Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

24results about How to "Improve solution quality" patented technology

Multi-AGV path planning method and system based on deep reinforcement learning

The invention belongs to the technical field of AGV path planning. According to the multi-AGV path planning method and system based on deep reinforcement learning, an MDP model of an AGV path planning problem is established, a reward function is constructed in a reward remodeling mode, and the AGVs are guided to evaluate real-time actions more accurately; an improved PPO algorithm is provided, an Actor-Critic network is established for an AGV path planning problem, and a strategy network is updated by using a synchronization strategy updating mode; different scales of task tests prove that the MAPPO algorithm provided by the invention has better solving performance compared with a PPO algorithm in a large-scale storage environment; in addition, compared with a traditional path planning method, the method has the advantages that the length of the solved average path is shorter, the number of inflection points is smaller, and higher solving quality is achieved.
Owner:SHANDONG UNIV

Multi-agent water-wind-light short-term power generation optimization scheduling method considering space-time coupling constraint

The invention relates to the technical field of hydropower dispatching, and discloses a multi-agent water-wind-light short-term power generation optimization dispatching method considering space-time coupling constraints. Firstly, on the basis of drainage basin characteristics, a hierarchical decomposition strategy is adopted, and overall centralized optimization solution of the water-wind-light complementary power supply system is converted into partial multi-agent collaborative optimization scheduling, so that the solution efficiency is improved; secondly, in combination with a multi-agent and unified optimization operation theory, constructing a double-layer nested short-term water consumption minimum model considering wind power and photovoltaic power prediction output, so as to realize intelligent modeling; and finally, an improved alternating direction multiplier method is adopted, and interaction among multiple agents is coordinated based on a modification strategy of a flow balance and electric quantity matching principle, so that the solving quality is improved. According to the method, the solving efficiency and precision can be effectively improved, and a solid theoretical basis and a feasible thought are provided for short-term power generation dispatching of a large-scale water-wind-light complementary power supply system.
Owner:DALIAN UNIV OF TECH

Robot task allocation method based on improved multi-target genetic algorithm

PendingCN119599318AImprove solution qualityFast solutionGenetic algorithmsAlgorithmGenetics algorithms
The invention discloses a robot task allocation method based on an improved multi-target genetic algorithm, and relates to the technical field of robot task allocation, and the method comprises the following steps: building a multi-target robot task allocation problem model, and initializing model parameters; and optimizing the multi-target robot task allocation problem model by adopting an improved multi-target genetic algorithm to obtain a task allocation result. According to the method, the population is divided into a plurality of sub-populations, improved crossover mutation operation, population knowledge sharing interaction operation and fusion selection operation are introduced, an improved multi-target genetic algorithm is formed and applied to optimization of a multi-target robot task allocation problem model, and the problems that an existing robot task allocation technology is poor in solving quality and high in efficiency can be effectively solved. The solving speed is slow, and the diversity of solution sets is poor.
Owner:GUANGZHOU UNIVERSITY

Underwater wireless sensor network target coverage deployment method based on submarine topography

ActiveCN119562268AImprove transmission qualityOptimize deployment locationNetwork topologiesTransmissionInteger non linear programmingCommunications system
The invention discloses an underwater wireless sensor network target coverage deployment method based on submarine topography, and the method comprises the steps: considering the underwater wireless sensor network target coverage problem of submarine topography, and constructing an integer nonlinear programming model INLP; and solving the integer nonlinear programming model INLP by adopting a Harris eagle optimization algorithm. According to the method, the submarine topographic features are creatively combined, the loss of the underwater acoustic signal is calculated by adopting the underwater acoustic simulator BELLHOP3D, and the transmission success rate of the link is further derived, so that the transmission quality of the underwater communication system is effectively improved. By constructing the integer nonlinear programming model, the deployment positions of the underwater sensor nodes are optimized, the coverage rate and the uniformity are maximized, and the problem that the influence of complex submarine topography on signal transmission cannot be fully considered in a traditional underwater network deployment method is solved.
Owner:TIANJIN UNIV

Mechanical arm sparse motion planning method and system based on cross-species optimization

The invention discloses a mechanical arm sparse motion planning method and system based on cross-species optimization, and belongs to the technical field of mechanical arm control, and the method comprises the steps: S1, building a constraint sparse motion planning model of a mechanical arm by taking the joint angle velocity space energy of the mechanical arm as a target function, converting into an unconstrained sparse motion planning model based on a Lagrangian multiplier method; s2, constructing an error momentum neural network for solving the unconstrained sparse motion planning model in the current iteration, wherein the error momentum neural network comprises a hidden layer and an output layer; s3, solving output layer variables of the error momentum neural network model under different initial points, taking each output layer variable as a particle, and searching an optimal output layer variable by using a particle swarm algorithm; s4, if the maximum number of iterations is not reached, turning to S2; otherwise, the sparse motion planning of the mechanical arm is realized according to the optimal output layer variable in each iteration. According to the method, the globally optimal solution can be quickly searched, and the solution quality of sparse motion planning of the mechanical arm is improved.
Owner:HUAZHONG UNIV OF SCI & TECH

Emergency logistics two-stage path optimization method based on truck-unmanned aerial vehicle cooperation

The invention discloses an emergency logistics two-stage path optimization method based on truck-unmanned aerial vehicle cooperation, and relates to the technical field of emergency logistics path optimization, the method is based on a truck-unmanned aerial vehicle cooperation two-stage path optimization algorithm, the method is composed of a self-adaptive K-means clustering algorithm and a variable neighborhood simulated annealing algorithm, the calculation efficiency is high, the solving quality is high, and the method is suitable for large-scale popularization and application. And the method has a relatively high practical value for the emergency logistics transportation optimization problem with relatively strict timeliness requirements. The method has high universality and transportability, can better deal with the scene that the road is interrupted and emergency materials are affected to arrive in time under the emergency situation, can provide reference for the government and decision consultation department to formulate an emergency logistics transportation mode, improves the emergency rescue efficiency, and ensures the credibility of decision.
Owner:JIANGSU AVIATION VOCATIONAL & TECH COLLEGE

Automatic driving obstacle recognition method, device, electronic device and storage medium

The present application discloses an obstacle recognition method, device, electronic device and storage medium for autonomous driving. The method includes: based on visual recognition, collecting image data and annotating the data; generating image samples based on a visual simulation generative adversarial network algorithm to expand image data; inputting the expanded data into a feature extraction model to train the feature extraction model; inputting the feature extracted data into a feature dimension reduction model to train the feature dimension reduction model; inputting the dimension reduction data into a classifier to train the classifier; performing visual obstacle recognition based on the trained feature extraction model, data dimension reduction model and classifier model. Through the above scheme, the image generated by the generative adversarial network and the feature enhancement loss function are generated to improve the recognition ability of the model on unseen obstacle images.
Owner:CHINA FAW CO LTD +1

Search and rescue robot group cooperative task allocation and path planning method and system

The invention provides a search and rescue robot group cooperative task allocation and path planning method and system. The method comprises the following steps: constructing a global product Markov decision process model according to task requirements corresponding to search and rescue robot group system tasks and current environment information; based on the MDP model, circularly selecting robots, and solving an optimal strategy of each robot in the local MDP model by using an improved Q-learning algorithm; the selected robot is controlled to move according to the optimal strategy, the environment estimation weight of each moving step of the robot is updated, and the environment estimation results of all the robots are fused; updating a global product MDP according to an environment fusion result, judging whether to enter a final state of the global product MDP, and if so, stopping calculation; if not, returning is carried out, and the final state is that all the robots complete the search and rescue tasks and all the positions in the implementation process are updated; the search and rescue robot aims at overcoming the defects in the prior art and effectively improving the applicability of the search and rescue robot in the actual task environment.
Owner:SHAANXI UNIV OF SCI & TECH

Multi-unmanned aerial vehicle task allocation method based on improved distribution estimation algorithm

The invention discloses a multi-unmanned aerial vehicle (UAV) task allocation method based on an improved distribution estimation algorithm, which adopts a mathematical threshold model in the generation probability part of the existing distribution estimation algorithm, and achieves a faster convergence effect in the subsequent population iteration by generating a probability model capable of showing the current capability of the UAV, and in addition, the probability model of the current capability of the UAV can be further improved. According to the method, two local search strategies are fused, the problem of falling into a local optimal solution possibly occurring in the optimization process is effectively solved, the local structure of an existing solution can be broken through to explore a new better solution by exchanging non-adjacent segments in a path, resource waste caused by waiting time can be effectively reduced through insertion operation, and the optimization efficiency is improved. Therefore, the local optimization effect is achieved, the solving quality is improved, and the flight cost of the unmanned aerial vehicle is reduced.
Owner:BEIJING INST OF TECH

Rider-drone collaborative delivery dynamic path optimization method based on order bundling

PendingCN122674958AVerify validityVerify solution performance
This invention belongs to the field of dynamic path optimization and discloses a dynamic path optimization method for rider-drone collaborative delivery based on order bundling. It includes constructing a dynamic path optimization model with the objective function of minimizing platform costs and customer satisfaction reduction costs. Platform costs include drone dispatch costs, drone delivery costs, rider dispatch costs, rider delivery costs, and rider salaries. The total delivery optimization period is divided into several order delivery plan re-optimization cycles using time windows. At the beginning of each order delivery plan re-optimization cycle and upon the arrival of a new order, an adjustment to the order delivery plan is triggered. This invention improves the delivery system's responsiveness and overall efficiency in dynamic environments by designing a dynamic optimization mechanism that considers order bundling and a two-stage order bundling strategy. Sensitivity analysis, comparative experiments, and ablation experiments based on simulation examples of different scales are conducted to verify the effectiveness of the proposed method.
Owner:WUHU REACHED STORAGE & TRANSPORTATION CO LTD

Selective disassembly sequence planning method based on improved sparrow algorithm

The invention relates to a selective disassembly sequence planning method based on an improved sparrow algorithm. The method is used for solving the problem that in the prior art, the quality and stability of a selective disassembly sequence are poor. The planning method comprises the following steps: establishing a priority constraint matrix Gp according to constraints among equipment parts; determining a target disassembly part, and searching a necessary disassembly part by utilizing a target reverse search method in combination with the priority constraint matrix Gp; establishing an initial disassembly sequence population, and calculating a sequence adaptive value by using a selective disassembly sequence index function F; and optimizing and disassembling the sequence population by using an improved sparrow algorithm, and solving an optimal solution in combination with the sequence concentration.
Owner:CHONGQING UNIV OF POSTS & TELECOMM

Hole group machining path optimization method

PendingCN119247767AImprove solution qualityAdaptive controlAlgorithmGenetics algorithms
The invention relates to a hole group processing path optimization method, and belongs to the technical field of hole group processing, and the method comprises the steps: S101, obtaining an initial population, the genes of individuals in the population comprising a hole group processing path, a genetic parameter and a simulated annealing parameter; s102, based on the genetic parameters of the initial population, performing selection, crossover and mutation operation on the simulated annealing parameters of the initial population to obtain an intermediate population; s103, based on the simulated annealing parameters of the intermediate population, performing simulated annealing operation on the hole group processing path of the intermediate population to obtain a target population; and step S104, substituting the target population as a new initial population into the step S102 until the genetic parameters of the target population meet a termination condition, and obtaining an optimal hole group machining path. By combining the advantages of the genetic algorithm and the simulated annealing algorithm, the solution quality of the hole group processing path optimization problem is effectively improved.
Owner:WUHAN UNIV OF TECH

Circuit hypergraph determination method, device, computer equipment and storage medium

The present invention relates to the field of FPGA technology, and discloses a circuit hypergraph determination method, device, computer equipment and storage medium, the method comprising: obtaining a topological diagram of an original circuit designed for an FPGA chip, and determining the topological order corresponding to each logic unit in the original circuit based on the topological diagram; determining at least one heterogeneous resource in the original circuit; determining the connection information between the logic units in each heterogeneous resource based on the topological order, and constructing a hypergraph of each heterogeneous resource according to the logic units and the connection information, so as to obtain a hypergraph collection corresponding to the original circuit. The present invention reduces the complexity of the hypergraph when solving by a layout algorithm, and at the same time reduces the constraints and reduces the difficulty of solving the layout algorithm. In addition, since there is no coupling relationship between the hypergraphs corresponding to different types of heterogeneous resources, the hypergraph collection can be operated in parallel, which further improves the solution efficiency and improves the solution quality.
Owner:SUZHOU YIGE TECH CO LTD

Method, system and device for searching solutions to parallel integer linear programming problems

ActiveCN118193930BReduce duplicate searchesImprove solution qualityDigital data processing detailsForecastingLocal optimumTheoretical computer science
The present invention provides a solution search method, system and device for parallel integer linear programming problems. The method comprises: running multiple local search solvers in parallel, each local search solver having the same integer linear programming problem to be solved and configured with different initial solutions; obtaining feasible solutions that meet preset solution quality requirements searched by each local search solver, and collecting the obtained feasible solutions into a preset solution pool; before reaching a preset solution time threshold, monitoring the operating state of each local search solver, and determining whether the corresponding local search solver falls into a local optimal state according to the operating state; selecting a feasible solution from the solution pool as a shared feasible solution, and using the shared feasible solution as a target local search solver that falls into a local optimal state to restart the initial solution of the local search and restart the local search, thereby reducing repeated searches caused by fixed rules, increasing the probability of searching solutions in different areas, and effectively improving the solution quality.
Owner:XIDE QIUSHUO (BEIJING) TECH CO LTD

Tokamak plasma current density reconstruction system based on a coherent ising machine

ActiveCN122334540Breduce the number of iterationsDoes not increase the main iteration complexity
The application relates to the cross technical field of quantum computing and nuclear fusion plasma profile reconstruction, in particular to a tokamak plasma current density reconstruction system based on a coherent Ising machine. The technical scheme comprises an electromagnetic diagnosis data acquisition unit and a Bayesian posterior modeling processor. The electromagnetic diagnosis data acquisition unit is used for collecting external electromagnetic measurement data of a tokamak device in real time to form a measurement vector. The Bayesian posterior modeling processor is connected with the electromagnetic diagnosis data acquisition unit and is used for constructing a posterior precision matrix and a linear term coefficient vector based on a conditional autoregressive prior model and electromagnetic measurement likelihood probability. The application organically fuses Bayesian inference modeling, spatial block decomposition, block coordinate descent iteration control and coherent Ising machine quantum solution, realizes high-precision, uncertainty-quantized and rapid reconstruction of a tokamak plasma current density profile under the constraint of existing quantum hardware bit capacity.
Owner:INST OF ENERGY HEFEI COMPREHENSIVE NAT SCI CENT (ANHUI ENERGY LAB) +2

High-speed rail passenger and freight train working diagram optimization method, system, equipment, medium and product

The invention discloses a high-speed rail passenger and freight train working diagram optimization method, system and device, a medium and a product, and the method comprises the steps: firstly determining an optimization target, including minimizing the total travel time of a freight train, the operation deviation of the passenger train and the cargo delivery delay time; thirdly, constructing a mathematical model, and defining decision variables, an objective function and constraint conditions to form a high-speed railway passenger and freight train working diagram optimization model; on the basis of the model, a rolling time domain decomposition strategy is adopted, and a global scheduling problem is segmented into a local optimization problem of a plurality of time windows. And for each time window, obtaining a local optimal solution by using a linear programming solver so as to ensure that the dispatching of each train accords with the set constraint. Then, global search is carried out on the local solutions through a simulated annealing algorithm, the departure time and the operation plan of the train are optimized, and local optimum is avoided. And finally, a variable neighborhood local optimization method is applied, and the quality of the whole scheme is further improved by finely adjusting the solution.
Owner:CHENGDU UNIV OF INFORMATION TECH

Data set construction method, electronic equipment and storage medium

The invention discloses a data set construction method, electronic equipment and a storage medium. The method comprises the steps of obtaining a preset open source model and a plurality of original data sets corresponding to a plurality of to-be-solved problem types; determining a plurality of initial supervision data sets corresponding to the plurality of original data sets and a plurality of problem word vector representations corresponding to the plurality of original data sets based on the plurality of original data sets and a preset open source model; cleaning the plurality of initial supervision data sets to obtain a plurality of intermediate supervision data sets; determining a plurality of to-be-mixed data sets in the plurality of intermediate supervision data sets based on the plurality of problem word vector representations; and merging the plurality of to-be-mixed data sets to obtain a target supervision data set. By utilizing the technology provided by the invention, high-quality supervision data can be formed to perform supervision fine tuning, and the robustness and generalization ability of a problem solving model are improved.
Owner:SHANGHAI PROCESSOR TECH INNOVATION CENT

Aviation composite material solidification scheduling method and system considering multilayer space and time window constraints

ActiveCN121787872Aincrease diversityEnhance global exploration capabilitiesComputational materials scienceInstruments
The invention discloses an aviation composite material solidification scheduling method and system considering multilayer space and time window constraints, and the method aims at multilayer board equipment space constraints, workpiece time window restrictions and batch processing demands in aviation composite material solidification production, and minimizes the maximum completion time as a target function. A single-machine batch scheduling model fusing multilayer space placement, laminate capacity and time window constraint is constructed, and meanwhile, an evolutionary algorithm combined with adaptive neighborhood search is adopted for solving; the improved strategies such as population initialization with time compatibility and random combination, a multi-dimensional neighborhood search operator and double-layer self-adaptive neighborhood selection are designed according to the characteristics of the composite material solidification scheduling, the global search and local optimization capability of the evolutionary algorithm is improved, and the solving quality and efficiency of the composite material solidification scheduling under the complex constraint are remarkably improved. The method can be widely applied to complex manufacturing scenes with multi-layer processing space, time window constraint and batch processing characteristics, such as aviation composite material forming and heat treatment furnace scheduling.
Owner:HOHAI UNIV

Multi-agent deep reinforcement learning-based double-gantry chip mounter taking and pasting sequence optimization method

The invention relates to a double-gantry chip mounter taking and mounting sequence optimization method based on multi-agent deep reinforcement learning, and belongs to the field of PCB mounting. The method comprises the following steps: defining a multi-agent deep reinforcement learning basic component under the optimization of a double-gantry chip mounter taking and pasting sequence; building an encoder network model; building a decoder network model embedded with an attention mechanism; building a commentator network model under an MAC-AC algorithm framework; introducing a mask mechanism to accelerate training; and performing neural network model training through an MAC-AC algorithm to obtain a pasting sequence optimization result. From the overall perspective, the problem of taking and pasting sequence optimization of the double-gantry chip mounter is solved end to end, and the problem solving quality is improved.
Owner:FUZHOU UNIV

A method and system for curing scheduling of aerospace composites considering multi-layer space and time window constraints

ActiveCN121787872Bincrease diversityEnhance global exploration capabilitiesAviationCompletion time
The application discloses a kind of considering multi-layer space and time window constraint's aviation composite curing scheduling method and system, the method is for the space constraint of multi-layer board equipment in aviation composite curing production, workpiece time window limit and batch processing demand, with minimizing maximum completion time as objective function, construct the single machine batch scheduling model of fusion multi-layer space placement, layer board capacity, time window constraint, while solving by using the evolutionary algorithm of combining adaptive neighborhood search, population initialization of time compatibility and random combination is designed for composite curing scheduling characteristics, multi-dimensional neighborhood search operator, double-layer adaptive neighborhood selection and other improvement strategies, improve the global search and local optimization ability of evolutionary algorithm, significantly improve the solution quality and efficiency of composite curing scheduling under complex constraint.The application can be widely applied to aviation composite forming, heat treatment furnace scheduling and other complex manufacturing scenarios with multi-layer processing space, time window constraint and batch processing characteristics.
Owner:HOHAI UNIV

A two-way feedback type storage location planning method and system

The application discloses a kind of two-way feedback type's warehouse location planning method and system, comprising: constructing multi-objective optimization model, determine weight space and variable space;Optimize weight vector is searched in weight space using particle swarm algorithm and is passed to genetic algorithm;Optimal warehouse location allocation and path sequence are searched in variable space using genetic algorithm;Elite solution set is extracted from optimal variable population and evaluated, generates the first feedback information from variable space to weight space;The statistical characteristics of current weight particle swarm are analyzed, generate the second feedback information from weight space to variable space;According to the search direction of first feedback information adjustment particle swarm algorithm, according to the second feedback information adjustment crossover probability and mutation probability of genetic algorithm;The history optimum of particle swarm and genetic algorithm is updated, records global optimal solution pair;Repeat iteration until convergence, output global optimal solution.The application improves the adaptability and robustness of warehouse location planning to dynamic environment by two-way feedback cooperative evolution.
Owner:QINGDAO RIRISHUN LOGISTICS CO LTD

Optimal control method for hydrogen-electricity coupling system

The invention belongs to the technical field of optimal control of a pressure delay osmotic energy-photovoltaic-solid oxide fuel cell and wind energy hybrid energy system, and particularly relates to an optimal control method for a hydrogen-electricity coupling system based on improved giant armadillo optimization. Based on a giant armadio optimization algorithm and a triangular topology aggregation optimizer, a key parameter, namely a random solution, is introduced in an exploration stage, an optimal solution is removed, the influence of a current solution on position updating is reduced, the convergence speed and the global search capability of the algorithm are improved, the solving quality is greatly improved, and the algorithm is more effective than a classical GAO algorithm, and has a wide application prospect. The real-time tracking and accuracy based on the IGAO algorithm are improved, and when the MPPT control problem is solved, the method has higher calculation accuracy and shorter operation time, can be used for a pressure delay osmotic energy-photovoltaic-solid oxide fuel cell and wind energy hybrid energy system to obtain higher power generation, and is beneficial to the development of the energy field.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Contract maximum demand optimization method based on user side energy storage

ActiveCN119398278Aimprove accuracySimplify the difficulty of solvingMarket predictionsForecastingMathematical modelSimulation
The invention discloses a contract maximum demand optimization method based on user side energy storage, relates to the technical field of contract maximum demand optimization, and solves the technical problem that in the prior art, when a user sets the maximum demand of a contract, a set value is often not accurate enough because the user depends on previous use experience and lacks a relatively scientific and systematic decision basis. The method comprises the following steps: acquiring energy storage data related to user side energy storage; constructing a double-layer mathematical model based on the energy storage data; wherein the double-layer mathematical model comprises an upper layer model and a lower layer model; solving the upper-layer model based on a golden section method to obtain a solution of the upper-layer model; solving the lower-layer model based on a Lagrange relaxation method to obtain a solution of the lower-layer model; and based on the solution of the upper-layer model and the solution of the lower-layer model, the maximized monthly income is obtained through calculation, and the technical problem is solved.
Owner:ANHUI UDAN TECH CO LTD