Federal Grant Award Summary

Louisiana Tech University received a $185,210 Engineering Research Initiation (ERI) grant from the National Science Foundation's Division of Civil, Mechanical, and Manufacturing Innovation (CFDA 47.041), awarded June 1, 2026, with completion targeted for May 31, 2028. The project develops a unified framework for adaptive anomaly detection in multivariate time series data applicable to critical engineering systems including manufacturing, energy infrastructure, and aerospace platforms. The primary deliverable is an innovative reinforcement learning-based approach that enables real-time identification of abnormal system behavior under changing operating conditions, utilizing a hybrid reward structure that reduces dependency on labeled training data while maintaining detection performance.

The research advances explainable artificial intelligence (AI) methodologies and produces open-source software tools and educational materials for broader dissemination. Complementary outputs include student training in AI and data-driven engineering disciplines and knowledge transfer that supports industrial productivity, infrastructure reliability, and workforce development priorities. The framework addresses a critical operational challenge facing modern engineering systems: the uncertainty and increased downtime resulting from difficulty in identifying abnormal behavior when operating conditions change, thereby improving system reliability and reducing maintenance costs.