论文部分内容阅读
本文建立了基于ＣＰＮ（ＣｏｕｎｔｅｒｐｒｏｐａｇａｔｉｏｎＮｅｕｒａｌＮｅｔｗｏｒｋ）神经网络的计算力学反问题分析方法，并将其应用于薄板振动系统识别。研究结果表明，神经网络计算是工程结构分析中一种很有发展潜力的新方法。
In this paper, a computational mechanics inverse problem analysis method based on CPN (Neural Network) is developed and applied to the identification of thin plate vibration system. The results show that neural network computing is a new method with great potential in engineering structural analysis.