Artificial neural network to predict degradation of non-metallic lining materials from laboratory tests
- Monsanto Co., St. Louis, MO (United States)
Artificial neural networks are computer simulations that have the potential of ``finding`` the same patterns that corrosion practitioners recognize to relate experimental test results to lifetime predictions. This potential ability was utilized to construct an artificial neural network to recognize the pattern between results from a sequential immersion test for organic non-metallic lining materials and their ability to function as linings in actual applications. The network so constructed has been shown to predict field performance from this test. The network was incorporated within an Expert System to simplify data input and output, allow for simple consistency checks, and to make the final prediction.
- OSTI ID:
- 80109
- Report Number(s):
- CONF-940222-; TRN: IM9532%%236
- Resource Relation:
- Conference: Corrosion 94: National Association of Corrosion Engineers (NACE) international annual conference, Baltimore, MD (United States), 28 Feb - 4 Mar 1994; Other Information: PBD: 1994; Related Information: Is Part Of Corrosion/94 conference papers; PB: 5005 p.
- Country of Publication:
- United States
- Language:
- English
Similar Records
Fracture-frequency prediction from borehole wireline logs using artificial neural networks
Design and development of an artificial neural network for estimation of formation permeability