Title :
Use of Artificial Neural Network in Predicting Mechanical Properties of High-Speed Steel (HSS)
Author :
Liujie, Xu ; Jiandong, Xing ; Shizhong, Wei ; Songmin, Zhang ; Yongzhen, Zhang ; Rui, Long
Author_Institution :
State Key lab. for Mech. Behavior of Mater., Xi´´an Jiaotong Univ.
Abstract :
This paper is dedicated to the application of artificial neural networks in building prediction models of mechanical properties of new high-speed steel, including predictions of hardness (H) and impact toughness (Ak) according to quenching and tempering temperatures (T1, T2). multilayer backpropagation (BP) networks are created and trained using comprehensive datasets tested by the authors. And very good performances of the neural networks are achieved. The prediction values sufficiently mine the basic domain knowledge of heat treatment process of HSS. A new application field of neural network was developed by the authors
Keywords :
backpropagation; hardness; impact (mechanical); mechanical engineering computing; neural nets; steel; artificial neural network; hardness prediction; high-speed steel; impact toughness; mechanical properties prediction; multilayer backpropagation networks; Artificial neural networks; Backpropagation; Heat treatment; Mechanical factors; Multi-layer neural network; Neural networks; Predictive models; Steel; Temperature; Testing; BP neural network; heat treatment temperature; high-speed steel; mechanical property;
Conference_Titel :
Mechatronics and Automation, Proceedings of the 2006 IEEE International Conference on
Conference_Location :
Luoyang, Henan
Print_ISBN :
1-4244-0465-7
Electronic_ISBN :
1-4244-0466-5
DOI :
10.1109/ICMA.2006.257520
