Automatic Fault Detection in Power Transmission Lines
We have developed a new user friendly Web-Based software “Automatic Fault Detection in Power Transmission Lines” (AFTL) using deep learning techniques in order to find more than 80 type of defects in power transmission lines, especially faults of insulators.
In this project, high resolution RGB images are captured by the unmanned aerial vehicles (UAVs) imaging power transmission lines. The training and test datasets from the captured faulty images are created from annotation by experts. In order to construct the training dataset, nearly eighty percent of the whole set faulty images were selected and labeled.
Different faults such as damaged and broken insulators, shortage of bolts and nuts, corrosion and rust could be defined by AFTL. The overall accuracy of test dataset is higher than 96 percent. It is noteworthy that the obtained results could significantly reduce of the time and cost of electric power companies by detecting the defects automatically and preventing the occurrence of many power outages.
Finally, AFTL software creates a technical report for the technician that identifies the existing faults of the power transmission lines in different formats such as Excel and PDF. It also defines the exact geographic locations of faults in GIS format as well. The technician can also use the results in the report perform the other analysis such as estimating the expected average lifetime of electrical components.
Please contact us for more information.
