Hybrid DE-NSGA ? Optimization Algorithm And Its Application In Gear Pump

With the development of intelligent manufacturing and automatic control technology,multi-objective optimization problems generally exist in various fields of industrial design.In multi-objective optimization problems,the relationship between multiple objectives is complex or even completely contradictory.How to accurately characterize this relationship and obtain the optimal solution set for this type of problem is a key problem to be solved urgently.Based on this,this paper mainly studies the algorithm characteristics of non-dominated sorting genetic algorithm(NSGA-?)and differential evolution algorithm(DE)under different evolution strategies;the adaptive evolution factor is used to improve the NSGA-? algorithm.The combination of the NSGA-? algorithm and the DE algorithm,a new hybrid evolutionary multi-objective optimization algorithm was established;and the internal gear pump was taken as the object,and the hybrid DE-NSGA ? algorithm was carried out on the gear pump tooth profile parameter optimization design.applied research.The main research contents of this paper include:(1)Aiming at the problem that the population of non-dominated sorting genetic algorithm(NSGA-?)is easy to fall into local extremum in the early stage of evolution and the convergence is slow in the later stage of evolution,an adaptive evolution factor improvement strategy based on evolutionary algebra is proposed,which effectively improves the global optimization ability of the algorithm.(2)Considering that the scaling factor in the DE algorithm has a great influence on the performance of the algorithm,this paper conducts a correlation analysis on the scaling factor based on the standard benchmark function,and further analyzes the convergence characteristics of the DE algorithm under different scaling factor values.At the same time,in order to improve the population diversity and algorithm convergence speed,this paper combines the different evolution strategies of NSGA-? and DE algorithms,and designs a hybrid DE-NSGA ? algorithm.(3)Based on the working principle of the internal gear pump,a multi-objective optimization mathematical model was established to maximize the average flow and minimize the flow pulsation and volume.The multi-objective optimization research of gear pump tooth profile parameters is carried out by using the hybrid algorithm of NSGA-? and DE proposed above.The experimental results show that the algorithm proposed in this paper has been effectively improved in terms of convergence speed and global optimization ability.At the same time,after the tooth profile is optimized,the displacement of the pump is increased by 6.63%,and the flow pulsation rate and volume are reduced by 24.65% and 5.49%,respectively.