SBIR Phase I: A Manufacturing Monitoring System Using Sound Spectrograms and Artificial Intelligence

The broader impact of this Small Business Innovation Research (SBIR) Phase I project is to improve manufacturing performance at decreased costs. The project will develop a smart internal sound sensor- and artificial intelligence (AI)-based machine and process monitoring system as a simple plug-and-play edge device. It aims to be a low-cost, versatile, and customizable solution for a wide range of equipment and devices on production floors.

This technology can significantly reduce the product defect rate, improve product quality, prolong machine life, increase the overall equipment effectiveness, and enable better human decisions. While this monitoring system can be deployed by any new/modern manufacturers, small and mid-sized enterprise (SME) companies can retrofit legacy equipment/ devices for understanding their machines, process behaviors, timely maintenance, and remaining life, etc.

The proposed project is a stethoscope-like sensor that captures internal sounds across many frequencies without contamination from external factory sounds. To interpret the captured sounds into useful information for dashboard publishing in terms of machine/process events (anomaly, situation, downtime, etc.), this project is developing AI-based sound classification or ‘machine speech’ recognition techniques.

The sound data can be wirelessly acquired and processed, enabling a device for non-invasive application on the outside of target equipment.

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.