Artificial neural networks are computer simulations that have the potential to find the same patterns that corrosion practitioners recognize to relate experimental test results to lifetime predictions. This potential was used to construct an artificial neural network to recognize the pattern between results from a sequential immersion test for organic nonmetallic lining materials and their ability to function as linings in actual applications. The network was shown to predict field performance. The network was incorporated within an expert system to simplify data input and output, to allow for simple consistency checks between sample appearance and network output, and to make the final prediction.

You do not currently have access to this content.