Fingrid, Finland’s national transmission system operator, was facing a great technological leap. Their aim was to modernise the maintenance of substations and enhance the reliability of the grid and the cost-effectiveness of maintenance. Solita met this challenge by creating a data platform that uses IoT technology, sensor data and machine learning. The result is an even more robust electrical grid, data-driven maintenance and a foundation for predictive maintenance.
As Finland’s transmission system operator, Fingrid is responsible for the national network used to transmit 77 per cent of all electricity in Finland. This network is a vital infrastructure for Finnish society. The oldest parts of the grid are up to 90 years old (the average age being 26 years), so maintenance has been less than modern, mostly relying on physical measuring visits and periodic maintenance.
Fingrid had started using sensors to measure the devices at their substations and was looking for a partner who could build a comprehensive IoT system around the data. The sensor data needed to be broken down and processed into something usable, which required the implementation of new cloud technology. Solita’s multitalented team took the reins of the project in the spring of 2018. There were two objectives: create the framework for using IoT data and lay a foundation for future development.
We are seeking to improve usability, reliability and cost-effectiveness. The IoT data platform plays a major role in this.Marcus Stenstrand, Digitalisation Manager, Fingrid
Fingrid needed to take a big technological leap to modernise the maintenance of their transmission system. Data needed to be collected from substations to gauge the devices’ status and need for maintenance in real time. Different data communication solutions were needed to transfer the measurements to a cloud environment. In addition, the data had to be unpacked and arranged so that it could be used to manage the maintenance of the whole transmission system.
The designing of the sensors for collecting the data is a close effort between the sensor suppliers and the Solita team. The data collected by over 400 sensors installed in a single substation are mined and modelled using machine learning. The result is a real-time dashboard running on the Microsoft Azure platform, which displays the status of the substations and their devices to end users, like Fingrid’s maintenance specialists.
“The building of IoT analytics might sound simple, but when you take a look under the hood, you realise how many different things you need to do and what variety of skills you need, and that it’s beyond the capabilities of most regular engineers.”
– Marcus Stenstrand, Digitalisation Manager, Fingrid
“The assessment of substation maintenance needs and the system development of predictive maintenance require enormous volumes of data to be processed and analysed. Our high degree of specialisation in data science and data system development made it possible to build the comprehensive solution Fingrid needed.”
– Kimmo Koskinen, Account Director, Solita.
The shift to real-time data modelling brings more transparency for maintenance specialists, reducing the number of unnecessary service and measuring visits. This saves person-hours, as maintenance personnel are no longer required to check substations on-site and can instead visit them only if there is a need for maintenance. In these cases, the maintenance specialists will know in advance which device is in need of maintenance.
This does not mean removing people from the equation – this is about redefining human work.
The data platform will have a swift impact on the work we and our service providers do. Maintenance specialists will change from reactive measures based on measuring visits to a more real-time and need-based model. The system will also create a need for new types of roles in our company related to the maintenance and monitoring of the platform.Marcus Stenstrand, Digitalisation Manager, Fingrid
The data platform will help Fingrid achieve their objective of a more reliable and cost-effective transmission system. The Internet of Things solution makes it easier to predict equipment failures and minimise the resulting problems.
The technological advancements made during the project have also laid the foundation for predictive maintenance: when the status of substations is known precisely, machine learning models can be used to estimate future maintenance needs and proactive responses.
“Our cooperation with Solita has been quite smooth. Solita had solid expertise but were also eager to learn more about our business. Learning has taken place both ways: Solita taught us analytics methods and we instructed Solita on our equipment and how to measure data from substations.” – Marcus Stenstrand, Digitalisation Manager, Fingrid
