粒子群优化算法及其在圆柱度误差评定中的应用

提出了将粒子群优化算法用于圆柱度误差评定的设想。对算法的基本原理和实现步骤做了具体阐述,给出了圆柱度误差评定的基本问题,及其优化目标函数及算法的适应度函数和编码方式,对算法进行了可行性和准确性验算。计算结果表明,该方法对于圆柱度误差评定这类具有复杂目标函数和较多参数的非线性优化问题有很好的计算性能,优于最小二乘法;与遗传算法和其它满足最小区域条件计算方法相比,计算精度略优于前者或者与前者相当,能够获得精度较高的结果,而突出优点是简单,易于实现而且计算效率较高。

Research on cylindricity evaluation based on the Particle Swarm Optimization(PSO)

A cylindricity evaluation approach based on the Particle Swarm Optimization(PSO) was proposed.The fundamentals and implementation techniques of PSO were discussed.The problem of cylindricity evaluation was presented and its optimization goal and variables were given.The fitness function of PSO with real number encoding of particles was also described.Taking a example for verifying the feasibility and computation precision of the approach,the computation results show that the PSO-based approach is a useful tool for solving such nonlinear optimization problems as cylindricity evaluation with complicated goal function and more parameters.It is superior to that given by the Least Square Method(LSM) and a little better than or equal to those given by GA-based method and another Minimum Zone Method(MZM).Moreover,the PSO-based approach is not only effective but also simple and easy to implement for computers.