Reliability Analysis of Mechanical Products Based on Regenerative Samples
- Tengfei Chen, Erling Gong
- Corresponding Author
- Tengfei Chen
Available Online June 2017.
- https://doi.org/10.2991/ammee-17.2017.126How to use a DOI?
- Mechanical products; small sample; time censoring; Bootstrap; BP neural network
- Aiming at the problem of reliability estimation of mechanical products in small sample size and time censored test under Weibull distribution, this paper proposed a method which combined Bootstrap and BP neural network for reliability evaluation. Firstly, Bootstrap method was used to expand the reliability and failure time sample. Secondly, the BP neural network was trained by the expanded sample. Then the parameters of Weibull distribution can be estimated by the trained BP neural network. Finally, the reliability characteristics of the product can be obtained. In the end, an example was analyzed to illustrate the applicability of the method.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Tengfei Chen AU - Erling Gong PY - 2017/06 DA - 2017/06 TI - Reliability Analysis of Mechanical Products Based on Regenerative Samples BT - Advances in Materials, Machinery, Electrical Engineering (AMMEE 2017) PB - Atlantis Press SN - 2352-5401 UR - https://doi.org/10.2991/ammee-17.2017.126 DO - https://doi.org/10.2991/ammee-17.2017.126 ID - Chen2017/06 ER -