论文部分内容阅读
激光立体成形是一种新型的加工技术,成形表面质量是多种因素的作用结果,为了提高激光立体成形表面质量的预测精度,提出一种改进人工神经网络的激光立体成形表面质量预测模型。首先确定激光立体成形的加工工艺参数,并通过实验记录它们的数据;然后将它们和激光立体成形层高组合在一起作为学习样本,并输入到人工神经网络进行建模,建立激光立体成形表面质量预测模型,并针对人工神经网络的缺陷进行相应的改进,最后模拟实验结果表明,本文模型可以对激光立体成形表面质量进行准确预测,预测值与实际值之间的偏差要小于传统人工神经网络模型。
Laser three-dimensional forming is a new processing technology. The quality of forming surface is the result of many factors. In order to improve the prediction accuracy of laser three-dimensional forming surface quality, an improved three-dimensional laser surface forming quality prediction model based on artificial neural network is proposed. Firstly, the processing parameters of laser three-dimensional forming are determined and their data are recorded experimentally. Then they are combined with the laser three-dimensional forming layer as learning samples and input to the artificial neural network for modeling to establish the laser three-dimensional forming surface quality Finally, the simulation results show that the model can accurately predict the surface quality of laser three-dimensional forming, the deviation between the predicted value and the actual value is less than that of the traditional artificial neural network model .