Enhancing Heat Treatment Processes through Machine Learning

This research project aims to develop a comprehensive predictive framework for heat treatment furnaces to enhance operational efficiency, product quality, and environmental sustainability. The project focuses on creating a data preprocessing pipeline tailored for big machinery sensor data, innovative AI-enabled anomaly detection models, real-time furnace operation analysis, and quality prediction models. Key objectives include obtaining reliable furnace operation data, designing advanced AI-based anomaly detection systems, implementing real-time analysis of furnace operations, and predicting the quality of heat-treated products. By addressing these objectives, the project seeks to improve furnace performance, reduce downtime and maintenance costs, and optimize heat treatment processes. The integration of precise control and monitoring through advanced sensor networks and AI-driven solutions aims to enhance the mechanical, physical, and chemical properties of alloy steels. Ultimately, this project will lead to more efficient furnace operations, higher quality products, and reduced environmental impact.

Faculty Supervisor:

Bijan Raahemi

Student:

Partner:

Nitrex H.T. Inc

Discipline:

Computer science

Sector:

Manufacturing

University:

University of Ottawa

Program: