Application of the recurrent multilayer perceptron in modeling complex process dynamics

Journal Article · Mon Feb 28 23:00:00 EST 1994 · IEEE Transactions on Neural Networks (Institute of Electrical and Electronics Engineers); (United States)

DOI:https://doi.org/10.1109/72.279189· OSTI ID:7204331

Parlos, A G ^[1]; Chong, K T ^[2]; Atiya, A F ^[3]

---

1. Texas A M Univ., College Station, TX (United States). Dept. of Nuclear Engineering
2. Yeungnam Univ., Kyungsan (Korea, Republic of). Dept. of Mechanical Engineering
3. Cairo Univ. (Egypt). Dept. of Computer Engineering

A nonlinear dynamic model is developed for a process system, namely a heat exchanger, using the recurrent multilayer perceptron network as the underlying model structure. The recurrent multilayer perceptron is a dynamic neural network, which appears effective in the input-output modeling of complex process systems. A dynamic gradient descent learning algorithm is used to train the recurrent multilayer perceptron, resulting in an order of magnitude improvement in convergence speed over a static learning algorithm used to train the same network. In developing the empirical process model the effects of actuator, process, and sensor noise on the training and testing sets are investigated. Learning and prediction both appear very effective, despite the presence of training and testing sets are investigated. Learning and prediction both appear very effective, despite the presence of training and testing set noise, respectively. The recurrent multilayer perceptron appears to learn the deterministic part of a stochastic training set, and it predicts approximately a moving average response of various testing sets. Extensive model validation studies with signals that are encountered in the operation of the process system modeled, that is steps and ramps, indicate that the empirical model can substantially generalize operational transients, including accurate prediction of process system instabilities not included in the training set. However, the accuracy of the model beyond these operational transients has not been investigated. Furthermore, on-line learning becomes necessary during some transients and for tracking slowly varying process dynamics.

• DOE Contract Number: FG02-89ER12893
• OSTI ID: 7204331
• Journal Information: IEEE Transactions on Neural Networks (Institute of Electrical and Electronics Engineers); (United States), Journal Name: IEEE Transactions on Neural Networks (Institute of Electrical and Electronics Engineers); (United States) Vol. 5:2; ISSN 1045-9227; ISSN ITNNEP
• Country of Publication: United States
• Language: English

Related Subjects

42 ENGINEERING
420400 -- Engineering-- Heat Transfer & Fluid Flow
99 GENERAL AND MISCELLANEOUS
990200* -- Mathematics & Computers
ARTIFICIAL INTELLIGENCE
COMPUTERIZED CONTROL SYSTEMS
CONTROL
CONTROL SYSTEMS
HEAT EXCHANGERS
MATHEMATICAL MODELS
NEURAL NETWORKS
NONLINEAR PROBLEMS
ON-LINE CONTROL SYSTEMS
ON-LINE SYSTEMS
PROCESS CONTROL
TRANSIENTS