An integrated data-driven surrogate model and thermofluid network-based model of a 620 MW e utility-scale boiler

• Published in: Proceedings of the Institution of Mechanical Engineers. Part A, Journal of power and energy Journal of power and energy, 2023-08, Vol.237 (5), p.1061-1079
• Main Authors: Rawlins, Brad Travis, Laubscher, Ryno, Rousseau, Pieter
• Format: Article
• Language: English
• Subjects: Boilers; Flue gas; Machine learning; Mathematical models; Multilayer perceptrons; Multilayers; Power plants; Scale (corrosion); Uncertainty
• ISSN: 0957-6509; 2041-2967
• DOI: 10.1177/09576509221148231

An integrated data-driven surrogate model and one-dimensional (1-D) process model of a 620 [MWe] utility scale boiler is presented. A robust and computationally inexpensive computational fluid dynamic (CFD) model of the utility boiler was utilized to generate the solution dataset for surrogate model training and testing. Both a standard multi-layer perceptron (MLP) and mixture density network (MDN) machine learning architectures are compared for use as a surrogate model to predict the furnace heat loads and the flue gas inlet conditions to the convective pass. A hyperparameter search was performed to find the best MLP and MDN architecture. The MDN was selected for surrogate model integration since it showed comparable accuracy and provides the ability to predict the associated uncertainties. Validation of the integrated model against plant data was performed for a wide range of loads, and critical results were predicted within 5–8% of the measured results. The validated model was subsequently used to investigate the effects of using a poor-quality fuel for the 100% maximum continuous rating load case. The uncertainties predicted by the surrogate model were propagated through the integrated model using the Monte Carlo technique, adding valuable insight into the operational limits of the power plant and the uncertainties associated with it.