基于MATLAB神经网络的切削力预测  

Prediction of Turning Force with Artificial Neural Network Based on MATLAB

作　　者：范胜波[1] 王太勇[1] 汪文津[1] 何慧龙[1] 

机构地区：[1]天津大学机械工程学院,天津300072

出　　处：《机床与液压》2006年第1期4-5,14,共3页Machine Tool & Hydraulics

基　　金：国家自然科学基金资助项目(50175081)

摘　　要：借助MATLAB人工神经网络,对切削力预测进行了研究。通过比较快速BP算法和LM算法在网络训练时的收敛速度,确定了网络的结构和工具函数,并分析了影响切削力预测精度的因素,实现了切削力的精确预测。其研究结果为车削零件加工质量的物理仿真以及加工参数的优化选择提供了依据。Turning force prediction was studied with the help of artificial neural network based on MATLAB. The structure of network and toolbox functions were determined by comparing convergence speed between rapid BP algorithm and LM algorithm, the factors of cutting force prediction error were analyzed and turning forces were predicted accurately. The work can be applied to physical simulation of machining quality and optimization of cutting parameters in turning.

关 键 词：切削力 预测 MATLAB 人工神经网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TG501.3[自动化与计算机技术—控制科学与工程]