Simulation of dynamic processes with adaptive neural networks
- Argonne National Lab., IL (United States)
Many industrial processes are highly nonlinear and complex. Their simulation with first-principle or conventional input-output correlation models is not satisfactory, either because the process physics is not well understood or it is so complex that direct simulation is either not adequately accurate, or it requires excessive computation time, especially for on-line applications. Artificial intelligence techniques (neural networks, expert systems, fuzzy logic) or their combination with simple process-physics models can be effectively used for the simulation of such processes. Feedforward (static) neural networks (FNNs) can be used effectively to model steady-state processes. They have also been used to model dynamic (time-varying) processes by adding to the network input layer input nodes that represent values of input variables at previous time steps. The number of previous time steps is problem dependent and, in general, can be determined after extensive testing. This work demonstrates that for dynamic processes that do not vary fast with respect to the retraining time of the neural network, an adaptive feedforward neural network can be an effective simulator that is free of the complexities introduced by the use of input values at previous time steps. The objective of this simulation was to predict the brightness of high-quality paper as a function of the inputs of materials used in a paper mill to control the optical properties of paper.
- OSTI ID:
- 644250
- Report Number(s):
- CONF-980606-; ISSN 0003-018X; TRN: IM9824%%123
- Journal Information:
- Transactions of the American Nuclear Society, Vol. 78; Conference: Annual meeting of the American Nuclear Society, Nashville, TN (United States), 7-12 Jun 1998; Other Information: PBD: 1998
- Country of Publication:
- United States
- Language:
- English
Similar Records
An Investigation of LES Wall Modeling for Rayleigh–Bénard Convection via Interpretable and Physics-Aware Feedforward Neural Networks with DNS
Classification of machine learning frameworks for data-driven thermal fluid models