the master station system, thereby achieving real-time update and closed-loop management of the power grid equipment status, and improving the efficiency and safety of power grid operation and maintenance.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] The distribution automation terminal operation and maintenance method based on 104 protocol includes:

[0010] Step S1: The distribution automation terminal collects the power grid equipment status data in real time through the IEC 104 protocol at a predetermined time interval, and encapsulates and transmits it to the master station system;

[0011] Step S2: After receiving the power grid equipment status data packet, the master station system performs verification and decoding, and uses the intelligent fault diagnosis model to process and analyze the decoded power grid equipment status data. At the same time, according to the output results of the intelligent fault diagnosis model, the identified faults are classified and graded;

[0012] Step S3: If a fault or abnormality is identified, the master station system immediately triggers the fault warning mechanism. At the same time, according to the classification and classification of the fault, a corresponding fault notification is generated and sent to the operation and maintenance personnel;

[0013] Step S4: After receiving the fault notification, the operation and maintenance personnel remotely operate the faulty equipment through the intelligent operation and maintenance APP. At the same time, after completing the fault processing, the operation and maintenance personnel will feedback the processing results to the main station system and update the operating status information of the power grid equipment.

[0014] Specifically, the specific steps of step S2 include:

[0015] S2.1: The master station system receives the power grid equipment status data packet X={x1,…,x n}, and perform data freshness verification on the received power grid equipment status data packet, where x n represents the nth power grid device status data, where n represents the number of power grid device status data;

[0016] If the data packet verification fails, the error information is recorded and a notification is sent to the operation and maintenance personnel. At the same time, the fault warning mechanism is triggered;

[0017] If the verification is passed, the verified power grid equipment status data packet is decoded according to the IEC 104 protocol to restore the original power grid equipment status data, and the decoded power grid equipment status data is preprocessed;

[0018] S2.2: Load the pre-trained intelligent fault diagnosis model, and use the intelligent fault diagnosis model to process and analyze the pre-processed power grid equipment status data, calculate and output the fault diagnosis results;

[0019] S2.3: Based on the output results of the intelligent fault diagnosis model, an improved adaptive clustering algorithm is introduced to classify faults. At the same time, a multi-factor evaluation model is used to intelligently classify and prioritize the classified faults, combining fault history data, equipment importance, and current grid equipment operating status;

[0020] S2.4: Based on the fault classification and priority sorting results, the master station system automatically triggers the corresponding emergency response plan and establishes a cross-departmental collaborative workflow platform.

[0021] Specifically, the specific steps of performing data freshness verification in S2.1 include:

[0022] S2.11: The master station system monitors the power grid equipment status data packet sent by the distribution automation terminal through the TCP / IP protocol network interface. When the data packet arrives, the master station system receives it completely and temporarily stores it in the memory or disk;

[0023] S2.12: Extract timestamp information from received power grid device status data packets t , and compare the timestamp in the power grid equipment status data packet with the current system time t, and calculate the time error e = a t -t;

[0024] S2.13: Set the time threshold h1=5;

[0025] If e≤h1, it means the data packet is fresh;

[0026] If e>h1, it means that the data packet is outdated and a notification is sent to the operation and maintenance personnel.

[0027] Specifically, the specific steps of S2.2 include:

[0028] S2.21: Obtain pre-processed power grid equipment status data And load the pre-trained intelligent fault diagnosis model, where: represents the mth preprocessed power grid device status data, and m represents the number of preprocessed power grid device status data;

[0029] S2.22: Input into the intelligent fault diagnosis model, at the same time, The forward propagation process is carried out through the convolutional layer and the fully connected layer of the intelligent fault diagnosis model until the output layer of the model is reached, and the preliminary fault diagnosis result is calculated based on the result of the forward propagation. The formula is:

[0030]

[0031] Among them, Y represents the output of the preliminary fault diagnosis result, σ(·) represents the activation function, β i represents the attention weight of the i-th preprocessed power grid equipment state data, W i Represents the transformation function for each feature The corresponding weight matrix is, represents the characteristic transformation function of the i-th preprocessed power grid equipment state data, represents the residual term, and b represents the bias term.

[0032] Specifically, the specific steps of S2.2 also include:

[0033] S2.23: Introduce a multi-source verification mechanism and collect multi-source verification data. At the same time, use the cosine similarity algorithm to compare and verify the preliminary fault diagnosis results with the multi-source verification data;

[0034] S2.24: According to the result of the multi-source verification, the preliminary fault diagnosis result is corrected, and the corrected fault diagnosis result is converted into a visual report, and at the same time, the parsed fault diagnosis result is output to a designated location;

[0035] S2.25: Establish a continuous learning mechanism to feed back each fault diagnosis result and actual situation to the intelligent fault diagnosis model to optimize and update the intelligent fault diagnosis model.

[0036] Specifically, the specific steps of S2.3 include:

[0037] S2.31: Obtain preliminary fault diagnosis results Y = {y1, ..., y N}, and preprocess the preliminary fault diagnosis results, where y N represents the Nth preliminary fault data, where N represents the number of preliminary fault data;

[0038] S2.32: Use the improved adaptive clustering algorithm to cluster Y = {y1, ..., y N} Perform cluster analysis and calculate y N The silhouette coefficient is obtained by N At the same time, the clustering effect is evaluated according to the value of the average silhouette coefficient. The formula is:

[0039]

[0040] Among them, Sim jk represents Y={y1,...,y N}, f(·) represents the hierarchical clustering function, w d represents the weight after adaptive adjustment, w or,jk represents the original weight between data point j and data point k, fact ad (·) represents the adaptive function, CM lu Represents the silhouette coefficient index, feat j Represents the eigenvalue of data point j, feat k represents the eigenvalue of data point k, Iter represents the number of iterations of the current clustering process, CS j Indicates the number of data points contained in the cluster where data point j is located, CS k It represents the number of data points contained in the cluster where the data point k is located, and λ represents the adjustment parameter.

[0041] Specifically, the specific steps of S2.3 also include:

[0042] S2.33: Collect fault history data, equipment importance and current grid equipment operating status information, and integrate them to form multi-factor information Z = {z1,...,z M}, and at the same time, the multi-factor information is transformed into quantifiable evaluation indicators to form an evaluation indicator system, where z M represents the Mth multi-factor information, and M represents the number of multi-factor information;

[0043] S2.34: Use a comprehensive evaluation method to determine the weights of the evaluation indicators, and construct a multi-factor evaluation model based on the evaluation index system and the weights of the evaluation indicators. The formula of the multi-factor evaluation model is:

[0044]

[0045] Among them, Q represents the comprehensive evaluation value, L liang,r Represents the quantitative value of the r-th multi-factor information, w′ r represents the weight of the r-th multi-factor information, δ r represents the adjustment factor of the r-th multi-factor information, η r represents the time decay factor of the r-th multi-factor information, I r represents the environmental factor of the rth multi-factor information, and c represents the constant term.

[0046] S2.35: Use a multi-factor evaluation model to intelligently classify the clustered fault data, and prioritize the faults based on the fault classification results and the actual operation of the power grid.

[0047] Specifically, the power grid equipment status data in step S1 includes operation status data and fault information.

[0048] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of a distribution automation terminal operation and maintenance method based on the 104 protocol when executing the computer program.

[0049] A computer-readable storage medium stores computer instructions, which, when executed, execute the steps of a distribution automation terminal operation and maintenance method based on the 104 protocol.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] 1. The present invention proposes a distribution automation terminal operation and maintenance method based on the 104 protocol. The distribution automation terminal regularly collects and transmits the power grid equipment status data to the master station system in real time. Combined with the intelligent fault diagnosis model, the data is accurately processed and analyzed, thereby realizing comprehensive monitoring of the power grid equipment status and rapid fault identification, improving the intelligence level of power grid operation and maintenance, and ensuring the stability and safety of power grid operation.

[0052] 2. The present invention proposes a distribution automation terminal operation and maintenance method based on the 104 protocol. When a fault or abnormal situation is identified, the master station system can immediately trigger the early warning mechanism and generate a detailed fault notification, so that the operation and maintenance personnel can respond quickly. The operation and maintenance personnel perform remote operations through the intelligent operation and maintenance APP, which not only improves the efficiency of fault handling, but also reduces the risk of on-site operations. At the same time, the timely feedback of fault handling results and the update of power grid equipment status information form a closed-loop management. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1It is a schematic diagram of the distribution automation terminal operation and maintenance method based on 104 protocol of the present invention;

[0054] Figure 2 This is a principle flow chart of the distribution automation terminal operation and maintenance method based on the 104 protocol of the present invention;

[0055] Figure 3 This is a flow chart of power grid equipment status data packet verification in the power distribution automation terminal operation and maintenance method based on the 104 protocol of the present invention;

[0056] Figure 4 The present invention is a flow chart for obtaining fault diagnosis results of the distribution automation terminal operation and maintenance method based on the 104 protocol. DETAILED DESCRIPTION

[0057] Example 1

[0058] See also Figure 1-Figure 2 , an embodiment provided by the present invention: a distribution automation terminal operation and maintenance method based on 104 protocol, comprising the following steps:

[0059] Step S1: The distribution automation terminal collects the power grid equipment status data in real time through the IEC 104 protocol at a predetermined time interval, and encapsulates and transmits it to the master station system;

[0060] Furthermore, the specific steps of step S1 include:

[0061] S1.1: Configure the parameters of the IEC 104 protocol on the distribution automation terminal, including the communication port, communication rate, data bit, and check bit, to ensure communication compatibility with the master station system. At the same time, set a predetermined time interval as the cycle of data collection. In the present invention, data collection is performed every 5 minutes;

[0062] S1.2: The distribution automation terminal obtains the status data of the power grid equipment in real time through sensors at predetermined time intervals, including operating status data and fault information. The operating status includes voltage, current, and power data, and the fault information includes equipment abnormality alarm and protection action information.

[0063] S1.3: Encapsulate the collected data according to the specifications of the IEC 104 protocol to obtain the power grid equipment status data packet. The IEC 104 protocol is based on TCP / IP, so the data encapsulation usually includes TCP / IP header information and application layer data specific to the IEC 104 protocol. At the same time, during the encapsulation process, it is necessary to ensure the integrity, correctness and security of the data, including adding checksum and timestamp information;

[0064] S1.4: The distribution automation terminal transmits the encapsulated power grid equipment status data packet to the master station system through the established TCP / IP connection. During the transmission process, a retransmission and verification mechanism is required according to the network status to ensure reliable data transmission.

[0065] Step S2: After receiving the power grid equipment status data packet, the master station system performs verification and decoding, and uses the intelligent fault diagnosis model to process and analyze the decoded power grid equipment status data. At the same time, according to the output results of the intelligent fault diagnosis model, the identified faults are classified and graded;

[0066] Step S3: If a fault or abnormality is identified, the master station system immediately triggers the fault warning mechanism. At the same time, according to the classification and classification of the fault, a corresponding fault notification is generated and sent to the operation and maintenance personnel;

[0067] It should be noted that once a fault or abnormal situation is identified, the master station system immediately triggers the built-in fault warning mechanism. The warning mechanism includes multiple means such as setting thresholds, pattern recognition, and trend analysis to ensure the accuracy and timeliness of the warning.

[0068] At the same time, according to the preset classification standards and grading rules, when the identified faults or anomalies are classified and graded, the classification method is based on the fault type, location of occurrence or impact range factors. Among them, the fault types include hardware faults, software faults, and network faults, and the locations of occurrence include system level, equipment level, and component level.

[0069] Moreover, the fault notification should contain specific information about the fault, such as fault type, occurrence time, location, impact scope, possible causes, and recommended countermeasures.

[0070] Step S4: After receiving the fault notification, the operation and maintenance personnel remotely operate the faulty equipment through the intelligent operation and maintenance APP;

[0071] The operations include restarting the device and adjusting parameters.

[0072] Step S5: After the operation and maintenance personnel complete the fault processing, they will feed back the processing results to the master station system and update the operating status information of the power grid equipment.

[0073] Among them, the processing results include the processing process, measures taken, and processing effects.

[0074] Example 2

[0075] See also Figure 3 and Figure 4 In this embodiment, the specific steps of step S2 include:

[0076] S2.1: The master station system receives the power grid equipment status data packet from the distribution automation terminal through the network interface, and performs data freshness verification on the received power grid equipment status data packet;

[0077] If the data packet verification fails, the error information is recorded and a notification is sent to the operation and maintenance personnel. At the same time, the fault warning mechanism is triggered. The sending methods include SMS, email, and APP push;

[0078] If the verification is passed, the verified power grid equipment status data packet is decoded according to the IEC 104 protocol to restore the original power grid equipment status data, and the decoded power grid equipment status data is preprocessed;

[0079] S2.2: Load the pre-trained intelligent fault diagnosis model, and use the intelligent fault diagnosis model to process and analyze the pre-processed power grid equipment status data, calculate and output the fault diagnosis results;

[0080] The output fault diagnosis results include fault type and fault location.

[0081] S2.3: Based on the output results of the intelligent fault diagnosis model, an improved adaptive clustering algorithm is introduced to classify faults. At the same time, a multi-factor evaluation model is used to intelligently classify and prioritize the classified faults, combining fault history data, equipment importance, and current grid equipment operating status;

[0082] S2.4: Based on the fault classification and priority sorting results, the master station system automatically triggers the corresponding emergency response plan and establishes a cross-departmental collaborative workflow platform.

[0083] Among them, the emergency response plan includes generating maintenance work orders, dispatching emergency repair resources, and updating the power grid operation diagram.

[0084] The specific steps for data freshness verification in S2.1 include:

[0085] S2.11: The master station system monitors the data packets of the power grid equipment status sent by the distribution automation terminal through the TCP / IP protocol network interface. When the data packet is detected to arrive, the master station system receives it completely and temporarily stores it in the memory or disk;

[0086] The timestamp usually indicates the time when the data packet is generated or sent. It is important to ensure that the timestamp is valid and conforms to the expected format, such as the ISO 8601 standard.

[0087] S2.12: Extract timestamp information from received power grid device status data packets t, and compare the timestamp in the power grid equipment status data packet with the current system time t, and calculate the time error e = a t -t;

[0088] S2.13: Set the time threshold h1=5;

[0089] If e≤h1, it means the data packet is fresh;

[0090] If e>h1, it means that the data packet is outdated and a notification is sent to the operation and maintenance personnel.

[0091] The specific steps of S2.2 include:

[0092] S2.21: Obtain pre-processed power grid equipment status data And load the pre-trained intelligent fault diagnosis model, where: represents the mth preprocessed power grid device status data, and m represents the number of preprocessed power grid device status data;

[0093] S2.22: Input into the intelligent fault diagnosis model, at the same time, The forward propagation process is carried out through the convolutional layer and the fully connected layer of the intelligent fault diagnosis model until the output layer of the model is reached, and the preliminary fault diagnosis result is calculated based on the result of the forward propagation. The formula is:

[0094]

[0095] Among them, Y represents the output of the preliminary fault diagnosis result, σ(·) represents the activation function, β i represents the attention weight of the i-th preprocessed power grid equipment state data, W i Represents the transformation function for each feature The corresponding weight matrix is, represents the characteristic transformation function of the i-th preprocessed power grid equipment state data, represents the residual term, b represents the bias term;

[0096] It should be noted that in the present invention, the modified formula combines multiple advantages and integrates multiple feature transformations in the form of a weighted sum. The output of each transformation is passed through its corresponding weight W i and coefficient β i Scaling increases the flexibility and expressiveness of the intelligent fault diagnosis model; at the same time, the residual term is introduced Allows intelligent fault diagnosis models to directly learn input The direct difference between the output Y helps to capture complex relationships that are difficult to express directly through feature transformation; finally, the bias term b provides additional degrees of freedom to adjust the output, so that the intelligent fault diagnosis model can fit the data more accurately; in summary, the formula in the present invention enhances the complexity and adaptability of the intelligent fault diagnosis model by integrating multiple transformations, residual learning and bias adjustment, so that it can more effectively process complex data and tasks.

[0097] S2.23: Introduce a multi-source verification mechanism and collect multi-source verification data. At the same time, use a cosine similarity algorithm to compare and verify the preliminary fault diagnosis results with the multi-source verification data. The calculation formula of the cosine similarity algorithm is the prior art content in this field, which is not an inventive solution of the present application and is not described in detail here.

[0098] S2.24: According to the result of the multi-source verification, the preliminary fault diagnosis result is corrected, and the corrected fault diagnosis result is converted into a visual report, and at the same time, the parsed fault diagnosis result is output to a designated location;

[0099] The corrections include changing the fault type, adjusting the fault severity, and adding diagnostic information; the visual report should include the fault type, fault location, fault time, fault impact range, and repair suggestion information; the specified location can be a folder in the file system, a database, a web interface, or any user-specified location.

[0100] Furthermore, the specific steps of correcting the preliminary fault diagnosis result include:

[0101] (1) Compare the preliminary fault diagnosis results with the multi-source verification data, including checking whether the fault type, fault location, and fault time information are consistent. Pay special attention to those information points that are different or contradictory in the multi-source verification data;

[0102] (2) Compare and logically analyze the results to evaluate the rationality and accuracy of the preliminary diagnostic results. At the same time, analyze the errors or omissions in the preliminary diagnostic results and explore their possible causes;

[0103] (3) Based on the results of logical analysis, make correction decisions, including the following situations:

[0104] If the preliminary diagnosis result is highly consistent with the multi-source verification data and is logically reasonable, no correction is required;

[0105] If there is a significant difference or contradiction between the preliminary diagnosis result and the multi-source verification data, and the multi-source verification data is more reliable, the preliminary diagnosis result needs to be revised;

[0106] If there are omissions or errors in the initial diagnosis, but the multi-source verification data provide supplementary information, this information needs to be incorporated in the revision process;

[0107] (4) Based on the correction decision, make specific corrections to the preliminary diagnosis results, including changing the fault type, adjusting the fault location, and correcting the fault time. At the same time, during the correction process, it is necessary to ensure that the corrected results are logically reasonable, accurate in terms of data, and consistent with multi-source verification data;

[0108] (5) Re-verify the corrected fault diagnosis results to ensure the correctness and effectiveness of the correction, and record the correction process and results.

[0109] S2.25: Establish a continuous learning mechanism to feed back each fault diagnosis result and actual situation to the intelligent fault diagnosis model to optimize and update the intelligent fault diagnosis model.

[0110] The specific steps of S2.3 include:

[0111] S2.31: Obtain preliminary fault diagnosis results Y = {y1, ..., y N}, and preprocess the preliminary fault diagnosis results, where y N represents the Nth preliminary fault data, where N represents the number of preliminary fault data;

[0112] S2.32: Use the improved adaptive clustering algorithm to cluster Y = {y1, ..., y N} Perform cluster analysis and calculate y N The silhouette coefficient is obtained by N At the same time, the clustering effect is evaluated according to the value of the average silhouette coefficient. The formula is:

[0113]

[0114] Among them, Sim jk represents Y={y1,...,y N}, f(·) represents the hierarchical clustering function, w d represents the weight after adaptive adjustment, w or,jk represents the original weight between data point j and data point k, fact ad (·) represents the adaptive function, CM lu Represents the silhouette coefficient index, feat j Represents the eigenvalue of data point j, feat k represents the eigenvalue of data point k, Iter represents the number of iterations of the current clustering process, CS jIndicates the number of data points contained in the cluster where data point j is located, CS k represents the number of data points contained in the cluster where the data point k is located, and λ represents the adjustment parameter;

[0115] It should be noted that the formula in the present invention introduces an adaptive factor fact ad (·) is used to dynamically adjust the weights. Its advantage is that it can flexibly optimize and adjust the weights based on clustering metrics, data features, number of iterations, cluster size, and adjustment parameter λ, thereby improving the accuracy and adaptability of clustering analysis. This dynamic adjustment strategy can better adapt to the characteristics of complex data sets and continuously optimize the weight distribution during the clustering process to achieve a more optimized clustering effect.

[0116] S2.33: Collect fault history data, equipment importance and current grid equipment operating status information, and integrate them to form multi-factor information Z = {z1,...,z M}, and at the same time, the multi-factor information is transformed into quantifiable evaluation indicators to form an evaluation indicator system, where z M represents the Mth multi-factor information, and M represents the number of multi-factor information;

[0117] Among them, fault history data is collected from equipment fault reports, maintenance records, operator feedback and related documents to ensure that the data contains fault description, cause analysis, solution and repair step information; equipment importance assessment data is obtained from equipment manuals, power grid topology diagrams, and historical fault impact analysis reports.

[0118] Furthermore, the specific formula for converting multi-factor information into quantifiable evaluation indicators is:

[0119] L liang,p =f1(z p ,θ1,...,θ p );

[0120] Where f1(·) represents the quantization function, θ p represents the quantitative parameter of the p-th multi-factor information, z p Represents the pth multi-factor information.

[0121] S2.34: Use a comprehensive evaluation method to determine the weights of the evaluation indicators, and construct a multi-factor evaluation model based on the evaluation index system and the weights of the evaluation indicators. The formula of the multi-factor evaluation model is:

[0122]

[0123] Among them, Q represents the comprehensive evaluation value, L liang,r represents the quantitative value of the r-th multi-factor information, wr ′ represents the weight of the r-th multi-factor information, δ r represents the adjustment factor of the r-th multi-factor information, η r represents the time decay factor of the r-th multi-factor information, I r represents the environmental factor of the r-th multi-factor information, and c represents the constant term;

[0124] It should be noted that the formula in the present invention introduces multiple parameters, such as adjustment factors, time attenuation factors, environmental factors and constant terms, to make the evaluation process more comprehensive, flexible and dynamic. These newly added factors can more accurately reflect the actual impact of the evaluation indicators at different times and under different environmental conditions, thereby improving the accuracy and reliability of the evaluation results; at the same time, the formula also retains the basic weighted summation structure, maintaining the simplicity and operability of the evaluation method.

[0125] S2.35: Use a multi-factor evaluation model to intelligently classify the clustered fault data, and prioritize the faults based on the fault classification results and the actual operation of the power grid.

[0126] Among them, according to the comprehensive evaluation value, the clustered fault data is divided into different levels, such as emergency Q>0.9, important 0.7<Q≤0.9, general 0.4<Q≤0.7, and minor Q≤0.4. It should be noted that the classification standard can be set according to the actual needs and experience of power grid operation.

[0127] When prioritizing faults, the actual situation of power grid operation, such as current load conditions, power supply needs of important users, and weather conditions, is mainly considered to prioritize the classified faults. At the same time, priority sorting should comprehensively consider factors such as fault level, fault impact range, repair difficulty, and the safety and stability of power grid operation, and high-priority faults should be handled first to ensure safe and stable operation of the power grid.

[0128] Example 3

[0129] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a distribution automation terminal operation and maintenance method based on the 104 protocol are implemented. For details, please refer to the above method embodiment, which will not be repeated here.

[0130] A computer-readable storage medium having computer instructions stored thereon, which executes the steps of a distribution automation terminal operation and maintenance method based on the 104 protocol when the computer instructions are executed, wherein the storage medium may be a volatile or non-volatile computer-readable storage medium.

[0131] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in the field may also change, modify, replace and modify the above-mentioned embodiments without departing from the purpose and scope of protection of the present invention, and all of these are within the protection of the present invention.

Claims

1. A distribution automation terminal operation and maintenance method based on 104 protocol, characterized in that: include: Step S1: The distribution automation terminal collects the power grid equipment status data in real time through the IEC 104 protocol at a predetermined time interval, and encapsulates and transmits it to the master station system; Step S2: After receiving the power grid equipment status data packet, the master station system performs verification and decoding, and uses the intelligent fault diagnosis model to process and analyze the decoded power grid equipment status data. At the same time, according to the output results of the intelligent fault diagnosis model, the identified faults are classified and graded; Step S3: If a fault or abnormality is identified, the master station system immediately triggers the fault warning mechanism. At the same time, according to the classification and classification of the fault, a corresponding fault notification is generated and sent to the operation and maintenance personnel; Step S4: After receiving the fault notification, the operation and maintenance personnel remotely operate the faulty equipment through the intelligent operation and maintenance APP. At the same time, after completing the fault processing, the operation and maintenance personnel will feedback the processing results to the main station system and update the operating status information of the power grid equipment.

2. The distribution automation terminal operation and maintenance method based on 104 protocol according to claim 1, characterized in that: The specific steps of step S2 include: S2.1: The master station system receives the power grid equipment status data packet X={x1,…,x n }, and perform data freshness verification on the received power grid equipment status data packet, where x n represents the nth power grid device status data, where n represents the number of power grid device status data; If the data packet verification fails, the error information is recorded and a notification is sent to the operation and maintenance personnel. At the same time, the fault warning mechanism is triggered; If the verification is passed, the verified power grid equipment status data packet is decoded according to the IEC 104 protocol to restore the original power grid equipment status data, and the decoded power grid equipment status data is preprocessed; S2.2: Load the pre-trained intelligent fault diagnosis model, and use the intelligent fault diagnosis model to process and analyze the pre-processed power grid equipment status data, calculate and output the fault diagnosis results; S2.3: Based on the output results of the intelligent fault diagnosis model, an improved adaptive clustering algorithm is introduced to classify faults. At the same time, a multi-factor evaluation model is used to intelligently classify and prioritize the classified faults, combining fault history data, equipment importance, and current grid equipment operating status; S2.4: Based on the fault classification and priority sorting results, the master station system automatically triggers the corresponding emergency response plan and establishes a cross-departmental collaborative workflow platform.

3. The distribution automation terminal operation and maintenance method based on 104 protocol as claimed in claim 2, characterized in that: The specific steps of performing data freshness verification in S2.1 include: S2.11: The master station system monitors the power grid equipment status data packet sent by the distribution automation terminal through the TCP / IP protocol network interface. When the data packet arrives, the master station system receives it completely and temporarily stores it in the memory or disk; S2.12: Extract timestamp information from received power grid device status data packets t , and compare the timestamp in the power grid equipment status data packet with the current system time t, and calculate the time error e = a t -t; S2.13: Set the time threshold h1=5; If e≤h1, it means the data packet is fresh; If e>h1, it means that the data packet is outdated and a notification is sent to the operation and maintenance personnel.

4. The distribution automation terminal operation and maintenance method based on 104 protocol as claimed in claim 3 is characterized in that: The specific steps of S2.2 include: S2.21: Obtain pre-processed power grid equipment status data m≤n, and load the pre-trained intelligent fault diagnosis model, where: represents the mth preprocessed power grid device status data, and m represents the number of preprocessed power grid device status data; S2.22: Input into the intelligent fault diagnosis model, at the same time, The forward propagation process is carried out through the convolutional layer and the fully connected layer of the intelligent fault diagnosis model until the output layer of the model is reached, and the preliminary fault diagnosis result is calculated based on the result of the forward propagation. The formula is: Among them, Y represents the output of the preliminary fault diagnosis result, σ(·) represents the activation function, β i represents the attention weight of the i-th preprocessed power grid equipment state data, W i Represents the transformation function for each feature The corresponding weight matrix is, represents the characteristic transformation function of the i-th preprocessed power grid equipment state data, represents the residual term, and b represents the bias term.

5. The distribution automation terminal operation and maintenance method based on 104 protocol as claimed in claim 4, characterized in that: The specific steps of S2.2 also include: S2.23: Introduce a multi-source verification mechanism and collect multi-source verification data. At the same time, use the cosine similarity algorithm to compare and verify the preliminary fault diagnosis results with the multi-source verification data; S2.24: According to the result of the multi-source verification, the preliminary fault diagnosis result is corrected, and the corrected fault diagnosis result is converted into a visual report, and at the same time, the parsed fault diagnosis result is output to a designated location; S2.25: Establish a continuous learning mechanism to feed back each fault diagnosis result and actual situation to the intelligent fault diagnosis model to optimize and update the intelligent fault diagnosis model.

6. The distribution automation terminal operation and maintenance method based on 104 protocol as claimed in claim 5, characterized in that: The specific steps of S2.3 include: S2.31: Obtain preliminary fault diagnosis results Y = {y1, ..., y N }, and preprocess the preliminary fault diagnosis results, where y N represents the Nth preliminary fault data, where N represents the number of preliminary fault data; S2.32: Use the improved adaptive clustering algorithm to cluster Y = {y1, ..., y N } Perform cluster analysis and calculate y N The silhouette coefficient is obtained by N At the same time, the clustering effect is evaluated according to the value of the average silhouette coefficient. The formula is: Among them, Sim jk represents Y={y1,...,y N }, f(·) represents the hierarchical clustering function, w d represents the weight after adaptive adjustment, w or,jk represents the original weight between data point j and data point k, fact ad (·) represents the adaptive function, CM lu Represents the silhouette coefficient index, feat j Represents the eigenvalue of data point j, feat k represents the eigenvalue of data point k, Iter represents the number of iterations of the current clustering process, CS j Indicates the number of data points contained in the cluster where data point j is located, CS k It represents the number of data points contained in the cluster where the data point k is located, and λ represents the adjustment parameter.

7. The distribution automation terminal operation and maintenance method based on 104 protocol according to claim 6, characterized in that: The specific steps of S2.3 also include: S2.33: Collect fault history data, equipment importance and current grid equipment operating status information, and integrate them to form multi-factor information Z = {z1,...,z M }, and at the same time, the multi-factor information is transformed into quantifiable evaluation indicators to form an evaluation indicator system, where z M represents the Mth multi-factor information, and M represents the number of multi-factor information; S2.34: Use a comprehensive evaluation method to determine the weights of the evaluation indicators, and construct a multi-factor evaluation model based on the evaluation index system and the weights of the evaluation indicators. The formula of the multi-factor evaluation model is: Among them, Q represents the comprehensive evaluation value, L liang,r Represents the quantitative value of the r-th multi-factor information, w′ r represents the weight of the r-th multi-factor information, δ r represents the adjustment factor of the r-th multi-factor information, η r represents the time decay factor of the r-th multi-factor information, I r represents the environmental factor of the rth multi-factor information, and c represents the constant term. S2.35: Use a multi-factor evaluation model to intelligently classify the clustered fault data, and prioritize the faults based on the fault classification results and the actual operation of the power grid.

8. The distribution automation terminal operation and maintenance method based on 104 protocol as claimed in claim 7, characterized in that: The power grid equipment status data in step S1 includes operating status data and fault information.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the distribution automation terminal operation and maintenance method based on the 104 protocol described in any one of claims 1-8 are implemented.

10. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the computer instructions are executed, the steps of the distribution automation terminal operation and maintenance method based on the 104 protocol as described in any one of claims 1-8 are executed.

Images