34 results about "Memetic algorithm" patented technology

The invention discloses a multi-agent path planning algorithm based on an adaptive memetic algorithm, and aims to solve the problems that the multi-agent path planning algorithm is not mature enough and the convergence speed of the algorithm is low. According to the optimization method, through an algorithm structure in which a global optimization algorithm is matched with local search, chromosomes are used as generation paths in a two-dimensional grid map, strategies such as'selection 'and'crossing' are carried out on the generation paths to optimize fitness values of the generation paths, and a hill climbing algorithm is used as a sub-algorithm to carry out local optimization on the generation paths, so that a generated solution is prevented from falling into local optimum, and the generation efficiency of the two-dimensional grid map is improved. Therefore, the multi-agent motion control precision is improved, and the convergence speed and optimization efficiency of the algorithm are enhanced. The problems that the algorithm convergence speed is low and the path optimization precision is low in the current multi-agent-based path planning field are solved. Experimental results show that the method can accurately realize multi-target-point path optimization for multiple agents, each path is converged to the global optimal path length along with the population iteration average length, and the algorithm test achieves an expected effect.

The invention discloses a discrete orthogonal code sequence optimization method based on an iterative greedy code search memetic algorithm, and belongs to the technical field of radar waveform design. The performance of the method provided by the invention is superior to that of the existing method, and the self-correlation and cross-correlation performance of the discrete orthogonal code sequence set optimized by the method provided by the invention is further close to the existing lower bound, so that the difference between the self-correlation and cross-correlation performance of the discrete orthogonal code sequence set and the existing lower bound is reduced. Compared with a greedy code search method, the iterative greedy code search strategy provided by the invention is stronger in local search capability, better in optimization effect and higher in search efficiency. And the method can improve the final search optimization result of the algorithm under the condition of not increasing the operation time of the algorithm. By simultaneously adopting crossover and mutation operators in each iteration, the search diversity of the algorithm is increased, and the search space of the algorithm is expanded, so that a discrete orthogonal code sequence set with better orthogonality can be obtained more possibly.

The invention discloses a post-disaster city full-coverage detection method based on a heterogeneous unmanned system, and belongs to the technical field of rescue, and the method comprises the steps: taking an unmanned plane and an unmanned vehicle as the heterogeneous unmanned system, and constructing a full-coverage path planning model of the heterogeneous unmanned system; discretizing the full-coverage path planning model of the heterogeneous unmanned system to obtain a discrete optimization model of the full-coverage path planning of the heterogeneous unmanned system; an improved memetic algorithm is adopted to optimize the on-off state of path points in the discrete optimization model, an optimal open point set is obtained, a mower algorithm is adopted to traverse the optimal open point set, and a shortest full-coverage detection path is obtained; and constructing a charging point dynamic adjustment mechanism, and performing full-coverage detection based on the shortest full-coverage detection path and the charging point dynamic adjustment mechanism. According to the method, the global search capability and the convergence speed of the memetic algorithm are effectively improved, a two-way convergence charging point dynamic adjustment strategy is designed, and the charging waiting time is effectively shortened.

The invention relates to a multi-target logistics distribution path optimization method based on AI, and the method comprises the following steps: obtaining order data, road network data and vehicle data of logistics distribution of a customer point, extracting basic information from the three types of data, and constructing the multi-dimensional features of the customer point; inputting the multi-dimensional features of the customer points into a pre-trained graph attention network for feature embedding, generating a distribution network feature graph fusing customer demands and a road network relationship, inputting a pre-trained reinforcement learning agent, and generating an initial path population with quality and diversity balance; performing iterative optimization on the initial path population based on a Memetic algorithm framework; and calculating the fitness of each individual on a plurality of preset optimization objectives, maintaining a Pareto solution set by adopting a multi-objective evolutionary algorithm with reference points, and recommending a final path scheme from the Pareto solution set based on user preferences. The method has the effect of remarkably improving the quality, efficiency and dynamic adaptability of path optimization.

The invention discloses a post-disaster multi-center material distribution method and system based on a double repair mechanism, and the method comprises the steps: inputting road network basic data, vehicle data, distribution point data and disaster-affected point data into a preset material distribution path planning model, and obtaining a material distribution strategy generated by the material distribution path planning model, wherein the material distribution path planning model takes the minimization of the total time of a vehicle from each distribution point to all disaster-affected points as an optimization problem, the optimization problem is solved through a memetic algorithm to obtain an optimal solution of path planning, and the memetic algorithm is used for repairing individuals with vehicle constraint violation in the initial population through a double repair mechanism. According to the post-disaster multi-center material distribution method and system based on the double-repair mechanism, the double-repair mechanism is provided, infeasible individuals in a population are repaired as much as possible, search of an algorithm can be carried out towards a feasible area, and an optimal material distribution strategy is obtained.

The invention provides a supply chain risk prediction method and device based on a graph neural network, and the method comprises the steps: S1, processing risk propagation sequence data during supply chain risk propagation into graph structure data, and obtaining a supply chain network time sequence risk propagation topological graph; s2, designing a deep neural network model, combining a graph convolutional neural network and a recurrent neural network in a series connection mode, and finally connecting a multi-layer perceptron in series; s3, a multi-population Memetic algorithm is utilized to train the deep neural network model, the multi-population Memetic algorithm is that a population of the Memetic algorithm is divided into a plurality of subgroups, and the subgroups are independently evolved through evolutionary operators; and S4, using the trained deep neural network model to predict the number of enterprises increased by infected nodes in a window T in a future period of time. According to the supply chain risk prediction method based on the graph neural network provided by the invention, more accurate and efficient risk prediction is realized, and a manager is helped to take measures in advance to reduce loss.

The application belongs to the field of workshop scheduling, and aims at solving the problem that the existing production scheduling method is only applicable to the homogeneous factory model.The method comprises the following steps: S1, establishing a distributed heterogeneous flow shop scheduling model; S2, initializing the basic parameters of the meme algorithm, and generating an initial population according to a hybrid initialization strategy; S3, evaluating the fitness value of the population individuals, and performing a Pareto non-dominated sorting; S4, performing a crossover operation on the individuals in the population with a certain probability; S5, performing a collaborative search on the population by using a search operator; S6, merging the offspring population and the parent population, and selecting half of the individuals as local search targets; S7, performing a local search on the selected target individuals; S8, updating the population; S9, if the algorithm meets the stopping condition, ending the algorithm process, and outputting a non-dominated solution set; otherwise, the algorithm goes to S4 and continues iteration.

The present invention discloses a double - layer and double - row layout method for a separated human - vehicle transportation elevator, comprising the following steps: S1, establishing a mixed - integer linear programming model, the model including an objective function and constraint conditions, the objective function being the minimum material movement cost and the minimum personnel movement cost, and the constraint conditions including: constraints on the relationship between machines and rows, constraints on the positional relationship between machines, constraints on the relationship between machines and floors, constraints on the position of freight elevators, constraints on the position of machines and freight elevators, safety layout constraints, personnel movement constraints, and material movement constraints; S2, generating an initial population based on three - layer coding and reverse learning; S3, solving the model based on the memetic algorithm and a solver. The present invention is based on the transportation scenarios in real workshops. To improve the safety of the layout, a new double - layer and double - row layout structure considering a separated human - vehicle transportation elevator is proposed, and a corresponding layout method is established, and this method has good effects.

The invention relates to the technical field of sewage treatment and detection, in particular to a self-organizing modular neural network effluent ammonia nitrogen detection method and system based on a memetic algorithm, and the method comprises the steps: collecting actual operation data of an urban sewage treatment plant to construct a data set; dividing a data segment of the training sample into a plurality of different operation conditions by adopting a multivariate segmentation method based on a memetic algorithm; designing a self-organizing sub-network based on variance sensitivity-mutual information, and training each sub-network by using different operation condition data; and inputting a test data sample into the model, integrating output results of each sub-network, carrying out reverse normalization on model output, and outputting an effluent ammonia nitrogen predicted value. Real-time detection of effluent ammonia nitrogen in the sewage treatment process is achieved through the effluent ammonia nitrogen soft measurement model, and the problem that the effluent ammonia nitrogen concentration in the sewage treatment process is difficult to detect in real time is solved.

The invention discloses a hybrid production flexible assembly job shop scheduling method considering multi-assembly sequence change and transportation tasks based on a Q-Learning model algorithm. The method comprises the following steps: S1, establishing a scheduling model taking total production completion time, total inventory time and total manpower cost as optimization targets; s2, providing a Q-Learning memetic algorithm to solve the scheduling model, designing a five-layer segmented mixed chromosome coding structure and a two-subgeneration chromosome updating method, and introducing a variable neighborhood search strategy and an elite retention strategy; s3, adaptively adjusting the cross range of the chromosomes through Q-Learning to improve the algorithm efficiency; and S4, through comparison with other three algorithms, validity and robustness of the proposed algorithm are verified. Based on the scheduling method provided by the invention, the processing and assembling sequences of product parts can be optimized simultaneously in the scheduling process of multi-product mixed production and consideration of transportation tasks, and meanwhile, machines, workers and AGV resources are reasonably allocated, so that the production cycle of products is effectively shortened.

The present invention provides a method for optimizing the path of traffic flow monitoring of a multi-UAV road network, comprising the steps of: S1, collecting road network information data and monitoring requirements, and constructing a multi-UAV traffic flow monitoring road network; S2, constructing a multi-objective optimization model for the path planning of traffic flow monitoring of a multi-UAV road network under the constraint of collection interval; S3, solving the multi-objective optimization model using a variable neighborhood local search genetic algorithm, i.e., a meme algorithm, constructed based on feasible solutions, to obtain a set of optimal paths for UAVs. The present invention constructs multiple optimization target models for minimizing equipment cost and minimizing energy consumption, and solves them through a variable neighborhood local search genetic algorithm, thereby obtaining a set of optimal path planning for multiple UAVs under the constraints of the monitored accuracy of road network traffic flow and the monitored collection interval market, providing economical and portable strong guarantees for the real-time and safety of road traffic informatization.

The invention relates to a hydro meteorology change point detection method and system, and belongs to the technical field of hydro meteorology scientificity, and the method comprises the steps: obtaining the observation data of a hydro meteorology time sequence; the number of change points of the observation data is initially 1; judging whether the number of change points is greater than a given maximum value or not; when the number of the change points is smaller than or equal to the maximum value, calculating the change rate of the fitness function under the current number of the change points according to a change point set obtained by carrying out change point detection on the observation data by utilizing a memetic algorithm and a corresponding fitness function value, and adding 1 to the number of the change points until the number of the change points is larger than the maximum value; and when the number of change points is greater than a given maximum value, determining an optimal number of change points and an optimal change point set according to the change rate of the fitness function corresponding to different numbers of change points. According to the invention, the dynamic change of the time sequence data can be adaptively processed, and the performance of hydro-meteorological change point detection is improved.

The present application relates to the technical field of inspection, and discloses a campus open space room heterogeneous unmanned cluster three-dimensional security inspection method, comprising: a central control platform based on an event type-atomic task-robot capability mapping knowledge base, decomposing a complex event into an atomic task set, and defining a capability demand vector; collecting real-time states of robots, constructing a constrained multi-objective optimization problem, and using a two-stage collaborative solving method combining an improved meme algorithm and conflict-oriented search to output an optimal task allocation and collaborative space-time path plan; issuing instructions through wireless communication, and robots working collaboratively and uploading data in real time; the central control platform fuses and analyzes data, triggers a rapid generation of an adjustment scheme when re-planning, and collects data after the completion of a task; to solve the technical problem that heterogeneous robots lack intelligent task allocation capability in a three-dimensional complex environment, resulting in low inspection collaboration efficiency.

The invention discloses a hybrid production flexible assembly job shop scheduling method considering multi-assembly sequence change based on a hybrid memetic algorithm, and the method comprises the following steps: S1, building a hybrid production flexible assembly job shop scheduling model with total production completion time, total inventory time and total labor cost as optimization targets under dual-resource constraint; a flexible assembly job shop scheduling mathematical model for multi-assembly sequence change mixed production is considered; s2, on the established mathematical model, providing a hybrid memetic algorithm to solve the provided problem, designing a four-layer segmented hybrid chromosome coding structure adapted to the problem and an updating method of two sub-generation chromosomes, and introducing a variable neighborhood search strategy and an elite retention strategy; s3, proving the superiority of the proposed scheduling method through case research; and S4, through comparison with a flower pollination algorithm and a rapid non-dominated genetic algorithm, verifying the effectiveness and robustness of the proposed algorithm. According to the hybrid production flexible assembly job shop scheduling method considering the multi-assembly sequence change based on the hybrid memetic algorithm, the processing sequence and the assembly sequence of product parts can be optimized at the same time in the multi-product hybrid production scheduling process, and machine and worker resources are reasonably distributed at the same time; and the production cycle of products is effectively shortened.

The invention discloses an unmanned aerial vehicle-unmanned vehicle air-ground cooperative logistics scheduling method, system and device, a medium and a product, and relates to the field of logistics distribution, and the method comprises the steps: obtaining the state parameter information of a logistics entity; on the basis of the state parameter information, a collaborative logistics mixed integer programming model is constructed by taking minimization of logistics scheduling completion total time as a target; and constructing an improved memetic algorithm, and performing iterative solution on the collaborative logistics mixed integer programming model through the improved memetic algorithm based on the state parameter information to obtain a collaborative logistics scheduling scheme. According to the method, the calculation cost can be effectively reduced, the solving efficiency and the practicability of the scheduling scheme are improved, and the real-time performance and safety of air-ground collaborative distribution are guaranteed.

The invention discloses an efficient dynamic roadside unit deployment method and system capable of detecting a Sybil attack. The method comprises the steps of collecting geographic information, evaluating roadside unit service coverage, an overlapping range and an accident information initial diffusion speed of a deployment area, and establishing an RSU deployment constraint capable of detecting the Sybil attack; constructing an RSU deployment scheme based on particle swarm optimization and an improved memetic algorithm; obtaining transportation and reconstruction RSU overhead, and obtaining a minimum RSU adjustment cost based on a bipartite graph matching algorithm; and collecting the working load of each RSU, and constructing a heuristic RSU minimum cost adjustment scheme based on a Pareto optimal principle. Under the constraint that the Sybil attack can be detected, by constructing a heuristic RSU efficient deployment and low-cost adjustment scheme, the service effective coverage range and the accident information initial diffusion speed in RSU deployment are improved, load balancing between RSUs is achieved with the minimum cost, and the capability of detecting the Sybil attack is achieved; the problems that a traditional RSU deployment scheme is low in comprehensive performance and cannot detect Sybil attacks are solved.

The invention discloses an automatic attack countermeasure method based on a multi-target memetic algorithm, which comprises the following steps: sampling after sorting loss values from a complete data set, and selecting a small data set for rough evaluation; initializing a population, generating an initial population containing a plurality of random attack sequences, and evaluating the robust precision and time consumption of each individual by using a small data set; generating a progeny population through crossover and mutation operations, and evaluating individuals in the progeny population; performing non-dominated sorting and crowding degree distance calculation on individuals of the parent population and the descendant population, and selecting a certain number of excellent individuals to form a current population; optimal individuals in the current population are randomly selected, local search is carried out by adjusting a loss function, an iteration step length or a restart point, and iteration is continuously carried out until a preset termination condition is not met; and carrying out local search on a better individual by utilizing the complete data set, adjusting a loss function, an iterative step length or a restart point, and outputting an optimal adversarial attack combination mode.

The invention discloses a whole vehicle logistics loading optimization method based on uniform counterweight constraints, which comprises the following steps of: taking a to-be-transported commercial vehicle attribute set and an available car transport vehicle attribute set as input data, setting model parameters and algorithm parameters, setting decision variables and objective functions, setting uniform counterweight constraints, and constructing a mixed integer programming model; and solving the model by adopting a memetic algorithm, and taking an optimal solution of a target function value as a final scheduling scheme to realize transportation income maximization.

The invention discloses a double-layer double-row layout method considering a separated human-vehicle transport elevator, which comprises the following steps: S1, a mixed integer linear programming model is established, the model comprises objective functions and constraint conditions, the objective functions are minimum material movement cost and minimum personnel movement cost, and the constraint conditions are constraint conditions; the constraint conditions comprise machine and line relation constraint, machine position relation constraint, machine and layer relation constraint, cargo elevator position constraint, machine and cargo elevator position constraint, safety layout constraint, personnel movement constraint and material movement constraint; s2, generating an initial population based on three-layer coding and reverse learning; and S3, solving the model based on a memetic algorithm and a solver. Based on a transportation scene in a real workshop, in order to improve the layout safety, the invention provides a new double-layer double-row layout structure considering the separated human-vehicle transportation elevator, and meanwhile, a corresponding layout method is established, and the method has a relatively good effect.

The invention discloses a multi-unmanned aerial vehicle multi-task target air route guiding method, and belongs to the field of unmanned aerial vehicle intelligent optimization algorithms. Providing a feasible waypoint set generation method for a multi-target collaborative detection scene; meanwhile, a feasible waypoint set reduction method is designed based on requirements in the aspects of unmanned aerial vehicle performance, sensor performance and communication conditions; in addition, a set of complete air route guiding conflict detection and resolution mechanism is also constructed, so that the continuity of the air route guiding solution of the unmanned aerial vehicle is ensured. And finally, establishing an optimal model of the feasible waypoint for flight, and resolving by means of an improved memetic algorithm, thereby successfully implementing rapid and stable tracking detection on a plurality of targets on the premise of guaranteeing collaborative operation.

The invention discloses a language model training method and device, a storage medium and a product, and relates to the technical field of natural language processing, and the method comprises the steps: sending a language model to each second device, so that each second device employs corresponding local private data to train the language model, obtaining an agent model corresponding to each second device; the proxy models sent by the second devices are received, model aggregation is carried out on the basis of a memetic algorithm and the proxy models, an aggregation model is obtained, and the aggregation model is determined as a new language model; iteration is carried out in this way until a preset training ending condition is met, and a trained language model is obtained. Therefore, the model training efficiency can be improved under the condition of protecting the data privacy of the data owner.

The invention discloses a full-precision model scheduling method for a super-sensitive earth observation satellite, which comprises the following steps of: 1, accurately calculating attitude switching time of adjacent tasks through an Euler angle and a rotation matrix, 2, searching task insertion time based on attitude switching satisfaction deviation values of the adjacent tasks on two sides, and simultaneously realizing a local search algorithm for scheduling the super-sensitive satellite. Step 3, based on discrete integer coding and minimum graph decoding, realizing optimal path exchange and reserved crossover and mutation operators, and further realizing a global search evolutionary algorithm of hypersensitive satellite scheduling; step 4, based on a memetic algorithm combining the step 2 and the step 3, realizing scheduling high-efficiency solution of the full-precision model of the hypersensitive satellite; according to the method, the problem of efficient scheduling of the full-precision model of the hypersensitive satellite is solved.

The invention discloses a transient stability assessment method and system for a power system. The method comprises the following steps: firstly, acquiring multi-dimensional real-time electric quantity data of a power system; thirdly, performing feature selection optimization by applying a knowledge-guided memetic algorithm, combining global evolutionary search and local fine search and fusing expert knowledge to obtain an optimal feature combination and a time window; then, constructing a reservoir calculation network formed by differential neuron ring oscillators based on the combination, and extracting deep dynamic features of the system; and finally, inputting the deep features into a CNN-LSTM hybrid model for evaluation, and obtaining a transient stability probability value. According to the method, through innovative feature optimization and dynamic feature extraction mechanisms and in combination with the deep fusion model, rapid and accurate evaluation of the transient stability of the power system is realized, and the safety protection level of a power grid is remarkably improved.

The present invention discloses a method and system for ASRS task scheduling and storage location allocation under classified storage. The shelves are partitioned according to the characteristics of goods. The model for inbound and outbound task scheduling and storage location allocation considers the dynamic allocation of storage locations. This model is a dynamic programming model that includes the allocation of stacker cranes for inbound and outbound tasks, the sorting of inbound tasks, the sorting of outbound tasks, and the state transition of the storage location set. An integer programming model is established with the goal of minimizing the Hamming distance of the inbound and outbound task matching to sort the inbound tasks. The inbound task sequence optimization model is embedded in the memetic algorithm to achieve the overall optimization of the inbound and outbound task sorting, allocation, and storage location selection problems. The local search of the memetic algorithm includes two storage location exchange operators; the present invention optimizes the sequence of outbound and inbound tasks. The empty storage locations generated by the outbound tasks can be used for subsequent inbound operations. At the same time, the optimal solution is obtained through a method combining global and local searches, reducing the task completion time and delay time.

The application discloses a kind of high-efficiency dynamic roadside unit deployment methods and systems that can detect witch attack, including collection geographic information, assess the service coverage of roadside unit in deployment area, overlapping range and accident information initial diffusion speed, establish the RSU deployment constraint that can detect witch attack;Based on particle swarm optimization and improved genetic algorithm, RSU deployment scheme is constructed;Obtain transportation and reconstruction RSU overhead, obtain minimum RSU adjustment cost based on bipartite graph matching algorithm;Collect each RSU work load, and based on Pareto optimal principle, heuristic RSU minimum cost adjustment scheme is constructed.The application is under the constraint that can detect witch attack, by constructing the efficient deployment and low-cost adjustment scheme of heuristic RSU, improve the service effective coverage range in RSU deployment, accident information initial diffusion speed, minimum costly realize load balancing between RSU and have the ability of detecting witch attack, solve the problem that traditional RSU deployment scheme comprehensive performance is low, cannot detect witch attack.

The application belongs to the field of workshop scheduling, and aims at solving the problem of low efficiency of the existing scheduling method of heterogeneous factories. The application comprises the following steps: S1, constructing a distributed heterogeneous flow shop scheduling model; S2, determining the value of the basic parameters of the algorithm, and generating an initial population by using a random strategy according to the coding rules; S3, evaluating the initial population, and performing a Pareto non-dominated sorting according to the fitness value; S4, performing an EOX crossover operation on the population with two-layer coding; S5, searching the solution space by using multiple operators; S6, adopting an elite reservation strategy, merging the parent population and the child population, and selecting half of the individuals as the evolution target of the next stage; S7, performing an evolution operation of local search on the selected individuals; S8, updating the population; S9, if the algorithm reaches the stopping condition, the algorithm is ended and the result is output, otherwise, the algorithm jumps to step S4 and continues to execute.

The invention discloses a circuit design method and device based on an improved culture gene algorithm, equipment and a medium, and relates to the technical field of circuit design. The method comprises the following steps: setting a coding format, an evaluation function and a plurality of performance functions according to attribute information of a target circuit; randomly generating a plurality of coding groups as individuals of the first generation population; determining a processing circuit corresponding to each individual; calculating the fitness value of each individual through an evaluation function; the elite individuals are reserved to serve as individuals of the next-generation population, crossover and mutation are conducted on the other individuals of the current population according to the dynamically-adjusted crossover probability and mutation probability, the individuals of the next-generation population are generated, and dynamic neighborhood search is conducted on the generated individuals of the next-generation population; and determining the processing circuit corresponding to the optimal individual as a target circuit. According to the method provided by the embodiment of the invention, the algorithm convergence speed can be accelerated, the computing resource consumption is reduced, the algorithm is effectively prevented from falling into local optimum, and the global search capability is improved.

This invention discloses a vehicle logistics loading optimization method based on uniform weight constraint. The method takes the set of attributes of the vehicles to be transported and the set of attributes of available car carriers as input data, sets model parameters and algorithm parameters, sets decision variables and objective function, sets uniform weight constraint to construct a mixed integer programming model, uses the meme algorithm to solve the model, and takes the optimal solution of the objective function value as the final scheduling scheme to maximize transportation revenue.

The invention discloses a multi-unmanned aerial vehicle multi-task target air route guiding method, and belongs to the field of unmanned aerial vehicle intelligent optimization algorithms. Providing a feasible waypoint set generation method for a multi-target collaborative detection scene; meanwhile, a feasible waypoint set reduction method is designed based on requirements in the aspects of unmanned aerial vehicle performance, sensor performance and communication conditions; in addition, a set of complete air route guiding conflict detection and resolution mechanism is also constructed, so that the continuity of the air route guiding solution of the unmanned aerial vehicle is ensured. And finally, establishing an optimal model of the feasible waypoint for flight, and resolving by means of an improved memetic algorithm, thereby successfully implementing rapid and stable tracking detection on a plurality of targets on the premise of guaranteeing collaborative operation.

The invention discloses a no-waiting flow shop bad scene set robust scheduling method based on a memetic algorithm, and the method comprises the steps: carrying out the processing time description of a to-be-processed workpiece set and a processing machine set through employing a discrete multi-scene method, defining a threshold value bad scene set according to a preset performance threshold value, and building a robust optimization model of the threshold value bad scene set. According to the method, a threshold value bad scene set robust scheduling model of a wait-free flow shop is established, and an optimization objective function is determined. An initial population is generated by using a scene-based NEH heuristic algorithm. And performing global search on the current population through a genetic operator and a selection mechanism, selecting a target scene by using a strategy related to the model, constructing a neighborhood structure by using knowledge related to problems in the target scene, and performing local search. The whole optimization process is circularly executed under iteration control until the preset maximum iteration number is reached, and finally the optimal scheduling solution in the optimized population is output. The method can effectively cope with the uncertainty of the processing time, improves the robustness and optimization efficiency of no-waiting flow shop scheduling, gives consideration to the global search capability and the local refinement capability, and achieves the quick solving of a high-quality scheduling scheme.