Performance prediction of a clean coal power plant via machine learning and deep learning techniques

Mariana Haddadin, Omar Mohamed, Wejdan Abu Elhaija and Mustafa Matar

Energy & Environment, 2024, vol. 35, issue 7, 3575-3599

Abstract: Computer simulation of energy resources has led to significant achievements in the interdisciplinary fields of energy and environment. Apart from renewable resources, fossil-fuel power generation plants can be made cleaner to satisfy the future climate targets while keeping secure and stable grid. Clean coal power plants are still among the dominant options for power generation, which are committed through energy-efficient operation, carbon capture and storage, or combination of both strategies. On the other hand, machine learning and deep learning techniques have a leading integrity in the field of simulation. This paper presents accurate models of a cleaner coal-fired supercritical (SC) unit using two types of artificial neural network, which are Elman neural network (ENN) and generalized regression neural network (GRNN). The models newly embed higher coverage range and more accurate results than previously published models. Each subsystem of the models has been structured as a multi-input single-output (MISO) component to predict the behavior of significant variables in the plant, mainly the supercritical pressure in MPa, the steam temperature in °C and the production in MW. Those variables have been intentionally selected as they are clear indicators for the energy-efficient and cleaner production. Simulation results of four sets of data have indicated satisfactory performance of both models with a bit higher superiority of the GRNN that has given negligible or zero Mean Squared Error (MSE) for all outputs, whereas the minimum MSE of the deep ENN is 3.131  ×  10 −3 .

Keywords: Clean coal power plants; supercritical power plants; machine learning; deep learning; modeling; identification; simulation (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://journals.sagepub.com/doi/10.1177/0958305X231160590 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:sae:engenv:v:35:y:2024:i:7:p:3575-3599

DOI: 10.1177/0958305X231160590

Access Statistics for this article

More articles in Energy & Environment
Bibliographic data for series maintained by SAGE Publications ().