【摘要】 介绍了一种在线估算数控车床上车刀磨损量的方法。该方法通过实时采样切削过程中　切削力的变化，并考虑切削用量，利用具有变因子ＢＰ学习算法的前馈感知器型神经网络，在　线提取车刀的磨损信息。该方法利用一个静态神经网络和一个动态神经网络构成一个估计系　统，动态神经网络用来估算车刀磨损量，静态神经网络为动态网络提供学习信息，从而保证　在切削参数和切削条件变化时系统输出的准确性。更多还原

【Abstract】 ： A method to estimate the tool wear in NC lathe, which base d on multi-layered feed-forward neural networks with varying-factors BP learning algorithm extracts the information of tool wear from the changes of cutting forc e over the cutting process The system consists of a dynamic and a static neura l network The dynamic one estimates the components of the tool wear and the s tatic one update the dynamic neural network according to the changes of cutting force components The adaptability of the dynamic neural network ensures that c hanges in machining parameters can be accommodated更多还原