Paper Contents
Abstract
Industrial waste incineration facilities increasingly face challenges from high-calorific and unpredictable waste streams, particularly medical waste. This study proposes a reverse modeling framework that uses clinker temperaturemeasured downstream along the under-furnace conveyoras a proxy to infer upstream waste input characteristics in real time. An artificial neural network (ANN) model was developed to estimate the calorific value and volume of medical waste based solely on clinker temperature and operational data, eliminating the need for direct compositional analysis. The model achieved strong predictive performance (R > 0.92, MAPE < 7%), enabling dynamic input control, predictive maintenance, and improved compliance with Japans emission regulations. This framework represents the first known application of clinker temperature for real-time reverse inference in waste incineration. With scalability and cost-effectiveness, it bridges AI-driven modeling with practical plant operations, supporting safer, more efficient, and regulation-aligned waste treatment.
Copyright
Copyright © 2025 wasantha samarathunga. This is an open access article distributed under the Creative Commons Attribution License.
