Papers
7
Total Citations
56
H-Index
4
About
Mohammad Siami is a researcher specializing in intelligent robotic inspection systems, computer vision, and condition monitoring of industrial infrastructure, with a particular focus on belt conveyor systems in opencast mining environments. His work sits at the intersection of thermal imaging, deep learning, and autonomous robotics, addressing critical challenges in predictive maintenance for hazardous industrial settings. Siami's most impactful contribution — his infrared image processing pipeline for robotic conveyor inspection (21 citations) — established a foundational framework for automating what were previously dangerous, labor-intensive maintenance tasks. Building on this, he advanced the field through CNN-based binary classification for detecting overheated idlers (13 citations) and U-Net semantic segmentation techniques applied to thermal defect analysis (12 citations), demonstrating progressive sophistication in his methodological approach. Beyond thermal imaging, Siami has broadened his research to incorporate acoustic diagnostics and heterogeneous sensor fusion, combining multiple data modalities through ensemble classifiers to improve reliability in harsh environments. His cumulative body of work — totaling over 56 citations — reflects a coherent research agenda: making industrial inspection safer, more efficient, and more intelligent through the integration of mobile robotics and advanced image analytics. His research holds significant practical value for mining enterprises worldwide seeking to reduce downtime and improve worker safety.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6Acoustic-based diagnostics of belt conveyor idlers in real life mining conditions by mobile inspection robot2 citations · 2022
- 7