Browsing by Author "Atanu Roy, Sabyasachi Pramanik, Kalyan Mitra, Manashi Chakraborty"

Now showing 1 - 2 of 2

Advanced hybrid neural network techniques for minimizing gas turbine emissions
(World Journal of Engineering | Emerald Publishing, 2024-10-08) Atanu Roy, Sabyasachi Pramanik, Kalyan Mitra, Manashi Chakraborty
Purpose Emissions have significant environmental impacts. Hence, minimizing emissions is essential. This study aims to use a hybrid neural network model to predict carbon monoxide (CO) and nitrogen oxide (NOx) emissions from gas turbines (GTs) to enhance emission prediction for GTs in predictive emissions monitoring systems (PEMS). Design/methodology/approach The hybrid model architecture combines convolutional neural networks (CNN) and bidirectional long-short-term memory (Bi-LSTM) networks called CNN-BiLSTM with modified extrinsic attention regression. Over five years, data from a GT power plant was uploaded to Google Colab, split into training and testing sets (80:20), and evaluated using test matrices. The model’s performance was benchmarked against state-of-the-art emissions prediction methodologies. Findings The model showed promising results for GT CO and NOx emissions. CO predictions had a slight underestimation bias of −0.01, with root mean-squared error (RMSE) of 0.064, mean absolute error (MAE) of 0.04 and R ² of 0.82. NOx predictions had an RMSE of 0.051, MAE of 0.036, R ² of 0.887 and a slight overestimation bias of +0.01. Research limitations/implications While the model demonstrates relative accuracy in CO emission predictions, there is potential for further improvement in future research. Practical implications Implementing the model in real-time PEMS and establishing a continuous feedback loop will ensure accuracy in real-world applications, enhance GT functioning and reduce emissions, fuel consumption and running costs. Social implications Accurate GT emissions predictions support stricter emission standards, promote sustainable development goals and ensure a healthier societal environment. Originality/value This paper presents a novel approach that integrates CNN and Bi-LSTM networks. It considers both spatial and temporal data to mitigate previous prediction shortcomings.
Application of Neural Network for Reducing Emission and Optimizing Performance of Hydrogen with Biofuel CI Engine
(Machine Learning for Social Transformation | Springer, 2025-01-03) Atanu Roy, Sabyasachi Pramanik, Kalyan Mitra, Manashi Chakraborty
Fuel selection influences internal combustion engine (ICE) performance and toxic emissions. However, predictive monitoring plays an imperative function in the validation and support of the machine. It optimizes engine running performance, reduces emissions, and increases efficiency. This study investigates the emission reduction and optimization of brake thermal efficiency (BTE) using a blended fuel—hydrogen, biofuel, and water on a one-cylinder compression ignition (CI) engine. Simulink simulations are used to collect data, which is then preprocessed and analyzed using advanced feature extraction to increase prediction accuracy. In this paper, a hybrid deep reinforcement learning, and artificial neural network (DRL-ANN) is initiated and designed to predict CI engine emission attributes. To optimize the prediction model, this method combines DRL and neural networks. As a result, the model achieved superior predictive accuracy compared with earlier approaches regarding accuracy (BTE 0.96851, CO 0.95124, HC 0.96624), mean-squared errors (BTE 0.00018, CO 0.00058, HC 0.00055) and R2 (BTE 0.95478, CO 0.94694, HC 0.97015). This study demonstrated the prediction model's efficacy in optimizing CI engine running characteristics and fuel types.