Paper Contents
Abstract
Medical waste, due to its high calorific value, has a pronounced effect on furnace temperature in industrial waste treatment facilities. While it contributes to energy recovery, uncontrolled input volumes can lead to overheating, equipment degradation, and regulatory violations. This study introduces a lightweight, data-driven artificial neural network (ANN) model that predicts furnace temperature based on medical waste input quantity. Trained on operational data, the model achieves approximately 80% prediction accuracy, particularly within the critical 12501400C range. Unlike rule-based or deep learning approaches, the ANN model offers fast convergence and low computational overhead, making it suitable for real-time deployment in control room environments. Proposed model is ready to be integrated into a practical assistive system that includes temperature forecasting, input waste recommendations, alerts. Further well aligned with Japans 2024 exhaust gas regulations, enhances operational safety, combustion efficiency, and environmental compliance. This research bridges academic modeling and industrial application, offering a regulation-ready solution which also brings profit to plant.
Copyright
Copyright © 2025 wasantha samarathunga. This is an open access article distributed under the Creative Commons Attribution License.
