SoundSort leverages acoustic signatures and machine learning for rapid, non-invasive metal scrap sorting, distinguishing between ferrous and non-ferrous metals and identifying anomalies to improve quality control and yield prediction.
SoundSort is an innovative technology that integrates acoustic analysis with machine learning to revolutionize metal scrap sorting. By analyzing the acoustic response patterns of metal scraps through controlled impulse excitation, SoundSort accurately distinguishes between ferrous and non-ferrous materials. This rapid, non-invasive system also identifies anomalies such as rust, coatings, and contaminants, significantly enhancing quality control and yield prediction in metal recycling processes.
Key features:
SoundSort is currently at Technology Readiness Level 4, with a prototype system in development. Future validation will involve field testing to assess performance metrics like accuracy and integration within operational environments. The system is designed to scale across entire recycling processes after refinement based on feedback from real-world applications.
University of Wisconsin–Milwaukee is a comprehensive public research university in the state’s largest metro, pairing broad academic breadth with an applied, urban mission. Industry engages through an innovation campus and research park that co-locate university labs with startups and corporate teams, plus shared-use core facilities. Its location puts partners near a major regional medical center and within a leading freshwater and advanced manufacturing cluster, enabling pilots, internships, and joint development. Research is supported by competitive federal funding from agencies such as NSF, NIH, and DOE. A dedicated technology transfer office and affiliated foundation manage IP, licensing, corporate agreements, and seed funding to accelerate commercialization.