摘要
针对刀具寿命影响因素与刀具寿命之间的高度非线性关系,引入BP神经网络技术对刀具寿命进行预测,建立了刀具寿命预测模型。针对标准反向传播算法存在收敛速度慢、容易陷入局部极小值及全局搜索能力弱等缺陷,采用粒子群算法优化网络权值及阈值,提高了神经网络的预测精度。仿真结果表明,与标准BP神经网络相比,PSO-BP神经网络用于刀具寿命预测的精度更高。
According to the nonlinear relationship between factors and tool life, Artificial neural network was introduced into the prediction of tool life.In the prediction process, there were some disadvantages in Back Propagation algorithm , such as low converg ence speed,easily falling into local minimum point and weak global search capability. To settle these problems,function and weights are optimized by PSO algorithm. Therefore it has enhanced forecasting accurate.The simulation results show that the prediction of PSO-BP neural network has higher accuracy than that of the traditional BP neural network.
出处
《现代制造技术与装备》
2017年第11期53-54,60,共3页
Modern Manufacturing Technology and Equipment
关键词
粒子群算法
BP神经网络
刀具寿命
预测
particle swarm optimization, BP neural network, tool life, prediction
