Wind turbines are particularly versatile in placement and oftentimes sprawl from the north pole to the desert, in urban areas, and even at the sea. Hence, the cumbersome accessibility and extreme weather conditions turn maintenance of turbines into a challenging job, thus underpinning the urge to foresee a prospective defect. In addition, the growing complexity of turbines only impedes the data interpretation for the engineers, prompting the need for assisting tools. For this reason, Bit teamed up with an international energy supplier to prototype a machine-learned predictive maintenance model.
Using bearing temperature as the single indicator for failure would only work under specific turbine and weather conditions like cold, heat, and wind. Therefore, technically experienced engineers and data-driven experts trained a model including a variety of features like outside temperature and turbine spinning speed. Within weeks the model was able to accurately reproduce the historic data, indicating that it would also be able to predict future failures. During a prototype demo, a recently noticed aberration in one of the turbines came up - a somewhat perfect moment to check if our tool detected it, too. And guess what? The data indication did not keep us waiting.
RESULTS: Outcomes for our client
We finalized the project by implementing a control panel in our client’s control room, assisting the engineers with machine-based predictive maintenance. This way, not only a potential defect can be identified right on spot, but also be timely prevented without unsolicited hazard and accompanying losses. Forewarned is forearmed, right?