A method and system for planning the configuration of equipment in a facility based on equipment commissioning feedback.

Abstract

This invention discloses a method and system for power grid power station equipment configuration planning based on equipment commissioning feedback, belonging to the field of power grid power station planning technology. It aims to solve the problems of long commissioning cycles and difficult compatibility adaptation of equipment from multiple manufacturers during power station construction. The method acquires power station scene maps through LiDAR scanning and UAV aerial photography, extracts equipment physical location information, and constructs 3D models, spacing matrices, and electromagnetic interference threshold sets; it collects basic information on equipment from multiple manufacturers to establish a database, and constructs a commissioning feedback influencing factor model based on historical commissioning data; it uses AI algorithms to generate an initial configuration parameter set, enabling automatic equipment identification, network matching, and on-site deployment according to planned locations; and it collects commissioning feedback data through interoperability testing, iteratively optimizing parameters until commissioning requirements are met. This invention eliminates the need to wait for technical personnel from various manufacturers to arrive on-site, significantly shortening the power station construction and commissioning cycle, and improving the reliability of interoperability among equipment from multiple manufacturers and the scientific nature of configuration planning.

Description

Technical Field

[0001] This invention relates to the field of power grid station planning technology, specifically to a station equipment configuration planning method and system based on equipment commissioning feedback. Background Technology

[0002] Power grid substations are the core hubs for power transmission and distribution. With the accelerated construction of new power systems, substation scale continues to expand, and equipment is increasingly integrated across multiple manufacturers. Equipment configuration planning and joint commissioning are crucial for the smooth commissioning of substations, and their efficiency directly impacts construction cycles, operational reliability, and the grid's supply-demand balance. Efficient and intelligent substation equipment configuration planning technologies can promote rapid substation commissioning and support the intelligent upgrading of the power grid, which is of significant practical importance for improving the overall operational efficiency of the power system.

[0003] Existing methods and systems for site equipment configuration planning based on equipment commissioning feedback largely rely on manual coordination of technical personnel from various manufacturers to complete parameter configuration. This results in long commissioning cycles and a lack of integration with the physical location information of site equipment. Consequently, spatial factors such as equipment spacing and electromagnetic interference can lead to poor commissioning feedback and low parameter matching accuracy. Furthermore, parameter configuration depends on manual experience and lacks data-driven influencing factor models. The compatibility adaptation process for equipment from multiple manufacturers is complex, making it difficult to achieve efficient equipment interconnection. Therefore, a site equipment configuration planning method and system based on equipment commissioning feedback is needed to address the aforementioned problems. Summary of the Invention

[0004] To address the aforementioned technical issues, this paper provides a method and system for planning the configuration of equipment at a site based on equipment commissioning feedback. This solution resolves the problems raised in the background section regarding existing methods and systems for planning the configuration of equipment at a site based on equipment commissioning feedback. These methods and systems often rely heavily on manual coordination of technical personnel from various manufacturers to complete parameter configuration, resulting in long commissioning cycles. Furthermore, they fail to incorporate the physical location information of the equipment at the site for parameter configuration, making them susceptible to poor commissioning feedback and low parameter matching accuracy due to spatial factors such as equipment spacing and electromagnetic interference. Additionally, parameter configuration depends on manual experience and lacks data-driven influencing factor models. The process for adapting and compatibility with equipment from multiple manufacturers is complex, making it difficult to efficiently achieve equipment interconnection and interoperability.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A method for planning the configuration of station equipment based on equipment commissioning feedback includes: S1. Obtain scene diagrams and construction planning schemes for power grid substations in the power system, and extract the physical location information of substation equipment; S2. Collect basic information on the model parameters, communication protocols, and operating thresholds of power grid equipment from various manufacturers, and establish an equipment information database; S3. Collect historical commissioning data of the station, and construct a commissioning feedback influencing factor model based on the historical commissioning data, equipment compatibility data and physical location information of the station equipment; S4. Based on the equipment information database and the joint debugging feedback impact factor model, generate the initial configuration parameter set for each device; S5. Based on the initial configuration parameter set, automatically identify multi-vendor equipment in the access site, complete equipment identity verification and network matching, further schedule equipment from each vendor to automatically arrive at the site for deployment according to the planned physical location, and synchronously push the appropriate configuration parameters; S6. Initiate equipment interconnection and interoperability testing, collect feedback data on signal transmission delay, fault trigger response speed, and parameter matching accuracy during the joint debugging process, compare the feedback data with the preset standard threshold, iteratively optimize the configuration parameters until the joint debugging requirements are met, and complete the configuration planning.

[0006] In an optional embodiment, step S1 specifically includes: S1.1. Using laser-excited radar scanning, UAV aerial photography, and GIS geographic information collection, the terrain data, building layout data, and preset equipment installation area data of the site are acquired simultaneously, and a multi-source original scene data set is output. The multi-source original scene data set includes terrain elevation data, building outline coordinate data, and installation area boundary data. S1.2. Preprocess the multi-source original scene data in the multi-source original scene data set to obtain a preprocessed clean data set; S1.3. Construct a three-dimensional scene model of the site based on the clean data set. Using the geodetic coordinate system as the reference, map the preprocessed terrain elevation data, building outline coordinate data, and installation area boundary data to the three-dimensional space to generate a complete model containing terrain, buildings, and installation area. S1.4. Extract the core parameters of the physical location of the equipment from the 3D scene model, identify the fixed points of the equipment within the installation area, output the 3D coordinates of each point, and form a set of point coordinates; S1.5. Obtain the physical distance between adjacent device locations and construct a distance matrix; The formula for calculating the physical distance between adjacent equipment points is as follows: ; In the formula, For any two points in the set of point coordinates and The spacing, , , Points The coordinate values ​​on the X, Y, and Z axes, , , Points Coordinate values ​​on the X, Y, and Z axes; The formula for expressing the spacing matrix is: ; In the formula, Number of points; S1.6. Combining the electromagnetic interference characteristics of power grid equipment, determine the electromagnetic interference threshold for each point based on the spacing matrix, and further output the threshold set; The formula for calculating the electromagnetic interference threshold is as follows: ; In the formula, For point The corresponding electromagnetic interference threshold, The electromagnetic attenuation coefficient, The rated power of adjacent equipment; S1.7. Integrate the set of point coordinates, spacing matrix, and electromagnetic interference threshold set to form a complete physical location information package.

[0007] In an optional embodiment, step S2 specifically includes: S2.1. Collect core information of power grid equipment from various manufacturers through manufacturer interfaces, equipment manual parsing, and industry standard databases, including equipment model, rated voltage, rated current, communication protocol type, protection action threshold, equipment size parameters, and compatibility adaptation list, and output the original equipment information set. S2.2. Standardize the original equipment information in the original equipment information set and output a standardized information set; S2.3. Based on the z-axis height data in the point coordinate set and the height value in the equipment size parameters, determine whether the equipment installation space meets the equipment installation space constraint inequality, and further output the adaptability verification result; The compatibility verification result includes a device compatibility value, where a device compatibility value of 1 indicates compatibility and a device compatibility value of 0 indicates incompatibility. The formula for expressing the inequality regarding the equipment installation space constraint is: ; In the formula, For the first The height value in the equipment dimension parameters corresponding to each device. For the installation surface elevation, For the first The set of point coordinates corresponding to each device is the first Z-axis height data for each fixed point of the equipment; S2.4. Extract compatibility data of the adapted devices, filter out devices with a device compatibility value of 1 from the standardized information set, and further obtain cross-matching results from the compatibility compatibility list to construct a compatibility matrix; The compatibility matrix is ​​expressed as follows: ; In the formula, Indicates compatibility, This indicates incompatibility. To accommodate the number of devices; S2.5. Establish an equipment information database, which includes a basic parameter table, a communication protocol table, a compatibility table, a physical adapter table, and a manufacturer service data table.

[0008] In an optional embodiment, step S3 specifically includes: S3.1. Collect equipment configuration parameters, physical location distribution, and joint commissioning feedback results of similar power grid stations over the past 5 years to obtain historical joint commissioning data of the stations. The joint commissioning feedback results include signal transmission delay, fault triggering accuracy, and parameter matching error. S3.2. Extract influencing factor variables from the historical commissioning data of the station and determine the core influencing factors. The core influencing factors include equipment spacing, equipment compatibility, parameter configuration deviation, electromagnetic interference intensity, and communication protocol type. S3.3. Normalize the core impact factors to obtain a normalized set of impact factors; S3.4. The normalized set of influencing factors is used as the input feature, and the signal transmission delay, fault triggering accuracy, and parameter matching error are used as the output labels. The equipment configuration parameters, physical location distribution, and joint commissioning feedback results of similar power grid stations in the past 5 years are divided into training set and test set in a 7:3 ratio. The model is then trained further. The training model parameters include the number of decision trees, node splitting threshold, and feature importance weight, thereby outputting the initial prediction model. S3.5. Combining the spacing matrix and electromagnetic interference threshold set in the physical location information packet, adjust the weight coefficients of each influencing factor to minimize the model prediction error; The weighting coefficients of each influencing factor include the weighting coefficients for equipment spacing, equipment compatibility, parameter configuration deviation, electromagnetic interference intensity, and communication protocol type. S3.6. Determine the mean absolute error and coefficient of determination of the initial prediction model using test set data, and further output the final joint feedback influence factor model.

[0009] In an optional embodiment, step S4 specifically includes: S4.1. Based on the parameter vector set and the joint feedback influence factor model, determine the optimization objective of the AI ​​algorithm; The optimization objective includes minimizing parameter configuration deviations and joint debugging costs while meeting equipment operation safety constraints and joint debugging feedback index constraints. S4.2. Initialize the particle swarm population. Each particle corresponds to a set of device configuration parameter schemes. The particle dimension is the product of the number of devices and the number of parameters. The initial value of the particle is generated based on the initial parameters in the parameter vector set and the influence factor weights of the model. S4.3. Constructing the fitness function: ; in, The configuration parameter scheme for the particles. For parameter deviation, To reduce the cost of joint commissioning, To constrain violations and penalties, , , All are fitness function weights; The formula for calculating the parameter deviation is: ; In the formula, For the first in the plan The first of the equipment One configuration parameter, For the first The first of the equipment The standard parameters corresponding to each configuration parameter This represents the total number of parameters. S4.4. Construct velocity update formulas and position update formulas, and iteratively update the position and velocity of the particle swarm; The speed update formula is as follows: ; In the formula, For inertial weights, , As a learning factor, , A random number in the range [0,1]. For the first The particle in the first The optimal position of the individual in the next iteration. For the first The particle in the first The global optimal position at the next iteration. For the first The particle in the first Speed ​​at the next iteration In the The first particle The current velocity at the next iteration; The position update formula is: ; In the formula, For the first The particle in the first The displacement at the next iteration For the first The particle in the first The current displacement at the next iteration; S4.5. Obtain a fitness value once for each iteration, and after each iteration, predict the joint debugging feedback index corresponding to the current parameter scheme X through the joint debugging feedback influence factor model. If the joint debugging feedback index does not meet the constraints, adjust the particle velocity direction and increase the optimization intensity of the parameters corresponding to the high priority influence factors. S4.6. When the number of iterations reaches the preset maximum value or the change in the global optimal fitness value is less than or equal to the preset iteration change threshold for 10 consecutive iterations, stop the iteration and output the parameter scheme corresponding to the global optimal particle, which is the initial configuration parameter set of each device. S4.7. Call the power grid equipment safe operation standard database to perform safety verification on the initial configuration parameter set of each device, thereby determining the verified initial configuration parameter set.

[0010] In an optional embodiment, step S5 specifically includes: S5.1. Read the unique identification code of the equipment on site, combine it with the equipment information database, query the core information of the power grid equipment corresponding to the unique identification code, complete the preliminary verification of the equipment identity, and output the identity verification result; S5.2. Based on equipment size parameters and point spacing matrix, optimize equipment installation sequence and output installation point allocation results; S5.3. Based on the installation point allocation results and the three-dimensional scene model of the site, plan the optimal path for the equipment from the entrance to the installation point, and further output a set of scheduling instructions; S5.4. After the equipment arrives on site, collect the real-time status data of the equipment, compare it with the preset standard status data, output the status detection results, and trigger the manufacturer's after-sales response mechanism for abnormal equipment; S5.5. Based on the communication protocol parameters in the initial configuration parameter set, the system automatically switches to the corresponding communication mode, verifies the networking compatibility between devices through the compatibility matrix, establishes the device interconnection topology, and outputs the networking results; S5.6. Transmit the parameter set corresponding to the device in the initial configuration parameter set to the device control unit through an encrypted communication channel, verify the integrity of the parameter set transmission, and output the parameter transmission result; S5.7. For devices that fail to push, analyze the reason for the failure. If it is a communication problem, re-establish the communication connection and push again. If it is a compatibility problem, re-optimize the parameter set of the corresponding device until all device parameters are successfully pushed. Finally, output a device deployment completion signal.

[0011] In an optional embodiment, step S6 specifically includes: S6.1. Simulate the normal operation and fault triggering conditions of the power grid, collect the operating data of each device, including signal transmission delay, fault response time, parameter matching accuracy, data transmission packet loss rate, and output the joint debugging test data set; S6.2. Determine the comprehensive indicators for joint commissioning feedback; The calculation formula for the integrated index of joint debugging feedback is as follows: ; In the formula, For the first Comprehensive indicators of joint debugging feedback from the equipment. , For the first Normalized latency and response time of the device. For the first Accuracy of parameter matching for each device. For the first Data transmission packet loss rate of the device , , , These are the weighting coefficients corresponding to signal transmission delay, fault response time, parameter matching accuracy, and data transmission packet loss rate, respectively. S6.3. Based on the integrated index of joint commissioning feedback, determine the set of integrated indexes. For equipment in the integrated index set that fails the integrated index of joint commissioning feedback, analyze the core influencing factors in conjunction with the joint commissioning feedback influencing factor model. If it is related to physical location, extract the point coordinates and spacing of the equipment and determine the optimal spacing after adjustment. The formula for calculating the adjusted optimal spacing is as follows: ; In the formula, For the first The optimal spacing after adjustments for equipment whose overall performance indicators failed to meet the requirements of the joint commissioning feedback. For the first The spacing of equipment that failed to meet the overall performance indicators reported by the joint commissioning system before adjustment. This is the spacing adjustment amount; S6.4. If the core influencing factor is parameter deviation, then adjust the parameters using the gradient descent formula; The gradient descent formula is as follows: ; In the formula, For the first The adjusted configuration parameter set for equipment whose overall performance indicators failed the joint commissioning feedback. For the first The initial configuration parameter set of equipment whose overall performance indicators failed the joint commissioning feedback before adjustment. For learning rate, As a standard comprehensive indicator for joint debugging feedback, For the first The current integrated performance indicators of the equipment under joint commissioning. The gradient of the fitness function at the initial parameter set; S6.5. Restart the joint debugging test, collect the adjusted equipment operation data, obtain the new joint debugging feedback comprehensive index, and compare it with the new joint debugging feedback comprehensive index. Integrated indicators of joint debugging feedback Change ; like and The equipment has passed the commissioning process. like or Then repeat steps S6.3-S6.4 until... ; in, , In This represents the number of iterations for equipment integration and testing.

[0012] Furthermore, a station equipment configuration planning system based on equipment commissioning feedback is proposed to implement any of the planning methods mentioned above, including: The physical location sensing module is used to acquire scene maps and construction planning schemes of power grid stations in the power system, and extract the physical location information of station equipment. The equipment information database construction module is used to collect basic information such as model parameters, communication protocols, and operating thresholds of power grid equipment from various manufacturers to establish an equipment information database. The impact factor modeling module is used to collect historical joint commissioning data of the station and, based on the historical joint commissioning data, equipment compatibility data and physical location information of the station equipment, construct a joint commissioning feedback impact factor model. An initial parameter generation module is used to generate an initial configuration parameter set for each device based on the device information database and the joint debugging feedback influence factor model. The automatic equipment deployment module is used to automatically identify multi-vendor equipment in the access site based on the initial configuration parameter set, complete equipment identity verification and network matching, and further schedule the equipment of each vendor to automatically arrive at the site for deployment according to the planned physical location, and synchronously push the appropriate configuration parameters. The joint debugging parameter optimization module is used to initiate equipment interconnection and interoperability testing, collect feedback data on signal transmission delay, fault trigger response speed, and parameter matching accuracy during the joint debugging process, compare the feedback data with preset standard thresholds, iteratively optimize configuration parameters until the joint debugging requirements are met, and complete the configuration planning.

[0013] In an optional embodiment, the physical location sensing module includes: A multi-source scene data acquisition unit is used to acquire terrain data, building layout data, and preset equipment installation area data of the site simultaneously by using lidar scanning, drone aerial photography, and GIS geographic information acquisition, and output a set of multi-source original scene data. A scene data preprocessing unit is used to preprocess the multi-source original scene data in the multi-source original scene data set to obtain a preprocessed clean data set. The three-dimensional scene modeling unit is used to construct a three-dimensional scene model of the site based on the clean data set. Using the geodetic coordinate system as a reference, the preprocessed terrain elevation data, building outline coordinate data, and installation area boundary data are mapped to the three-dimensional space to generate a complete model containing terrain, buildings, and installation areas. The location parameter extraction unit is used to extract the core parameters of the physical location of the equipment from the three-dimensional scene model, identify the fixed points of the equipment within the installation area, and output the three-dimensional coordinates of each point to form a set of point coordinates. A spacing matrix construction unit is used to obtain the physical spacing between adjacent device points and construct a spacing matrix; An electromagnetic threshold calculation unit is used to determine the electromagnetic interference threshold of each point based on the spacing matrix, taking into account the electromagnetic interference characteristics of power grid equipment, and further output a threshold set. The physical information integration unit is used to integrate the set of point coordinates, the spacing matrix, and the set of electromagnetic interference thresholds to form a complete physical location information package.

[0014] In an optional embodiment, the joint debugging parameter optimization module includes: The joint debugging data acquisition unit is used to simulate the normal operation and fault triggering conditions of the power grid, collect the operating data of each device, including signal transmission delay, fault response time, parameter matching accuracy, data transmission packet loss rate, and output a set of joint debugging test data. A comprehensive index calculation unit is used to determine the joint debugging feedback comprehensive index; The influencing factor analysis unit is used to determine the comprehensive index set based on the joint debugging feedback comprehensive index, and to analyze the core influencing factors of equipment with unqualified joint debugging feedback comprehensive index in the comprehensive index set, combined with the joint debugging feedback influencing factor model. The parameter / position adjustment unit is used to adjust the equipment parameters and position based on the core influencing factors. If it is related to the physical location, the point coordinates and spacing of the equipment are extracted to determine the optimal spacing after adjustment. If the core influencing factor is parameter deviation, the parameters are adjusted by the gradient descent formula. The joint debugging and iterative verification unit is used to restart the joint debugging test, collect the adjusted equipment operation data, obtain the new joint debugging feedback comprehensive index, compare the change of the new joint debugging feedback comprehensive index with the original joint debugging feedback comprehensive index, and determine whether the equipment joint debugging is qualified. If it is not qualified, the adjustment steps are repeated. The configuration planning completion unit is used to complete the configuration planning until the joint debugging requirements are met.

[0015] Compared with the prior art, the beneficial effects of the present invention are: This solution proposes a site equipment configuration planning method based on equipment commissioning feedback. By acquiring site scene maps and extracting equipment physical location information, a three-dimensional scene model, spacing matrix, and electromagnetic interference threshold set are constructed. Combined with the commissioning feedback influencing factor model, parameter configuration is carried out, which realizes the accurate adaptation of physical location to equipment commissioning feedback, avoids commissioning deviation caused by spatial factors, and improves the spatial rationality of equipment configuration planning. This solution proposes a site equipment configuration planning method based on equipment commissioning feedback. It generates an initial configuration parameter set through AI algorithms, realizes automatic identification, network matching and on-site deployment of equipment from multiple manufacturers according to the planned location, and pushes the adaptation parameters simultaneously. This achieves an automated configuration process without waiting for the technical personnel of each manufacturer to arrive on-site, which greatly shortens the commissioning cycle of site construction and reduces the manpower cost of cross-manufacturer coordination. This solution proposes a site equipment configuration planning method based on equipment commissioning feedback. By initiating equipment interoperability testing to collect commissioning feedback data and combining iterative optimization of configuration parameters with preset standard thresholds, it achieves dynamic and precise adjustment of equipment configuration parameters, improves the interoperability reliability and parameter matching accuracy of equipment from multiple manufacturers, and ensures stable operation of the site after commissioning. Attached Figure Description

[0016] Figure 1 This is a flowchart of a station equipment configuration planning method based on equipment commissioning feedback proposed in this invention; Figure 2 This is a flowchart illustrating the construction process of the joint feedback influence factor model in this invention. Figure 3 This is a flowchart illustrating the construction process of the initial configuration parameter set in this invention. Figure 4 This is a system framework diagram of a station equipment configuration planning system based on equipment commissioning feedback proposed in this invention. Detailed Implementation

[0017] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0018] Reference Figure 1 - Figure 4 As shown, a site equipment configuration planning method based on equipment commissioning feedback includes: S1. Obtain scene diagrams and construction planning schemes for power grid substations in the power system, and extract the physical location information of substation equipment; S2. Collect basic information on the model parameters, communication protocols, and operating thresholds of power grid equipment from various manufacturers, and establish an equipment information database; S3. Collect historical commissioning data of the station, and construct a commissioning feedback influencing factor model based on the historical commissioning data, equipment compatibility data and physical location information of the station equipment; S4. Based on the equipment information database and the joint debugging feedback impact factor model, generate the initial configuration parameter set for each device; S5. Based on the initial configuration parameter set, automatically identify multi-vendor equipment in the access site, complete equipment identity verification and network matching, further schedule equipment from each vendor to automatically arrive at the site for deployment according to the planned physical location, and synchronously push the appropriate configuration parameters; S6. Initiate equipment interconnection and interoperability testing, collect feedback data on signal transmission delay, fault trigger response speed, and parameter matching accuracy during the joint debugging process, compare the feedback data with the preset standard threshold, iteratively optimize the configuration parameters until the joint debugging requirements are met, and complete the configuration planning.

[0019] Furthermore, step S1 specifically includes: S1.1. Using laser-induced radar scanning, UAV aerial photography, and GIS geographic information collection, the terrain data, building layout data, and preset equipment installation area data of the site are acquired simultaneously, and a multi-source original scene data set is output, which includes terrain elevation data, building outline coordinate data, and installation area boundary data. S1.2. Preprocess the multi-source original scene data in the multi-source original scene data set to obtain a preprocessed clean data set; Preprocessing of multi-source original scene data in the multi-source original scene dataset includes removing noise points in terrain elevation data using median filtering algorithm, using image stitching technology to fuse fragmented aerial images of building outline coordinate data into a complete building layout map, and using boundary extraction algorithm to optimize the regional outline accuracy of installation area boundary data. S1.3. Construct a three-dimensional scene model of the site based on the clean data set. Using the geodetic coordinate system as the reference, map the preprocessed terrain elevation data, building outline coordinate data, and installation area boundary data to the three-dimensional space to generate a complete model containing terrain, buildings, and installation area. S1.4. Extract the core parameters of the physical location of the equipment from the 3D scene model, identify the fixed points of the equipment within the installation area, output the 3D coordinates of each point, and form a set of point coordinates; S1.5. Obtain the physical distance between adjacent device locations and construct a distance matrix; The formula for calculating the physical distance between adjacent equipment points is as follows: ; In the formula, For any two points in the set of point coordinates and The spacing, , , Points The coordinate values ​​on the X, Y, and Z axes, , , Points Coordinate values ​​on the X, Y, and Z axes; The formula for expressing the spacing matrix is: ; In the formula, Number of points; S1.6. Combining the electromagnetic interference characteristics of power grid equipment, determine the electromagnetic interference threshold for each point based on the spacing matrix, and further output the threshold set; The formula for calculating the electromagnetic interference threshold is as follows: ; In the formula, For point The corresponding electromagnetic interference threshold, The electromagnetic attenuation coefficient, The rated power of adjacent equipment; S1.7. Integrate the set of point coordinates, spacing matrix, and electromagnetic interference threshold set to form a complete physical location information package. The complete physical location information package serves as the spatial constraint for subsequent parameter configuration, including the location reference for equipment installation, the calculation basis for signal transmission attenuation, and the reference standard for configuring equipment anti-interference parameters.

[0020] Understandably, by collecting terrain, building, and installation area data through multi-source fusion of LiDAR, drone aerial photography, and GIS, and combining this with preprocessing techniques such as median filtering and image stitching to remove noise, the limitations of low efficiency and difficulty in covering high-risk areas in manual measurement are overcome, while ensuring data accuracy. A three-dimensional scene model is constructed using a geodetic coordinate system, extracting the three-dimensional coordinates of equipment locations and calculating the spacing matrix using Euclidean distance. This replaces abstract two-dimensional drawings, clearly defining the precise location and spatial relationship of equipment installation and avoiding installation conflicts. Interference thresholds are calculated by combining the electromagnetic characteristics of power grid equipment, integrating physical laws and industry standards into spatial parameters to predict the electromagnetic environment in advance. Finally, the locations, spacing, and thresholds are integrated to form a physical location information package, providing structured spatial constraints for subsequent AI parameter configuration and automatic equipment deployment. This avoids the joint debugging deviations caused by "emphasizing parameters over location" from the source, significantly improving the spatial rationality of configuration planning and the efficiency of subsequent processes.

[0021] Furthermore, step S2 specifically includes: S2.1. Collect core information of power grid equipment from various manufacturers through manufacturer interfaces, equipment manual parsing, and industry standard databases, including equipment model, rated voltage, rated current, communication protocol type, protection action threshold, equipment size parameters, and compatibility adaptation list, and output the original equipment information set. S2.2. Standardize the original equipment information in the original equipment information set and output a standardized information set. The standardization process is to convert the voltage, current and other parameters of different manufacturers into international standard units, map different communication protocol types to a unified code (such as IEC 61850 protocol code as 01, Modbus protocol code as 02), and supplement the missing compatibility list with a similarity matching algorithm based on the equipment model. S2.3. Based on the z-axis height data in the point coordinate set and the height value in the equipment size parameters, determine whether the equipment installation space meets the equipment installation space constraint inequality, and further output the adaptability verification result; The compatibility verification result includes a device compatibility value, where a device compatibility value of 1 indicates compatibility and a device compatibility value of 0 indicates incompatibility. The formula for expressing the inequality of equipment installation space constraints is: ; In the formula, For the first The height value in the equipment dimension parameters corresponding to each device. For the installation surface elevation, For the first The set of point coordinates corresponding to each device is the first Z-axis height data for each fixed point of the equipment; S2.4. Extract compatibility data of the adapted devices, filter out devices with a device compatibility value of 1 from the standardized information set, and further obtain cross-matching results from the compatibility compatibility list to construct a compatibility matrix; The formula for expressing the compatibility matrix is: ; In the formula, Indicates compatibility, This indicates incompatibility. To accommodate the number of devices; S2.5. Establish an equipment information database. The database includes a basic parameter table, a communication protocol table, a compatibility table, a physical adapter table, and a manufacturer service data table. The basic parameter table stores basic information such as equipment model and rated voltage. The communication protocol table stores protocol codes and corresponding configuration specifications. The compatibility table stores the compatibility matrix. The physical adapter table stores compatibility verification results and point matching relationships. The manufacturer service data table stores information such as the manufacturer's technical parameter update interface and equipment after-sales response time.

[0022] Furthermore, step S2 also configures a dynamic database update mechanism, sets a scheduled task to call the manufacturer's interface and industry standard database every 24 hours to synchronously update dynamic information such as equipment parameters and compatibility lists, adopts an incremental update algorithm to replace only the changed data entries, verifies the integrity of the updated data through data verification codes, and outputs an update log to ensure that the equipment information in the database DB is consistent with the actual equipment. Extract the core parameter vectors of the devices from the database (DB), with one parameter vector corresponding to each compatible device. (in For the physical location information packet L Determined initial anti-interference parameters), output parameter vector set .

[0023] Understandably, by collecting core information such as equipment model, rated voltage, communication protocol, and compatibility list from multiple channels, including manufacturer interfaces, equipment manual parsing, and industry standard databases, the limitations of incomplete information collection from a single channel (such as missing compatibility data) are overcome, ensuring coverage of key information required for the entire lifecycle management of the equipment. The raw information is standardized by unifying the encoding of parameter units (such as voltage kV / V) and communication protocol formats from different manufacturers, resolving the issue of "disorganized formats and incompatibility" among data from multiple manufacturers, and providing a unified input for subsequent cross-manufacturer equipment data retrieval (such as AI parameter calculation and identity verification). Installation compatibility is verified based on the constraint relationship between the z-axis height of the location and the equipment height, pre-screening equipment that is spatially incompatible. (With an adaptation value of 0), rework is avoided due to size mismatch with installation space after equipment arrives (e.g., equipment is too tall to install), reducing time and cost losses; a quantitative compatibility matrix is ​​constructed based on the compatibility list of compatible equipment to clarify the compatibility relationship between equipment, avoiding the blindness of "experience-based compatibility judgment" and reducing compatibility conflicts between multiple manufacturers' equipment during joint commissioning from the source (e.g., protection devices from manufacturer A are incompatible with current transformers from manufacturer B); finally, a structured database containing basic parameter tables, compatibility tables, etc., is established to transform scattered information into efficiently callable assets, supporting subsequent equipment identity verification and AI-generated initial parameters, and improving information query and update efficiency through classified storage, providing "standardized and traceable" data support for collaborative management of multi-manufacturer equipment.

[0024] Furthermore, step S3 specifically includes: S3.1. Collect equipment configuration parameters, physical location distribution, and joint commissioning feedback results of similar power grid stations over the past 5 years to obtain historical joint commissioning data of the stations. The joint commissioning feedback results include signal transmission delay, fault triggering accuracy, and parameter matching error. S3.2. Extract influencing factor variables from the historical commissioning data of the station and determine the core influencing factors. The core influencing factors include equipment spacing, equipment compatibility, parameter configuration deviation, electromagnetic interference intensity, and communication protocol type. Among them, the device spacing comes from the spacing matrix of the physical location information packet, the device compatibility comes from the compatibility matrix, the parameter configuration deviation is the difference between the configuration parameter and the standard parameter, the electromagnetic interference intensity comes from the electromagnetic interference threshold set, and the communication protocol type comes from the parameter vector.

[0025] S3.3. Normalize the core influencing factors to obtain a normalized set of influencing factors. The normalization process uses the min-max standardization formula, where the equipment compatibility factor is a 0-1 variable, and the normalized value of the communication protocol type is the ratio of the protocol type to the total number of protocol types. S3.4. The normalized set of influencing factors is used as the input feature, and the signal transmission delay, fault triggering accuracy, and parameter matching error are used as the output labels. The equipment configuration parameters, physical location distribution, and joint commissioning feedback results of similar power grid stations in the past 5 years are divided into training set and test set in a 7:3 ratio. The model is then trained further. The training model parameters include the number of decision trees, node splitting threshold, and feature importance weight, thereby outputting the initial prediction model. S3.5. Combining the spacing matrix and electromagnetic interference threshold set in the physical location information packet, adjust the weight coefficients of each influencing factor to minimize the model prediction error; The gradient boosting algorithm is used to adjust the weight coefficients of each influencing factor. The weight coefficients of each influencing factor include the weight coefficients of equipment spacing, equipment compatibility, parameter configuration deviation, electromagnetic interference intensity, and communication protocol type. The objective function that minimizes the model's prediction error is: ; In the formula, Let be the model prediction loss function to be minimized, representing the degree of prediction error of the model influenced by the joint feedback. The goal is to minimize this value. This represents the sample size of the historical joint debugging data. For the first The actual feedback metrics corresponding to each sample For the first The model prediction value corresponding to each sample; S3.6. Determine the mean absolute error and coefficient of determination of the initial prediction model using test set data, and further output the final joint-tuning feedback influence factor model; The formula for calculating the mean absolute error is as follows: ; The formula for calculating the coefficient of determination is: ; In the formula, To provide the average of the feedback indicators, when Less than or equal to 0.05 and When the value is greater than or equal to 0.9, the final joint feedback influence factor model is output.

[0026] Specifically, after step S3.6 is executed, it is also necessary to extract the priority ranking of the influencing factors based on the final joint debugging feedback influencing factor model. According to the size of the feature weight coefficients (equipment spacing weight coefficient, equipment compatibility weight coefficient, parameter configuration deviation weight coefficient, electromagnetic interference intensity weight coefficient, and communication protocol type weight coefficient), it is determined that the physical location-related factors (equipment spacing and electromagnetic interference intensity) have a higher priority than the compatibility factor (equipment compatibility) and the protocol factor (communication protocol type). This provides a weight basis for subsequent parameter configuration and ensures that the influence of physical location on joint debugging feedback is given priority.

[0027] Understandably, by collecting equipment configuration parameters, physical location distribution, and joint commissioning feedback results (including core data such as signal transmission delay and fault triggering accuracy) from similar power grid stations over many years, a high-quality data foundation covering multiple scenarios and long periods is provided for the construction of the joint commissioning feedback influencing factor model. This avoids model limitations caused by insufficient data sample size or single scenario, ensuring that the model can fit the actual joint commissioning needs of the stations. Core influencing factors such as equipment spacing, equipment compatibility, parameter configuration deviation, electromagnetic interference intensity, and communication protocol type are accurately extracted from historical data, and irrelevant variables are eliminated, allowing the model to focus on the key driving factors of the joint commissioning effect, improving the targeting and effectiveness of subsequent predictions. The core influencing factors are normalized to eliminate differences in data scale between different factors (such as the dimensional difference between equipment spacing in meters and compatibility values ​​in 0-1), providing a unified standard for fair calculation of model input features and preventing the large numerical range of a certain type of factor from dominating the model's prediction results. The normalized factors are then... As input and joint commissioning feedback indicators as output, the training and test sets are scientifically divided and the model is trained. Simultaneously, parameters such as the number of decision trees and node splitting thresholds are optimized to ensure the model has good generalization ability and can adapt to joint commissioning scenarios of different scales and equipment combinations. The weight coefficients of each influencing factor are adjusted based on the actual physical location information of the site (spacing matrix, electromagnetic interference threshold) to ensure that the model prediction does not deviate from actual spatial constraints, avoiding a disconnect between theoretical predictions and on-site joint commissioning effects, and further reducing model prediction errors. The mean absolute error (MAE) and coefficient of determination (R²) are calculated using test set data to verify model performance, ensuring that the prediction accuracy of the final output joint commissioning feedback influencing factors meets the standards (e.g., MAE ≤ 0.05, R² ≥ 0.9). This provides a reliable quantitative basis for subsequent AI algorithms to generate initial configuration parameters and analyze the causes of unqualified equipment during joint commissioning, avoiding reliance on manual experience to judge joint commissioning influencing factors, significantly improving the scientific nature and efficiency of joint commissioning planning, and reducing trial-and-error costs.

[0028] Furthermore, step S4 specifically includes: S4.1. Based on the parameter vector set and the joint feedback influence factor model, determine the optimization objective of the AI ​​algorithm; The optimization objectives include minimizing parameter configuration deviations and commissioning costs while meeting equipment operation safety constraints and joint debugging feedback index constraints. S4.2. Initialize the particle swarm population. Each particle corresponds to a set of device configuration parameter schemes. The particle dimension is the product of the number of devices and the number of parameters (e.g., if each device contains 5 configuration parameters, then the particle dimension is the number of devices × 5). The initial particle value is generated based on the initial parameters in the parameter vector set and the influence factor weights of the model. S4.3. Constructing the fitness function: ; in, The configuration parameter scheme for the particles. For parameter deviation, To reduce the cost of joint commissioning, To constrain violations and penalties, , , All are fitness function weights; The formula for calculating parameter deviation is: ; In the formula, For the first in the plan The first of the equipment One configuration parameter, For the first The first of the equipment The standard parameters corresponding to each configuration parameter This represents the total number of parameters. Specifically, if safety constraints are violated... , It is a relatively large constant. The cost of joint commissioning is positively correlated with the difficulty of parameter matching; S4.4. Construct velocity update formulas and position update formulas, and iteratively update the position and velocity of the particle swarm; The speed update formula is as follows: ; In the formula, For inertial weights, , As a learning factor, , A random number in the range [0,1]. For the first The particle in the first The optimal position of the individual in the next iteration. For the first The particle in the first The global optimal position at the next iteration. For the first The particle in the first Speed ​​at the next iteration In the The first particle The current velocity at the next iteration; The position update formula is: ; In the formula, For the first The particle in the first The displacement at the next iteration For the first The particle in the first The current displacement at the next iteration; S4.5. Obtain a fitness value once for each iteration, and after each iteration, predict the joint debugging feedback index corresponding to the current parameter scheme X through the joint debugging feedback influence factor model. If the joint debugging feedback index does not meet the constraints, adjust the particle velocity direction and increase the optimization intensity of the parameters corresponding to the high priority influence factors. S4.6. When the number of iterations reaches the preset maximum value or the change in the global optimal fitness value is less than or equal to the preset iteration change threshold for 10 consecutive iterations, stop the iteration and output the parameter scheme corresponding to the global optimal particle, which is the initial configuration parameter set of each device. The initial configuration parameter set for each device includes core configuration items such as the turns ratio parameters of the high-voltage transformer, the breaking capacity parameters of the circuit breaker, and the protection settings of the relay protection device. The preset iterative change threshold is 10. -4 ; S4.7. Call the power grid equipment safe operation standard database to perform safety verification on the initial configuration parameter set of each device, thereby determining the verified initial configuration parameter set; Specifically, security verification refers to the process of verifying the value of a parameter in the initial configuration parameter set of each device through a security verification function. Indicates that the parameters are safe, and indicates that the parameters are abnormal. For abnormal parameters, the final joint debugging feedback influence factor model is used for re-optimization until all parameters meet the requirements. The final output is the verified initial configuration parameter set. For the initial configuration parameter set, each is a set of parameters. Each includes a set of core configuration items such as the turns ratio parameters of a high-voltage transformer, the breaking capacity parameters of a circuit breaker, and the protection settings of a relay protection device.

[0029] Understandably, by combining parameter vector sets with the joint debugging feedback influencing factor model, the optimization objective of the AI ​​algorithm—"minimizing parameter configuration deviation and joint debugging cost"—is clarified under the dual premises of "meeting equipment operation safety constraints and joint debugging feedback index constraints." This avoids parameter generation falling into a single orientation of "emphasizing accuracy over safety" or "controlling cost over joint debugging effect," thus defining a scientific boundary for subsequent parameter optimization and ensuring that the initial configuration parameters meet both the bottom line of equipment safe operation and reduce joint debugging resource consumption. By initializing the particle swarm population, each particle corresponds to a complete set of equipment configuration parameter schemes, and the particle dimension matches the actual requirement of "number of devices × number of parameters." The initial particle values ​​are generated by combining parameter vectors and influencing factor weights, breaking the limitations of traditional manual formulation of single parameter schemes based on experience. This enables parallel exploration of multiple parameter schemes, covering more potential suitable combinations and reducing the risk of rework in subsequent joint debugging due to a single scheme. By constructing a fitness function that integrates "parameter bias, joint debugging cost, and constraint violation penalty," and balancing the influence of these three factors through weighting coefficients, the originally abstract "quality of parameter schemes" is transformed into a quantifiable numerical indicator. This replaces the traditional method that relies on the subjective judgment of technicians regarding the rationality of parameters, making scheme evaluation more objective and consistent, and avoiding parameter configuration bias caused by individual experience differences. By constructing a velocity and position update formula for iterative optimization of the particle swarm, and combining it with a joint debugging feedback influence factor model, the joint debugging index of the current parameter scheme is predicted in real time. If constraints are not met, the particle velocity direction is dynamically adjusted, and the parameter optimization intensity of high-priority influence factors is strengthened. At the same time, stopping conditions such as "upper limit of iteration count" and "stable threshold of global optimal fitness value" are set to ensure that parameter optimization converges towards a better direction while avoiding meaningless over-iteration, thus balancing optimization accuracy and efficiency. By calling the power grid equipment safety operation standard database, the generated initial configuration parameter set is verified for safety. For parameters that are found to be abnormal (such as protection settings that exceed safety thresholds or communication protocol parameters that do not conform to operating specifications), the parameters are re-optimized in conjunction with the joint commissioning feedback impact factor model, forming a closed loop of "parameter generation - safety verification - anomaly correction". This avoids the triggering of faults during equipment joint commissioning due to parameter safety hazards (such as malfunction of protection devices or equipment overload), and lays a solid safety foundation for the subsequent automatic deployment and joint commissioning of equipment.

[0030] Furthermore, step S5 specifically includes: S5.1. Read the unique identification code of the equipment on site, combine it with the equipment information database, query the core information of the power grid equipment corresponding to the unique identification code, complete the preliminary verification of the equipment identity, and output the identity verification result; S5.2. Based on the equipment size parameters and the point spacing matrix, optimize the equipment installation sequence and output the installation point allocation results. The optimization of the equipment installation sequence adopts a greedy algorithm, prioritizing the deployment of core control equipment (such as relay protection devices) and then deploying auxiliary equipment (such as current transformers). S5.3. Based on the installation point allocation results and the three-dimensional scene model of the site, plan the optimal path for the equipment from the entrance to the installation point, and further output a set of scheduling instructions, including information such as path coordinates, transportation type, and arrival time window; Specifically, the optimal path for planning equipment from the entrance to the installation point is determined using the A* algorithm.

[0031] S5.4. After the equipment arrives on site, collect real-time status data of the equipment (such as battery power and appearance integrity), compare it with the preset standard status data, output the status detection results, and trigger the manufacturer's after-sales response mechanism for abnormal equipment; S5.5. Based on the communication protocol parameters in the initial configuration parameter set, the system automatically switches to the corresponding communication mode, verifies the networking compatibility between devices through the compatibility matrix, establishes the device interconnection topology, and outputs the networking results. The networking results include a list of connected devices for any device p. S5.6. Transmit the parameter set corresponding to the device in the initial configuration parameter set to the device's control unit through an encrypted communication channel, verify the integrity of the parameter set transmission, and output the parameter transmission result. The device's control unit can be the device's own control system. S5.7. For devices that fail to push, analyze the reasons for the failure, such as communication interruption and device incompatibility. If it is a communication problem, re-establish the communication connection and push again. If it is a compatibility problem, re-optimize the parameter set of the corresponding device until all device parameters are successfully pushed. Finally, output a device deployment completion signal.

[0032] Understandably, by reading the unique identifier of each device and combining it with the device information database to complete identity verification, the system ensures accurate matching of the identities of multiple manufacturers' devices connected to the site. Based on device size parameters and point spacing matrices, the system optimizes the installation sequence and plans the optimal path for devices to arrive at the site using a 3D scene model, improving the orderliness of device deployment and transportation efficiency. Real-time status data of arriving devices is collected and compared with preset standards, triggering timely after-sales responses from manufacturers for abnormal devices and proactively eliminating potential equipment problems during the deployment phase. The system automatically switches communication modes according to the communication protocols in the initial configuration parameters, verifies the network compatibility between devices through a compatibility matrix, and constructs a stable device interconnection topology. Encrypted communication channels are used to transmit device parameters and verify transmission integrity, ensuring the security and accuracy of parameter push. For devices that fail to push parameters, the system categorizes and resolves them according to communication or compatibility issues, repeatedly trying to ensure that all devices can successfully receive the adapted parameters. Ultimately, this achieves fully automated deployment and connection of multiple manufacturers' devices from identity verification, arrival scheduling, status detection, and parameter delivery, providing an efficient and reliable hardware and parameter foundation for subsequent device interconnection and interoperability testing.

[0033] Furthermore, step S6 specifically includes: S6.1. Simulate the normal operation and fault triggering conditions of the power grid, collect the operating data of each device, including signal transmission delay, fault response time, parameter matching accuracy, and data transmission packet loss rate, and output the joint debugging test data set, wherein each element in the joint debugging test data set contains multi-condition test data of a single device. S6.2. Determine the comprehensive indicators for joint commissioning feedback; The formula for calculating the comprehensive index of joint commissioning feedback is as follows: ; In the formula, For the first Comprehensive indicators of joint debugging feedback from the equipment. , For the first Normalized latency and response time of the device. For the first Accuracy of parameter matching for each device. For the first Data transmission packet loss rate of the device , , , These are the weighting coefficients for signal transmission delay, fault response time, parameter matching accuracy, and data transmission packet loss rate (the sum of which is 1). S6.3. Based on the joint commissioning feedback comprehensive index, determine the comprehensive index set. For equipment in the comprehensive index set that fails the joint commissioning feedback comprehensive index (equipment with a joint commissioning feedback comprehensive index less than 0.9, where 0.9 is an empirical threshold), combine the joint commissioning feedback influencing factor model to analyze the core influencing factors. If it is related to physical location, extract the point coordinates and spacing of the equipment and determine the optimal spacing after adjustment. The formula for calculating the adjusted optimal spacing is as follows: ; In the formula, For the first The optimal spacing after adjustments for equipment whose overall performance indicators failed to meet the requirements of the joint commissioning feedback. For the first The spacing of equipment that failed to meet the overall performance indicators reported by the joint commissioning system before adjustment. This is the spacing adjustment amount; S6.4. If the core influencing factor is parameter deviation, then adjust the parameters using the gradient descent formula; The gradient descent formula is as follows: ; In the formula, For the first The adjusted configuration parameter set for equipment whose overall performance indicators failed the joint commissioning feedback. For the first The initial configuration parameter set of equipment whose overall performance indicators failed the joint commissioning feedback before adjustment. For learning rate, As a standard comprehensive indicator for joint debugging feedback, For the first The current integrated performance indicators of the equipment under joint commissioning. The gradient of the fitness function at the initial parameter set; S6.5. Restart the joint debugging test, collect the adjusted equipment operation data, obtain the new joint debugging feedback comprehensive index, and compare it with the new joint debugging feedback comprehensive index. Integrated indicators of joint debugging feedback Change ; like and The equipment has passed the commissioning process. like or Then repeat steps S6.3-S6.4 until... ; in, , In This represents the number of iterations for equipment integration and testing.

[0034] Furthermore, the commissioning pass rate of all equipment is statistically analyzed. When the pass rate is ≥99%, the iterative optimization is stopped and the final configuration parameter set is output. If the pass rate is <99%, the common problems of the non-passing equipment (such as equipment quality defects from the manufacturer) are analyzed, and a special handling process is triggered. The final configuration parameter set, joint commissioning feedback data, physical location adjustment records and other information are stored in the database DB, and the historical joint commissioning data set is updated to provide data support for the configuration planning of similar sites in the future. At the same time, a configuration planning report is generated, which includes equipment list, parameter configuration details, joint commissioning test results (such as the percentage reduction in commissioning cycle and the degree of reduction in dependence on manufacturer personnel).

[0035] Specifically, To iteratively adjust the threshold for the amount of change, it is typically set to 0.05. The value is 0.9. Power systems typically require core equipment commissioning indicators (such as relay protection operation accuracy, signal transmission reliability, and parameter matching accuracy) to be ≥90% (industry-standard acceptance criteria); while the comprehensive commissioning feedback indicator is the weighted sum of these indicators (with a total weight of 1). A threshold of 0.9 corresponds to "all sub-indicators meet the industry's minimum practical standards" (e.g., parameter matching accuracy ≥ 90%, data packet loss rate ≤ 10%, fault response delay ≤ the upper limit of milliseconds allowed by the power grid). This not only meets the core requirement of "stable equipment operation without triggering safety risks" but also avoids the problem of a surge in the number of joint debugging iterations and a significant extension of the debugging cycle due to excessively high thresholds (e.g., 0.95). The threshold for iterative adjustment of the change amount is usually set to 0.05. This is because if the threshold is too small (e.g., 0.01), the improvement in the overall index after a single adjustment is negligible, easily leading to ineffective iterations of "repeated adjustments with little effect." 0.05 corresponds to "significant improvement in sub-indicators" (e.g., an increase in parameter matching accuracy from 85% to 90%, contributing exactly about 0.05 to the overall index increase), clearly demonstrating the actual effect of the adjustment measures. If the threshold is too large (e.g., 0.1), significant adjustments to equipment parameters (e.g., relay protection settings, communication protocol thresholds) are required, easily causing parameters to deviate from safe ranges (e.g., overly aggressive protection settings may trigger equipment malfunctions). A threshold of 0.05 corresponds to "small, precise optimization of parameters," ensuring index improvement without exceeding the equipment's safe operating boundaries.

[0036] Furthermore, a station equipment configuration planning system based on equipment commissioning feedback is proposed to implement any of the planning methods mentioned above, including: The physical location sensing module is used to acquire scene maps and construction planning schemes of power grid stations in the power system, and extract the physical location information of station equipment. The equipment information database module is used to collect basic information such as model parameters, communication protocols, and operating thresholds of power grid equipment from various manufacturers to establish an equipment information database. The impact factor modeling module is used to collect historical commissioning data of the station and, based on the historical commissioning data, equipment compatibility data, and physical location information of the station equipment, construct a commissioning feedback impact factor model. The initial parameter generation module is used to generate the initial configuration parameter set for each device based on the device information database and the joint debugging feedback influence factor model. The automatic equipment deployment module is used to automatically identify multi-vendor equipment in the access site based on the initial configuration parameter set, complete equipment identity verification and network matching, and further schedule equipment from each vendor to automatically deploy to the site according to the planned physical location, while simultaneously pushing the appropriate configuration parameters. The joint debugging parameter optimization module is used to initiate equipment interconnection and interoperability testing, collect feedback data on signal transmission delay, fault trigger response speed, and parameter matching accuracy during the joint debugging process, compare the feedback data with preset standard thresholds, iteratively optimize configuration parameters until the joint debugging requirements are met, and complete the configuration planning.

[0037] Furthermore, the physical location sensing module includes: The multi-source scene data acquisition unit is used to acquire terrain data, building layout data, and preset equipment installation area data of the site simultaneously by using LiDAR scanning, UAV aerial photography, and GIS geographic information collection, and output a set of multi-source raw scene data. The scene data preprocessing unit is used to preprocess the multi-source original scene data in the multi-source original scene data set to obtain a preprocessed clean data set. The 3D scene modeling unit is used to build a 3D scene model of the site based on the clean data set. Using the geodetic coordinate system as the reference, it maps the preprocessed terrain elevation data, building outline coordinate data, and installation area boundary data to the 3D space to generate a complete model containing terrain, buildings, and installation area. The location parameter extraction unit is used to extract the core parameters of the physical location of the equipment from the 3D scene model, identify the fixed points of the equipment within the installation area, and output the 3D coordinates of each point to form a set of point coordinates. Spacing matrix construction unit: This unit is used to obtain the physical spacing between adjacent device points and construct a spacing matrix. The electromagnetic threshold calculation unit is used to determine the electromagnetic interference threshold of each point based on the spacing matrix, taking into account the electromagnetic interference characteristics of power grid equipment, and further outputting a threshold set. The physical information integration unit is used to integrate the set of point coordinates, the spacing matrix, and the set of electromagnetic interference thresholds to form a complete physical location information package.

[0038] Furthermore, the joint debugging parameter optimization module includes: The joint commissioning data acquisition unit is used to simulate the normal operation and fault triggering conditions of the power grid, collect the operating data of each device, including signal transmission delay, fault response time, parameter matching accuracy, data transmission packet loss rate, and output a set of joint commissioning test data. The comprehensive indicator calculation unit is used to determine the comprehensive indicators for joint commissioning feedback. The influencing factor analysis unit is used to determine the comprehensive index set based on the joint commissioning feedback comprehensive index. For equipment in the comprehensive index set that fails the joint commissioning feedback comprehensive index, the core influencing factors are analyzed in conjunction with the joint commissioning feedback influencing factor model. The parameter / position adjustment unit is used to adjust the equipment parameters and position based on the core influencing factors. If it is related to the physical location, the unit extracts the point coordinates and spacing of the equipment and determines the optimal spacing after adjustment. If the core influencing factor is parameter deviation, the unit adjusts the parameters using the gradient descent formula. The joint debugging and iterative verification unit is used to restart the joint debugging test, collect the adjusted equipment operation data, obtain the new joint debugging feedback comprehensive index, compare the changes of the new joint debugging feedback comprehensive index with the original joint debugging feedback comprehensive index, and determine whether the equipment joint debugging is qualified. If it is not qualified, the adjustment steps are repeated. The configuration planning completion unit is used to complete the configuration planning until the joint debugging requirements are met.

[0039] The advantages of this invention are as follows: It constructs a data-driven technical system covering the entire process from site spatial planning to equipment commissioning optimization. It collects site physical location information through multi-source fusion and constructs a 3D model with electromagnetic interference threshold constraints. Combined with a standardized database of equipment from multiple manufacturers and historical commissioning data, it trains a commissioning feedback influencing factor model. Relying on AI algorithms, it generates an initial configuration parameter set that balances safety constraints and cost optimization. This enables fully automated deployment of equipment from multiple manufacturers, from automatic identity verification, installation path planning, network compatibility verification to encrypted parameter push. Furthermore, it collects commissioning data under simulated operating conditions, calculates comprehensive indicators, and iteratively optimizes parameters based on gradient adjustment and location optimization. The entire process deeply integrates the characteristics of power equipment, electromagnetic physics laws, and industry acceptance standards. Through a collaborative design of "spatial constraints – data modeling – intelligent optimization – closed-loop verification," it efficiently solves core problems such as compatibility adaptation, spatial interference, and blind parameter configuration in multi-manufacturer equipment commissioning. Simultaneously, it ensures equipment operational reliability through safety verification mechanisms and quantitative threshold control. Ultimately, it achieves scientific site configuration planning, automated deployment processes, and stable commissioning effects, effectively supporting the rapid commissioning and intelligent operation needs of power grid sites.

[0040] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A method for planning the configuration of station equipment based on equipment commissioning feedback, characterized in that, include: S1. Obtain scene diagrams and construction planning schemes for power grid substations in the power system, and extract the physical location information of substation equipment; S2. Collect basic information on the model parameters, communication protocols, and operating thresholds of power grid equipment from various manufacturers, and establish an equipment information database; S3. Collect historical commissioning data of the station, and construct a commissioning feedback influencing factor model based on the historical commissioning data, equipment compatibility data and physical location information of the station equipment; S4. Based on the equipment information database and the joint debugging feedback impact factor model, generate the initial configuration parameter set for each device; S5. Based on the initial configuration parameter set, automatically identify multi-vendor equipment in the access site, complete equipment identity verification and network matching, further schedule equipment from each vendor to automatically arrive at the site for deployment according to the planned physical location, and synchronously push the appropriate configuration parameters; S6. Initiate equipment interconnection and interoperability testing, collect feedback data on signal transmission delay, fault trigger response speed, and parameter matching accuracy during the joint debugging process, compare the feedback data with the preset standard threshold, iteratively optimize the configuration parameters until the joint debugging requirements are met, and complete the configuration planning.

2. The method for planning the configuration of station equipment based on equipment commissioning feedback according to claim 1, characterized in that, Step S1 specifically includes: S1.

1. Using laser-excited radar scanning, UAV aerial photography, and GIS geographic information collection, the terrain data, building layout data, and preset equipment installation area data of the site are acquired simultaneously, and a multi-source original scene data set is output. The multi-source original scene data set includes terrain elevation data, building outline coordinate data, and installation area boundary data. S1.

2. Preprocess the multi-source original scene data in the multi-source original scene data set to obtain a preprocessed clean data set; S1.

3. Construct a three-dimensional scene model of the site based on the clean data set. Using the geodetic coordinate system as the reference, map the preprocessed terrain elevation data, building outline coordinate data, and installation area boundary data to the three-dimensional space to generate a complete model containing terrain, buildings, and installation area. S1.

4. Extract the core parameters of the physical location of the equipment from the 3D scene model, identify the fixed points of the equipment within the installation area, output the 3D coordinates of each point, and form a set of point coordinates; S1.

5. Obtain the physical distance between adjacent device locations and construct a distance matrix; The formula for calculating the physical distance between adjacent equipment points is as follows: ； In the formula, For any two points in the set of point coordinates and The spacing, , , Points The coordinate values ​​on the X, Y, and Z axes, , , Points Coordinate values ​​on the X, Y, and Z axes; The formula for expressing the spacing matrix is: ； In the formula, Number of points; S1.

6. Combining the electromagnetic interference characteristics of power grid equipment, determine the electromagnetic interference threshold for each point based on the spacing matrix, and further output the threshold set; The formula for calculating the electromagnetic interference threshold is as follows: ； In the formula, For point The corresponding electromagnetic interference threshold, The electromagnetic attenuation coefficient, The rated power of adjacent equipment; S1.

7. Integrate the set of point coordinates, spacing matrix, and electromagnetic interference threshold set to form a complete physical location information package.

3. The method for planning the configuration of station equipment based on equipment commissioning feedback according to claim 2, characterized in that, Step S2 specifically includes: S2.

1. Collect core information of power grid equipment from various manufacturers through manufacturer interfaces, equipment manual parsing, and industry standard databases, including equipment model, rated voltage, rated current, communication protocol type, protection action threshold, equipment size parameters, and compatibility adaptation list, and output the original equipment information set. S2.

2. Standardize the original equipment information in the original equipment information set and output a standardized information set; S2.

3. Based on the z-axis height data in the point coordinate set and the height value in the equipment size parameters, determine whether the equipment installation space meets the equipment installation space constraint inequality, and further output the adaptability verification result; The compatibility verification result includes a device compatibility value, where a device compatibility value of 1 indicates compatibility and a device compatibility value of 0 indicates incompatibility. The formula for expressing the inequality regarding the equipment installation space constraint is: ； In the formula, For the first The height value in the equipment dimension parameters corresponding to each device. Elevation of the installation surface For the first The set of point coordinates corresponding to each device is the first Z-axis height data for each fixed point of the equipment; S2.

4. Extract compatibility data of the adapted devices, filter out devices with a device compatibility value of 1 from the standardized information set, and further obtain cross-matching results from the compatibility compatibility list to construct a compatibility matrix; The compatibility matrix is ​​expressed as follows: ； In the formula, Indicates compatibility, This indicates incompatibility. To accommodate the number of devices; S2.

5. Establish an equipment information database, which includes a basic parameter table, a communication protocol table, a compatibility table, a physical adapter table, and a manufacturer service data table.

4. The method for planning the configuration of station equipment based on equipment commissioning feedback according to claim 3, characterized in that, Step S3 specifically includes: S3.

1. Collect equipment configuration parameters, physical location distribution, and joint commissioning feedback results of similar power grid stations over the past 5 years to obtain historical joint commissioning data of the stations. The joint commissioning feedback results include signal transmission delay, fault triggering accuracy, and parameter matching error. S3.

2. Extract influencing factor variables from the historical commissioning data of the station and determine the core influencing factors. The core influencing factors include equipment spacing, equipment compatibility, parameter configuration deviation, electromagnetic interference intensity, and communication protocol type. S3.

3. Normalize the core impact factors to obtain a normalized set of impact factors; S3.

4. The normalized set of influencing factors is used as the input feature, and the signal transmission delay, fault triggering accuracy, and parameter matching error are used as the output labels. The equipment configuration parameters, physical location distribution, and joint commissioning feedback results of similar power grid stations in the past 5 years are divided into training set and test set in a 7:3 ratio. The model is then trained further. The training model parameters include the number of decision trees, node splitting threshold, and feature importance weight, thereby outputting the initial prediction model. S3.

5. Combining the spacing matrix and electromagnetic interference threshold set in the physical location information packet, adjust the weight coefficients of each influencing factor to minimize the model prediction error; The weighting coefficients of each influencing factor include the weighting coefficients for equipment spacing, equipment compatibility, parameter configuration deviation, electromagnetic interference intensity, and communication protocol type. S3.

6. Determine the mean absolute error and coefficient of determination of the initial prediction model using test set data, and further output the final joint feedback influence factor model.

5. The method for site equipment configuration planning based on equipment commissioning feedback according to claim 4, characterized in that, Step S4 specifically includes: S4.

1. Based on the parameter vector set and the joint feedback influence factor model, determine the optimization objective of the AI ​​algorithm; The optimization objective includes minimizing parameter configuration deviations and joint debugging costs while meeting equipment operation safety constraints and joint debugging feedback index constraints. S4.

2. Initialize the particle swarm population. Each particle corresponds to a set of device configuration parameter schemes. The particle dimension is the product of the number of devices and the number of parameters. The initial value of the particle is generated based on the initial parameters in the parameter vector set and the influence factor weights of the model. S4.

3. Constructing the fitness function: ； in, The configuration parameter scheme for the particles. For parameter deviation, To reduce the cost of joint commissioning, To constrain violations and penalties, , , All are fitness function weights; The formula for calculating the parameter deviation is: ； In the formula, For the first in the plan The first of the equipment One configuration parameter, For the first The first of the equipment The standard parameters corresponding to each configuration parameter This represents the total number of parameters. S4.

4. Construct velocity update formulas and position update formulas, and iteratively update the position and velocity of the particle swarm; The speed update formula is as follows: ； In the formula, For inertial weights, , As a learning factor, , A random number in the range [0,1]. For the first The particle in the first The optimal position of the individual in the next iteration. For the first The particle in the first The global optimal position at the next iteration. For the first The particle in the first Speed ​​at the next iteration In the The first particle The current velocity at the next iteration; The position update formula is: ； In the formula, For the first The particle in the first The displacement at the next iteration For the first The particle in the first The current displacement at the next iteration; S4.

5. Obtain a fitness value once for each iteration, and after each iteration, predict the joint debugging feedback index corresponding to the current parameter scheme X through the joint debugging feedback influence factor model. If the joint debugging feedback index does not meet the constraints, adjust the particle velocity direction and increase the optimization intensity of the parameters corresponding to the high priority influence factors. S4.

6. When the number of iterations reaches the preset maximum value or the change in the global optimal fitness value is less than or equal to the preset iteration change threshold for 10 consecutive iterations, stop the iteration and output the parameter scheme corresponding to the global optimal particle, which is the initial configuration parameter set of each device. S4.

7. Call the power grid equipment safe operation standard database to perform safety verification on the initial configuration parameter set of each device, thereby determining the verified initial configuration parameter set.

6. The method for planning the configuration of station equipment based on equipment commissioning feedback according to claim 5, characterized in that, Step S5 specifically includes: S5.

1. Read the unique identification code of the equipment on site, combine it with the equipment information database, query the core information of the power grid equipment corresponding to the unique identification code, complete the preliminary verification of the equipment identity, and output the identity verification result; S5.

2. Based on equipment size parameters and point spacing matrix, optimize equipment installation sequence and output installation point allocation results; S5.

3. Based on the installation point allocation results and the three-dimensional scene model of the site, plan the optimal path for the equipment from the entrance to the installation point, and further output a set of scheduling instructions; S5.

4. After the equipment arrives on site, collect the real-time status data of the equipment, compare it with the preset standard status data, output the status detection results, and trigger the manufacturer's after-sales response mechanism for abnormal equipment; S5.

5. Based on the communication protocol parameters in the initial configuration parameter set, the system automatically switches to the corresponding communication mode, verifies the networking compatibility between devices through the compatibility matrix, establishes the device interconnection topology, and outputs the networking results; S5.

6. Transmit the parameter set corresponding to the device in the initial configuration parameter set to the device control unit through an encrypted communication channel, verify the integrity of the parameter set transmission, and output the parameter transmission result; S5.

7. For devices that fail to push, analyze the reason for the failure. If it is a communication problem, re-establish the communication connection and push again. If it is a compatibility problem, re-optimize the parameter set of the corresponding device until all device parameters are successfully pushed. Finally, output a device deployment completion signal.

7. The method for site equipment configuration planning based on equipment commissioning feedback according to claim 6, characterized in that, Step S6 specifically includes: S6.

1. Simulate the normal operation and fault triggering conditions of the power grid, collect the operating data of each device, including signal transmission delay, fault response time, parameter matching accuracy, data transmission packet loss rate, and output the joint debugging test data set; S6.

2. Determine the comprehensive indicators for joint commissioning feedback; The calculation formula for the integrated index of joint debugging feedback is as follows: ； In the formula, For the first Comprehensive indicators of joint debugging feedback from the equipment. , For the first Normalized latency and response time of the device. For the first Accuracy of parameter matching for each device. For the first Data transmission packet loss rate of the device , , , These are the weighting coefficients corresponding to signal transmission delay, fault response time, parameter matching accuracy, and data transmission packet loss rate, respectively. S6.

3. Based on the integrated index of joint commissioning feedback, determine the set of integrated indexes. For equipment in the integrated index set that fails the integrated index of joint commissioning feedback, analyze the core influencing factors in conjunction with the joint commissioning feedback influencing factor model. If it is related to physical location, extract the point coordinates and spacing of the equipment and determine the optimal spacing after adjustment. The formula for calculating the adjusted optimal spacing is as follows: ； In the formula, For the first The optimal spacing after adjustments for equipment whose overall performance indicators failed to meet the requirements of the joint commissioning feedback. For the first The spacing of equipment that failed to meet the overall performance indicators reported by the joint commissioning system before adjustment. This is the spacing adjustment amount; S6.

4. If the core influencing factor is parameter deviation, then adjust the parameters using the gradient descent formula; The gradient descent formula is as follows: ； In the formula, For the first The adjusted configuration parameter set for equipment whose overall performance indicators failed the joint commissioning feedback. For the first The initial configuration parameter set of equipment whose overall performance indicators failed the joint commissioning feedback before adjustment. For learning rate, As a standard comprehensive indicator for joint debugging feedback, For the first The current integrated performance indicators of the equipment under joint commissioning. The gradient of the fitness function at the initial parameter set; S6.

5. Restart the joint debugging test, collect the adjusted equipment operation data, obtain the new joint debugging feedback comprehensive index, and compare it with the new joint debugging feedback comprehensive index. Integrated indicators of joint debugging feedback Change ; like and The equipment has passed the commissioning process. like or Then repeat steps S6.3-S6.4 until... ; in, , In This represents the number of iterations for equipment integration and testing.

8. A station equipment configuration planning system based on equipment commissioning feedback, used to implement the planning method as described in any one of claims 1-7, characterized in that, include: The physical location sensing module is used to acquire scene maps and construction planning schemes of power grid stations in the power system, and extract the physical location information of station equipment. The equipment information database construction module is used to collect basic information such as model parameters, communication protocols, and operating thresholds of power grid equipment from various manufacturers to establish an equipment information database. The impact factor modeling module is used to collect historical joint commissioning data of the station and, based on the historical joint commissioning data, equipment compatibility data and physical location information of the station equipment, construct a joint commissioning feedback impact factor model. An initial parameter generation module is used to generate an initial configuration parameter set for each device based on the device information database and the joint debugging feedback influence factor model. The automatic equipment deployment module is used to automatically identify multi-vendor equipment in the access site based on the initial configuration parameter set, complete equipment identity verification and network matching, and further schedule the equipment of each vendor to automatically arrive at the site for deployment according to the planned physical location, and synchronously push the appropriate configuration parameters. The joint debugging parameter optimization module is used to initiate equipment interconnection and interoperability testing, collect feedback data on signal transmission delay, fault trigger response speed, and parameter matching accuracy during the joint debugging process, compare the feedback data with preset standard thresholds, iteratively optimize configuration parameters until the joint debugging requirements are met, and complete the configuration planning.

9. A station equipment configuration planning system based on equipment commissioning feedback according to claim 8, characterized in that, The physical location sensing module includes: A multi-source scene data acquisition unit is used to acquire terrain data, building layout data, and preset equipment installation area data of the site simultaneously by using lidar scanning, drone aerial photography, and GIS geographic information acquisition, and output a set of multi-source original scene data. A scene data preprocessing unit is used to preprocess the multi-source original scene data in the multi-source original scene data set to obtain a preprocessed clean data set. The three-dimensional scene modeling unit is used to construct a three-dimensional scene model of the site based on the clean data set. Using the geodetic coordinate system as a reference, the preprocessed terrain elevation data, building outline coordinate data, and installation area boundary data are mapped to the three-dimensional space to generate a complete model containing terrain, buildings, and installation areas. The location parameter extraction unit is used to extract the core parameters of the physical location of the equipment from the three-dimensional scene model, identify the fixed points of the equipment within the installation area, and output the three-dimensional coordinates of each point to form a set of point coordinates. A spacing matrix construction unit is used to obtain the physical spacing between adjacent device points and construct a spacing matrix; An electromagnetic threshold calculation unit is used to determine the electromagnetic interference threshold of each point based on the spacing matrix, taking into account the electromagnetic interference characteristics of power grid equipment, and further output a threshold set. The physical information integration unit is used to integrate the set of point coordinates, the spacing matrix, and the set of electromagnetic interference thresholds to form a complete physical location information package.

10. A station equipment configuration planning system based on equipment commissioning feedback according to claim 8, characterized in that, The joint debugging parameter optimization module includes: The joint debugging data acquisition unit is used to simulate the normal operation and fault triggering conditions of the power grid, collect the operating data of each device, including signal transmission delay, fault response time, parameter matching accuracy, data transmission packet loss rate, and output a set of joint debugging test data. A comprehensive index calculation unit is used to determine the joint debugging feedback comprehensive index; The influencing factor analysis unit is used to determine the comprehensive index set based on the joint debugging feedback comprehensive index, and to analyze the core influencing factors of equipment with unqualified joint debugging feedback comprehensive index in the comprehensive index set, combined with the joint debugging feedback influencing factor model. The parameter / position adjustment unit is used to adjust the equipment parameters and position based on the core influencing factors. If it is related to the physical location, the point coordinates and spacing of the equipment are extracted to determine the optimal spacing after adjustment. If the core influencing factor is parameter deviation, the parameters are adjusted by the gradient descent formula. The joint debugging and iterative verification unit is used to restart the joint debugging test, collect the adjusted equipment operation data, obtain the new joint debugging feedback comprehensive index, compare the change of the new joint debugging feedback comprehensive index with the original joint debugging feedback comprehensive index, and determine whether the equipment joint debugging is qualified. If it is not qualified, the adjustment steps are repeated. The configuration planning completion unit is used to complete the configuration planning until the joint debugging requirements are met.

Images