Search

Predictive analytics is a technique to make predictions about future unknown events by analyzing current and historical data. The market for predictive analysis is expected to reach $12.4 billion in 2022. Prognostic analysis is one dimension of predictive analytics in engineering discipline and focuses on predicting the time when a system or a component will no longer perform its intended function. A robust and accurate prognostic analysis makes for the increment of production reliability and safety as well as maintenance cost reduction, thus becoming one key task of condition-based maintenance (CBM). Given multiple sensors to simultaneously monitor the health condition during the age of Internet of Things (IoT) and Industry 4.0, traditional prognostic technologies have the limited ability of handling large-scale dataset embedded with complex structures. Therefore, this dissertation mainly focuses on developing high-performance Deep Learning (DL) technologies for condition monitoring and prognostic analysis under the data-rich environment. Besides the CBM, the proposed DL technologies can be also successfully extended and applied into other fields, like battery power estimation, Alzheimer’s Disease (AD) prediction, etc., which have been validated in the dissertation with real case studies. In addition, this dissertation also studied and answered research questions like how to evaluate the quality of features for prognostic analysis, how to select and extract high-level features from original dataset, how to capture the interactions between different features, and so forth. The answers for these questions play important roles in model development for prognostic analysis.

Structural health monitoring (SHM) is a rapidly growing field focused on detecting damage in complex systems before catastrophic failure occurs. SHM systems provide the potential to improve safety and significantly reduced costs. Advanced sensor technologies are necessary to fully harness SHM in applications involving harsh or remote environments, life-critical systems, mass production vehicles, robotic systems, and others. Fiber Bragg grating (FBG) sensors are an attractive solution for in-situ health monitoring due to their low weight, resistance to electromagnetic noise, ability to be multiplexed, and accuracy for real-time measurements. However, effective embedment of FBG sensors into metal has proved challenging. Ultrasonic additive manufacturing (UAM) has been demonstrated for solid-state fabrication of 3D structures with embedded FBG sensors. In this thesis, UAM embedded FBG sensors for SHM applications are investigated. Embedment of a fiber using UAM was shown to have little effect on the tensile and fatigue properties of aluminum coupons. Furthermore, the ability of UAM embedded FBG sensors to detect and monitor crack growth in Compact Tension (CT) specimens is demonstrated. UAM embedded FBG sensors 3 mm from the initiation site were able to accurately detect cracks of length 0.286 ± 0.033 mm. UAM embedded FBG sensors are shown to accurately track crack growth until near failure. Furthermore, UAM embedded FBG sensors 3 mm, 6 mm, and 9 mm from the initiation site detected a crack that initiated to 0.350 mm. Finally, the potential for high temperature applications is also examined through elevated temperature testing. Fiber optics embedded into aluminum using UAM are shown to be more resilient to degradation at elevated temperatures than exposed fibers. UAM embedded FBG sensors are therefore shown to be an effective type of sensor for SHM applications.