Acellent Technologies Inc. and Prof. F. G. Yuan at North Carolina State University (NCSU) are proposing to develop a Hybrid Distributed Sensor Network Integrated with Self-learning Symbiotic Diagnostic Algorithms and Models to determine materials state awareness and its evolution, including identification of precursors, detection of microdamages and flaws near high stress area or in a distributed region. The SMART Layer concept will be used as a basis for the development of the hybrid distributed sensor network. The nonlinear behavior of microstructure defects (called micro-defects hereafter), which is intentionally eliminated or simply disregarded in the current conventional ultrasonic diagnosis, will be served as the basis for the development of nonlinear diagnostics for materials state awareness. The Self-learning Symbiotic Diagnostic Algorithms will employ nonlinear acoustic interpretation and statistical data driven analysis. The approach will be based on the principal physics of nonlinearity of materials and its effect on macro scale sensor signals together with an intelligent self instructing data driven algorithm as a wrapper program. Once developed, the sensor network permanently integrated with the structure can be used to accurately and robustly detect the precursors to damages that occur in the structure during scheduled stops or during scheduled maintenance intervals.
Keywords: Materials State Awareness, Materials State Awareness, Self-Learning, Nonlinear-Modulated Ultrasonic Diagnostics, Symbiotic Diagnostic Algorithm, Detection Of Precursors, Nonli