Ashraf, Waqar Muhammad; Dua, Vivek; (2023) Machine learning enabled modelling and sensitivity analysis for the power generation from a 660 MW supercritical coal power plant. In: Kokossis, Antonios C and Georgiadis, Michael C and Pistikopoulos, Efstratios, (eds.) 33rd European Symposium on Computer Aided Process Engineering. (pp. 2941-2946). Elsevier: Amsterdam, The Netherlands.

Text Ashref_Machine learning enabled modelling and sensitivity analysis for the power generation from a 660 MW supercritical coal power plant.pdf Access restricted to UCL open access staff Download (1MB)

Abstract

The modelling of large-scale industrial power generation system is a challenging task owing to the hyperdimensional input space of the variables and the non-linear interactions among them. In this work, the power production operation from 50% to 100% generation capacity of a 660 MW supercritical coal power plant is modeled on almost three months’ operational data by artificial neural network (ANN). The hyperparameters of the ANN model are optimized, an effective ANN model is developed and validated on the power generation conditions. The partial derivative-based sensitivity analysis is carried out and it reveals that main steam flow rate is the most significant input variable on the power production followed by coal flow rate, reheat steam temperature and main stem temperature. This research work presents a reliable utilization of ANN model for the modelling of large capacity power plants that can be extended to conduct the enterprise-level performance enhancement analytics.

Download activity - last month

Export as XMLJSONCSV

Download activity - last 12 months

Export as JSONCSVXML

Downloads by country - last 12 months

Export as XMLJSONCSV

Archive Staff Only

View Item