University of Wisconsin Extended Campus is now Wisconsin Online Collaboratives! This name reflects the partnerships of the 13 universities within the Universities of Wisconsin–our state's premier system of public higher education. Through these partnerships we will continue to support online degrees, certificates and courses–along with support services to you.

Capstone Projects

Modeling Lead-Acid AGM Battery Performance from Process Data

Program: Data Science Master's
Host Company: Clarios
Location: Milwaukee, Wisconsin (remote)
Student: Joseph Taylor Ashworth

Energy storage is of critical importance in a variety of industries, nowhere more so than in automotive applications. Advanced batteries such as absorbent glass mat (AGM) are critical as both a primary and secondary source of electrification in vehicles with internal combustion engines or electric drivetrains, as well as hybrid models. Batteries are responsible for a wide range of safety, operational, and comfort features and the electrochemical nature of the product makes the manufacturing process highly complex. Ensuring newly built batteries meet label ratings and, ultimately, customer expectations is a key consideration for companies that manufacture batteries. This study researched key performance measures of new batteries and considered several models for predicting battery performance. The study ultimately recommended a best fit random forest model for predicting battery performance from manufacturing process indicators.