Neural network implementation for the prediction of load curves of a flat head indenter on hot aluminum alloy
Neural network implementation for the prediction of load curves of a flat head indenter on hot aluminum alloy
复制标题
DOI：
10.1016/j.procir.2020.05.094
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
G. Baiocco;D. Almonti;S. Genna;G. S. Ponticelli;V. Tagliaferri;N. Ucciardello
中科院分区：
文献类型：
--
作者：
G. Baiocco;D. Almonti;S. Genna;G. S. Ponticelli;V. Tagliaferri;N. Ucciardello
用平头压头进行的压痕试验是一种有价值的非破坏性方法，用于在局部范围内评估金属。特别地，从压痕曲线可以实现若干机械性能。本文的目的是实现一种人工神经网络来预测铝基底压入载荷与渗透深度的函数关系。特别是，神经网络是针对温度和压痕率的函数的散装机械特性。结果表明，曲线预测精度较高。
The indentation test performed by means of a flat-ended indenter is a valuable non-destructive method for assessment of metals at a local scale. Particularly, from the indentation curves it is possible to achieve several mechanical properties. The aim of this paper is the implementation of an artificial neural network for the prediction of the indentation load as a function of the penetration depth for an aluminium substrate. In particular, the neural network is addressed to the mechanical characterization of the bulk in function of temperature and indentation rate. The results obtained showed a high accuracy in curves prediction.