26 results about "Hybrid genetic algorithms" patented technology

The invention relates to a joint estimation method for SOC and SOH of a power battery, in particular to a joint estimation method for SOC and SOH of a lithium ion power battery based on FOASEKF-EKF, comprising fractional order equivalent circuit models of two parallel fractional order CPE branches, and providing a hybrid genetic algorithm HGA fusing a differential evolution strategy and an adaptive variation mechanism. Accurate estimation of SOC and terminal voltage under a fast time scale is realized by introducing a sliding-mode observer and an FOASEKF, periodic online correction is performed on model parameters and battery capacity based on an EKF under a slow time scale, and high-precision and high-robustness battery SOC and SOH joint estimation is realized. The method is suitable for complex industrial environments such as electric automobiles and rail transit, does not need to set a large number of hyper-parameters, does not excessively depend on the quality and quantity of data, has good interpretability, adaptability and engineering practicability, can still achieve high-precision cooperative estimation of SOC and SOH especially under the working conditions of frequent start and stop and unsteady operation, and has good application prospects. And misjudgment and drift estimation risks are obviously reduced.

The invention discloses a private generation type large model optimization system based on a hybrid genetic algorithm, belongs to the technical field of artificial intelligence, and aims to solve the technical problems of how to compress the model scale, simplify the feature dimension to improve the reasoning efficiency and maintain the model precision as much as possible. Comprising a multi-source heterogeneous data fine adjustment module, a large model construction module, a hybrid genetic algorithm optimization module, a diffusion type encoder feature extraction module, a course type noise robustness improvement module, an activation function optimization module and a feature dimension reduction and low-rank compression module, the large model is gradually and deeply optimized from the aspects of data, structure, training, robustness, activation function and model compression, and a generative large model which can fully learn financial data of the new energy vehicle enterprise and is excellent in performance, reliable in robustness and friendly to resources is produced.

The invention relates to the technical field of intelligent optimization of discrete combination problems, in particular to a distributed heterogeneous machining workshop order allocation method and system based on simulation, workshops are accurately described by constructing simulation models of the machining workshops, and a hybrid genetic algorithm is combined with simulation to find order allocation schemes meeting requirements, so that the optimization of the machining workshops is realized. According to the method, a factory delivery date relaxation calculation mode is improved, maximization and minimum factory delivery date relaxation are taken as a target, a high-quality order allocation scheme is efficiently generated, whether each order can be completed in time or not is verified through production simulation of each machining workshop, an order transfer operation is designed to adjust overdue order allocation, and the order allocation efficiency is improved. Compared with a traditional method, the efficiency of processing heterogeneous workshops is higher, order allocation of simulation verification is more real and reliable, the resource utilization rate and the on-time completion rate can be improved in a complex distributed manufacturing scene, the order delay risk is reduced, and the method is suitable for the field of multi-factory collaborative production scheduling.

The invention belongs to the technical field of power system operation and planning, and discloses a power grid net load fluctuation scene generation method, system and device based on an ARIMA and Copula combined model and a medium, so as to solve the problem of poor scene generation accuracy. The method comprises the following steps: decomposing and reconstructing an original time sequence of the net load of the power grid by using discrete wavelet transform; taking permutation entropy minimization as an optimization target, adopting a variable chromosome length hybridization genetic algorithm to divide time segments for the low-frequency linear subsequences, and respectively establishing ARIMA models to generate linear trend scenes; establishing a joint probability distribution model of the high-frequency fluctuation subsequences at adjacent moments based on a Copula function, and deducing conditional probability distribution in combination with a Bayesian formula to generate a fluctuation scene; and the linear trend scene and the fluctuation scene are superposed to form an initial net load scene set, and a k-means clustering algorithm is adopted to reduce the initial net load scene set to obtain a representative scene set.

The invention discloses a medical image feature selection method based on population tree search and hybrid intelligent heredity. The method comprises the following steps: acquiring a to-be-processed medical image feature data set; initializing a population tree; evaluating and calculating the fitness; and executing branch evolution, starting from the current tree node, and generating a plurality of sub-generation branches in parallel. Each branch generates a new population by applying a hybrid genetic algorithm to the parent medical image feature subset population; analyzing statistical summary information of all filial generation branches by using a decision model; and performing depth-first search on the population tree until a preset termination condition is met. And finally, outputting a medical image feature subset with the highest fitness found in the whole search process as an optimal feature selection result. According to the method, the problems that a traditional feature selection method is prone to falling into local optimum in high-dimensional data and lacks intelligent guidance are solved, and the global search capability, the convergence speed and the solution quality of the feature selection process are improved.

The invention discloses a graph anomaly detection method and system based on graph contrast learning, and relates to the technical field of graph neural networks. The method comprises the following steps: constructing a graph encoder DP-GNN, and obtaining effective node representation in an attribute graph for a subsequent graph anomaly detection task; a cross-scale contrast learning model is constructed, and joint detection of attribute anomaly and structure anomaly is realized by maximizing semantic distances of positive and negative samples in an attribute space and a structure space; and constructing a feature screening framework of global search and local optimization, and realizing screening of key feature subsets through a hybrid genetic algorithm. According to the method, joint detection of the node attribute anomaly and the structure anomaly can be realized, and the anomaly detection accuracy is improved.

The invention relates to the field of agricultural machinery intelligent operation, and discloses a multi-type agricultural plot agricultural machinery collaborative operation simulation system which comprises a plot data input module, an agricultural machinery parameter setting module, an operation task distribution module, a multi-agent collaborative scheduling module, a simulation operation module and a result evaluation module. Firstly, information of agricultural plots is collected through the plot data input module; then agricultural machine performance parameters are managed through an agricultural machine parameter setting module, and a random forest regression model is used for self-adaptive optimization; performing operation task allocation through a hybrid genetic algorithm and a particle swarm optimization algorithm, and optimizing operation time and energy consumption; the multi-agent system simulates and cooperates with operation of multiple agricultural machines, and an A * algorithm and a reinforcement learning algorithm are used to optimize a path; and finally, the operation efficiency, the energy consumption and the soil influence are evaluated through a result evaluation module, and a detailed evaluation report is generated. The working efficiency of the agricultural machine is improved, energy is saved, and soil is protected.

The present invention relates to the field of data processing technology, and in particular to a method, device, equipment and storage medium for generating an optical cable laying plan. The method comprises: processing engineering information to extract road section information; converting the road section information into a feature vector and inputting the feature vector into a laying method decision model to determine the laying method; determining whether to correct the laying method based on feature labels included in the road section information, and obtaining a cost correction coefficient if no correction is required; constructing an objective function and constraint conditions; solving the objective function using a hybrid genetic algorithm to obtain optical fiber information; integrating road section information, laying methods and optical fiber information to generate an optical cable laying plan; the method disclosed in the present application can automatically process engineering information to quickly obtain road section information, significantly shorten the design cycle to several days, reduce manual intervention, and improve planning efficiency; in addition, by constructing feature vectors and decision models, personalized optimization of road section laying is achieved to ensure accurate adaptation of the plan.

The invention discloses a mine transportation scheduling method and system based on a hybrid genetic algorithm, and belongs to the technical field of intelligent optimization scheduling. The method comprises the following steps: S100, inputting mine tunnel network, facility and equipment parameters; s200, a Dijkstra algorithm and breadth-first search are combined, and an optimal path set containing a shortest path and a secondary short path is generated for each pair of ore unloading fields and mining sites so as to disperse traffic flows; s300, establishing a multi-objective optimization model for minimizing waste time and fuel consumption and maximizing transportation volume; s400, a non-dominated sorting genetic algorithm is adopted for solving, the core of the non-dominated sorting genetic algorithm is that a special triple coding mode is adopted, an execution vehicle is allocated for each transportation task, a going route is selected for each transportation task, a return route is selected for each transportation task, and complex constraints are fused into a chromosome structure; s500, performing dynamic simulation on each scheduling scheme, updating the vehicle state and speed based on the real-time road congestion degree, and accurately evaluating the performance of the scheme; s600, selecting a final scheme from the Pareto optimal solution set by using a multi-attribute decision-making method; and S700, when a fault occurs, automatically re-evaluating and allocating tasks. According to the method, the problems of single path, inaccurate model and uncomfortable coding of a traditional method are effectively solved, and high efficiency, energy conservation and high robustness of vehicle scheduling in a complex mine tunnel network are realized.

The application provides a full-line grounding state evaluation method based on an improved hybrid genetic algorithm, belongs to the grounding resistance monitoring problem of a power system, and comprises the following steps: measuring each grounding resistance; establishing an objective function of the improved hybrid genetic algorithm; constructing a suitable BP neural network; training the BP neural network; and judging whether the error reaches the specified requirement or not.The application improves the grounding resistance measurement mode, realizes real-time monitoring of the grounding resistance, performs trend analysis and early warning, reduces the workload of manual measurement, and improves the work efficiency.

The application provides an automatic guided vehicle scheduling method and device, computer equipment and a storage medium, and belongs to the technical field of production scheduling. The method comprises the following steps: acquiring the workpiece quantity, the process quantity and the parallel machine quantity for processing the workpiece of the automatic guided vehicle; encoding the priority of the workpiece transportation and the parallel machine selection of each workpiece in each process according to the workpiece quantity, the process quantity and the parallel machine quantity, to obtain an initial scheduling scheme; for any workpiece, determining the transportation plan of the workpiece in the current process, the state of the corresponding parallel machine and the position of the automatic guided vehicle in the idle state, and determining the transportation plan of the workpiece in the next process; constructing a parallel multi-population hybrid genetic algorithm, iteratively optimizing the initial scheduling scheme according to the transportation plan of any workpiece in the next process, to obtain an optimal scheduling scheme; and scheduling the automatic guided vehicle according to the optimal scheduling scheme. In this way, the utilization efficiency of AGV scheduling can be effectively improved.

The invention discloses a large model coding agent system of a hybrid genetic algorithm and an implementation method. The system comprises a user interaction and configuration layer, an evolution core layer, a large model coding agent layer and a data storage and result layer. The invention provides a system framework for deeply coupling a global population evolution mechanism of a genetic algorithm and deep code understanding and intelligent generation capability of a large language model coding agent, and realizes a novel intelligent code generation and optimization system capable of efficiently discovering, generating and optimizing high-quality and innovative codes and algorithms.

The invention relates to the field of power plant energy saving, and discloses a power plant energy-saving optimization control method, which comprises the steps of calling historical efficiency data, calculating deviation based on an optimized actual energy efficiency value, quantifying energy-saving potential, generating a potential evaluation report, updating an optimized equipment parameter set on the basis of the potential evaluation report, and giving an adjustment suggestion. According to the method, global search and local optimization can be considered through combination of the hybrid genetic algorithm and the particle swarm algorithm, and limitation of a single algorithm, such as premature convergence of the genetic algorithm or falling into local optimization of the particle swarm algorithm, is avoided, so that optimization precision and efficiency are improved. According to the method, the optimization direction is accurately positioned, the defect that a key loss item is neglected in a traditional single balance method is overcome, the energy-saving potential is continuously excavated through closed-loop adjustment, it is ensured that the energy efficiency value continuously approaches the target, the optimization stagnation phenomenon is avoided, and the continuity and operability of energy-saving optimization of the power plant are improved.

The application discloses a kind of based on big data analysis's automobile sealing production resource intelligent scheduling method, specifically related to production resource scheduling field, for solving the problem that it is difficult to match between resource allocation and assembly quality in the process of existing multi-sealing assembly production scheduling;Scheme by constructing sealing assembly coupling topological relation network, identifying coupling sealing assembly, establishing component collaborative size distribution domain and assembly stable sub-domain, constructing size collaborative deviation index, and combining historical production resource allocation to build associated prediction model, on this basis, with the minimum size collaborative deviation cumulative amount as the goal, using hybrid genetic algorithm to jointly optimize equipment resources, material resources and process path resources, generate production scheduling strategy for assembly stability, so as to realize the systematization, refinement and intelligent scheduling of sealing production resources.

A general assembly project scheduling optimization method based on importance and a resource unavailable time window comprises the following steps: analyzing topological characteristics and information transfer capability of a process in a complex equipment general assembly network through a process importance evaluation method, and after the process importance is obtained, generating a global approximate optimal scheduling scheme according to a hybrid genetic-variable neighborhood search algorithm. According to the method, through an optimization module for process importance quantification, global search of a hybrid genetic algorithm and local search of an improved variable neighborhood search algorithm, heuristic information mining and scheduling optimization of a complex equipment general assembly system are integrated, so that the algorithm search efficiency is remarkably improved, and meanwhile, premature convergence to a local optimal solution is avoided; and a new thought is provided for solving a production scheduling optimization problem in a complex production environment.

This invention discloses a dual-tunnel scheduling optimization method based on a hybrid genetic algorithm and rolling time domain, belonging to the field of tunnel engineering construction management technology. It includes: constructing a multi-objective scheduling model for dual-tunnel construction with the objectives of minimizing the total project duration and minimizing the weighted resource peak value; using a constraint method to transform the multi-objective scheduling model into a resource-balanced single-objective optimization model under a fixed project duration constraint; using a hybrid genetic algorithm to perform static global optimization on the single-objective optimization model; establishing a dynamic monitoring mechanism based on rolling time domain through multi-dimensional IoT sensing; updating the parameters or status of affected processes according to the type of interference event when interference events are detected; using a heuristic local scheduling strategy to reschedule unscheduled tasks after interference, predicting the final project state, and generating a dynamically adjusted construction scheduling scheme. This invention combines static global optimization with dynamic real-time adjustment to achieve dual optimization of project duration and resources.

The embodiment of the invention discloses a liner path and navigational speed collaborative optimization method and system considering an emission control area. The method comprises the steps that S1, assumed conditions corresponding to liner path selection and navigational speed optimization problems of containers considering the emission control area and perishable products are defined; s2, creating a liner path selection and navigational speed optimization model which corresponds to the optimization target and considers emission control area limitation and perishable product transportation; and S3, solving the liner path selection and navigational speed optimization model through an adaptive hybrid genetic algorithm to generate a corresponding liner path and navigational speed collaborative optimization scheme. According to the method, the policy constraint of an emission control area (ECA) and the transportation time requirement of perishable products are analyzed, a mixed integer nonlinear programming model with the minimum total operation cost as the target is constructed, and an improved self-adaptive hybrid genetic algorithm is adopted for solving; and an optimal ship path and speed cooperation scheme is dynamically generated based on multiple factors such as an ECA region boundary, a fuel price and a port time window.

The invention discloses a garbage can overflow state recognition and intelligent clearance scheduling method and system based on a lightweight visual model, and belongs to the technical field of smart cities. The method comprises the following steps: constructing an end-edge-cloud three-level collaborative architecture; local reasoning is carried out on the internal image of the garbage can through a lightweight visual model on the terminal side, and a fine-grained filling state is obtained; after uploading the state data, constructing a clearance demand portrait on the cloud based on the multi-dimensional information; modeling a clearance task into a dynamic vehicle path problem with constraints through an intelligent scheduling model fusing a hybrid genetic algorithm and deep reinforcement learning, solving the dynamic vehicle path problem, and generating an optimal clearance route and a scheduling instruction; and finally, the on-demand and efficient clearing operation is realized. The system correspondingly comprises a terminal sensing module, an edge gateway module and a cloud platform management module. According to the invention, high-precision and low-power-consumption dynamic intelligent scheduling of state sensing and data driving is realized, the clearing efficiency and the response speed are obviously improved, and the operation cost is reduced.

The present application relates to a power battery SOC and SOH joint estimation method, in particular to a lithium ion power battery SOC and SOH joint estimation method based on FOA SEKF-EKF, containing a fractional order equivalent circuit model of two parallel fractional order CPE branches, a hybrid genetic algorithm HGA is proposed by fusing differential evolution strategy and adaptive mutation mechanism, the precise estimation of SOC and terminal voltage in fast time scale is realized by introducing a sliding mode observer and FOA SEKF, the model parameters and battery capacity are periodically online corrected based on EKF in slow time scale, realizing high-precision, strong-robustness battery SOC and SOH joint estimation. The present application is suitable for complex industrial environments such as electric vehicles and rail transit, without setting a large number of hyperparameters, and without excessive dependence on the quality and quantity of data, with good interpretability, adaptability and engineering practicability, especially in frequent start-stop and non-steady-state operating conditions, high-precision collaborative estimation of SOC and SOH can still be realized, significantly reducing the risk of misjudgment and estimation drift.

This application belongs to the technical field of hydraulic suspension stiffness and damping design optimization, specifically involving a hydraulic suspension stiffness and damping full-condition matching design method and system, including the following steps: S1: Establishing the structural parameters of the damping orifice and one-way valve. S The dataset, with 1 as input and flow coefficient as output, simultaneously establishes the cylinder. 、 Piston rod structural parameters S 2. Initial inflation pressure p For input, elastic force F 2( x, p, S 2) The output dataset; S2: Establish the structural parameters through the neural network. S 1. Speed v With damping force F 1( v, S 1) Mapping; Initial inflation pressure p Structural parameters S 2. Location x With elastic force F 2( x, p, S 2) Mapping; S3. Optimization using a hybrid genetic algorithm based on the LM algorithm; S4: Outputting the optimal parameters; The advantage is that, through the coordinated optimization of the damping orifice, one-way valve, cylinder, piston rod structure, and initial charging pressure, the precise design and efficient structural matching of the stiffness and damping of the oil-gas spring are achieved.

The application discloses a dynamic task planning method based on a hybrid genetic algorithm, belongs to the technical field of dynamic task planning of unmanned aerial vehicles, and is used for realizing dynamic task distribution in a search reconnaissance task scene. First, the hybrid genetic algorithm is used to perform pre-planning according to task information and unmanned aerial vehicle capability information, and a pre-planning scheme is obtained. The hybrid genetic algorithm is combined by an original genetic algorithm and a variable neighborhood search algorithm, the basic genetic algorithm is used to ensure the exploration ability of the algorithm, and the variable neighborhood search algorithm is used to ensure the development ability of the algorithm. Then, dynamic task information is loaded, and dynamic tasks are sorted according to the time when the dynamic task information appears. Then, a dynamic distribution mechanism is used for distributing the dynamic tasks, four kinds of dynamic adjustment strategies are designed for different task scenes, and the four kinds of dynamic adjustment strategies are respectively a random distribution strategy, a distribution strategy based on clustering center distribution, a nearest distribution strategy and a distribution strategy based on fuel remaining amount. Finally, the unmanned aerial vehicle updates a task sequence.

The invention relates to a software defined network topology discovery process optimization method and device, equipment and a medium. According to the method, dynamic optimization of the topology discovery time of the software defined network is realized by constructing a ternary coupling model of a topology detection period, topology discovery time and a control message proportion and designing a three-stage optimization framework of feature extraction, model prediction and constraint solution. A topological feature driven double-task neural network prediction mechanism is adopted, and the complex nonlinear relation between the network state and the performance index is effectively captured; self-adaptive adjustment of periodic parameters is realized in combination with an improved hybrid genetic algorithm, and limitation of a static configuration mode is broken through; the topology convergence time delay is obviously reduced on the premise of ensuring the control message proportion constraint, and the control plane efficiency and the data plane load are both considered; for network topologies of different scales and structures, a global optimal decision is realized by dynamically adjusting a detection period, stable performance is kept in a heterogeneous scene, and the method has good environmental adaptability, decision real-time performance and engineering expandability.

The application discloses a double-fed fan control identification method based on a hybrid genetic algorithm, and comprises the following steps: step S1, a control model of a double-fed fan RSC is established, and double-fed fan identification parameters are determined according to the control model of the double-fed fan RSC; step S2, an immune algorithm and an adaptability optimization function are introduced to construct a hybrid genetic algorithm, and the hybrid genetic algorithm is used to identify the identification parameters; step S3, an individual identification, an elite reservation and a whole identification strategy are used for iterative training, and trained identification parameters are obtained; and step S4, the trained identification parameters are input into an identification model to obtain corresponding active power and reactive power output simulation curves, a weighted average absolute deviation is calculated according to the output simulation curves, and error analysis is carried out according to the weighted average absolute deviation; the application introduces an immune strategy, and elite parameters in the parameters are reserved in the iteration process, so that the convergence speed is improved, and falling into a local solution is avoided.

The invention belongs to the field of logistics distribution optimization, and relates to a logistics distribution path optimization technology, in particular to a two-stage path optimization method based on key node selection, which comprises the following steps: step 1, key node selection; the method comprises the following steps: firstly, analyzing all road network nodes in a distribution area by using an asynchronous dominant actor commentator algorithm, and selecting a plurality of key nodes according to factors of node importance, traffic flow and surrounding road conditions; 2, preliminarily planning a path; on the basis of the key nodes, in combination with road constraint information, connection paths from a distribution starting point to all the key nodes, between the key nodes and paths from the key nodes to a distribution terminal point are preliminarily planned by using a hybrid genetic algorithm based on a deep Q network; step 3, re-planning a path; in the vehicle driving process, real-time road condition information is considered, if the road condition information changes suddenly to influence the vehicle passing road section, the delivery path between the affected nodes is adjusted, and the order delay rate is reduced.

The invention discloses a photovoltaic maximum power point tracking (MPPT) method based on a hybrid genetic algorithm and a particle swarm algorithm (PSO-GA), and belongs to the technical field of photovoltaic power generation and intelligent control. The method comprises the following steps: firstly, carrying out rapid preliminary search in a solution space by utilizing a particle swarm optimization algorithm, and approaching a better power region in a shorter time; and then, taking a globally optimal solution output by the particle swarm algorithm and population information thereof as an initial population of a genetic algorithm, and further breaking a local optimal trap and enhancing global search capability through selection, crossover and mutation operations of the genetic algorithm, thereby realizing accurate positioning of a global maximum power point (GMPP). Compared with a traditional PSO algorithm, the method has the advantages of being high in optimization precision, high in convergence speed and high in dynamic response capability, and can maintain the high efficiency and stability of the operation of the photovoltaic system under the complex shading condition.

The invention discloses an automobile sealing element production resource intelligent scheduling method based on big data analysis, particularly relates to the field of production resource scheduling, and is used for solving the problem that cooperative matching between resource configuration and assembly quality is difficult to plan as a whole in the existing multi-sealing element assembly production scheduling process. According to the scheme, a sealing element assembly coupling topological relation network is constructed, a coupling sealing assembly is identified, an assembly cooperation size distribution domain and an assembly stability subdomain are established, a size cooperation deviation index is constructed, a correlation prediction model is constructed in combination with historical production resource configuration, and on the basis, the size cooperation deviation cumulant is minimized as a target. A hybrid genetic algorithm is adopted to perform joint optimization on equipment resources, material resources and process path resources, and a production scheduling strategy oriented to assembly stability is generated, so that systematized, refined and intelligent scheduling of sealing element production resources is realized.