Shiprepair & Maintenance: 4th Quarter 2019
A new algorithm, claimed to be ‘advanced and sophisticated’, and based on both a physical and data driven engine model, has been jointly developed by engine manufacturer Winterthur Gas & Diesel (WinGD) and technical university ETH Zürich, in a bid to further enhance predictive maintenance for marine two-stroke engines. The solution, which deploys a hybrid approach to modelling engine behaviour, will be further tested and validated before being applied in future versions of the WinGD Integrated Digital Expert (WiDE) engine data analytics system.
WiDE diagnostics, currently being piloted on WinGD engines in operation and available for all new WinGD engines, uses machine learning and modelling based on performance benchmarking and sensor data to detect and predict potential failures. The enhanced system developed under the project with ETH Zürich uses a new approach to modelling engine behaviour that combines this data-driven engine modelling with physical modelling.
While data-driven models use condition monitoring, or rules derived from experiments, physical modelling relies on complex simulations that can be time-consuming and costly. To align with WiDE’s purpose of providing instant, online diagnostics, the system will apply a thermodynamic model that, according to WinGD, takes just milliseconds to calculate. According to the company, such hybrid modelling will improve WiDE’s ability to predict and prevent engine failures, cutting downtime and maintenance costs for shipowners and operators.
Rudolph Holtbecker, director operations, said: “The first iteration of our WiDE system brought remote diagnostics and predictive maintenance to marine two-stroke engines. The project with ETH Zürich will increase the predictive maintenance capability of WiDE to a level not yet seen in our industry.”
The WiDE platform, created in cooperation with software provider Propulsion Analytics and automation and communication specialist Enamor, was first introduced last year. The collected engine data is assessed through three different levels of analysis: thermodynamic, know-how-based and machine learning. The combination of such analyses is designed to provide a comprehensive engine diagnostic picture and to create real understanding of the engine condition.
To support the WiDE data analytics system, WinGD is opening a new support centre in 2020 which aims to connect shipowners and operators with engine experts to facilitate advanced predictive maintenance. Staff at the centre will be able to quickly troubleshoot and resolve issues through access to accurate data analysis and will be in close contact with the engine manufacturer’s service providers to address problems raised by the crew requesting support.
As the IMO sulphur cap deadline approaches, WinGD is having an increasing number of conversations with shipowners about the potential of a retrofit to the X-DF technology on its X engine range. “Not all shipowners have been in a position to consider a newbuild and the installation of scrubbers isn’t necessarily the best choice for long-term OPEX,” says Holtbecker. “Switching to a dual-fuel engine is the better choice for compliance over the coming years. Our global service providers are working with individual shipowners to discuss the best options for them to consider, if retrofit is a viable option.”
