Particle Diameter Inversion Method Based On Genetic Algorithm

Problems of low precision,large inversion error and long inversion time exist in the genetic algorithm when it is used to inverse the particle size distribution.The inversion calculation of the particle size distribution genetic algorithm is studied.The mathematical model is set up to carry out experimental simulation,and then compare the charts of the noise free simulation experiment and the 5% noise simulation experiment respectively with the initial distribution map.Genetic algorithm of the particle size distribution inversion is improved.Simulation experiment is carried out through traditional genetic algorithm,non-negative least squares algorithm and the combined algorithm of the traditional genetic algorithm and non-negative least squares algorithm,and then the experimental data and the experimental results are analyzed and compared.The results show that when the evolutionary algebra is 10,the root mean square error of the improved genetic algorithm inversion is 0.977,the maximum error is 3.032 and the time is 1.526s;when the evolutionary algebra is 30,the root mean square error of the improved genetic algorithm inversion is 0.901,the maximum error is 2.922 and the time is 3.578 s.A hybrid inversion algorithm of particle size distribution is established through the combination of the artificial bee colony algorithm and the generalized pattern search algorithm,and the simulation experiment is carried out to obtain the inversion results.The research results show that the hybrid algorithm can be effectively used for the reconstruction of single R-R distribution inversion.Compared with the Phillips-Twomey method and genetic algorithm,it can be known the reconstruction error and the time is greatly reduced,which demonstrates the hybrid algorithm is better than genetic algorithm.