Data-Driven Prognostics for Lead-Acid Truck Batteries Lecture with Erik Frisk
All dates for this event occur in the past.
Prognostics is a useful tool with a potential to provide more flexible maintenance planning and increased system reliability. This presentation covers lead-acid battery failure prognosis for heavy-duty trucks. Modelling battery degradation is difficult and requires high quality data. Here, there are large amounts of data available, logged from about 60,000 trucks in operation. However, data is coarse, static, and not closely related to battery health which makes battery prognostics challenging. Therefore, a probabilistic data-driven prognostics model based on random forests is presented together with techniques to estimate prediction quality using bootstrap techniques.
About Erik Frisk
Erik Frisk was born in Stockholm, Sweden in 1971. He received the Ph.D. degree from Linköping University, Linköping, Sweden, in 2001. He is currently an Associate Professor at the Department of Electrical Engineering, Linköping University. His research interests include issues in model-based fault diagnosis and fault isolation, prognostics, and observer theory.