Machine Learning Approaches for Estimating the Efficiency of Combined Cycle Power Plant

Kaewprapha, Phisan; Prempaneerach, Pradya; Singh, Vishakha; Tinikul, Trilot; Intarangsi, Nutty

doi:10.1109/ieecon53204.2022.9741611

Cited by 4 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A statistical inference predictive performance model with outstanding outcomes and cost benefts in the entire process has been identifed by Dutta and Ghosh [47]. A study by Kaewprapha et al [48] reported the monitoring process of a combined power plant optimised via the incorporation of machine learning estimators. A multilinear regression machine learning methodology for optimum predictive load estimator is acknowledged [49].…”

Section: Literature Reviewmentioning

confidence: 99%

Modelling and Output Power Estimation of a Combined Gas Plant and a Combined Cycle Plant Using an Artificial Neural Network Approach

Xezonakis,

Samuel,

Enweremadu

2024

Journal of Engineering

View full text Add to dashboard Cite

Artificial neural networks (ANNs) have gained prominence among contemporary computing techniques due to their capacity to handle complicated stochastic datasets and nonlinear modelling in combined gas and combined cycle power (COGAS) plants. Researchers, academicians, and stakeholders have been unable to predict, ensure effective operation, and prevent power outages in COGAS due to the nonlinearity. The first implementation of the simultaneous adoption of three types of ANNs using Levenberg–Marquardt (LM), Bayesian regularisation (BR), and scaled conjugate gradient (SCG) configurations for training and assessing a combined cycle power plant output is presented. The dataset used in this research is a 9568-unit full combined cycle power plant basis load dataset, accessible through the public UCI Machine Learning Repository. It incorporates ambient temperature, exhaust vacuum, ambient pressure, and relative humidity as input parameters to predict the electric output power. The most accurate and dependable electric power predictions could be identified for 70% of the total data, of which 6698 were trained, 15% were tested, and 15% were validated (2870). By using the three training techniques, namely, LM, BR, and SCG, the parameterized networks are studied, increasing the number of hidden layers from 20 to 500. The lowest root-mean-square error value for a multilayer perceptron (MLP) architecture is 3.631%, which is lower than the values of 4.17%, 4.35%, and 4.63% for comparable MLP structures (20 to 500), documented in the literature. The LM and BR algorithms outperform SCG. These adopted algorithms could be a cutting-edge application in the power plant industry and other real-world applications for reliable solutions, to satisfy emerging societal needs with environmental benefits.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Modelling and Output Power Estimation of a Combined Gas Plant and a Combined Cycle Plant Using an Artificial Neural Network Approach

Xezonakis,

Samuel,

Enweremadu

2024

Journal of Engineering

View full text Add to dashboard Cite

show abstract

“…Dengan menganalisis data historis, machine learning dapat membangun model prediktif yang mampu meramalkan kinerja CCPP berdasarkan variasi kondisi lingkungan [7]. Banyak penelitian terdahulu yang menggunakan machine learning dalam memprediksi daya listrik seperti penelitian [8] tentang prediksi daya output listrik pembangkit siklus gabungan berdasarkan faktor lingkungan. Hasil penelitian ini, menekankan pentingnya pemahaman yang mendalam terhadap faktor lingkungan dalam pengelolaan CCPP.…”

Section: Pendahuluanunclassified

Prediksi Daya Listrik Pada Pembangkit Listrik Siklus Gabungan Berdasarkan Kondisi Lingkungan Menggunakan Metode Machine Learning

Hendra

2023

EJI

View full text Add to dashboard Cite

The utilization of machine learning methods in energy simulation enables the optimization of energy use and improves energy efficiency. In this research, the modeling of predicting power output was conducted under full load conditions in a Combined Cycle Power Plant (CCPP) based on the surrounding environmental conditions. Historical data of CCPP operation were used to model and predict power output under various environmental conditions. In this study, four machine learning algorithms, namely Linear Regression (LR), Decision Tree (DT), Random Forest (RF), and Artificial Neural Network (ANN), were compared and evaluated for their performance. The evaluation metrics used to measure the model performance were Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R-Squared. The research results indicate that the Random Forest (RF) model achieved the best performance compared to other models with MAE of 2.314, RMSE of 3.372, and R-squared of 0.961. Additionally, the RF model also performed the best compared to other models in external testing with new data, where RF obtained values of MAE 2.579, RMSE 3.315, and R-squared 0.957. These results are consistent with the previous testing, indicating that RF has stable and reliable performance in predicting larger and more diverse datasets. This research contributes to understanding the potential application of machine learning in the power generation industry, especially in CCPP.

show abstract

“…En las centrales termoeléctricas se utilizan diferentes máquinas motrices de vapor o gas, según sea el combustible a disposición. El vapor necesario para la central, se produce en las calderas donde dentro de las mismas se encuentra agua a altas temperaturas y presiones, y el vapor se conduce por medio de tuberías adecuadas a los niveles de presión propios hacia las turbinas (Kaewprapha et al, 2022).…”

Section: Fundamento Teóricounclassified

Rendimiento de una central termoeléctrica de ciclo combinado basado en su modelo energético

Barrera-Singaña

Reinoso

Tamayo

et al. 2022

SIJIS

View full text Add to dashboard Cite

El presente documento da a conocer un modelo energético de una central termoeléctrica de ciclo combinado y que está basado en el cálculo de propiedades sus termodinámicas y con énfasis en un análisis desde el punto de vista de la Ingeniería Eléctrica, es decir, sin representar a detalle sus procesos mecánicos. Se realiza la formulación teórica de los ciclos de gas y de vapor respectivamente, presentando un caso de estudio donde se determinan los rendimientos de cada ciclo por separado y del ciclo combinado, encontrándose que el tener una central térmica de ciclo combinado desde el punto de vista de aprovechamiento de recursos tiene un mejor rendimiento. Para calcular las propiedades termodinámicas de los ciclos se emplea el software EES, el cual dispone de una amplia librería con propiedades de varias sustancias, siendo el aire como gas ideal y el agua aquellas empleadas en el caso propuesto. Con el propósito de estudiar las características de rendimiento del ciclo, se lleva a cabo un análisis paramétrico, del cual se obtienen gráficas ilustrativas y de tendencias que evidencian las acciones que pueden llevarse a cabo para mejorar el rendimiento del ciclo combinado.

show abstract

Machine Learning Approaches for Estimating the Efficiency of Combined Cycle Power Plant

Cited by 4 publications

References 4 publications

Modelling and Output Power Estimation of a Combined Gas Plant and a Combined Cycle Plant Using an Artificial Neural Network Approach

Modelling and Output Power Estimation of a Combined Gas Plant and a Combined Cycle Plant Using an Artificial Neural Network Approach

Prediksi Daya Listrik Pada Pembangkit Listrik Siklus Gabungan Berdasarkan Kondisi Lingkungan Menggunakan Metode Machine Learning

Rendimiento de una central termoeléctrica de ciclo combinado basado en su modelo energético

Contact Info

Product

Resources

About