An image analysis system for defect detection in power transmission lines has been developed by an institute under the State Grid Corporation of China.

The system is based on artificial intelligence. It has a recognition rate for typical defects such as bird's nests of more than 94 percent, said a report by the Science and Technology Daily.

With an operating efficiency of three to five times that of manual checks, the system has been popularized and applied in the country's 27 provinces.

The system has a daily detection capacity of more than 5,000 images. Since this year, it has automatically detected a total of 2.65 million images and recognized over 7,000 hidden defects, said Wu Peng with the institute.

Natural disasters in China, with wide distribution and high frequency, pose a serious threat to the safe and stable operation of the power grid. Therefore, there is an urgent need to strengthen the detection of hidden defects along the country's power transmission lines.

By integrating advanced technologies such as the Internet of Things, big data and cloud storage, the institute also developed systems including a meteorological disaster monitoring system for the power grid to guarantee its stable operation amid the COVID-19 epidemic, said the report.