融合机床精度与工艺参数的铣削误差预测模型

为弥补现有五轴联动数控铣床加工飞机结构件的加工精度评估系统的不足，提出利用机床精度检测数据和零件特征及其工艺参数来构建评估指标体系，基于BP神经网络建立了飞机结构件加工误差预测模型。通过完成训练的网络权值分布，计算出各输入指标对最后评估结果的影响，并通过实例分析检验了模型的可靠性。结果表明，经BP神经网络模型训练得到的结果和样本零件的三坐标测量机测量数据基本吻合，选取的评价指标具有有效性。该评估模型能够有效地融合机床精度检测数据和零件特征及其加工工艺参数，对飞机结构件的铣削加工误差进行预测。

Prediction model of machining errors based on precision and process parameters of machine tools

To overcome the deficiency of machining accuracy evaluation system of five-axis NC milling machine in processing aircraft structural parts, an evaluation system is constructed using machine tool precision detection data, characteristics structural parts and their machining parameters. Based on the BP neural network, a prediction model for machining errors of five-axis NC milling machine is built up. The influence of each input index on the evaluation result is calculated through weight distribution of the trained network, and effectiveness of the model is verified by an example. It is shown that the results obtained by the BP neural network model are in good agreements with those by the coordinate measuring machine, demonstrating the effectiveness of those selected evaluation indexes. The prediction model can effectively evaluate the processing accuracy of the five-axis NC milling machine by combining the machine tool precision detection data, characteristics of the parts and process parameters.