提出基于Kohonen自组织神经网络的装夹面分组与选择算法和基于遗传算法的定位点优化算法,利用人工神经网络来处理装夹面选择中各种复杂的影响因素,选择最佳的装夹表面;在此基础上,参考夹具校验的一些结论,通过一些参数来模拟工件的稳定性与变形特性,利用遗传算法进行组合优化,确定最优定位点。最后用实例验证了算法的有效性。
This paper presented an algorithm of fixturing surfaces grouping and selection based on Kohonen self--organizing neural network and the algorithm of optimizing locating points based on genetic algorithm. Artificial neural network was utilized to deal with the complicated influencing factors in fixturing surface selection to select the best fixturing surfaces. Based on the results of fixture verifi cation, the stiffness and deformation of the workpiece was simulated. Genetic algorithm was then adopted to optimize the combination of locating points. Examples were presented to validate the algorithms.