The Particle Swarm-Simulated Annealing Fusion Algorithm And Its Application In Function Optimization

Optimization is an application technology,which based on mathematics to solve all kinds of practical problems.Its purpose is to choose the best plan from numerous plans,to find the optimal value of the objective function in solving actual problem. With people's cognition and transformation world ability enlarge day by day,at actual system and engineering fields,emerge more multi-objectives,non-linear,not differentiable,even mixed system.Traditional optimization methods can not solve these questions effectively,so we must use Computational Intelligence technology to solve these problems.Since 1980s Intelligent Optimization Algorithm(such as:Artificial Neural Networks,Simulated Annealing Algorithm,Genetic Algorithm,Particle Swarm Optimization Algorithm and Ant Colony Algorithm),developed by simulating some of the natural phenomena and processes,provide new ideas and tools to the optimization theory,and has been widely used in the scientific,economic,and engineering fields.As a improvement algorithm of Particle Swarm Optimization Algorithm-Linear Inertia Weight Particle Swarm Optimization improve the Particle Swarm Optimization algorithm easily fall into the local optimal conditions.However,but the Inertia Weight decreases linearly make the Algorithm once run into the area near local optimal point,it will be very difficult to jump out,and get a local optimal point. Its Iterations is usually very large.Therefore the thesis presents a non-linear inertia weight adjustment strategy,so we get the Un-Linear Inertia Weight Particle Swarm Optimization Algorithm(ULWPSO),although it get good result in optimizing Single-peak function and multi-peak function.But in Multi-peak function optimization process the ULWPSO algorithm also has low convergence accuracy and low convergence success rate defects.In the process of evolution algorithm's research,algorithm's detecting and development capability depend on one algorithm are often unable obtained effectively.Therefore,fusing other optimized method to the Particle Swarm Optimization Algorithm detecting process is an efficient method to raise the PSO Algorithm detecting efficiency and solution quality.So the thesis fused the Simulated Annealing Algorithm's Metropolis thought to the Un-Linear Inertia Weight Particle Swarm Optimization Algorithm(ULWPSO Algorithm),so we get the ULWPSO-SA Fusion Algorithm.The ULWPSO-SA Fusion Algorithm make in Swarm's flight process,the Swam not only can accept good function value point,but also can accept worse function value point by certain probability.Through carried experiment,the result show ULWPSO-SA Fusion Algorithm increased the Swarm's multiplicity,and strengthened Swarm's get rid of the partial optimal solution ability,can't run into local minimum easily,strengthen the overall situation detecting ability,and has higher convergence rate and precision.