Mining is one of the most demanding industrial sectors, where safety, environmental impact, and equipment reliability are constant challenges. Failures in drilling systems can cause costly downtime and safety risks.
In her research at Tampere University, MSc (Tech) Marzieh Zare developed a data-driven framework that uses machine learning and sensor fusion to monitor rock drilling operations in real time. The study focused on optimizing sensor placement and developing models to automatically detect abnormal operating conditions.
The research combined simulated and real-world data to enhance the accuracy of operation analysis and fault detection. The results demonstrate the potential of intelligent monitoring systems to improve safety, reliability, and sustainability in modern mining operations.
Conducted in collaboration with Sandvik Mining and Construction, the study shows how advanced data analysis can enhance predictive maintenance and support the digital transformation of heavy industry.
Public defence on Friday 10 October
The doctoral dissertation of MSc (Tech) Marzieh Zare in the field of Computing Sciences titled Automated Health Monitoring in Rock Drilling via Machine Learning: Industrial mining application will be publicly examined via Zoom at 12:00 on Friday, 10 October 2025.
The Opponent will be Professor Behzad Ghodrati from Luleå University of Technology, Sweden. The Custos will be Professor Ari Visa from the Faculty of Information Technology and Communication Sciences, Tampere University.
The doctoral dissertation is available online.
The public defence can be followed via remote connection.