94 results about "Engineering optimization" patented technology

The invention discloses a large model prompt project optimization system and method fusing a domain knowledge graph. The system comprises an analysis module, a template generation engine module, a large model interaction interface module, a feedback analysis module and an optimization strategy module. And the analysis module forms a constraint coding signal containing an entity attribute incidence matrix. The template generation engine module forms an enhanced prompt text stream with a reservoir physical property parameter slot; the large model interaction interface module receives the enhanced prompt text stream and generates a question and answer response data stream containing geological terminologies; the feedback analysis module forms a feedback signal containing semantic deviation measurement through a semantic error vector calculation algorithm; and the optimization strategy module forms a parameter optimization instruction signal and transmits the parameter optimization instruction signal to the analysis module to complete iterative updating of the constraint condition. According to the large model prompt project optimization system fusing the domain knowledge graph, the problem of low answer accuracy of a large model in the oil-gas exploration field due to lack of professional constraints can be solved.

The invention discloses a multi-agent cooperative cue word engineering optimization method, system and device and a medium, and relates to the technical field of cue word engineering, the method comprises the following steps: after initially receiving a user input task, starting a cue word optimization process; an initial cue word template is created through a cue word generation agent, historical optimal templates are retrieved from a knowledge base for fusion, and candidate cue word templates are generated. And the analysis agent inputs the candidate template into the second large language model to generate a candidate answer. And the evaluation agent performs multi-dimensional evaluation on the answers and gives scores and defect analysis. And according to an analysis result, updating the cue word to generate a candidate template of the intelligent agent. And arranging the intelligent agent to cyclically execute the steps until the stop condition is met, and outputting the optimal cue word template. And finally, storing the optimal template into a knowledge base and establishing a semantic index to support subsequent retrieval reuse. According to the method, manual intervention is not needed, and a complete automatic process of generating, evaluating and optimizing the cue word is realized.

The invention discloses an engineering optimization method based on an improved particle swarm algorithm, and the method comprises the steps: constructing a particle swarm optimization model according to an engineering problem mathematical model, and initializing the position and speed of particles; then, calculating a fitness value index and a diversity index of the particles according to the model, and constructing convergence and diversity data according to the fitness value index and the diversity index; the two kinds of data are used for updating the initial positions and speeds of the particles, and the middle adjustment positions and speeds are obtained. Then, on the basis of the particle swarm optimization model and the intermediate adjustment position, the particle individuals and the global position are updated, and individual convergence and global convergence positions are obtained; and calculating a particle swarm output result according to convergence and diversity data and individual and global convergence positions. And finally, obtaining an optimal solution of the engineering problem according to an output result. According to the embodiment of the invention, two kinds of data are constructed by taking population diversity and fitness value as evaluation criteria, the population position and speed are updated, the optimal solution can be found more quickly and accurately, and the engineering optimization problem is efficiently solved.

The invention provides a multi-objective optimization method and system for material layout beside a production line based on evolutionary optimization, and relates to the technical field of intelligent manufacturing and industrial engineering optimization. The method comprises the following steps: firstly, acquiring basic information data required by material layout optimization beside a production line, and carrying out data preprocessing and standardization; then establishing a multi-objective optimization mathematical model for layout of materials beside the production line, and determining an objective function and constraint conditions; aiming at the material layout multi-objective optimization mathematical model beside the production line, adopting a heuristic initialization strategy and a dynamic Thompson sampling mechanism to improve the MOEA / D algorithm to obtain a heuristic initialization MOEA / D algorithm; and finally, based on a heuristic initialization MOEA / D algorithm, solving the multi-objective optimization mathematical model for the layout of the materials beside the production line, and obtaining a Pareto optimal solution set through iterative optimization, namely obtaining the optimal layout of the materials beside the production line. According to the method, the reasonability and efficiency of material arrangement can be effectively improved.

The invention is suitable for the technical field of structure optimization design, and provides a tension-compression spring design method based on an improved particle swarm optimization algorithm. According to the improved particle swarm optimization (SuperMOP) algorithm provided by the invention, an elite archive strategy and an advantage combination learning strategy are fused, and a mutation operator based on an individual level is introduced. Different roles are allocated to particles according to the performance of the particles, so that a learning strategy is dynamically updated. The improved particle swarm optimization algorithm is compared with several most advanced algorithms, and the result shows that the SuperMOP algorithm effectively balances the exploration and utilization process, improves the population diversity and enhances the diversity of learning samples. According to the method, the improved particle swarm optimization algorithm is applied to the design problem of the tension-compression spring, a new mode with strong global search capability is provided for the design problem of the tension-compression spring, and the method is particularly suitable for solving the optimization problem of complex and changeable constraint engineering.

The invention discloses a multi-strategy improved fox-monkey optimization algorithm for global optimization and application thereof, and belongs to the technical field of optimization algorithms, the method comprises the following steps: firstly, using Chebyshev chaotic mapping to initialize a population so as to improve the diversity and coverage range of the initial population; secondly, a difference population evolution strategy is introduced in the iteration process, and the algorithm is prevented from falling into local optimum in the later period; and finally, introducing a crisscross strategy to enhance global search capability and maintain population diversity. 20 benchmark test functions and a part of complex functions in a cec2017 function set are adopted for a simulation experiment, and the experiment result shows that the optimization precision, the convergence speed and the stability of the improved algorithm are obviously improved. The improved algorithm is applied to the engineering optimization problem, compared with an original algorithm, the convergence precision of the algorithm in three actual engineering problems is improved by 19.56%, 19.18% and 6.7% respectively, the standard deviation is reduced by 91.44%, 27.56% and 92.19% respectively, and the feasibility of the improved algorithm is further verified.

The invention relates to the technical field of extremely-small curved surface structures, in particular to an optimal design method, system and equipment for an extremely-small curved surface structure and a storage medium. The minimum curved surface structure optimization design method comprises the steps that a multi-objective optimization problem is determined according to design variables and optimization objectives of a three-period minimum curved surface lattice structure; constructing an approximate function relationship between the optimization target and the design variable by utilizing a self-adaptive multi-target engineering optimization method of a Kriging agent model; latin hypercube sampling and a sequential quadratic programming optimization algorithm are combined to carry out optimization design on the three-period minimal curved surface lattice structure. According to the design method, the light / bearing / wave-absorbing minimum curved surface lattice sandwich structure with good structure-performance dual characteristics can be designed, the wave-absorbing structure is filled with the minimum curved surface lattice structure in a shape follow-up mode, design and manufacturing of a wave-absorbing and bearing integrated structure are achieved, and rapid iteration and performance improvement of design of the wave-absorbing and bearing structure are supported.

The invention provides a bank business peak period prediction method and system based on a real-time computing platform, and the method comprises the steps: S1, collecting historical transaction data and external factor data from a bank database in real time, and carrying out the cleaning and preprocessing of the collected data; s2, extracting the preprocessed time, historical window and external factor features, and carrying out feature coding and engineering optimization processing on the features; s3, constructing a machine learning model, taking the encoded time, historical window and external factor characteristics as input to train the model, adjusting hyper-parameters through cross validation, and evaluating the performance of the model; s4, receiving real-time data, extracting input features, inputting the real-time data into the trained model for reasoning, and outputting a prediction result; and S5, dynamically adjusting the resource configuration of the bank according to the prediction result, and reversely optimizing the model by monitoring the actual operation condition in real time. According to the method, system resources are dynamically adjusted through the real-time prediction result, and the pressure of business peaks on hardware and human resources is relieved.

The invention provides a jacket type offshore electrical platform optimization method based on a sequential quadratic programming algorithm. The jacket type offshore electrical platform optimization method comprises the following steps: S1, establishing a parameterized offshore electrical platform structure analysis model; s2, calculating an environmental load borne by the offshore electrical platform by adopting an equivalent static load method; s3, establishing an offshore electrical platform optimization model which comprises a target function and a constraint function; s4, performing optimization design by adopting a sequential quadratic specification algorithm; and S5, performing dynamic analysis on the optimal structure, judging whether the optimal structure meets a constraint condition or not under a dynamic load working condition, if so, ending optimization, and if not, manually adjusting the size of the component which does not meet the constraint until the constraint condition is met. According to the method, the sequential quadratic programming algorithm is adopted, the optimization efficiency is high, the engineering optimization requirement is met, the size optimization of the offshore structure considering the pile-soil interaction under wind, wave and flow loading can be achieved, and the cost is further reduced on the premise that the structural stability and safety are guaranteed.

The invention relates to an engineering optimization method and system based on a whale optimization algorithm, and a medium, and belongs to the technical field of intelligent optimization algorithms. Comprising the following steps: S1, initializing parameters and populations: setting a population scale, a maximum number of iterations, dimensions and upper and lower bounds of variables, generating an initial population, and initializing a global optimal solution and a current optimal solution; s2, executing an individual variation strategy: recording a global optimal individual position and a current iteration optimal individual position; s3, executing a unified search strategy; s4, executing a group communication strategy; and S5, judging whether the current number of iterations reaches the maximum number of iterations, if so, outputting a globally optimal solution, otherwise, adding 1 to the current number of iterations and returning to the step S2 to continue iteration. The algorithm provided by the invention aims to improve the global search capability and convergence precision of the algorithm and maintain the time complexity equivalent to that of the original WOA at the same time.

The invention discloses a high-speed aircraft aerodynamic configuration agile optimization method based on an artificial intelligence model. The method comprises the following steps: A1, establishing an aerodynamic force agent model; a2, performing a global optimization algorithm; a3, establishing an intelligent autonomous decision-making model; by constructing a multi-target adaptive weight distribution model, weight dynamic collaborative optimization of proxy model confidence, a constraint penalty function and target function key elements is achieved, the mathematical modeling problem of dynamic matching of weight parameters and optimization targets in the iteration process is solved, a closed-loop optimization system with the autonomous perception-decision-execution capacity is developed, and the optimization efficiency is improved. Therefore, the convergence speed is improved in a complex engineering optimization scene, local optimum is avoided, and the robustness of a global optimal solution is ensured; and A4 pneumatic optimization iteration: based on the proxy model for predicting indexes such as the lift-drag ratio, performing global optimization of design parameters by using an artificial intelligence optimization algorithm, performing verification through CFD, and after verification, putting a CFD calculation result into a training set of the model to re-train the model and continuing optimization until optimization design is converged.

The application discloses a kind of based on manifold constraint's elastic body erosion profile multimodal self-attention fusion prediction method, comprising: data set construction and pre-processing;Build multimodal self-attention fusion network model;Based on the geometric manifold characteristics and physical evolution law of elastic body erosion profile, build the dual compound constraint loss function including data loss, geometric manifold regularization loss and physical consistency loss;Model training and hyperparameter optimization;The microstructure image and physical parameter under the working condition to be predicted are input into the trained model, and the discrete coordinate points and continuous profile curve of the elastic body erosion profile are output, and the importance of different input features to the prediction result is quantified by the integrated explainability analysis module.The application realizes the high-precision and rapid prediction of the elastic body erosion profile, and has the advantages of strong generalization ability and explainability, which provides important technical support for the completion of ammunition warhead design, protection engineering optimization and damage efficiency evaluation tasks.

The invention relates to the technical field of structural engineering optimization design and intelligent model selection, in particular to a structured generative adversarial network-based pipe truss structural design and model selection method, which comprises the following steps of: obtaining pipe truss load data and corresponding structural design schemes under different load conditions; respectively coding the load data and the design scheme to obtain a multi-dimensional dynamic load feature vector and graph structure information; inputting the two schemes into a generator, and generating a design scheme and a model selection scheme by taking the minimum steel use amount as a target under the constraint of physical information; discriminating the generation scheme and the real scheme through a discriminator, calculating an adversarial loss, and alternately training the generator and the discriminator until convergence; and finally, inputting the preset load and the structure design scheme into a convergence generator, and outputting an optimal scheme. According to the method, the end-to-end mapping from the dynamic load to the optimal design and model selection scheme is realized, the design efficiency is remarkably improved, and the structural lightweight is realized while the engineering reliability is ensured.

The invention provides a construction project cost analysis method and device, a storage medium and a program product, and relates to the technical field of construction cost analysis. Performing budget reverse decomposition operation on the current construction project by using the cloud computing service center to obtain a sub-item project parameter set, geographic position data, sub-item budget constraint conditions and a sub-item project optimization strategy; a background database is used for executing missing parameter influence operation on the subentry engineering parameter set according to the geographic position data and the material supply chain data, and a cost influence weight is obtained; key parameter locking operation is executed on the front-end application software according to the cost influence weight, so that key parameters are obtained; and utilizing a background database to generate a cost decision analysis report according to the key parameters, the sub-item engineering parameter set, the sub-item engineering optimization strategy and the sub-item budget constraint conditions. The technical problem that the parameter processing efficiency is low in the construction project cost analysis process in the prior art is solved.

The application provides an engineering optimization method based on failure state variable routing and landscape discrimination, and relates to the technical field of engineering design optimization.The application comprises the following steps: establishing an engineering design constraint optimization model; constructing a fitness evaluation function; initializing a differential evolution algorithm population and parameters; according to individual historical failure states and population evolution states, self-adaptively selecting and generating a first mutation vector from a plurality of pre-defined mutation strategies; constructing a reference direction based on excellent individuals in the population, discriminating and repairing the first mutation vector for direction consistency, and obtaining a second mutation vector; discriminating the problem form of a current search area according to the correlation between population distribution information and fitness sequences, and adjusting the search behavior accordingly; updating the population through a crossover operation; iterating until a termination condition is met, and outputting optimal engineering design parameters.The application improves the optimization precision and convergence efficiency of complex engineering design problems through failure state driven variable routing and landscape structure discrimination.

The invention relates to the technical field of engineering optimization, in particular to an accurate sloping design and earth volume dynamic optimization method oriented to electric power engineering. According to the method, the technical problem that the slope boundary of the complex terrain is not accurately determined is solved through the steps of dynamically shifting the polyline, performing multi-stage encryption intersection, performing three-dimensional topology reconstruction and the like. According to the method, a gradient trigger encryption mechanism and combined integral earthwork calculation are innovatively introduced, in the scenes such as a transformer substation side slope and a power transmission line tower footing, the slope boundary precision is improved by 300% or above, the earthwork volume calculation error is controlled within 5%, and the reliability and economical efficiency of electric power engineering design are remarkably improved.

The invention relates to the technical field of water conservancy and hydropower engineering construction, discloses an optimal design method for a diversion project of an extra-high core wall rock-fill dam, and provides a scientific theoretical basis and technical support for reducing the investment of the diversion project, ensuring the flood safety of hydropower engineering construction and the like. The optimization design method comprises the following steps: S1, establishing a mathematical model for the optimization design of the diversion engineering of the extra-high core-wall rockfill dam; s2, building a flood-fighting water retaining elevation calculation model in the initial-middle stage of construction of the extra-high core-wall rockfill dam; s3, constructing a risk mathematical model of the construction flood control of the extra-high core-wall rockfill dam; s4, systematic analysis is conducted on the dam filling rising randomness, and distribution parameters of all random factors are determined; s5, parameter analysis is conducted on random factors of the construction flood process and the drainage capacity of the diversion tunnel, and distribution parameters of the random factors are determined; and S6, the deep optimization design of the flow guide engineering of the extra-high core wall rock-fill dam is carried out.

The application provides an Abaqus multivariable and multi-target fast optimization method and system based on a Bipod flexible support structure, and includes: five modules of Main_Optimizing.py, Sub_Parameter_Sensitivity_Analysis.py, Sub_Parameter_Range.py, Sub_Model_Bulider.py and Sub_Job_Submit.py work cooperatively, functions of coordinating a global process, identifying key design variables, determining an optimal search space, automatically generating a parameterized finite element model and realizing batch simulation calculation are realized, and therefore a finite element oriented multivariable and multi-target fast optimization is realized. The application can effectively coordinate conflicts among optimization targets, obtain a satisfactory parameter solution in a short time, solve problems of low efficiency of artificial experience parameter optimization and time-consuming and laborious large batch manual modeling, and is helpful to meet urgent needs of modern engineering fields for efficient and accurate structure optimization design.

The invention relates to a credible AI system solution based on double-domain modeling and quantum computing, and aims to solve the defects of the existing AI system in the aspects of cross-culture adaptability, physical correctness and decision real-time performance. Through deep fusion of modern mathematical tools (such as tensor analysis and normative field theory), quantum computing thought (such as advanced path optimization algorithm) and engineering optimization technology, a unified framework capable of processing subjective cognition and objective laws at the same time is constructed. The method specifically comprises the following steps: 1, realizing unification of cultural dynamics and physical law stability through a dual-domain modeling framework of a cognitive dependent domain (CDR) and a non-cognitive domain (NCR); 2, a hypergraph-tensor hybrid architecture which is used for representing a multivariate cultural relationship and verifying a kinematics equation; 3, an advanced computing architecture provides high-performance hardware support; and 4, a multi-mode verification system is adopted, so that the reliability and the safety of the system are ensured. The method is suitable for multiple fields of automatic driving, industrial control, financial risk control and the like, and shows strong universality and commercial potential.

A reliability design optimization method suitable for separating impact components of a shedding connector belongs to the technical field of engineering optimization. In order to solve the problems that traditional reliability optimization design is highly dependent on physical test, and the test cycle is long and the cost is high, the present application proposes a spatial self-adaptive sampling strategy for Kriging surrogate model, which combines model prediction uncertainty and gradient information, dynamically identifies active constraints, thereby effectively reducing misclassification and redundant sampling; in view of the different response characteristics of the objective function and the constraint function, an anisotropic sampling space is constructed for each function, guiding the sample to focus on the area with higher optimization potential; based on the maximum chord deviation criterion, the sampling points are placed in the nonlinear significant area, so as to improve the accuracy of the local surrogate model and accelerate the convergence speed, thereby realizing reliability design optimization.

The invention relates to the technical field of carbon capture and sequestration (CCS) simulation, and particularly provides a CCS rapid simulation method based on a multi-feature fusion neural network. According to the method, a U-FNO network fusing a U neural network (U-Net) and a Fourier neural operator (FNO) is constructed, and the prediction precision of a pressure field and a saturation field on a long-time sequence in the CO2 geological sequestration process is improved; meanwhile, a yield sequence prediction network based on a transformer encoder (TE) is adopted, the output end of the U-FNO network is directly connected to the input end of a TE network, and direct prediction from geological parameters and well control curves to pressure and saturation field time sequence distribution and corresponding yield curves is achieved; the method effectively overcomes the problem that the existing CCS simulation technology is difficult to process multi-feature input and output at the same time, improves the prediction efficiency of the influence of the CO2 storage rate on the reservoir safety, and can provide an efficient and reliable intelligent simulation tool for CCS engineering optimization and history fitting.

The invention discloses a method and equipment for improving engineering problem modeling quality and a storage medium, and belongs to the field of engineering optimization problem modeling by a large language model. The method comprises the following steps: step 1, organizing a series of engineering optimization problems according to hierarchical classification and complexity, and constructing a tree structure knowledge base; step 2, receiving natural language description of a target engineering problem to be modeled, performing recursive search on the tree structure knowledge base in the step 1, and identifying modeling sub-problems corresponding to nodes related to the target engineering problem until the most matched and most specific modeling sub-problem is found; 3, retrieving an advanced modeling thought corresponding to the modeling sub-problem in the step 2, and combining the advanced modeling thought with the description of the target engineering problem to generate a global modeling thought; and 4, automatically generating an optimization model and solver codes of the target engineering problem by using the large language model according to the global modeling thought in the step 3. According to the method, the automatic modeling quality of solving a complex engineering optimization problem by using a large language model can be improved.

The invention discloses a modeling method of a Saint-Venant equation group containing a gate based on a model reduction technology, which belongs to the technical field of water conservancy engineering, and includes: S1, constructing an original Saint-Venant equation group containing a gate; S2, discretizing the constructed original Saint-Venant equation group to obtain a nonlinear function in a high-dimensional system; S3, based on the simulation purpose, using the original Saint-Venant equation group to simulate the system, collecting state variables to construct a snapshot matrix; S4, based on the nonlinear function in the high-dimensional system, using the model reduction technology to simplify the snapshot matrix, and then constructing a low-dimensional reduced-order model corresponding to the original Saint-Venant equation group, and completing the construction of the Saint-Venant equation group containing a gate. This method greatly improves the calculation efficiency while ensuring the simulation accuracy by reducing the order of the model, and meets the needs of real-time simulation and control; it has a wide range of application prospects and can be used in the fields of river channel scheduling, water conservancy engineering optimization, and flood prevention and early warning.

The present invention relates to the field of communication technology, and discloses a SRv6 progressive deployment and traffic engineering method based on deep reinforcement learning, including: training a deep reinforcement learning agent in a simulated network where all SRv6 nodes are deployed; obtaining a pre-set number of nodes that transmit the most SRv6 traffic and upgrading them to SRv6 nodes based on the optimization results of the current network historical traffic matrix by the trained agent, and obtaining a hybrid network; optimizing the traffic matrix of the hybrid network by the agent, and using a local search method to correct the optimization results of the agent. Based on the optimization results of the representative traffic matrix by the deep reinforcement learning agent, the present invention accurately identifies the key nodes that contribute the most to the optimization of traffic engineering, and upgrades them to SRv6 nodes first. In the case of a small number of deployments, the maximum link utilization optimization effect close to the entire SRv6 network can be achieved, reducing the cost of equipment upgrades.

The invention relates to the technical field of unreal engines, and particularly discloses an unreal engine engineering optimization packaging method suitable for a localized platform, which is used for carrying out localized platform adaptation and compatibility analysis on an unreal engine, carrying out performance optimization and completing operation system adaptation. Installing and configuring a necessary SDK (Software Development Kit), ensuring that a tool chain is compatible with a platform, and setting a construction environment; constructing and packaging the project into a format required by the target platform, and generating an executable file; testing items on the target platform, debugging specific problems of the platform, and carrying out performance testing and pressure testing; the project is published to the target platform, and the project is successfully deployed and stably runs on the target platform. According to the method, by carrying out localized platform adaptation, compatibility analysis and performance optimization on the unreal engine, the potential of localized platform hardware is fully excavated, the rendering performance is remarkably improved, the rendering efficiency is greatly improved compared with that before optimization, and smoother visual experience can be provided for a user.

The invention provides an interpretable knowledge mining system, method and device and a medium, and belongs to the technical field of interpretable artificial intelligence and intelligent data mining. The system comprises a data processing module, an algorithm and intelligent interpretation module, a visual analysis module and an operation management module. An explicit mathematical model which is simple in structure and easy to understand is generated through a multi-branch shallow symbol feature learning tree structure, a dynamic branch expansion strategy, LLM guide initialization and a staged grey wolf optimization selection strategy; and an LLM and retrieval enhancement generation (RAG) mechanism is introduced to perform automatic semantic analysis and intelligent interpretation on the generated model. According to the interpretable knowledge mining system, method and equipment and the medium, the technical threshold of interpretable modeling is effectively reduced, meanwhile, the prediction performance, the structure interpretability and the knowledge discovery efficiency of the model are improved, and the interpretable knowledge mining system, method and equipment and the medium are suitable for engineering optimization, scientific modeling and cross-domain data analysis.

The invention discloses a data analysis-based prospecting engineering optimization method and related equipment. According to the method, firstly, resource quantity estimation is conducted on an ore body through original drill holes and design drill holes, the original estimated resource quantity and the design estimated resource quantity are obtained, and the design drill holes comprise encrypted upgrading design drill holes and peripheral newly-added design drill holes; verifying correlation characteristics of the original estimated resource quantity and the designed estimated resource quantity by using data analysis; and finally, if the verification is not passed, optimizing and adjusting the designed drill hole. In the process, a design drilling hole and a variance analysis method are set, the accuracy of resource quantity estimation is improved, the effectiveness of encryption upgrading or peripheral newly-added design is verified through a statistical method, and therefore more reliable data support is provided for subsequent development plans.

The invention discloses a water engineering multi-objective scheduling method and system, and belongs to the technical field of water engineering optimization scheduling, and the method comprises the steps: S1, building a water engineering group optimization scheduling model with the maximum power generation amount, the maximum sand discharge amount and the minimum ecological water deficit amount as objective functions based on the basic information data of water engineering, meanwhile, constraint conditions are set for the water engineering group optimization scheduling model; s2, based on the water engineering group optimization scheduling model, a double-population optimization mechanism is adopted to solve a water engineering optimal scheduling scheme; s3, outputting an optimal scheduling scheme; according to the water engineering multi-target scheduling method and system provided by the invention, the relationship among power generation, desilting and ecology of the water engineering can be coordinated, a water engineering group scheduling scheme set can be quickly given, the benefits of the water engineering can be played to the greatest extent, and the method and the system have the advantages of few calculation parameters, high convergence speed, high global optimization capability, difficulty in falling into local optimum and the like; and a more effective technical method is provided for solving a complex water engineering multi-target engineering problem.

The invention relates to the technical field of communication technology, and discloses an SRv6 progressive deployment and traffic engineering method based on deep reinforcement learning, comprising: training a deep reinforcement learning agent in a simulation network in which all SRv6 nodes are deployed; according to an optimization result of the trained intelligent agent on the current network historical traffic matrix, obtaining a previous set number of nodes which transmit the most SRv6 traffic and upgrading the nodes to SRv6 nodes to obtain a hybrid network; a traffic matrix of the hybrid network is optimized through an intelligent agent, and an optimization result of the intelligent agent is corrected by using a local search method. According to the method, based on the optimization result of the representative traffic matrix by the deep reinforcement learning agent, the key node which contributes most to traffic engineering optimization is accurately identified, the key node is preferentially upgraded to be the SRv6 node, the maximum link utilization rate optimization effect close to a full SRv6 network can be realized under the condition of small deployment, and the equipment upgrading cost is reduced.