The SRSL team recently received an award from the National Science Foundation (NSF) to investigate probabilistic and explainable deep learning for the intuitive predictive maintenance of industrial and agricultural equipment. The approach will not only predict the remaining useful life of a machine component, but it will also quantify the uncertainty of a prediction. As a result, maintenance decisions can be made from a risk-based perspective, eliminating unnecessary maintenance stemming from low-confidence predictions. This STTR Phase I project is in collaboration with a local-to-Iowa industry partner, Percēv (a subsidiary of Grace Technologies) and Grace, and is set to be completed in November 2021.
Funding
New Funding for Battery Early Life Prediction Research
SRSL has received research funding from the Iowa Energy Center, administrated by the Economic Development Authority (IEDA), for a collaborative project with Alliant Energy, SunCrate Energy, and Iowa Lakes Community College. This project is titled “Predicting Battery Lifetime with Early-Life Data for Grid Applications.” This two-year project ($280K in total) will develop a new software tool that harnesses the power of machine learning to accelerate the evaluation of battery lifetime in grid applications. The ISU Co-PIs are Dr. Anne Kimber (ECpE), Dr. Zhaoyu Wang (ECpE), and Dr. Gül E. Kremer (IMSE).
New Funding for Battery Prognostics Research
SRSL has received research funding from the National Science Foundation for a new project on battery prognostics. This project is titled “Physics-Based Probabilistic Prognostics for Battery Health Management.” This three-year project ($385K in total) will be carried out through collaboration with Dr. Shan Hu (ISU ME) and Dr. Simon Laflamme (ISU CCEE).
Opposites attract: Cyclone engineers team up to improve battery reliability and safety
New Funding for Real-Time Machine Learning Research
SRSL has received research funding from the National Science Foundation for a collaborative project with the University of South Carolina (UofSC). This project is titled “RTML: Small: Collaborative: A Programming Model and Platform Architecture for Real-time Machine Learning for Sub-second Systems.” This three-year project ($500K in total with $240k coming to ISU) will create and evaluate novel frameworks for achieving real-time machine learning in sub-second systems. It will be carried out through collaboration with Dr. Simon Laflamme (PI at ISU), Dr. Austin Downey (PI at UofSC), and Dr. Jason Bakos (Co-PI at UofSC).
New Funding for Machinery Prognostics Research
SRSL has received research funding from the National Science Foundation (NSF) for the project titled “PFI-TT: Physics-based Deep Transfer Learning for Predictive Maintenance of Industrial and Agricultural Machinery”. This two-year project ($240K in total) will create an industrial internet of things (IIoT) platform for practical and scalable predictive maintenance of rotating machinery. It will be carried out through collaboration with Dr. Simon Laflamme (CCEE at ISU), Dr. Matthiew Darr (ABE at ISU), Mr. Carey Novak (CIRAS at ISU), and Dr. Andy Zimmerman (Grace Engineered Products, Inc.).
CoE researchers to develop safer, more reliable machines with new grant
New Funding for Battery Reliability Research
SRSL has received research funding from the National Science Foundation for a new project on battery reliability assessment. This project is titled “Data-Driven Dynamic Reliability Assessment of Lithium-Ion Battery Considering Degradation Mechanisms.” This three-year project ($330K in total) will be carried out through collaboration with Dr. Shan Hu (ISU ME). It will create a dynamic reliability assessment platform for lithium-ion batteries that will enable battery management system (BMS) to develop predictive maintenance/control through concurrently analyzing degradation mechanisms and anticipating failure modes.
New Funding for Resilience Research
SRSL has received research funding from the National Science Foundation (NSF) for the project titled “Designing Complex Cyber-Physical Systems for Failure Resilience”. This two-year project ($175K in total) will develop a novel design platform to improve failure resilience in complex cyber-physical systems (CPSs).