Propulsion company Brunvoll, together with compressor supplier Sperre Air Power, research partner Sintef and the shipowner Altera Infrastructure, formed a joint project in 2019 known as FAST, which was partially funded through a grant from the Research Council Norway.
Condition monitoring and various types of condition/predictive maintenance systems is being developed. The goal of the FAST project was to develop and implement a system where the OEM product knowledge is key in the development of artificial intelligence for condition monitoring and decision making onboard and onshore.
The FAST project aimed to:
- Implement, and demonstrate, a solution for effective collection and compression of data from the Brunvoll deliveries and sensor data from other systems aboard the vessel.
- Develop infrastructure for secure data transmission from vessel to shore.
- Make use of artificial intelligence and machine learning to utilize data for optimised maintenance and operations.
- Visualise relevant data and findings in dashboards for both client and internal use.
Brunvoll, seeing potential for added value for itself and its customers, has now prepared business models that should prove attractive for shipowners.
An infrastructure for secure dataflow from vessels that feed live data from equipment in the field back to the Brunvoll data centre has been established. The collected sensor and control system data, findings from advanced algorithms, and Brunvoll product knowledge are synthesised in condition indicators that are visualised for the customer through a customer portal and dashboard. This dashboard may be integrated with the vessel’s planned maintenance system. In addition to the digital online services, Brunvoll has opened an Operations Centre at the Brunvoll Head Office staffed by company specialists.
The new Brunvoll Condition Monitoring System has been created from the FAST project. The system is designed for advanced monitoring of thruster and propulsion systems, and includes hardware and various algorithms for detecting concrete events and operational characteristics that have significance from an optimised maintenance and operations perspective.
