210results about How to "Improve local search capabilities" patented technology

The invention provides a cooperative air combat firepower distribution method based on an improved multi-target leapfrog algorithm and belongs to the technical field of computer simulation and method optimization. The method comprises the steps that firstly, required data information is obtained through a cooperative air combat formation command and control system; secondly, a multi-target optimization module of cooperative air combat firepower distribution is established; then a multi-target quantum leapfrog algorithm based on a self-adaptive mesh method is carried out, and a Pareto non-inferior solution of firepower distribution problem is solved; finally, rules can be selected independently according to the optimal distribution scheme, and the optimal firepower distribution scheme is selected from the non-inferior solution. The cooperative air combat firepower distribution method based on the improved multi-target leapfrog algorithm has the major functions that weapons on a fighter aircraft on an attack mission are distributed to multiple targets according to the optimal firepower distribution scheme, the formed cooperative air combat is enabled to realize the optimal cooperative attack effect, and the maximum operational effectiveness is obtained.

The invention discloses and proposes a reservoir dispatching method based on multi-target shuffled frog leaping and differential algorithms. The reservoir dispatching method comprises the following steps of S11, acquiring basic information data of a reservoir; S12, building a multi-target optimal dispatching mathematic model considering constraint conditions of water balance, machine set output, discharged volume and generation power, wherein the target function is built based on maximum generation power, minimum water deficit, minimum surplus water and minimum output; S13, figuring out Pareto optimal solution of the multi-target optimal dispatching mathematic model by using the multi-target shuffled frog leaping and differential algorithms; and S14, automatically determining a reservoir optimal dispatching scheme by a multi-target decision method on the basis of the Pareto optimal solution. By the reservoir dispatching method, global optimization is achieved, the calculation efficiency is improved, and the requirement of automatically selecting the multi-target optimal dispatching scheme of the reservoir is met.

The invention relates to a real-time path planning method of AUV (Autonomous Underwater Vehicle), in particular to a method for carrying out online, real-time local path planning according to an online map in an AUV real-time collision preventation process. The method comprises the steps of: setting the quantity of small populations according to the quantity of path points of the AUV, initializing; carrying out immune selection on each small population to obtain subgroups; carrying out genetic manipulation on one subgroup, carrying out cell cloning on the other subgroup; then clustering through a vaccination and an antibody to form the next generation of small population, judging whether the next generation of small population meets the conditions or not; if yes, selecting optimal individuals of the small populations; and selecting the optimal individuals from the set consisting of all optimal individuals to be used as a planning path. According to the invention, the diversity of the population is maintained by using an antibody clustering principle, the premature convergence of an algorithm is avoided, and the global optimization is facilitated. The established immune genetic algorithm is used for clustering and analyzing generated filial generations by adopting a self-regulating mechanism, and the diversity of the population is ensured.

The invention discloses a method for cloud manufacturing resource optimization configuration based on an improved whale algorithm, and the method comprises the steps: building a problem model, and defining a fitness function; setting improved whale algorithm parameters, and generating an initial population; Calculating fitness values of all individuals in the population, obtaining a current optimal resource allocation scheme and converting the current optimal resource allocation scheme into whale individual position vectors; Introducing a parameter p, and judging whether p is less than or equal to 0.5; If not, performing spiral motion iteration updating to complete population updating; If yes, whether the value A (1) of the coefficient vector of the improved whale algorithm is met or not is judged; If yes, performing shrinkage encircling iteration updating; If not, performing random search predation iteration updating; Obtaining a current optimal resource configuration scheme; Adding 1to the number of iterations, and judging whether the current number of iterations is smaller than the maximum number of iterations; If yes, repeating the operation; And if not, outputting the currentoptimal resource configuration scheme. The whale algorithm is improved, so that the algorithm convergence speed is higher, the optimal solution is easier to achieve, and a new method is provided forsolving the problem of resource allocation.

The multi-parking-lot and multi-vehicle-type vehicle path scheduling control method comprises the steps of 1, establishing an objective function by taking the lowest total cost of all delivery vehicles as an objective; Step 2, performing a coding step; 3, performing population initialization; 4, evaluating all the individuals by adopting the objective function as a fitness function; Step 5, performing selection and crossover operation; step 6, performing mutation operation; 7, performing neighborhood search on each individual in the population by using an improved extreme value optimization algorithm; Step 8, calculating fitness of all individuals in the population; Step 9, performing selecting; Step 10, performing elite retention; Step 11, completing iteration in sequence; Step 12, judging whether a termination condition is met or not, the termination condition being that the number of iterations g reaches the maximum number of iterations MaxGen or the number of iterations Nu of whichthe Gb fitness value remains unchanged reaches the specified number of iterations Kbest, if yes, continuing to execute the step 13, and if not, returning to execute the step 5; Step 13, outputting the individual Gb and the fitness value fGb thereof; And 14, interpreting the optimal individual Gb and the fitness value fGb thereof. The invention aims to improve the search efficiency and convergencespeed of the algorithm.

The invention relates to a method for genetic algorithm with local modularity for community detecting and belongs to the technical field of complex network community mining. The method comprises the steps of encoding network community division; initializing populations; calculating fitness functions; performing genetic operation: crossing, mutation and selection; and performing decoding to obtain optimum community division. According to the genetic algorithm method, roulette selection is added in a crossing operator rather than individuals in the populations are selected randomly for crossing operation, so that the high-fitness individuals have priority selective properties, and generation of optimum division can be accelerated; a local modularity function is introduced in a mutation operator, so that a mutated candidate solutions is close to an optimal solution, the local search capacity of the mutation operator can be improved, the pertinency is achieved, and the search performance of the algorithm is improved; and a good division effect can be obtained when a genetic algorithm with local modularity for community detecting (LMGACD) is used for mining complex network communities, and the time complexity is low.

The invention discloses a particle swarm improved algorithm based on chaotic backward learning. The algorithm mainly comprises a backward learning strategy and chaotic particle swarm optimization. The basic principle of the backward learning strategy includes: the backward learning strategy generates a corresponding backward solution for each initial candidate solution, and selects the solutions with short distance (high fitness) from two kinds of solutions (candidate solutions and corresponding backward solutions) as members of an initial population so that the convergence rate in an optimization process can be increased. In order to maintain the diversity of the population and enable individuals of the initial population to be uniformly distributed as much as possible, the initial population is generated by employing the backward learning strategy.

The invention relates to a distributed photovoltaic power generation maximum consumption capability calculation system based on an active power distribution network. The system comprises an input module, an initialization module, a load flow calculation module, a particle swarm operation module and an output module; the input module is used to obtain a distribution network parameter, a photovoltaic power generation system parameter, a photovoltaic time sequence characteristic parameter, a load time sequence characteristic parameter, the number of various typical days in a year and an adaptive chaotic particle swarm algorithm parameter; the initialization module initializes a population by utilizing a chaotic algorithm, and each particle in the population represents a distributed photovoltaic access scheme; the load flow calculation module performs a load flow calculation considering active management and obtains adaptive values of the particles in a time section t; the particle swarm operation module performs a loop computation through adoption of an adaptive chaotic particle swarm algorithm and obtains a particle having an optimal total adaptive value; and the output module outputs an optimal distributed photovoltaic access scheme and the maximum year consumption amount under the distributed photovoltaic access scheme. Compared with the prior art, the system has the advantages of high calculation efficiency, high integration and the like, and is closely combined with the actual.

The invention discloses a multi-objective quantum Shuffled Frog Leaping Algorithm (SFLA) based water resource optimization and diversion method, comprising the following steps: firstly obtaining basic information data on water resources; establishing multi-objective optimization and diversion models for water resources; executing the shuffled Frog Leaping Algorithm (SFLA) to find the best solutions to Pareto of the multi-objective optimization and diversion of water resources; and finally according to a multi-objective decision theory, choosing the best theory to divert water resources by combining objective weights and subjective weights. According to the invention, optimization is achieved through an overall choosing process. Calculation efficiency is increased so as to meet the requirements for best multi-objective diversion programs in a water resource system.

A two-dimensional irregular layout method based on an improved particle swarm algorithm comprises the following steps of: converting geometric figures of a sample wafer and a material into a train of two-dimensional coordinate intervals, judging whether the two-dimensional intervals of the sample wafer and the material are overlapped with a heuristic bottom-left searching algorithm to move the position of the sample wafer relative to the material, and executing an improved PSO (Particle Swarm Optimization) searching process. According to the method of dividing multiple subpopulations, the influence of subpopulation optimal solutions on particles in the subpopulations is added under the condition of not changing a parameter trending to the current optimal solution, when the iteration time of a particle swarm reaches the initially set maximum iteration time, the particles stop iteration, and the current globally optimal solution is obtained as the final layout scheme. The two-dimensional irregular layout method based on the improved particle swarm algorithm has good searching capability, and is high in searching speed, good in final solution and good in layout effect.

The invention discloses a multi-dimensional optimization method of an integrated energy system based on an improved whale algorithm. The method models the integrated energy system, takes the minimum overall operation cost as an objective function, takes the balance conditions of electricity, heat and cold as a constraint condition, and adopts the improved whale algorithm to obtain the global optimal solution of the objective function. The improved whale algorithm is based on the traditional whale algorithm by introducing adaptive weights and Cauchy mutation. On the one hand, the invention improves the global searching ability of the whale algorithm and avoids falling into local optimization; On the other hand, the local searching ability is improved, the convergence speed and precision areimproved, and the stability is good.

The invention relates to a multi-population simulated annealing hybrid genetic algorithm based on similarity expelling. The multi-population simulated annealing hybrid genetic algorithm includes the following steps: coding is carried out; initialization parameters are set; initial populations are created; fitness values are calculated; selecting operation is carried out; interlace operation is carried out; mutation operation is carried out; gene overturning operation is carried out; simulated annealing Metropolis rules are judged; migration operation based on similarity expelling is carried out; optimal storage is carried out; judgment is ended. The migration operation based on similarity expelling particularly includes the following steps: calculating the fitness values of individuals in a source population and a target population; selecting the individual with the largest fitness value from the source population to serve as the individual to be immigrated; conducting similarity calculation; conducting expelling replacement. The multi-population genetic algorithm with simulated annealing operation can improve the local search capability of the multi-population genetic algorithm, and the algorithm can search for approximate solutions even though optimal solutions to a larger extent. The individual similarity judgment is additionally carried out, attention is paid to differences between the individuals, the diversity of populations is maintained, premature convergence of the genetic algorithm is avoided, the solving quality of the algorithm is improved, and the algorithm is closer to the optimal solutions.

The invention relates to a wind farm multi-model draught fan optimized arrangement method based on a genetic algorithm. The method includes the following steps that (1) a wind farm region is divided into square meshes which are the same in size according to the diameter of a draught fan, and an integer matrix which is the same in line and row is generated randomly to be used as the initial solution of the algorithm; (2) the individual fitness value of a current generation is calculated; (3) parent individuals participating in crossover are selected through even random selection operators, and then filial generation individuals are generated by the adoption of improved crossover and mutation operators; (4) repairing operators are introduced to the individuals in a population; (5) a Tabu operator is introduced to an optimal solution of the current generation of the population, the optimal solution is used as the initial solution of a Tabu algorithm, and the neighborhood solution of the optimal solution is searched for; (6) whether the biggest number of iterations is reached or not is judged, if yes, the multi-model draught fan optimized arrangement is completed, and if not, the step (2) is executed again. Compared with the prior art, the wind farm multi-model draught fan optimized arrangement method based on the genetic algorithm has the advantages of being visual in coding mode, good in performance index, high in local search capacity, high in expansibility, high in practicability and the like.

The invention discloses an engineering optimization method of a Harris hawks algorithm based on multi-strategy enhancement. The engineering optimization method comprises the following steps: S1, constructing an optimization objective function of an actual engineering problem; S2, initializing parameters; S3, initializing the population position of the Harris hawks; calculating the fitness value ofeach Harris hawk in the initialized population according to the target function; S5, dynamically simulating the motion state of the prey and the execution state of the population so as to find the best execution strategy for each Harris hawk; s6, performing an exploration stage; s7, performing a development stage; s8, updating the position of the whole population through the steps S5 and S6, andenabling the updated new population to pass through an objective function and a constraint condition; s9, judging whether the maximum number of iterations is reached or not. The method has the following advantages and effects that a better solution can be found in an actual engineering optimization problem, and the precision of the solution of the constraint-containing engineering optimization problem is improved within limited time.

The invention provides a wireless sensor network node deployment method based on particle swarm optimization and a mutation operator. All sensors are randomly distributed in a target area, the initial coordinates of each sensor are taken as a particle initial position in a particle swarm algorithm, and the coverage rate of a wireless sensor network is taken as a target adaptive value function of the particle swarm algorithm. Through the particle swarm algorithm, a global historical optimal solution is obtained, an optimal value of a particle is obtained according to the optimal solution, and the optimal value is a best position of deploying a sensor in the target area. According to the method, through improving an inertia weight calculation method, the local search ability of the algorithm is improved, through giving a mutation probability to a particle individual, an individual historical optimal solution is recalculated, a condition that a whole algorithm falls into a local optimal solution is effectively avoided, the utilization rate of the sensors is improved, and the cost of constructing a wireless sensor network is reduced.

The invention discloses a flower pollination algorithm optimization method based on adaptive Gaussian mutation. Firstly, the population is firstly ranked according to adaptability values and is grouped, and then the position of the worst individual in each group is updated, thereby enhancing the local depth search ability of the algorithm and enhancing the population diversity; and secondly, whether the algorithm falls into the local optimization is dynamically monitored through a bulletin board, and if yes, a Gaussian mutation operation operator is automatically introduced, mutation operation is executed on the global optimal individual, thereby not only improving the ability of the individual jumping out of the local optimization but also enhancing the population diversity and quickening the convergence rate. The method of the invention has better stability, better reliability, quicker convergence rate and higher optimization precision.

The embodiment of the invention discloses a short-term wind speed prediction method, apparatus and system. The short-term wind speed prediction method includes the steps: acquiring the wind speed historical data which is preprocessed; using an experience modal decomposition method to decompose the wind speed historical data to obtain a plurality of data components; inputting each data component to a pre-established BP neural network optimization model to predict, and obtaining each prediction sub-result which is one to one corresponding to each data component; and superposing each prediction sub-result to obtain the wind speed prediction result, wherein the establishing process of the BP neural network optimization model includes the steps: acquiring the training sample data, and inputting the training sample data to the BP neural network; and performing searching optimization processing on the parameters of the BP neural network by means of a particle swarm gravitation searching mixed algorithm, and obtaining a trained BP neural network optimization model. The short-term wind speed prediction method, apparatus and system can reduce the influence of natural wind fluctuation on prediction accuracy during the using process, and can improve the global convergence accuracy to enable the wind speed prediction result to be relatively more accurate.

The invention relates to a photovoltaic cell parameter identification method based on an improved Harris Hawk optimization algorithm. The method specifically comprises the following steps: 1, collecting and processing output current and voltage data of a photovoltaic cell; 2, establishing an engineering model of the photovoltaic cell, and constructing a fitness function; 3, introducing a flexibledecreasing strategy to improve a prey initial energy decreasing mode; 4, optimizing the current population by using a gold sine method, introducing a golden section number, screening out individuals with optimal fitness from the golden section number, and establishing a new population for next iteration; 5, calculating a fitness value according to parameter information carried by individuals in the population; and stopping until the fitness value of the prey meets the precision requirement or reaches the maximum number of iterations, outputting the parameter information of the prey as the optimal parameter value of the photovoltaic cell, drawing a fitting curve and an algorithm iteration curve, and comparing the current and voltage experiment results of the photovoltaic cell with the modelidentification result. The method can replace a traditional photovoltaic cell identification method, and the identification precision of photovoltaic cell parameters is effectively improved.

The present invention discloses a network community division method based on simulated annealing genetic algorithm, and mainly solves problems of poor search capability and low division efficiency in present genetic algorithm. The network community division method based on simulated annealing genetic algorithm comprises the following realizing steps: (1) reading in a network diagram; (2) generating an adjacent matrix according to the network diagram; (3) initializing genetic algorithm parameters; (4) decoding chromosomes and calculating objective function values; (5) selecting chromosomes with relatively large objective function values to form a parental population; (6) crossing and varying chromosomes and generating new chromosomes to form progeny populations; (7) initializing simulated annealing algorithm parameters and implementing a local search; (8) obtaining a next parental population and performing iteration; (9) determining whether or not the iterative algebra reaches the largest algebra Gmax; if the iterative algebra reaches Gmax, then the iteration is terminated and the chromosome with the largest objective function value is output, and division of every node in the output chromosome is a final division result of nodes in the community. The network community division method based on simulated annealing genetic algorithm has advantages of strong search capability and high accuracy.

The invention discloses a wireless sensor network clustering routing method based on a harmony search algorithm. The method comprises the following steps: (1) global information transmission and convergence: acquiring the global information, and transmitting the global information to an aggregation node; (2) the aggregation node performs optimization calculation and configuration of network clustering routing of the entire sensor network through the global information; (3) a common sensor node monitors, collects and processes application information, processes the application information into a data packet, and forwards the data packet to a cluster head node, and the cluster head node performs data fusion and sends the data packet to a next hop cluster head node; and (4) the next hop cluster head node adds its own dump energy information to the data packet after receiving the data packet, and continues to forward the data packet to the next hop cluster head node according to the optical routing in the data packet. By adoption of the method disclosed by the invention, the problems of unreasonable member node allocation, uneven power consumption of the cluster head nodes of a wireless sensor network are solved, the energy efficiency of the network is improved, and the life cycle of the network is prolonged.

The invention discloses an RBF (Radial Basis Function) neural network-based coal and gas outburst prediction method. The method comprises the steps of 1, performing dimensionality reduction on feature data of coal and gas outburst, and performing normalization processing on the feature data subjected to the dimensionality reduction to obtain normalized feature data; 2, clustering the normalized feature data by using a K-mean algorithm and calculating the center of an RBF; 3, training an RBF neural network on the normalized feature data, and introducing an optimal expansion factor and an optimal weight when the number of neurons in a hidden layer is determined by an adaptive differential evolution algorithm; 4, increasing the number of the neurons in the hidden layer, and repeating the steps 2-3 to obtain global optimal parameters of the RBF neural network, thereby determining a prediction model of the RBF neural network; and 5, predicting test data by using the prediction model of the RBF neural network. According to the method, the optimal parameter adaptive problem of the RBF neural network can be solved, so that the coal and gas outburst can be quickly and accurately predicted.