closeup view of a project management gantt chart (3d render)

Metroscope: Diagnosis software for operations and maintenance

FULL VERSION
Metroscope is a diagnosis software for operations and condition-based maintenance of nuclear plants. It relies on a unique technology combining a Digital twin  with an Artificial Intelligence to produce an automated diagnosis of the secondary circuit of a nuclear plant. The diagnosis consists in a real-time automated analysis of the health-state of the plant, providing a detection of any failure happening on the monitored perimeter. It is a strong tool for maintenance decision and asset management, especially in the context of ageing plants.

The Metroscope software is currently being deployed on the whole French nuclear fleet. More than 20 French plants are already equipped with the software and have access to the diagnosis, some have been using it for over a year. The technology is versatile and can monitor various industrial processes: it has also been deployed on a CCGT and the cooling system of a Datacenter.

The Digital Twin is a full numerical model of the secondary circuit of the nuclear plant, representing its thermodynamic behavior. The construction of this physics-based Digital Twin relies on the individual design of the plant as well as available historical data from the process. Each supervised component of the power plant is represented in the model by equations mirroring its physical behavior. Once this model is built, it needs to be calibrated: all the unknown parameters in the equations are determined thanks to historic data.

A list of all possible failure modes of the process is then built. The impact of each failure on measurements of the process is simulated: this creates the failure library. The Digital Twin is then ready.

When running, the software confronts  real-time data from the plant with the expected values given by the Digital Twin. Differences between measurements coming from sensors instrumenting the process and their expected values are called symptoms. The most likely failure scenario causing the observed symptoms is then calculated by the AI.

The technology behind Metroscope aims at producing a highly reliable and automated diagnosis of the plant. This diagnosis identifies the hazards currently affecting the secondary circuit and affecting the power output of the plant. The impact and likelihood of each hazard is estimated. This allows the operators to monitor closely the health state of their asset, and to better assess maintenance needs through enhanced condition-based maintenance.

¡Recibe nuestra newsletter!

    The data provided by you is processed by the Spanish Nuclear Society in accordance with EU Regulation 2016/679 on Data Protection, with the purpose of managing your requests, answering queries, administrative, statistical processing and sending SNE communications, about your activity, events, etc. The transfer of data is not foreseen (unless legally required) or international data transfers; and through the Privacy Policy you have all the rights that assist you in terms of privacy.