Перейти к содержанию

Russian fiber optic cable turned into 400 sensors using AI

AI was taught to recognize car passages, people walking, and excavation work by vibrations

Russian scientists have transformed an ordinary fiber optic communication line into a distributed sensor network. The cable picks up vibrations around it, and artificial intelligence determines what caused them — for example, a passing car or a person's movement.

Image source: chatgpt

The experiment was conducted by Novosibirsk State University and the T8 company on a 4.3 km line between the university and Akademgorodok. With a registration step of about 10 m, it effectively turned into approximately 400 observation points.

This did not require laying separate sensor lines. A special device, an interrogator, was connected to the existing fiber, which analyzes backscattered light. Vibrations and deformations of the cable change the signal parameters, allowing the location and nature of the impact to be determined.

You can connect a special device to an existing fiber optic line and use the fiber itself as a distributed sensor, without laying a new sensor line.
Pyotr Dergach, research author

The obtained data is sent to the server of the Novosibirsk State University Artificial Intelligence Center. Machine learning algorithms classify events and determine their approximate location.

The technology is being considered for perimeter security, road and construction work monitoring, building and engineering structure monitoring, as well as detecting anomalous vibrations and seismic activity.

Read more on the topic: