Prediction of Aluminum Pitting in Natural Waters Via Artificial Neural Network Analysis
One mission of the Department of Energy''s Savannah River Site (SRS) is to store spent nuclear fuel (SNF) and other waste products while permanent storage facilities for such materials are prepared. This extended storage increases the probability of pitting corrosion for aluminum-based SNF stored in natural (fresh) waters. The Back Propagation of Error method was used to train and test an Artificial Neural Network (ANN) model using archival pitting data. For aluminum AA1100 (UNS A91100), a database from the British Non-Ferrous Metals Research Association (BNFMRA) was used because it contained the relevant chemical species for pitting. A trained ANN, consisting of two hidden layers of six and four elements each, provided a better estimate of pit depth as a function of water chemistry after 150000 training cycles than a regression (linear, quadratic and cross-product) model.
- Research Organization:
- Savannah River Site (SRS), Aiken, SC (United States)
- Sponsoring Organization:
- US Department of Energy (US)
- DOE Contract Number:
- AC09-96SR18500
- OSTI ID:
- 9832
- Report Number(s):
- WSRC-MS-99-00579; TRN: US0103205
- Journal Information:
- Corrosion Journal, Other Information: PBD: 13 Aug 1999
- Country of Publication:
- United States
- Language:
- English
Similar Records
Evaluation of water chemistry on the pitting susceptibility of aluminum
Melt-Dilute Treatment Technology for Aluminum Based Research Reactor Spent Fuel