Principal Investigator
← Research projects
Ongoing project
Design and Development of an AI-Controlled Biomass-Powered Industrial Dryer for Sustainable Agro-Processing
Summary
Agro-products such as maize, cassava, coffee, fruits, vegetables, and fish require efficient drying to reduce moisture and prevent spoilage. Conventional biomass dryers often have poor thermal control, high fuel consumption, long drying times, and inconsistent product quality.
To develop and demonstrate an energy-efficient AI-controlled biomass dryer for sustainable and high-quality agro-processing.
A 100–500 kg/batch indirect biomass-fired dryer will integrate a combustion chamber, heat exchanger, drying chamber, and exhaust heat recovery. Sensors will monitor temperature, relative humidity, airflow, biomass consumption, and product moisture. AI models such as ANN, Random Forest, XGBoost, or LSTM will predict moisture content and control biomass feed and airflow to optimize drying conditions.
The project integrates biomass energy, heat recovery, IoT monitoring, AI prediction, and intelligent process control to create an adaptive smart drying system.
The project will produce a functional prototype, AI moisture-prediction model, intelligent control algorithm, performance database, and techno-economic and environmental assessment. Target outcomes include >65% thermal efficiency, 20–40% lower biomass consumption, 20–30% shorter drying time, improved moisture uniformity, and AI prediction error below 10%.
The system will reduce drying costs and biomass consumption, improve product quality, minimize environmental impacts, and provide a scalable thermal-processing technology for agro-processing SMEs |
To develop and demonstrate an energy-efficient AI-controlled biomass dryer for sustainable and high-quality agro-processing.
A 100–500 kg/batch indirect biomass-fired dryer will integrate a combustion chamber, heat exchanger, drying chamber, and exhaust heat recovery. Sensors will monitor temperature, relative humidity, airflow, biomass consumption, and product moisture. AI models such as ANN, Random Forest, XGBoost, or LSTM will predict moisture content and control biomass feed and airflow to optimize drying conditions.
The project integrates biomass energy, heat recovery, IoT monitoring, AI prediction, and intelligent process control to create an adaptive smart drying system.
The project will produce a functional prototype, AI moisture-prediction model, intelligent control algorithm, performance database, and techno-economic and environmental assessment. Target outcomes include >65% thermal efficiency, 20–40% lower biomass consumption, 20–30% shorter drying time, improved moisture uniformity, and AI prediction error below 10%.
The system will reduce drying costs and biomass consumption, improve product quality, minimize environmental impacts, and provide a scalable thermal-processing technology for agro-processing SMEs |