公开(公告)号：US20150356402A1

公开(公告)日：2015-12-10

申请号：US14295404

申请日：2014-06-04

Applicant: GM Global Technology Operations LLC

Inventor： Qigui Wang ,  Yucong Wang ,  Zhiqiang Gao ,  Zhibin Quan

IPC: G06N3/08 ,  G06F17/10 ,  C22F1/04

CPC classification number: G06N3/08 ,  C22F1/04 ,  G06F17/10 ,  G06F17/50 ,  G06F17/5018 ,  G06F2217/41 ,  G06N3/10 ,  Y02T10/82

Abstract: A computer-implemented system and method of rapidly predicting at least one of residual stress and distortion of a quenched aluminum casting. Input data corresponding to at least one of topological features, geometrical features and quenching process parameters associated with the casting is operated upon by the computer that is configured as a neural network to determine output data corresponding to at least one of the residual stress and distortion based on the input data. The neural network is trained to determine the validity of at least one of the input data and output data and to retrain the network when an error threshold is exceeded. Thereby, residual stresses and distortion in the quenched aluminum castings can be predicted using the embodiments in a tiny fraction of the time required by conventional finite-element based approaches.

Abstract translation: 一种计算机实现的系统和方法，其快速预测淬火铝铸件的残余应力和变形中的至少一种。 对应于与铸造相关联的拓扑特征，几何特征和淬火处理参数中的至少一个的输入数据由配置为神经网络的计算机进行操作，以确定对应于基于残余应力和失真的至少一个的输出数据 对输入数据。 训练神经网络以确定输入数据和输出数据中的至少一个的有效性，并且当超过错误阈值时重新训练网络。 因此，可以在传统的基于有限元法的方法所需的很小一部分时间内使用实施例来预测淬火铝铸件中的残余应力和变形。

公开(公告)号：US09489620B2

公开(公告)日：2016-11-08

申请号：US14295404

申请日：2014-06-04

Applicant: GM Global Technology Operations LLC

Inventor： Qigui Wang ,  Yucong Wang ,  Zhiqiang Gao ,  Zhibin Quan

IPC: G06N3/10 ,  G06N3/08 ,  G06F17/10 ,  C22F1/04 ,  G06F17/50

CPC classification number: G06N3/08 ,  C22F1/04 ,  G06F17/10 ,  G06F17/50 ,  G06F17/5018 ,  G06F2217/41 ,  G06N3/10 ,  Y02T10/82

Abstract: A computer-implemented system and method of rapidly predicting at least one of residual stress and distortion of a quenched aluminum casting. Input data corresponding to at least one of topological features, geometrical features and quenching process parameters associated with the casting is operated upon by the computer that is configured as a neural network to determine output data corresponding to at least one of the residual stress and distortion based on the input data. The neural network is trained to determine the validity of at least one of the input data and output data and to retrain the network when an error threshold is exceeded. Thereby, residual stresses and distortion in the quenched aluminum castings can be predicted using the embodiments in a tiny fraction of the time required by conventional finite-element based approaches.

Abstract translation: 一种计算机实现的系统和方法，其快速预测淬火铝铸件的残余应力和变形中的至少一种。 对应于与铸造相关联的拓扑特征，几何特征和淬火处理参数中的至少一个的输入数据由配置为神经网络的计算机进行操作，以确定对应于基于残余应力和失真的至少一个的输出数据 对输入数据。 训练神经网络以确定输入数据和输出数据中的至少一个的有效性，并且当超过错误阈值时重新训练网络。 因此，可以在传统的基于有限元法的方法所需的很小一部分时间内使用实施例来预测淬火铝铸件中的残余应力和变形。