The Analysis of a Process Monitoring system based on Functional Link Associative Network
Yoon En Sup, Cho Jae Kyu, Lee Dong Eon, Kim Yong Ha, Ahn Sung Jun · Journal of the Korean Institute of Gas · 2003
To operate process plant safely and economically, process monitoring is very important. There are a great number of data acquired through distributed control system and process information system. Fault monitoring is the task with difficulties owing to not only the huge amount of data, but also nonlinearity of chemical processes. In this research, the program, REFA, based on PCA and functional link associative neural network has developed. REFA has better learning capabilities, generalization abilities, and shorter learning time than existing neural network programs. In this work its usefulness has proven by application to Tennessee Eastman process.