The modern electric power transmission system is a geographically extensive network which can span hundreds of kilometres, crossing harsh terrain and making manual inspection of its components costly. While aerial inspections allow relatively quick inspection of transmission routes, they are not usually used for condition assessment due to the high capturing altitude of images which would require time consuming manual processing to identify defects on hundreds to thousands of images. This project developed a health index scale and deep learning estimation method that automatically isolates transmission poles, disaggregates components, detects defects and determines the health index of concrete structures and insulators from aerial images.

Associated Publications:

1. Manninen, Henri, Craig J. Ramlal, Arvind Singh, Jako Kilter, and Mart Landsberg. "Multi-stage deep learning networks for automated assessment of electricity transmission infrastructure using fly-by images." Electric Power Systems Research 209 (2022): 107948.
2. Manninen, Henri, Craig J. Ramlal, Arvind Singh, Sean Rocke, Jako Kilter, and Mart Landsberg. "Toward automatic condition assessment of high-voltage transmission infrastructure using deep learning techniques." International Journal of Electrical Power & Energy Systems 128 (2021): 106726.
3. Ramlal, Craig J., Arvind Singh, Sean Rocke, Henri Manninen, Jako Kilter, and Mart Landsberg. "Toward automated utility pole condition monitoring: A deep learning approach." In 2020 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe), pp. 255-259. IEEE, 2020.