Early detection of anomalies using big data analysis in a large-scale plant

Chugoku Electric Power Company

The Shimane Nuclear Power Plant, run by Chugoku Electric Power Company, has adopted NEC's Prediction Monitoring and Diagnostic System, which uses a massive amount of operation data (big data), including output, temperature, and pressure, to detect abnormal operation at an early stage.
The failure prediction monitoring system is the world's first system that uses data gathered from a large number of sensors installed in factories, power plants, and other large-scale industries for analysis using NEC-unique Invariant Analysis technology to discover any anomalies before they result in failures.
Three years of research with Chugoku Electric Power Company proved that it is possible to detect failures at several hours earlier stage then before by analyzing data from the past.
By discovering failures at an early stage, damage to plants can be minimized and switching to a backup unit and repairs are made possible.

Chugoku Electric Power Company
Invariant Analysis technology
Invariant Analysis technology
Automatically mapping the depth of relationship among all sensors during normal operation helps discover any abnormal relationships in operation.

Reading NEC Vision Book 2017

More information about NEC's vision for social value creation and the steps we are taking to achieve this vision can be found in NEC's Vision Books.