BP neural network prediction of the mechanical properties of porous NiTi shape memory alloy prepared by thermal explosion reaction
✍ Scribed by Qiang Li; Jing-Yuan Yu; Bai-Chun Mu; Xu-Dong Sun
- Publisher
- Elsevier Science
- Year
- 2006
- Tongue
- English
- Weight
- 175 KB
- Volume
- 419
- Category
- Article
- ISSN
- 0921-5093
No coin nor oath required. For personal study only.
✦ Synopsis
BP neural network model was developed for prediction of the mechanical properties of porous NiTi shape memory alloy (SMA) prepared by thermal explosion. In this paper, the model can well reflect the relationship between the process parameters including heating rate (v), green density (D) and particle size of Ti (d) and product mechanical properties including the compressive yield strength (σ 0.2 ) and Young's modulus (E). The model can satisfactorily predict σ 0.2 and E in the ranges used to build the model. The predicted results agree with the actual data within reasonable experimental error. So the model is critical for the quality control of the porous NiTi SMA and will be widely used in thermal explosion process. At the same time, it also provides a novel method for the study of thermal explosion products.