基于模拟退火改进的实参遗传算法及其工程应用

Improving Real-parameter Genetic Algorithm Based on Simulated Annealing and It's Engineering Application

由于继承性的问题,遗传算法在编码和解码中会花费大量的计算时间;另外,由于缺乏"爬山能力",遗传算法很容易早熟和局部收敛。提出一种新的自适应模拟退火遗传算法,具有遗传算法和模拟退火的优点,同时自适应机制的引入,保证了解的质量并提高了收敛速度。将这种方法应用于螺旋弹簧约束优化设计问题中,结果表明,尽管群体规模较小,但在处理复杂问题时,这种混合算法的全局搜索能力和收敛速度显著提高。

With its inheritance,genetic algorithm may spend much computation time in the encoding and decoding process.Also,since genetic algorithm lacks hill-climbing capacity,it easily fall in promatureness and local convergence.A novel adaptive real-parameter simulated annealing algorithm（ARSAGA） that maintains the merits of genetic algorithm（GA）and simulated annealing（SA）is proposed.Adaptive mechanisms are also added to insure the solution quality and to improve the convergence speed.This method to solve the helical spring constrained optimization design problem is applied.The results indicate that the global searching ability and convergence speed of this novel hybrid algorithm is significantly improved,even though small population size is used for a complex and large problem.