Agent-based engineering reconstruction scheme design method and system, medium and equipment

Abstract

The invention relates to an Agent-based engineering transformation scheme design method and system, a medium and equipment. The method comprises the following steps: acquiring demand information of engineering transformation; analyzing and processing the demand information of engineering transformation to obtain a design target and a constraint condition; obtaining field data, constructing a digital twinborn model based on the field data, and outputting basic data; generating a preliminary transformation scheme based on the design target, the constraint condition and the basic data; performing multi-specialty collaborative evaluation on the preliminary transformation scheme to obtain an evaluation result; performing iteration and optimization on the preliminary transformation scheme according to an evaluation result to obtain a target transformation scheme; and outputting and displaying the target transformation scheme. By means of the method, the design period can be remarkably shortened, the design quality and efficiency can be effectively improved, meanwhile, the labor cost and expert dependence can be reduced, the adaptability and robustness of the scheme can be remarkably improved, knowledge accumulation and inheritance can be promoted, and multi-specialty deep fusion and cooperation are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering transformation, and more particularly to an agent-based engineering transformation scheme design method, system, medium and equipment. Background Art

[0002] With the deepening of digital transformation, the renovation, upgrade, and functional optimization of existing engineering facilities have become the norm. However, the traditional engineering renovation design process faces numerous challenges, severely hampering design efficiency and quality. These include a heavy reliance on expert experience and knowledge, lengthy and inefficient design cycles, information silos and barriers to multidisciplinary collaboration, a lack of systematic tools for solution evaluation and optimization, and inadequate mechanisms for knowledge accumulation and utilization.

[0003] Although BIM (Building Information Modeling) technology has improved the visualization and collaboration capabilities of the design process to a certain extent, it is still primarily a tool and is still insufficient in the intelligent generation, automated evaluation, and optimization of solutions, and cannot fundamentally solve the above-mentioned problems. For example, BIM tools often require manual configuration and interpretation to conduct multi-criteria evaluation and optimization, especially when spanning different engineering disciplines. In addition, BIM models are mainly used to store project-specific data and lack mechanisms to learn from historical projects or dynamically update knowledge bases to improve future designs. For complex renovation projects such as nuclear power projects, which have extreme requirements for safety, reliability, and regulatory compliance, existing technologies, including BIM, still face huge challenges in achieving intelligent generation, automated evaluation and optimization of solutions, and multi-disciplinary intelligent collaboration, and it is difficult to efficiently and comprehensively meet their complexity and stringent requirements. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide an agent-based engineering transformation scheme design method, system, medium and equipment to address the problems existing in the prior art.

[0005] The technical solution adopted by the present invention to solve the technical problem is to construct an agent-based engineering transformation scheme design method, which includes the following steps:

[0006] Obtain demand information for engineering renovation;

[0007] Analyzing and processing the engineering transformation demand information to obtain structured engineering transformation design objectives and constraints;

[0008] Acquire field data, construct a digital twin model based on the field data, and output basic data;

[0009] generating a preliminary transformation plan based on the design goal, the constraint conditions, and the basic data;

[0010] Conduct a multi-disciplinary collaborative evaluation of the preliminary renovation plan and obtain evaluation results;

[0011] Iterate and optimize the preliminary transformation plan according to the evaluation results to obtain a target transformation plan;

[0012] The target transformation plan is output and displayed.

[0013] In the agent-based engineering transformation scheme design method of the present invention, the engineering transformation demand information is multimodal demand information;

[0014] The analysis and processing of the engineering transformation demand information to obtain structured engineering transformation design objectives and constraints include:

[0015] Performing natural language processing and semantic understanding on the multimodal demand information to extract key information;

[0016] Structured design goals and constraints are generated based on the key information.

[0017] In the agent-based engineering renovation scheme design method of the present invention, the steps of acquiring field data, constructing a digital twin model based on the field data, and outputting basic data include:

[0018] acquiring the on-site data;

[0019] constructing a digital twin model of the transformation object based on the field data;

[0020] Identifying, based on the field data, constraints on the existing structure, existing equipment, and existing pipelines of the transformation object;

[0021] The basic data is output according to the constraints of the existing structure, existing equipment, and existing pipelines.

[0022] In the agent-based engineering renovation scheme design method of the present invention, generating a preliminary renovation scheme based on the design goal, the constraint conditions, and the basic data includes:

[0023] Based on the design goal, the constraints and the basic data, the preliminary transformation plan is generated in combination with cases in the knowledge base or by using a generation algorithm.

[0024] In the agent-based engineering renovation scheme design method of the present invention, iterating and optimizing the preliminary renovation scheme according to the evaluation results to obtain the target renovation scheme includes:

[0025] Based on the evaluation results, the preliminary transformation plan is iteratively optimized using a multi-objective optimization algorithm until the comprehensive goals of the engineering transformation are met, thereby obtaining the target transformation plan.

[0026] In the agent-based engineering transformation scheme design method of the present invention, outputting and displaying the target transformation scheme includes:

[0027] The target transformation plan is output and displayed in the form of a three-dimensional visual model and a detailed report.

[0028] In the agent-based engineering transformation scheme design method of the present invention, the method further includes:

[0029] Monitor all data generated during the entire engineering renovation scheme design process in real time and dynamically update it to the knowledge base.

[0030] The present invention also provides an agent-based engineering transformation scheme design system, comprising:

[0031] Demand analysis agent, used to obtain demand information of engineering transformation, analyze and process the demand information of engineering transformation, and obtain structured design goals and constraints of engineering transformation;

[0032] Field data agent, used to obtain field data and construct a digital twin model based on the field data and output basic data;

[0033] A solution generation agent is used to generate a preliminary transformation solution based on the design goal, the constraint conditions and the basic data;

[0034] A professional evaluation agent group is used to conduct a multi-disciplinary collaborative evaluation of the preliminary transformation plan to obtain an evaluation result;

[0035] An optimization agent is used to iterate and optimize the preliminary transformation plan according to the evaluation results to obtain a target transformation plan;

[0036] Knowledge management agent, used to monitor all data generated during the entire engineering renovation plan design process in real time and dynamically update it to the knowledge base;

[0037] The user interaction agent is used to output and display the target transformation plan.

[0038] The present invention further provides a storage medium storing a computer program, wherein the computer program is suitable for being loaded by a processor to execute the steps of the above-mentioned agent-based engineering transformation scheme design method.

[0039] The present invention also provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the steps of the above-mentioned agent-based engineering transformation scheme design method by calling the computer program stored in the memory.

[0040] The implementation of the agent-based engineering transformation scheme design method, system, medium and equipment of the present invention has the following beneficial effects: including the steps of: obtaining demand information for engineering transformation; parsing and processing the demand information for engineering transformation to obtain design goals and constraints; obtaining field data and constructing a digital twin model based on the field data and outputting basic data; generating a preliminary transformation scheme based on the design goals, constraints and basic data; conducting a multi-disciplinary collaborative evaluation of the preliminary transformation scheme to obtain an evaluation result; iterating and optimizing the preliminary transformation scheme based on the evaluation result to obtain a target transformation scheme; and outputting and displaying the target transformation scheme. The present invention can significantly shorten the design cycle, effectively improve design quality and efficiency, reduce labor costs and expert dependence, significantly enhance the adaptability and robustness of the scheme, promote knowledge accumulation and inheritance, and achieve deep integration and collaboration among multiple disciplines. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0042] Figure 1 1 is a flow chart of a first embodiment of an agent-based engineering transformation scheme design method provided by the present invention;

[0043] Figure 2 1 is a flow chart of a second embodiment of the agent-based engineering transformation scheme design method provided by the present invention;

[0044] Figure 3 It is a logic block diagram of the engineering transformation scheme design system based on Agent provided by the present invention;

[0045] Figure 4 This is the overall system architecture diagram of the Agent-based engineering transformation solution design system provided by the present invention. DETAILED DESCRIPTION

[0046] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0047] To address the problems existing in the existing engineering renovation scheme design process, the present invention provides an agent-based engineering renovation scheme design method and system. By constructing a collaborative working platform composed of multiple intelligent agents with specific functions and knowledge, the system achieves automated, intelligent, and efficient design of engineering renovation schemes through the perception, reasoning, decision-making, action, and learning between agents.

[0048] In a preferred embodiment, Figure 1 As shown, the agent-based engineering transformation scheme design method includes the following steps:

[0049] Step S101: Obtaining engineering transformation demand information.

[0050] Specifically, the engineering renovation requirement information can be input by the user through the user interface layer and the user interaction agent. Optionally, in an embodiment of the present invention, the engineering renovation requirement information is multimodal requirement information, such as text, image, BIM model, etc.

[0051] Step S102: Analyze and process the engineering transformation demand information to obtain structured engineering transformation design objectives and constraints.

[0052] In some embodiments, parsing and processing the engineering transformation requirement information to obtain structured engineering transformation design goals and constraints includes: performing natural language processing and semantic understanding on multimodal requirement information to extract key information; and generating structured design goals and constraints based on the key information.

[0053] Specifically, after receiving engineering renovation requirements input from users via the user interaction agent, the Requirements Analysis Agent performs natural language processing and semantic understanding on the multimodal requirements information, extracting key information and forming structured design goals and constraints. These design goals and constraints include, but are not limited to, safety levels and regulatory requirements specific to nuclear power renovations, which are then passed on to subsequent agents. The Requirements Analysis Agent combines natural language processing (NLP), computer vision (CV), and BIM data parsing technologies to intelligently parse and structure multimodal (multi-source heterogeneous) renovation requirements, including text, images, and BIM models. This is particularly relevant for complex textual information, such as technical documents and safety reports, specific to the nuclear power sector.

[0054] Step S103: Acquire field data and construct a digital twin model based on the field data and output basic data.

[0055] In some embodiments, obtaining field data, constructing a digital twin model based on the field data, and outputting basic data include: obtaining field data; constructing a digital twin model of the transformed object based on the field data; identifying the constraints of the existing structure, existing equipment, and existing pipelines of the transformed object based on the field data; and outputting basic data based on the constraints of the existing structure, existing equipment, and existing pipelines.

[0056] Field data includes, but is not limited to, existing BIM models, CAD drawings, laser scanning data, and data specific to nuclear power facilities. This data can be acquired through a field data agent. Specifically, the field data agent integrates existing BIM models, CAD drawings, laser scanning data, and data specific to nuclear power facilities (such as reactor core parameters and radiation monitoring data) to construct an accurate digital twin model of the renovation object. It also identifies constraints such as existing structures, equipment, and pipelines, providing foundational data for solution generation. In this embodiment of the present invention, digital twin technology is used to create high-precision models of the renovation object. Combined with physical simulation, fluid simulation, and structural mechanics simulation, the renovation solution is virtually verified, identifying potential problems and risks in advance and reducing uncertainty during actual construction. For nuclear power projects, special emphasis will be placed on high-precision simulation of key parameters such as reactor physics, thermal hydraulics, and radiation transmission to verify the impact of the renovation solution on nuclear safety.

[0057] Step S104: Generate a preliminary transformation plan based on the design objectives, constraints and basic data.

[0058] In some embodiments, generating a preliminary modification plan based on the design goals, constraints, and basic data includes: generating the preliminary modification plan based on the design goals, constraints, and basic data, combining cases in a knowledge base, or using a generation algorithm.

[0059] In an embodiment of the present invention, a preliminary transformation plan can be directly generated by a solution generation agent. Specifically, based on the design goals and constraints provided by the demand analysis agent and the transformation object information (basic data) provided by the field data agent, the solution generation agent retrieves relevant cases from the knowledge base maintained by the knowledge management agent or uses a generation algorithm to quickly generate multiple multi-disciplinary preliminary transformation plans that meet basic requirements and preliminarily consider nuclear power-related safety and regulatory requirements. The solution generation agent uses a solution generation method that integrates generative AI and expert systems. That is, it combines the open generation capabilities of large language models (LLMs) and the rule reasoning capabilities of traditional expert systems to achieve more flexible, accurate, and engineering-compliant automatic generation of preliminary plans, ensuring that the generated plans meet the strict safety and technical requirements of the nuclear power field.

[0060] Step S105: Multi-professional collaborative evaluation is performed on the preliminary reconstruction scheme to obtain an evaluation result.

[0061] In the embodiment of the present application, the multi-professional collaborative evaluation on the preliminary reconstruction scheme can be implemented by a professional evaluation Agent group. Specifically, the professional evaluation Agent group is an Agent cluster composed of various professional evaluation Agents. Various professional evaluation Agents (such as instrument control, machinery, electricity, nuclear safety, and radiation protection) perform professional evaluation on the preliminary reconstruction scheme in parallel. Each professional evaluation Agent quantitatively evaluates the feasibility, safety, compliance, cost, and performance of the preliminary reconstruction scheme from the perspective of its own profession, identifies potential problems, and gives improvement suggestions, and the evaluation results are summarized. The evaluation results are summarized in the optimization Agent. By designing parallel evaluation of multi-professional evaluation Agents, a multi-Agent collaborative communication and conflict resolution mechanism can be achieved, that is, an efficient inter-Agent communication protocol (such as FIPA ACL), a task allocation mechanism (such as an auction mechanism, a negotiation mechanism), and a conflict detection and resolution strategy are designed to ensure efficient collaboration and problem solving of multi-Agents in complex and dynamic tasks, especially in nuclear power reconstruction, which can effectively solve the conflicts across professions and safety levels.

[0062] Step S106: The preliminary reconstruction scheme is iterated and optimized according to the evaluation result to obtain a target reconstruction scheme.

[0063] In the embodiment of the present application, the iteration and optimization of the preliminary reconstruction scheme according to the evaluation result to obtain a target reconstruction scheme includes: according to the evaluation result, the preliminary reconstruction scheme is iterated and optimized by using a multi-objective optimization algorithm until the comprehensive target of engineering reconstruction is met, and a target reconstruction scheme is obtained.

[0064] Specifically, the iteration and optimization of the preliminary reconstruction scheme can be implemented by an optimization Agent. Specifically, the optimization Agent collects feedback from various professional evaluation Agents, iterates and optimizes the scheme by using a multi-objective optimization algorithm until the preset comprehensive targets such as performance, cost, and construction period are met. In this process, nuclear safety and regulatory compliance will be the most important optimization constraint condition. During the optimization process, the optimization Agent can interact with the scheme generation Agent and the knowledge management Agent to obtain new generation strategies or knowledge. The multi-objective optimization algorithm includes but is not limited to genetic algorithm, particle swarm optimization algorithm, and simulated annealing algorithm. By using advanced optimization algorithms such as genetic algorithm, particle swarm optimization algorithm, and simulated annealing algorithm, multiple conflicting targets such as cost, construction period, performance, safety, and energy consumption are balanced, and a reconstruction scheme (target reconstruction scheme) with optimal or suboptimal comprehensive performance is generated. In the field of nuclear power, safety, reliability, and regulatory compliance will be the highest priority optimization target.

[0065] Step S107: Output and display the target transformation plan.

[0066] In an embodiment of the present invention, outputting and displaying the target transformation plan includes outputting and displaying the target transformation plan using a three-dimensional visualization model and a detailed report. In an embodiment of the present invention, outputting and displaying the target transformation plan can be achieved through a user interaction agent. Specifically, the optimized plan (i.e., the target transformation plan) is presented to the user via the user interaction agent in the form of a three-dimensional visualization model and a detailed report, allowing the user to review the target transformation plan, provide modification suggestions, and guide the agent for further adjustments. User feedback can be transmitted via the user interaction agent to relevant agents for fine-tuning or re-iteration.

[0067] Furthermore, in an embodiment of the present invention, the agent-based engineering transformation scheme design method also includes the following steps: real-time monitoring of all data generated during the entire engineering transformation scheme design process, and dynamic updates to the knowledge base. Specifically, during the entire engineering transformation scheme design process, the generated requirements, schemes, evaluation results, optimization processes, user feedback, and finalized scheme data are all learned and deposited into the knowledge base through the knowledge management agent, continuously updating and enriching the knowledge graph, especially key knowledge such as operating experience, safety analysis, and regulatory updates in the nuclear power field, thereby continuously improving the intelligence level and design capabilities of the system. Through the knowledge management agent, continuous learning of data, schemes, evaluation results, user feedback, etc. generated during the design process and dynamic updates of the knowledge graph are achieved, especially including key knowledge such as nuclear power operating experience, safety analysis reports, and regulatory updates, forming an evolvable design capability. Among them, the detailed process of the agent-based engineering transformation scheme design method of the present invention is as follows: Figure 2 shown. Figure 2 The specific steps of the agent-based engineering renovation scheme design method of the present invention are given in detail, including core links such as demand input and analysis, field data acquisition and modeling, preliminary scheme generation, multi-disciplinary collaborative evaluation, scheme optimization and iteration, user feedback and adjustment, and knowledge learning and accumulation, clearly showing the sequence and interaction between each link.

[0068] The agent-based engineering renovation design method of the present invention, through a multi-agent collaborative mechanism, fundamentally addresses the time-consuming, inefficient, expert-based, collaborative, and knowledge-intensive design challenges of engineering renovation schemes. Existing solutions struggle to meet the complexities and rigors of nuclear power engineering, a field with stringent safety, reliability, and regulatory compliance requirements. Therefore, the agent-based engineering renovation design method and system proposed in this invention offer unique advantages in comprehensiveness, intelligence, and efficiency. Currently, no fully equivalent alternatives exist that can fully achieve the objectives of this invention.

[0069] refer to Figure 3 , Figure 3 This is a logical block diagram of an agent-based engineering renovation solution design system provided by the present invention. The agents in this agent-based engineering renovation solution design system are software entities with perception, reasoning, decision-making, action, and learning capabilities. They communicate and collaborate through preset protocols to jointly complete the design of engineering renovation solutions.

[0070] Specifically, such as Figure 3 As shown in Figure 1, the agent-based engineering transformation scheme design system includes:

[0071] The demand analysis agent is used to obtain the demand information of the engineering transformation, analyze and process the demand information of the engineering transformation, and obtain the structured design goals and constraints of the engineering transformation.

[0072] In the embodiment of the present invention, the specific functions of the demand analysis agent are as follows:

[0073] Perception capability: Receive transformation requirements input by users, including natural language text descriptions, pictures, videos, existing documents (such as requirement specifications), etc.

[0074] Reasoning and decision-making: Use natural language processing (NLP), computer vision (CV) and other technologies to parse and semantically understand multimodal requirements, identify key demand points, design goals, and constraints (such as budget, construction period, performance indicators, and safety levels, radiation dose limits, and regulatory compliance specific to nuclear power transformation).

[0075] Action: Convert unstructured requirements into structured design tasks and parameter lists that can be understood by subsequent agents.

[0076] Field data agent is used to obtain field data, construct a digital twin model based on the field data, and output basic data.

[0077] In the embodiment of the present invention, the specific functions of the field data agent are as follows:

[0078] Perception capabilities: Access and process various data sources from site surveys, such as laser scanning point cloud data, drone aerial imagery, existing BIM models, CAD drawings, equipment lists, and historical maintenance records. For nuclear power projects, this also requires processing sensitive and complex data, including nuclear island structural diagrams, reactor core data, piping and valve material data, radiation field distribution data, and historical operating parameters.

[0079] Reasoning and Decision-Making: Based on input data, an accurate digital twin model of the renovation object is constructed. This model identifies and extracts information about existing structures, equipment, pipelines, and spatial layout, analyzing potential renovation constraints (such as load-bearing capacity, clear height, compatibility with existing equipment, pipeline conflicts, and nuclear power-specific material aging, radiation damage, equipment criticality, and safety margins).

[0080] Action: Provide geometric information, attribute data and constraints of the transformed object to other agents.

[0081] The solution generation agent is used to generate preliminary transformation solutions based on design goals, constraints and basic data.

[0082] In the embodiment of the present invention, the specific functions of the solution generation agent are as follows:

[0083] Perception capability: Receives design tasks from the demand analysis agent and transformation object information from the field data agent.

[0084] Reasoning and Decision-Making: Combining the knowledge base provided by the knowledge management agent (including design principles, specifications, historical cases, component libraries, and particularly nuclear power design specifications, safety guidelines, and nuclear-grade equipment selection principles), the system automatically generates multiple preliminary multi-disciplinary renovation plans that meet basic requirements using a variety of generation algorithms, such as rule-based expert system reasoning, case-based reasoning (CBR), parametric design, and even the generation capabilities of generative adversarial networks (GANs) or large language models (LLMs). Each plan includes preliminary design content for various disciplines, including architecture, structure, equipment, and electrical systems, and takes into account the specific requirements of nuclear power safety systems, radiation protection, and waste disposal.

[0085] Action: Output multiple preliminary transformation plans that can be evaluated.

[0086] The professional evaluation agent group is used to conduct multi-disciplinary collaborative evaluation of the preliminary transformation plan and obtain the evaluation results.

[0087] In an embodiment of the present invention, the professional assessment agent group is an agent cluster, and each professional assessment agent focuses on the assessment of a specific professional field and supports expansion. The professional assessment agent group includes but is not limited to: structural assessment agent, equipment assessment agent, electrical assessment agent, HVAC assessment agent, economic assessment agent, nuclear safety assessment agent, and radiation protection assessment agent. The perception capability of the professional assessment agent group is: receiving the preliminary transformation plan provided by the plan generation agent. Reasoning and decision-making are: using the knowledge and simulation models of their respective professional fields to quantitatively evaluate the plan, identify potential problems and risk points, and put forward specific improvement suggestions. Action: Feedback detailed assessment reports and improvement suggestions to the optimization agent. The functions of each professional assessment agent are as follows:

[0088] Structural Assessment Agent: Evaluates the structural safety and stability of the scheme, identifies whether structural reinforcement is needed, and estimates the reinforcement cost.

[0089] Equipment Evaluation Agent: Evaluates the rationality, performance indicators, compatibility, and energy consumption of equipment selected in the plan.

[0090] Electrical Assessment Agent: Evaluates the power load, power supply reliability, and wiring compliance of the solution.

[0091] HVAC Assessment Agent: Evaluates whether the ventilation, air conditioning, and heating designs of the plan meet indoor environmental requirements and estimates energy consumption.

[0092] Economic Evaluation Agent: Conducts a preliminary investment return analysis of the solution, including equipment procurement costs, construction costs, operation and maintenance costs, and expected benefits.

[0093] Nuclear Safety Assessment Agent: Specialized in assessing the impact of a plan on nuclear safety, including reactor safety, criticality safety, radiation protection, and accident response, to ensure compliance with national and international nuclear safety regulations and standards.

[0094] Radiation Protection Assessment Agent: Evaluate the radiation shielding design, personnel dose control, and radioactive material leakage risk of the scheme to ensure that radiation protection requirements are met.

[0095] The optimization agent is used to iterate and optimize the preliminary transformation plan based on the evaluation results to obtain the target transformation plan.

[0096] In the embodiment of the present invention, the specific functions of the optimization agent are as follows:

[0097] Perception capability: Receive evaluation reports and improvement suggestions from various professional evaluation agents.

[0098] Reasoning and Decision-Making: Using multi-objective optimization algorithms (such as genetic algorithms, particle swarm optimization, and simulated annealing), the optimization agent iteratively optimizes preliminary solutions based on multiple objectives, including cost, construction schedule, performance, safety, and energy consumption. It balances conflicts between these objectives to find the optimal or suboptimal balance. In nuclear power plant retrofits, safety and compliance are typically top priorities, and the optimization agent prioritizes achieving these goals. During the optimization process, it may interact with solution generation agents and knowledge management agents to acquire new strategies or knowledge.

[0099] Action: Output optimized transformation plan.

[0100] The knowledge management agent is used to monitor all data generated during the entire engineering transformation plan design process in real time and dynamically update it to the knowledge base.

[0101] In the embodiment of the present invention, the specific functions of the knowledge management agent are as follows:

[0102] Perception capability: Continuously monitor the design process, solutions, evaluation results, optimization iterations, and user feedback in the system.

[0103] Reasoning and Decision-Making: Responsible for collecting, organizing, structuring, storing, and updating this data. This includes building and maintaining a knowledge graph for engineering renovations, enabling effective organization and efficient retrieval of knowledge. Crucially, this will manage and update nuclear power expertise, such as nuclear safety regulations, IAEA standards, operational experience feedback, and equipment failure modes. Machine learning techniques will be used to learn new design patterns, evaluation rules, and optimization strategies from historical data.

[0104] Action: Provide real-time knowledge support to other agents and continuously improve the intelligence level of the system itself.

[0105] User interaction agent, used to output and display the target transformation plan.

[0106] In the embodiment of the present invention, the specific functions of the user interaction agent are as follows:

[0107] Perception capability: monitor user operations on the interface, and receive user instructions, feedback, and modification suggestions.

[0108] Reasoning and decision-making: Coordinate the responses of agents within the system and present the complex design process in a user-friendly manner.

[0109] Action: Provides 3D visualization, report generation, parameter adjustment and other functions to achieve human-machine collaboration.

[0110] Figure 4The overall architecture of the agent-based engineering transformation scheme design system of the present invention is shown. The agent-based engineering transformation scheme design system adopts a modular and layered architecture design. Figure 4 As shown in the figure, the agent-based engineering transformation solution design system specifically includes: application layer, agent core collaboration layer, agent function layer, data management layer, underlying technical support layer, etc. The specific functions of each layer are as follows:

[0111] The application layer serves as a portal for users to interact with the system, providing an intuitive web or desktop client interface. Through this layer, users can input transformation requirements, upload relevant data, view the progress of the scheme design in real time, browse and review the generated transformation scheme, and make scheme adjustments and feedback. The core function of the Agent Core Collaboration Layer is to manage and coordinate the activities of various intelligent agents. It is responsible for the registration and discovery of agents, the intelligent allocation of tasks, the management of communication protocols between agents, the scheduling of data flow, and the conflict resolution mechanism, ensuring that all agents can work together efficiently and orderly to jointly complete complex transformation scheme design tasks. The Agent Functional Layer contains various functional agents defined in this invention, each of which encapsulates its specific professional knowledge, algorithm model, and processing logic. These agents are the core of the system's intelligent realization, and they perform design tasks independently but in a collaborative manner. The data management layer provides powerful data storage, retrieval, management, and update services. It includes a field data management module (for processing BIM models, CAD drawings, point cloud data, etc.), a solution library (for storing historical and currently generated solutions), a knowledge base (for storing engineering specifications, industry standards, expert experience, historical cases, etc., especially nuclear power safety regulations, operational experience feedback, nuclear material characteristics, etc.), and an evaluation index library (for storing various evaluation models and parameters). The underlying technical support provides the necessary infrastructure and tools for the entire system. Including but not limited to: artificial intelligence frameworks (such as TensorFlow and PyTorch for model training and reasoning), big data processing technologies, various database systems (such as relational databases, NoSQL databases, and graph databases for knowledge graph storage), cloud computing platforms (for providing computing and storage resources), and digital twins and simulation engines.

[0112] Compared with traditional methods, the present invention has the following advantages:

[0113] Significantly shortened design cycles: Through the agent's automated requirements analysis, solution generation, parallel evaluation, and iterative optimization, traditional design cycles of weeks or even months are shortened to days or hours, significantly improving design efficiency and response speed, effectively shortening nuclear power facility downtime for maintenance and improving the economic benefits of power plants.

[0114] Significantly improved design quality and efficiency: The agent can learn from massive amounts of data and knowledge, avoiding errors that may occur in manual operations. It can also quickly generate and evaluate multiple solutions, helping designers select the best solution and improving design quality. In the nuclear power sector, this means higher safety margins, greater reliability, and stricter regulatory compliance.

[0115] Reduced labor costs and reliance on experts: By reducing repetitive work and reliance on the experience of experienced engineers, more renovation projects can be initiated and completed quickly, reducing labor costs in the design phase. In the nuclear power sector, this helps alleviate the scarcity of top expert resources and reduces design risks caused by human error.

[0116] Enhanced adaptability and robustness of solutions: The system can quickly respond to changing requirements and provide multi-dimensional assessment and optimization for complex, highly uncertain retrofit projects, resulting in more adaptable and robust solutions. For nuclear power retrofits, this means better ability to cope with complex technical challenges and evolving regulatory requirements.

[0117] Facilitating knowledge accumulation and transfer: Automated knowledge management and learning mechanisms enable the effective accumulation, organization, and reuse of engineering renovation experience, historical data, and best practices, fostering sustainable and evolving design capabilities and addressing the challenges of knowledge accumulation and reuse. In the nuclear power sector in particular, this allows for the effective accumulation and reuse of valuable operating experience, safety analysis data, and regulatory evolution information, providing a solid foundation for future renovations.

[0118] Achieving deep multi-disciplinary integration and collaboration: The collaborative work of various specialized agents breaks down traditional barriers and information silos between disciplines, enabling true multi-disciplinary integrated design and improving the consistency and coordination of the overall design. In nuclear power projects, this is crucial for ensuring seamless integration and overall safety across disciplines, such as the nuclear island, conventional island, and auxiliary systems.

[0119] In addition, an electronic device of the present invention includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program to implement an agent-based engineering transformation scheme design method as described in any one of the above. Specifically, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed by an electronic device and, when executed, performs the above-mentioned functions defined in the method of the embodiment of the present invention. The electronic device in the present invention can be a terminal such as a notebook, desktop, tablet computer, smart phone, or a server.

[0120] In addition, the present application also provides a storage medium storing a computer program, which is executed by a processor to implement the agent-based engineering modification scheme design method according to any one of the above. Specifically, it should be noted that the storage medium of the present application can be a computer readable signal medium or a computer readable storage medium or any combination of the above two. The computer readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present application, the computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer readable program code. Such a propagated data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium other than the computer readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or apparatus. The program code contained in the computer readable medium can be transmitted by any suitable medium, including but not limited to a wire, a cable, an RF (radio frequency) or the like, or any suitable combination of the above.

[0121] The above computer readable medium can be contained in the above electronic device or can exist separately and not be assembled into the electronic device.

[0122] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other. For the device disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method part.

[0123] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0124] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0125] The above embodiments are intended only to illustrate the technical concepts and features of the present invention. Their purpose is to enable those skilled in the art to understand the present invention and implement it accordingly. They are not intended to limit the scope of protection of the present invention. All equivalent variations and modifications within the scope of the claims of the present invention are intended to be covered by the claims of the present invention.

Claims

1. An agent-based engineering transformation scheme design method, characterized in that: The following steps are involved: Obtain demand information for engineering renovation; Analyzing and processing the engineering transformation demand information to obtain structured engineering transformation design objectives and constraints; Acquire field data, construct a digital twin model based on the field data, and output basic data; generating a preliminary transformation plan based on the design goal, the constraint conditions, and the basic data; Conduct a multi-disciplinary collaborative evaluation of the preliminary renovation plan and obtain evaluation results; Iterate and optimize the preliminary transformation plan according to the evaluation results to obtain a target transformation plan; The target transformation plan is output and displayed.

2. The agent-based engineering transformation scheme design method according to claim 1 is characterized in that: The engineering transformation demand information is multimodal demand information; The analysis and processing of the engineering transformation demand information to obtain structured engineering transformation design objectives and constraints include: Performing natural language processing and semantic understanding on the multimodal demand information to extract key information; Structured design goals and constraints are generated based on the key information.

3. The agent-based engineering transformation scheme design method according to claim 1 is characterized in that: The acquiring of field data, constructing a digital twin model based on the field data, and outputting basic data includes: acquiring the on-site data; constructing a digital twin model of the transformation object based on the field data; Identifying, based on the field data, constraints on the existing structure, existing equipment, and existing pipelines of the transformation object; The basic data is output according to the constraints of the existing structure, existing equipment, and existing pipelines.

4. The agent-based engineering transformation scheme design method according to claim 1 is characterized in that: Generating a preliminary transformation plan based on the design goal, the constraints, and the basic data includes: Based on the design goal, the constraints and the basic data, the preliminary transformation plan is generated in combination with cases in the knowledge base or by using a generation algorithm.

5. The agent-based engineering transformation scheme design method according to claim 1 is characterized in that: The iterating and optimizing the preliminary transformation plan according to the evaluation results to obtain the target transformation plan includes: Based on the evaluation results, the preliminary transformation plan is iteratively optimized using a multi-objective optimization algorithm until the comprehensive goals of the engineering transformation are met, thereby obtaining the target transformation plan.

6. The agent-based engineering transformation scheme design method according to claim 1 is characterized in that: The outputting and displaying the target transformation plan includes: The target transformation plan is output and displayed in the form of a three-dimensional visual model and a detailed report.

7. The agent-based engineering transformation scheme design method according to claim 1 is characterized in that: The method further comprises: Monitor all data generated during the entire engineering renovation scheme design process in real time and dynamically update it to the knowledge base.

8. An agent-based engineering transformation scheme design system, characterized by: include: Demand analysis agent, used to obtain demand information of engineering transformation, analyze and process the demand information of engineering transformation, and obtain structured design goals and constraints of engineering transformation; Field data agent, used to obtain field data and construct a digital twin model based on the field data and output basic data; A solution generation agent is used to generate a preliminary transformation solution based on the design goal, the constraint conditions and the basic data; A professional evaluation agent group is used to conduct a multi-disciplinary collaborative evaluation of the preliminary transformation plan to obtain an evaluation result; An optimization agent is used to iterate and optimize the preliminary transformation plan according to the evaluation results to obtain a target transformation plan; Knowledge management agent, used to monitor all data generated during the entire engineering renovation plan design process in real time and dynamically update it to the knowledge base; The user interaction agent is used to output and display the target transformation plan.

9. A storage medium, characterized in that: The storage medium stores a computer program, and the computer program is suitable for being loaded by a processor to execute the steps of the agent-based engineering transformation scheme design method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: The system comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the steps of the agent-based engineering transformation scheme design method according to any one of claims 1 to 7 by calling the computer program stored in the memory.

Images