论文部分内容阅读
为了有效地控制Al2O3陶瓷激光铣削层质量,以人工神经网络(ANN)技术为基础,以MATLAB软件作为开发平台,建立了Al2O3陶瓷激光铣削层质量与铣削参数之间的关系模型。并以激光功率、扫描速度和离焦量作为输入参数,激光铣削层深度和宽度作为输出参数,对激光铣削层质量进行了预测。结果表明,该模型的平均误差小,拟合精度高。并在训练样本之外,选取了5组工艺参数来检验网络模型的可靠性,检验输出值和实验样本值的最大相对误差为7.06%。说明运用该模型可以方便、准确地选择激光工艺参数,提高Al2O3陶瓷激光铣削层的加工质量。
In order to control the quality of Al2O3 ceramic laser milling layer effectively, based on artificial neural network (ANN) technology and MATLAB software as the development platform, the relationship model between the quality and milling parameters of Al2O3 ceramic laser milling layer was established. The laser power, scanning speed and defocus amount were taken as input parameters, and the depth and width of laser milling layer were taken as output parameters to predict the quality of laser milling layer. The results show that the average error of the model is small and the fitting accuracy is high. In addition to the training samples, five sets of process parameters were selected to test the reliability of the network model. The maximum relative error of the test output value and the experimental sample value was 7.06%. It shows that the model can be used to select laser process parameters conveniently and accurately and improve the processing quality of Al2O3 ceramic laser milling layer.