This award will enhance the Nation's competitiveness by reducing life cycle costs of battery-powered wireless devices that constitute networked sensor systems. Networked sensor systems are integral to emerging Internet of Things (IoT) applications in such diverse domains as manufacturing systems and civil infrastructure systems. Battery life continues to limit network performance. This project will investigate system-level performance improvements through individual battery management and group replacement strategies. By monitoring and controlling individual battery usage, system level quality of service can be dynamically adjusted, leading to more uniform useful battery life. When these networked systems are located in remote locations, cost-effective group replacement policies can lead to lower costs to maintain the network. The project will involve graduate students and will include mentoring activities to attract students from underrepresented groups.
The project is expected to advance the state of the art in the following aspects: (1) a prognostic algorithm that accurately predicts battery remaining useful life, using transfer learning to leverage condition monitoring data of all batteries in a connected environment; (2) a novel predictive maintenance policy designed for battery group replacement, enabled by active management of battery degradation processes; (3) optimal scheduling of battery maintenance activities under the presence of another independently managed maintenance program with higher priority. The project will advance knowledge on battery health management in connected environments and provide effective power management strategies for battery-powered wireless IoT devices.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
