Application of neural network technology for SCC prevention in power plants and cooling water circuits

This paper briefly describes modern neural network technology and its potential applications in the area of corrosion and corrosion prevention. It highlights some recent developments in this field and discusses in some detail neural network models for chloride-induced stress corrosion cracking (SCC) of austenitic stainless steels, and for stress corrosion cracking problems in high-temperature water. Based on case histories of service experience with austenitic stainless steel, its is possible to predict the stress corrosion risk in an intelligent, automated way by means of neural network technology. Such neural network is capable of extracting regularities from set of examples which can then be used for the processing of previously unseen instances. (orig.)