Technical university ETH Zürich and WinGD (Winterthur Gas & Diesel) have developed an algorithm based on a physical and data driven engine model to enhance predictive maintenance for marine two-stroke engines.
The solution, which deploys a new hybrid approach to modelling engine behaviour, will be further tested and validated to be applied in future versions of the WinGD Integrated Digital Expert (WiDE) engine data analytics system.
WiDE diagnostics are currently being piloted on WinGD engines in operation and were made available for all new WinGD engines ordered as of the beginning of 2018. It uses machine learning and modelling based on performance benchmarking and sensor data to detect and predict failures. The 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 match WiDE’s purpose of providing instant, online diagnostics the system will apply a thermodynamic model that takes milliseconds to calculate.
Hybrid modelling will improve WiDE’s ability to predict and prevent engine failures, cutting downtime and maintenance costs for shipowners and operators. ETH Zürich is collaborating with the US space agency NASA to validate the performance of the algorithm on turbofan engines. The algorithms have demonstrated superior performance for the prediction of the remaining useful lifetime compared to pure data-driven approaches.
“Tests with WinGD as well as with NASA’s data sets showed that we are more accurate on detecting failures than standard approaches,” said ETH Zürich researcher Manuel Arias Chao. “Furthermore, we can differentiate between different types of failures.”
Carmelo Cartalemi, general manager business development, WinGD commented: “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.”