Early Detection of Failure Precursors Using Symbolic Dynamics, Neural Networks, and Principal Component Analysis Navy SBIR FY2005.1 Sol No.: Navy SBIR FY2005.1 Topic No.: N05-024 Topic Title: Early Detection of Failure Precursors Using Symbolic Dynamics, Neural Networks, and Principal Component Analysis Proposal No.: N051-024-0326 Firm: Intelligent Automation, Inc. 15400 Calhoun Drive Suite 400 Rockville, Maryland 20855 Contact: Ravindra Patankar Phone: (301) 294-5248 Web Site: www.i-a-i.com Abstract: For early detection and monitoring of failure precursors in mechanical transmission couplings, we propose to develop signal processing capabilities that can map patterns in accelerometer data to an anomaly measure. Toward this end, Professor Asok Ray at Penn-State University has pioneered an elaborate mathematical theory based on symbolic time series analysis (STSA), statistical mechanics, and information theory. An anomaly detection algorithm is formulated by applying this novel STSA theory to create a robust statistical pattern recognition technique. For anomaly detection, this STSA technique has been shown to be superior to conventional pattern recognition techniques, such as artificial neural networks (ANN) and principal component analysis (PCA) because it exploits a common physical fact underling most anomalies which conventional techniques do not. This superiority has recently been demonstrated on electrical circuits, fatigue testing machines, and mechanical components undergoing fatigue due to vibrations. The research objectives are: (i) to develop a coupling model where gradually evolving damage phenomena can be introduced, (ii) to formulate and compare real-time algorithms for early detection and monitoring of failure precursors in model simulations based on three principal techniques and their variants - STSA, ANN, and PCA, and (iii) to demonstrate these algorithms on fatigue damage accumulating parts of a vibrating machine experiment. Benefits: Phase 2 will focus on obtaining real-time transmission coupling data from experiments and processing these data with the real-time algorithms developed in Phase 1. Algorithms based on the STSA technique have the potential to revolutionize signal processing for anomaly detection. IAI and Penn-State are committed to fundamental research in anomaly detection in collaboration with industry and Government laboratories (e.g., General Electric, Delphi Corporation, Sikorsky Aircraft, AFRL, and NASA Langley). This novel technology, which is not limited to transmission couplings, will be readily applicable in both military and commercial settings. Return