论文部分内容阅读
建立了氮化锆薄膜制备工艺参数与薄膜色度参数之间的人工神经网络预测模型,结果表明,预测结果与实测结果吻合,最大色差在5.45以内。利用所建立的模型研究了单个参数对薄膜颜色的影响规律,及多参数间交互作用与薄膜颜色的关系。并且利用神经网络根据加工要求反向预测工艺参数,从而实现了对加工参数的优化选择。
The artificial neural network prediction model between the technological parameters of the zirconium nitride thin films and the chromaticity parameters of the thin films was established. The results show that the predicted results agree well with the measured ones, and the maximum color difference is within 5.45. The influence of single parameters on the color of film was studied by using the established model and the relationship between the interaction of multi-parameters and the color of film was studied. And the neural network is used to predict the process parameters according to the processing requirements, so as to realize the optimization of machining parameters.