Electric power engineering design method and system based on large model

Abstract

The invention relates to the technical field of electric power engineering design, and provides an electric power engineering design method and system based on a large model, and the method comprises the steps: constructing a large model database related to electric power engineering; constructing an inference engine based on the large model database; designing requirements are defined through a user interface, a corresponding electric power engineering model and a corresponding risk assessment model are constructed, the corresponding electric power engineering model is solved to obtain an optimal electric power engineering design scheme, and the optimal electric power engineering design scheme is assessed through the corresponding risk assessment model; simulating an optimal electric power engineering design scheme through an automatic design tool, and collecting simulation data and user feedback information; and the inference engine is iterated based on simulation data and user feedback information, and the large model database is updated according to an iteration result, so that the problems that an existing electric power engineering design tool and system are single in function, relatively low in intelligent level, incapable of effectively integrating multi-source data and information and difficult to provide a comprehensive design scheme and risk assessment are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power engineering design, and in particular to a large model-based electric power engineering design method and system. Background Art

[0002] In the traditional power engineering design process, designers usually rely on personal experience and existing design specifications to complete tasks such as project planning, equipment selection, and path layout. These design activities often require a lot of time for calculation, analysis, and decision-making, and are easily limited by personal experience and knowledge. With the continuous expansion of the scale and complexity of power systems, traditional design methods have been unable to meet the needs of modern power engineering, especially in the context of rapidly changing energy markets and technological innovations.

[0003] Existing power engineering design tools and systems often have single functions, lack sufficient intelligence and automation, are unable to effectively integrate multi-source data and information, and have difficulty providing comprehensive design solutions and risk assessments. Summary of the invention

[0004] The purpose of the present invention is to provide a large-model-based power engineering design method and system, aiming to solve the problems that existing power engineering design tools and systems have single functions, low intelligence levels, cannot effectively integrate multi-source data and information, and are difficult to provide comprehensive design solutions and risk assessments.

[0005] The embodiments of the present invention are implemented by the following technical solutions:

[0006] A large model-based power engineering design method comprises the following steps:

[0007] Build a large model database related to power engineering;

[0008] Build an inference engine based on a large model database;

[0009] Define design requirements through the user interface, and the reasoning engine builds the corresponding power engineering model and the corresponding risk assessment model according to the defined design requirements, solves the corresponding power engineering model to obtain the optimal power engineering design solution, and evaluates the optimal power engineering design solution through the corresponding risk assessment model;

[0010] Use automated design tools to simulate optimal power engineering design solutions and collect simulation data and user feedback;

[0011] The inference engine is iterated based on simulation data and user feedback information, and the large model database is updated according to the iteration results.

[0012] Optionally, the specific process of constructing a large model database related to electric power engineering is:

[0013] Build a database based on equipment parameters, geographic information system data, environmental impact assessment data and historical design cases for substation and transmission projects, and synchronize it with real-time data from smart grids and sensor networks;

[0014] Standardize the data in the database and store it in a unified format and structure;

[0015] Encrypt data in the database and set access permissions.

[0016] Optionally, the specific process of building an inference engine based on a large model database is:

[0017] Preprocess the data in the large model database to obtain an initial data set;

[0018] Based on the initial data set, a design parameter model and an evaluation model are constructed, the design parameter model is optimized by an optimization algorithm to obtain an optimized design parameter model, and the evaluation result is obtained by performing risk evaluation on the optimized design parameter model by the evaluation model;

[0019] Based on the evaluation results, an initial design model is constructed through decision-making tools;

[0020] Combining historical design cases and user feedback data, the initial scheme design model is iteratively optimized through machine learning algorithms to obtain the scheme design model, and the large model database is updated based on the optimization results.

[0021] Optionally, the specific process of defining the design requirements through the user interface, the reasoning engine constructing a corresponding power engineering model according to the defined design requirements, and solving the corresponding power engineering model to obtain the optimal power engineering design solution is as follows:

[0022] Input and adjust design requirements through the user interface, and extract design parameters in the design requirements;

[0023] According to the extracted design parameters and corresponding design constraints and objectives, the corresponding power engineering model is constructed by optimizing the design parameter model;

[0024] The optimal power engineering design scheme is obtained by solving the corresponding power engineering model through optimization algorithm.

[0025] Optionally, the specific process of defining the design requirements through the user interface, the reasoning engine constructing a corresponding risk assessment model according to the defined design requirements, and evaluating the optimal power engineering design solution through the corresponding risk assessment model is as follows:

[0026] Input and adjust design requirements through the user interface, and extract design parameters and evaluation parameters in the design requirements;

[0027] According to the extracted design parameters, the optimal power engineering design scheme is established through the scheme design model, and according to the extracted evaluation parameters, the corresponding risk assessment model is constructed through the evaluation model;

[0028] Based on the large model database, the FTA model and ETA model are established. The corresponding risk assessment model evaluates the safety of the optimal power engineering design scheme, identifies the key risk points in the optimal power engineering design scheme through fault tree analysis, and tracks the probability of the final result caused by the specific initial events that trigger the key risk points through event tree analysis, and optimizes the key risk points;

[0029] Based on the large model database, the NPV model and IRR model are established. The corresponding risk assessment model is used to evaluate the economic feasibility of the optimal power engineering design scheme. The future cash flow and time value of the optimal power engineering design scheme are evaluated by solving the NPV model. The average annual rate of return of the optimal power engineering design scheme is evaluated by iteratively solving the IRR model.

[0030] Based on the large model database, an LCA model is established, and the corresponding risk assessment model is used to evaluate the environmental sustainability of the optimal power engineering design scheme. The environmental sustainability is evaluated by quantifying the environmental load of the optimal power engineering design scheme throughout its life cycle;

[0031] The corresponding risk assessment model integrates the assessment results into the risk matrix, feeds the risk matrix back to the assessment model, optimizes the assessment model, and generates a risk assessment report, which is displayed through the user interface.

[0032] Optionally, the FTA model and the ETA model are adaptively optimized and adjusted according to the large model database, collected real-time data and user feedback data, and the adaptive optimization results are updated to the risk matrix, and the structure and probability evaluation of the event tree are optimized through continuous iteration; the NPV model and the IRR model dynamically adjust the calculation parameters of the net present value and internal return according to market dynamics and project progress, identify the most economically beneficial design scheme, and give corresponding adjustment strategies, and update the corresponding parameters of the most economically beneficial design scheme to the risk matrix; environmental load data are continuously collected through the large model database, and the LCA model is continuously optimized, and the corresponding parameters of the optimized LCA model are updated to the risk matrix, the environmental risks in the design scheme are identified, and corresponding environmental improvement strategies are given.

[0033] Optionally, the specific process of simulating the optimal power engineering design solution by the automated design tool and collecting simulation data and user feedback information is as follows:

[0034] Transform key information of the optimal power engineering design scheme into specific design parameters through automated design tools;

[0035] Based on specific design parameters, the automated design tool generates a design draft according to the preset design standards and the user's design requirements;

[0036] Use automated design tools to decompose the design draft into several reusable components, each with corresponding parameters and properties;

[0037] Use automated design tools to simulate the design draft, test the performance and feasibility of the design draft, and dynamically adjust the parameters and properties of each component during the test process according to user design requirements;

[0038] Dynamically adjust and optimize the design draft according to the changes in parameters and properties of each component, collect data on each iteration and change of the design draft and users' opinions and suggestions on the automated design tool.

[0039] Optionally, an optimization algorithm is used to solve the optimal design parameter combination of the dynamically adjusted and optimized design draft; after the user confirms the optimal design parameter combination, the final design scheme is locked, and the large model database is updated based on the user's feedback and the data of the final design scheme.

[0040] Optionally, the specific process of simulating the design draft by using the automated design tool is:

[0041] Integrate computer vision systems and 3D graphics processing capabilities into automated design tools;

[0042] Through data fusion, data from different sources and different types in the design draft are integrated into a unified 3D model view;

[0043] Through deep learning networks, terrain, obstacles and existing infrastructure features are automatically identified, and augmented reality and virtual reality technologies are combined to enable users to interact with 3D models. At the same time, real-time data stream analysis is performed to monitor the construction environment or the status of existing facilities, and fit them with the 3D model to determine the feasibility of the design draft.

[0044] The present invention also provides a system for implementing the large model-based power engineering design method, comprising:

[0045] The large model database module is used to build a large model database related to power engineering, synchronize with the real-time data of smart grids and sensor networks, and standardize and encrypt the data and set access rights;

[0046] The inference engine construction module is used to build an inference engine based on a large model database, iterate the optimization scheme design model, and update the large model database according to the optimization results;

[0047] User interface module, used to provide users with an operating interface for inputting and adjusting design requirements, viewing design results and risk assessment reports, and providing feedback;

[0048] The demand modeling module is used to receive the design requirements defined by the user, extract the design parameters and evaluation parameters, build the power engineering model using the optimized design parameter model, and obtain the optimal power engineering design solution through the optimization algorithm;

[0049] The risk assessment module is used to evaluate the safety, economy and environmental sustainability of the design solution, generate a risk assessment report and display it through the user interface;

[0050] An automated design tool module that simulates optimal power engineering design solutions, tests the performance and feasibility of draft designs, and dynamically adjusts design parameters and properties based on user feedback;

[0051] The data collection and feedback module is used to collect simulation data and user feedback information, solve the optimal design parameter combination through the optimization algorithm, lock the final design solution, and update the large model database based on user feedback and the data of the final design solution;

[0052] The iterative optimization module is used to iteratively optimize the inference engine based on simulation data and user feedback information, and update the large model database.

[0053] The technical solution of the embodiment of the present invention has at least the following advantages and beneficial effects:

[0054] Improve design efficiency and accuracy: By building a large model database related to power engineering, integrating equipment parameters of substation and transmission projects, geographic information system data, environmental impact assessment data and historical design cases, it provides comprehensive and accurate data support for power engineering design. The construction and optimization of the inference engine, combined with optimization algorithms and machine learning algorithms, can automatically optimize the design scheme, improve the accuracy and innovation of the design, and reduce human errors.

[0055] Enhance the comprehensiveness and reliability of the design solution: The risk assessment model comprehensively considers the safety, economy and environmental sustainability of the design solution, and conducts multi-dimensional assessment through models such as FTA, ETA, NPV, IRR and LCA to ensure the comprehensiveness and reliability of the design solution. The risk assessment report details the results and risk mitigation measures of each assessment step, helping users understand the potential risks of the design solution and take corresponding measures;

[0056] Improve user experience and interactivity: The intuitive and responsive graphical user interface (GUI) supports users to input and adjust design requirements, provides real-time feedback and dynamic updates, and enhances the interactivity between users and the system; the user interface integrates parameter input module, requirement management module and feedback module, allowing users to easily define and track design requirements, view design results and risk assessment reports, and provide feedback;

[0057] Support for large-scale and complex projects: Automated design tools can simulate optimal power engineering design solutions, test the performance and feasibility of design drafts, and support the processing of large-scale and complex projects. Automated design tools integrate computer vision systems and 3D graphics processing functions, provide virtual environment testing, and enhance the flexibility and adaptability of design;

[0058] Achieve continuous learning and optimization: The system iteratively optimizes the inference engine by collecting simulation data and user feedback information, and updates the large model database based on the optimization results, forming a closed-loop system of continuous improvement and learning. The machine learning algorithm continuously learns from historical design cases and user feedback, optimizes the selection of design parameters, and improves the accuracy and innovation of the design solution.

[0059] Ensure data security and privacy protection: Encrypt data in the database and set access permissions to ensure the security of the database and its ability to resist external threats, strictly comply with data privacy regulations, and ensure the confidentiality of all personal and sensitive information;

[0060] Improve the geographical and environmental adaptability of the design: The geographical and environmental adaptability of the design is enhanced by integrating topographic, geomorphic and land use data obtained through advanced geographic information system technology, as well as the integration of environmental impact assessment data. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a flowchart of the large model-based power engineering design method in Embodiment 1 of the present invention;

[0062] Figure 2 It is a schematic diagram of the structure of the large model-based power engineering design system in Example 2 of the present invention. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0064] Example 1

[0065] Reference Figure 1 , a large model-based power engineering design method, comprising the steps of:

[0066] Step 1: Build a large model database related to power engineering;

[0067] Build a database based on equipment parameters, geographic information system data, environmental impact assessment data and historical design cases for substation and transmission projects, and synchronize it with real-time data from smart grids and sensor networks;

[0068] In this embodiment, the data in the large model database related to power engineering includes, but is not limited to, equipment parameters of substation and transmission engineering, geographic information system data, environmental impact assessment data, and historical design cases, and comprehensively collects key data and knowledge assets in the field of power engineering, including equipment specifications, performance indicators, and maintenance logs integrated from top equipment manufacturers, as well as terrain, landform, and land use data obtained through advanced geographic information system technology, and integration of environmental impact assessment data;

[0069] In this embodiment, by synchronizing with the real-time data of the smart grid and the sensor network, the dynamic update of the database and the immediacy of decision support are ensured.

[0070] The data in the database is standardized and stored in the database in a unified format and structure; in this embodiment, the data is optimized through an advanced database management system DBMS to ensure the consistency, integrity and high availability of the data;

[0071] Encrypt the data in the database and set access rights; in this embodiment, by deploying advanced encryption technology and access control mechanisms, ensure the security of the database and its ability to resist external threats; strictly comply with data privacy regulations to ensure the confidentiality of all personal and sensitive information; establish a continuous data update and quality control process to ensure the accuracy and real-time nature of the database content; regularly verify, clean and deduplicate data, and continuously evaluate and optimize data sources; through multi-dimensional indexing and advanced search algorithms, and support complex multi-condition queries, improve data retrieval efficiency and user experience, so that users can quickly and accurately find the information they need. Design a refined user rights management system to ensure that users with different roles and needs can access database resources safely and compliantly, while protecting sensitive data from unauthorized access; by integrating advanced data visualization and deep analysis tools, users can intuitively understand complex data, and conduct in-depth data mining and trend analysis to gain valuable business insights.

[0072] Step 2: Build an inference engine based on the large model database;

[0073] Preprocessing the data in the large model database to obtain an initial data set; in this embodiment, preprocessing includes cleaning the data, standardizing the format, and verifying the integrity and accuracy of the data to ensure the reliability of subsequent analysis;

[0074] Based on the initial data set, a design parameter model and an evaluation model are constructed, and the design parameter model is optimized by an optimization algorithm to obtain an optimized design parameter model. The optimized design parameter model is risk evaluated by the evaluation model to obtain an evaluation result. In this embodiment, the optimization algorithm can be an optimization algorithm such as a genetic algorithm and a particle swarm algorithm. The design parameters are optimized, and factors such as cost, efficiency and reliability are considered to find the optimal equipment layout, line path and power grid topology. The design parameter model is established according to the detailed design requirements input by the user, such as the voltage level of the substation, the capacity of the transformer, the length and material of the line, etc., according to different design constraints and Objective: flexibly adjust the design scheme, and use complex network modeling algorithms to represent the network structure of the power system, including nodes (substations, power stations) and edges (transmission lines). These algorithms process the connectivity of nodes, impedance parameters of lines, etc., laying the foundation for power flow calculation and network analysis; after optimization, use simulation and prediction algorithms, such as Monte Carlo simulation, to predict the performance of the power grid under different operating conditions, such as load fluctuations, equipment failures, etc. The power grid response, by constructing fault trees and event trees, analyze various failure modes and their impact on the system, and calculate the probability of system failure; consider the investment cost, operating cost and expected benefits of the project, and evaluate the economic feasibility and investment return of the optimized design parameter model through economic evaluation algorithms, such as IRR and NPV calculations; evaluate the long-term impact of the design scheme on the environment through the LCA algorithm, including greenhouse gas emissions, resource consumption, etc., to ensure the sustainability of the design scheme;

[0075] Based on the evaluation results, an initial design model is constructed through a decision-making tool; in this embodiment, the decision-making tool may be a decision tree, a multi-criteria decision analysis or other decision-making tool to help users understand the pros and cons of different design solutions and make the best choice;

[0076] Combined with the data of historical design cases and user feedback, the initial scheme design model is iteratively optimized through the machine learning algorithm to obtain the scheme design model, and the large model database is updated based on the optimization results; in this embodiment, the machine learning algorithm in the system continuously learns from the historical design cases and user feedback, optimizes the selection of design parameters, and improves the accuracy and innovation of the design scheme. These machine learning algorithms process data from different sources, such as GIS data, meteorological data, satellite images, etc., provide a comprehensive design scheme perspective, and enhance the geographical and environmental adaptability of the design; through the built-in design rule checking algorithm, ensure that the design scheme complies with national and international power engineering standards, such as IEEE and IEC; through the user feedback processing algorithm, analyze the user's evaluation of the design scheme, identify demand changes and optimization points, and realize iterative update of the design scheme; through the adaptive learning algorithm, automatically adjust the design parameters and algorithm parameters according to user feedback and new engineering cases, optimize the design knowledge base, and achieve continuous performance improvement; adopt parallel computing and algorithm acceleration technology to improve the execution efficiency of the algorithm, especially when dealing with large-scale or complex power engineering, to ensure rapid response and efficient execution.

[0077] Step 3: Define the design requirements through the user interface. The reasoning engine builds a corresponding power engineering model and a corresponding risk assessment model according to the defined design requirements, solves the corresponding power engineering model to obtain the optimal power engineering design solution, and evaluates the optimal power engineering design solution through the corresponding risk assessment model.

[0078] In this embodiment, the user interface can be an intuitive and responsive graphical user interface (GUI), which integrates a parameter input module to support users to input key design variables such as the location, scale, expected load, etc. of the substation according to different power engineering requirements; at the same time, the demand management module on the interface will allow users to define and track their design requirements, and provide customized options to adapt to different project specifications and preferences; in addition, the user interface has a real-time feedback mechanism to ensure that the parameters entered by the user are instantly verified and synchronized with the large model database, so as to achieve dynamic update and precise management of design requirements. Through this highly interactive and user-friendly design, it is ensured that users can communicate with the system efficiently and achieve a personalized and efficient power engineering design experience;

[0079] In this embodiment, the design requirements are input and adjusted through the user interface, and the design parameters in the design requirements are extracted; based on the extracted design parameters and the corresponding design constraints and objectives, the corresponding power engineering model is constructed by optimizing the design parameter model; and the corresponding power engineering model is solved by the optimization algorithm to obtain the optimal power engineering design solution.

[0080] In this embodiment, the design requirements are input and adjusted through the user interface, and the design parameters and evaluation parameters in the design requirements are extracted;

[0081] According to the extracted design parameters, the optimal power engineering design scheme is established through the scheme design model, and according to the extracted evaluation parameters, the corresponding risk assessment model is constructed through the evaluation model;

[0082] Based on the large model database, an FTA model and an ETA model are established, and the corresponding risk assessment model evaluates the safety of the optimal power engineering design scheme. The key risk points in the optimal power engineering design scheme are identified through fault tree analysis, and the probability of the final result caused by the specific initial event that triggers the key risk point is tracked through event tree analysis, and the key risk point is optimized. In this embodiment, the FTA model and the ETA model are adaptively optimized and adjusted according to the large model database, the collected real-time data and the user feedback data, and the adaptive optimization results are updated to the risk matrix, and the structure and probability evaluation of the event tree are optimized through continuous iteration;

[0083] Based on the large model database, an NPV model and an IRR model are established, and the corresponding risk assessment model is used to evaluate the economic feasibility of the optimal power engineering design scheme. The future cash flow and time value of the optimal power engineering design scheme are evaluated by solving the NPV model, and the average annual rate of return of the optimal power engineering design scheme is evaluated by iteratively solving the IRR model. In this embodiment, the NPV model and the IRR model dynamically adjust the calculation parameters of the net present value and the internal rate of return according to market dynamics and project progress, identify the most economically beneficial design scheme, and provide corresponding adjustment strategies, and update the corresponding parameters of the most economically beneficial design scheme to the risk matrix;

[0084] Based on the large model database, an LCA model is established, and the corresponding risk assessment model is used to evaluate the environmental sustainability of the optimal power engineering design scheme, and the environmental sustainability is evaluated by quantifying the environmental load of the optimal power engineering design scheme over its entire life cycle; in this embodiment, environmental load data is continuously collected through the large model database, the LCA model is continuously optimized, and the corresponding parameters of the optimized LCA model are updated to the risk matrix, the environmental risks in the design scheme are identified, and corresponding environmental improvement strategies are given;

[0085] The corresponding risk assessment model integrates the assessment results into the risk matrix, intuitively displays the severity and priority of the risk, guides risk management decisions, feeds the risk matrix back to the assessment model, optimizes the assessment model, and generates a risk assessment report. The risk assessment report is displayed through the user interface. The report details the results and risk mitigation measures of each assessment step, helping users understand the potential risks of the design plan and take corresponding measures.

[0086] Step 4: Use automated design tools to simulate the optimal power engineering design solution and collect simulation data and user feedback information;

[0087] In this embodiment, the optimal power engineering design scheme provided by the inference engine is intelligently analyzed, and the key information in the optimal power engineering design scheme is converted into specific design parameters through an automated design tool, such as equipment selection, layout requirements, and line paths;

[0088] Based on specific design parameters, the automated design tool generates a design draft according to the preset design standards and the user's design requirements;

[0089] Use automated design tools to decompose the design draft into several reusable components, each with corresponding parameters and properties;

[0090] The design draft is simulated by the automated design tool to test the performance and feasibility of the design draft. According to the user's design requirements, the corresponding parameters and properties of each component are dynamically adjusted during the test process to ensure the flexibility and adaptability of the design. At the same time, the automated design tool supports a variety of design output formats, such as DWG, DXF, PDF, etc., to meet the needs of different users and application scenarios. During the design draft generation process, the automated design tool uses the built-in design rule checking mechanism to ensure that all designs comply with industry standards and specifications. In addition, it provides user interactive editing functions, allowing users to intuitively adjust and optimize the automatically generated design drafts.

[0091] In this embodiment, a computer vision system and 3D graphics processing functions are integrated into an automated design tool;

[0092] Through data fusion, data from different sources and different types in the design draft are integrated into a unified 3D model view, allowing users to test the performance and feasibility of the design solution in a virtual environment;

[0093] Automatically identify terrain, obstacles and existing infrastructure features through deep learning networks, and combine augmented reality and virtual reality technologies to allow users to interact with 3D models. At the same time, real-time data stream analysis is performed to monitor the construction environment or the status of existing facilities, and fit them with the 3D model to determine the feasibility of the design draft;

[0094] According to the changes in the parameters and attributes of each component, the design draft is dynamically adjusted and optimized to ensure that the automated design tool can remain efficient and stable even when dealing with large-scale or complex power projects; the data of each iteration and change of the design draft and the opinions and suggestions of users on the automated design tool are collected to implement version control and historical tracking mechanisms, making it convenient for users to trace and compare different versions; the automated design tool also has the ability to automate technical reports and documents, and automatically compile technical reports and documents according to the design plan, including design instructions, material lists, construction details, etc.

[0095] In this embodiment, the optimal design parameter combination of the dynamically adjusted and optimized design draft is solved by an optimization algorithm; after the user confirms the optimal design parameter combination, the final design scheme is locked, and the large model database is updated based on the user's feedback and the data of the final design scheme; the functions of the automated design tool are continuously improved to enhance the user experience, and through a continuous feedback loop, it is ensured that the automated design tool always meets the actual needs of the user, promotes continuous innovation and optimization of the design process, greatly improves design efficiency, reduces human errors, and provides high-quality design outputs.

[0096] Step 5: Iterate the inference engine based on simulation data and user feedback information, and update the large model database according to the iteration results;

[0097] In this embodiment, the feedback and iteration mechanism of the system is a dynamic cycle process, which aims to continuously optimize the design scheme through user participation; feedback is collected through the user interface, allowing users to evaluate various aspects of the design draft and make modification suggestions. These feedbacks are automatically classified and analyzed in depth by the system to determine the specific concerns and needs of the user. The system identifies the design parameters that need to be adjusted based on the user's feedback. For example, if the user has doubts about the layout safety of a certain device, the system will re-evaluate and adjust the relevant parameters. Using the iterative algorithm, the system automatically adjusts the design parameters and generates an improved design draft. During the entire iteration process, the system supports multi-version management, records the design of each iterative version, and enables users to intuitively compare different versions and select the best solution; after each iteration, the system will automatically run the test and verification program to ensure that the new design meets all technical specifications and standards; at the same time, the risk assessment module will be updated and the safety, economy and environmental sustainability of the design scheme will be recalculated to ensure the comprehensiveness and reliability of the design scheme. The system integrates user feedback into the design process in real time to ensure timely response to user needs; using optimization algorithms, such as genetic algorithms or simulated annealing algorithms, the system searches for the best combination of design parameters to maximize the benefits of the design solution; the user confirms the design solution after multiple iterations and optimizations; the system provides a final confirmation interface and locks the design solution after user confirmation to ensure that the project can smoothly enter the next stage; at the same time, the system uses user feedback and the final confirmed design solution as data to continuously improve the performance and accuracy of the system, forming a closed-loop system of continuous improvement and learning. Through this feedback and iteration mechanism, the high quality of the design solution and user satisfaction can be ensured.

[0098] Example 2

[0099] Reference Figure 2 Based on Example 1, in this embodiment, a system for implementing a large model-based power engineering design method is provided, including:

[0100] The large model database module is used to build a large model database related to power engineering, synchronize with the real-time data of smart grids and sensor networks, standardize and encrypt the data, and set access rights; in this embodiment, the large model database module is responsible for building a large model database related to power engineering, which contains equipment parameters, geographic information system data, environmental impact assessment data and historical design cases of substation and transmission projects; synchronize with the real-time data of smart grids and sensor networks to ensure the dynamic update of the database and the immediacy of decision support; standardize the data in the database, store it in a unified format and structure, and ensure the consistency, integrity and high availability of the data through an advanced database management system DBMS; encrypt the data and set access rights to ensure the security of the database and compliance with data privacy; establish a continuous data update and quality control process, including data verification, cleaning, deduplication, and evaluation and optimization of data sources; support multi-dimensional indexing and advanced search algorithms to improve data retrieval efficiency.

[0101] The inference engine construction module is used to build an inference engine based on the large model database, iteratively optimize the scheme design model, and update the large model database according to the optimization results. In this embodiment, the inference engine is built based on the large model database, including data preprocessing, the construction of the design parameter model and the evaluation model; the design parameter model is optimized by an optimization algorithm, such as a genetic algorithm and a particle swarm algorithm, to obtain an optimized design parameter model; the evaluation model is used to perform risk assessment on the optimized design parameter model and generate evaluation results; the scheme design model is iteratively optimized by a machine learning algorithm in combination with historical design cases and user feedback data, and the large model database is updated according to the optimization results.

[0102] The user interface module is used to provide an operating interface for users to input and adjust design requirements, view design results and risk assessment reports, and provide feedback. In this embodiment, an intuitive and responsive graphical user interface (GUI) is provided to support users to input and adjust design requirements. The integrated parameter input module and requirement management module allow users to define and track design requirements. The parameters input by users are fed back in real time and synchronized with the large model database to realize dynamic updating of design requirements. The design results and risk assessment reports are displayed, and an operating interface is provided to provide users with feedback.

[0103] The demand modeling module is used to receive user-defined design requirements, extract design parameters and evaluation parameters, build a power engineering model using the optimized design parameter model, and obtain the optimal power engineering design solution through the optimization algorithm.

[0104] The risk assessment module is used to evaluate the safety, economy and environmental sustainability of the design scheme, generate a risk assessment report, and display it through a user interface; in this embodiment, based on a large model database, models such as FTA (fault tree analysis), ETA (event tree analysis), NPV (net present value), IRR (internal rate of return) and LCA (life cycle assessment) are established; the safety, economy and environmental sustainability of the optimal power engineering design scheme are evaluated, and a risk assessment report is generated; the evaluation results are integrated into a risk matrix to intuitively display the severity and priority of the risk.

[0105] The automated design tool module is used to simulate the optimal power engineering design scheme, test the performance and feasibility of the design draft, and dynamically adjust the design parameters and attributes according to user feedback; in this embodiment, the optimal power engineering design scheme is simulated and the design draft is decomposed into reusable components; simulation of the design draft is supported to test the performance and feasibility of the design draft; computer vision system and 3D graphics processing functions are integrated to provide virtual environment testing; design parameters and attributes are dynamically adjusted according to user feedback to ensure the flexibility and adaptability of the design; multiple design output formats are supported, and the ability to automate technical reports and documents is possessed.

[0106] The data collection and feedback module is used to collect simulation data and user feedback information, solve the optimal design parameter combination through the optimization algorithm, lock the final design solution, and update the large model database based on the user feedback and the data of the final design solution; in this embodiment, the simulation data and user feedback information are collected, and the iteration and change data of the design draft are recorded; the optimal design parameter combination is solved through the optimization algorithm, and the final design solution is locked after the user confirms; the large model database is updated based on the user feedback and the data of the final design solution.

[0107] An iterative optimization module is used to iteratively optimize the inference engine based on simulation data and user feedback information, and update the large model database; in this embodiment, the inference engine is iteratively optimized based on simulation data and user feedback information; the design parameters that need to be adjusted are identified, and an improved design draft is generated using an iterative algorithm; multi-version management is supported, and each iterative version of the design is recorded; the test and verification procedures are automatically run to ensure that the new design meets technical specifications and standards; the risk assessment module is updated to recalculate the safety, economy and environmental sustainability of the design; a closed-loop system of continuous improvement and learning is formed to ensure the high quality of the design and user satisfaction.

[0108] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A large-scale model-based power engineering design method, characterized in that: Includes steps: Build a large model database related to power engineering; Build an inference engine based on a large model database; Define design requirements through the user interface, and the reasoning engine builds the corresponding power engineering model and the corresponding risk assessment model according to the defined design requirements, solves the corresponding power engineering model to obtain the optimal power engineering design solution, and evaluates the optimal power engineering design solution through the corresponding risk assessment model; Use automated design tools to simulate optimal power engineering design solutions and collect simulation data and user feedback; The inference engine is iterated based on simulation data and user feedback information, and the large model database is updated according to the iteration results.

2. The large model-based power engineering design method according to claim 1, characterized in that: The specific process of constructing a large model database related to power engineering is as follows: Build a database based on equipment parameters, geographic information system data, environmental impact assessment data and historical design cases for substation and transmission projects, and synchronize it with real-time data from smart grids and sensor networks; Standardize the data in the database and store it in a unified format and structure; Encrypt data in the database and set access permissions.

3. The large model-based power engineering design method according to claim 1, characterized in that: The specific process of building an inference engine based on a large model database is as follows: Preprocess the data in the large model database to obtain an initial data set; Based on the initial data set, a design parameter model and an evaluation model are constructed, the design parameter model is optimized by an optimization algorithm to obtain an optimized design parameter model, and the evaluation result is obtained by performing risk evaluation on the optimized design parameter model by the evaluation model; Based on the evaluation results, an initial design model is constructed through decision-making tools; Combining historical design cases and user feedback data, the initial scheme design model is iteratively optimized through machine learning algorithms to obtain the scheme design model, and the large model database is updated based on the optimization results.

4. The large model-based power engineering design method according to claim 1, characterized in that: The specific process of defining the design requirements through the user interface, the reasoning engine constructing the corresponding power engineering model according to the defined design requirements, and solving the corresponding power engineering model to obtain the optimal power engineering design solution is as follows: Input and adjust design requirements through the user interface, and extract design parameters in the design requirements; According to the extracted design parameters and corresponding design constraints and objectives, the corresponding power engineering model is constructed by optimizing the design parameter model; The optimal power engineering design scheme is obtained by solving the corresponding power engineering model through optimization algorithm.

5. The large model-based power engineering design method according to claim 1, characterized in that: The specific process of defining the design requirements through the user interface, the reasoning engine building a corresponding risk assessment model according to the defined design requirements, and evaluating the optimal power engineering design solution through the corresponding risk assessment model is as follows: Input and adjust design requirements through the user interface, and extract design parameters and evaluation parameters in the design requirements; According to the extracted design parameters, the optimal power engineering design scheme is established through the scheme design model, and according to the extracted evaluation parameters, the corresponding risk assessment model is constructed through the evaluation model; Based on the large model database, the FTA model and ETA model are established. The corresponding risk assessment model evaluates the safety of the optimal power engineering design scheme, identifies the key risk points in the optimal power engineering design scheme through fault tree analysis, and tracks the probability of the final result caused by the specific initial events that trigger the key risk points through event tree analysis, and optimizes the key risk points; Based on the large model database, the NPV model and IRR model are established. The corresponding risk assessment model is used to evaluate the economic feasibility of the optimal power engineering design scheme. The future cash flow and time value of the optimal power engineering design scheme are evaluated by solving the NPV model. The average annual rate of return of the optimal power engineering design scheme is evaluated by iteratively solving the IRR model. Based on the large model database, an LCA model is established, and the corresponding risk assessment model is used to evaluate the environmental sustainability of the optimal power engineering design scheme. The environmental sustainability is evaluated by quantifying the environmental load of the optimal power engineering design scheme throughout its life cycle; The corresponding risk assessment model integrates the assessment results into the risk matrix, feeds the risk matrix back to the assessment model, optimizes the assessment model, and generates a risk assessment report, which is displayed through the user interface.

6. The large model-based power engineering design method according to claim 5, characterized in that: The FTA model and the ETA model are adaptively optimized and adjusted according to the large model database, collected real-time data and user feedback data, and the adaptive optimization results are updated to the risk matrix, and the structure and probability evaluation of the event tree are optimized through continuous iteration; the NPV model and the IRR model dynamically adjust the calculation parameters of the net present value and internal return according to market dynamics and project progress, identify the most economically beneficial design scheme, and provide corresponding adjustment strategies, and update the corresponding parameters of the most economically beneficial design scheme to the risk matrix; Environmental load data is continuously collected through a large model database, the LCA model is continuously optimized, the corresponding parameters of the optimized LCA model are updated to the risk matrix, the environmental risks in the design scheme are identified, and corresponding environmental improvement strategies are given.

7. The large model-based power engineering design method according to claim 1, characterized in that: The specific process of simulating the optimal power engineering design solution through the automated design tool and collecting simulation data and user feedback information is as follows: Transform key information of the optimal power engineering design scheme into specific design parameters through automated design tools; Based on specific design parameters, the automated design tool generates a design draft according to the preset design standards and the user's design requirements; Use automated design tools to decompose the design draft into several reusable components, each with corresponding parameters and properties; Use automated design tools to simulate the design draft, test the performance and feasibility of the design draft, and dynamically adjust the parameters and properties of each component during the test process according to user design requirements; Dynamically adjust and optimize the design draft according to the changes in parameters and properties of each component, collect data on each iteration and change of the design draft and users' opinions and suggestions on the automated design tool.

8. The large model-based power engineering design method according to claim 7, characterized in that: The optimal design parameter combination of the dynamically adjusted and optimized design draft is solved through the optimization algorithm; after the user confirms the optimal design parameter combination, the final design scheme is locked, and the large model database is updated based on the user's feedback and the data of the final design scheme.

9. The large model-based power engineering design method according to claim 7, characterized in that: The specific process of simulating the design draft by the automated design tool is as follows: Integrate computer vision systems and 3D graphics processing capabilities into automated design tools; Through data fusion, data from different sources and different types in the design draft are integrated into a unified 3D model view; Through deep learning networks, terrain, obstacles and existing infrastructure features are automatically identified, and augmented reality and virtual reality technologies are combined to enable users to interact with 3D models. At the same time, real-time data stream analysis is performed to monitor the construction environment or the status of existing facilities, and fit them with the 3D model to determine the feasibility of the design draft.

10. A system for implementing the large model-based power engineering design method according to any one of claims 1 to 9, characterized in that: include: The large model database module is used to build a large model database related to power engineering, synchronize with the real-time data of smart grids and sensor networks, and standardize and encrypt the data and set access rights; The inference engine construction module is used to build an inference engine based on a large model database, iterate the optimization scheme design model, and update the large model database according to the optimization results; User interface module, used to provide users with an operating interface for inputting and adjusting design requirements, viewing design results and risk assessment reports, and providing feedback; The demand modeling module is used to receive the design requirements defined by the user, extract the design parameters and evaluation parameters, build the power engineering model using the optimized design parameter model, and obtain the optimal power engineering design solution through the optimization algorithm; The risk assessment module is used to evaluate the safety, economy and environmental sustainability of the design solution, generate a risk assessment report and display it through the user interface; An automated design tool module that simulates optimal power engineering design solutions, tests the performance and feasibility of draft designs, and dynamically adjusts design parameters and properties based on user feedback; The data collection and feedback module is used to collect simulation data and user feedback information, solve the optimal design parameter combination through the optimization algorithm, lock the final design solution, and update the large model database based on user feedback and the data of the final design solution; The iterative optimization module is used to iteratively optimize the inference engine based on simulation data and user feedback information, and update the large model database.

Images