The system from Fujitsu and Fujitsu Laboratories involves use of sensors attached to the surface of a bridge to measure vibration. It then estimates the degree of the bridge's internal damage through the application of Fujitsu Human Centric AI Zinrai artificial intelligence technology.

Details will be announced at the Japan Society of Civil Engineers annual meeting, to be held at Kyushu University in September.

The technology has been verified using test data from the Research Association for Infrastructure Monitoring System (RAIMS). Fujitsu now plans to conduct trials using vibration data from actual bridges, with the goal of real-world usage by around 2018.

The company said that there have been many trials in recent years involving evaluation of the level of damage through the use of sensors attached to the deck surface and vibration data. “With the methods used until now, accurately understanding the degree of damage within the interior of the deck was an issue,” said a company statement. “Now, by expanding Fujitsu Laboratories' proprietary deep learning AI technology for time-series data, Fujitsu and Fujitsu Laboratories have developed technology that can discover anomalies and express in numerical terms degrees of change that demonstrate drastic changes in the status of objects such as structures or machinery, and detect the occurrence of abnormalities or distinctive changes.”

The test results showed that the geometric characteristics extracted from the vibration data by the technology would appear as a single cluster when the bridge was intact, but that the shape changes when the bridge had developed internal damage.

Moreover, it was confirmed that the degree of abnormality and the degree of change correspond with the results measured by strain sensors embedded within the bridge deck.

From the analysis results of data from an acceleration sensor at a single location on the surface of a bridge, Fujitsu found that it is possible to estimate the degree of damage across a wide area of a bridge's interior. “Detecting the occurrence of internal stress using this technology allows for the estimation of damage in its earliest stages, and can contribute to early countermeasures,” it said.