Font Size: a A A

Research On Optimization Problemfor Transverse Flux Induction Heating Based On SVM And PSO

Posted on:2017-11-19Degree:MasterType:Thesis
Country:ChinaCandidate:L X YinFull Text:PDF
GTID:2382330596458119Subject:Electrical engineering
Abstract/Summary:PDF Full Text Request
The transverse flux induction heating(TFIH)technology is likely to be popular in many industry fields because of its fast,efficient heating and good quality.But it has the problem that the temperature distribution of the strip at the outlet is not uniform,which limits its application.The main work of this paper is to use particle swarm optimization(PSO)to optimize this problem.Besides,there are many factors that affect the temperature distribution of the strip and the nonlinear coupled calculation of electromagnetic field and thermal field,which is involved in the optimization process,is very complex.Therefore,support vector machine(SVM)is used to establish a regression model between the induction heating current,frequency,coil size and the average relative error of temperature.So the complex calculation is replaced by the regression model and the complexity is reduced while the efficiency is improved.The improvement of PSO is one of the significant parts of this paper.PSO is a kind of swarm intelligence algorithm.It is simple and easy to implement.But it also has the problem of low search accuracy and being easy to fall into local extrema.So this paper proposes an improved PSO,called the velocity-controlled PSO(VCPSO),based on the analysis of the particles' distribution during the optimization process.The improvement is reflected in two points: the first is the uniform initialization of the population;the second is the velocity regulation according to the number of particles that exceed the feasible region during the optimization process.Simulation test results of several typical functions show that the VCPSO performs much better than the standard PSO(SPSO).In this paper,the TFIH optimization based on SVM and VCPSO is implemented with MATLAB.The whole process mentioned above is carried out successfully to reduce the computational complexity and save time,which can provide a theoretical reference for the optimization design of the TFIH device.
Keywords/Search Tags:support vector machine, particle swarm optimization, algorithm improvement, transverse flux induction heating, optimization
PDF Full Text Request
Related items