The proposed research seeks to provide a comprehensive framework for how to collect and assess degradation data over the product lifecycle from design to usage phases. The proposed framework will enhance both data-driven modeling and physics-based modeling techniques outlined in previous prognostic research. By using the coupled model scheme, the requirements for data quality and complete product design information can be reduced. The scheme can be validated on a critical rotary machinery component, such as a bearing, as well as for more complex components and structures, such an electrical vehicle battery.
The proposed work on developing a combined data driven and physics driven model for fault prognostication has the potential to yield significant cost reduction in manufacturing systems and processes. The work is supported by the Industry Advisory Board as well as individual industry members of the center and has the potential to extend the center?s portfolio. The center has actively involved minority and female students in its research through Research Experiences for Teachers and Undergraduates (RET and REU) projects and will continue to do so through the proposed effort.
(PHM) research. Current PHM research efforts in the literature focus on either data-driven or physics-based methods, while both research directions may suffer from various difficulties and technical challenges in real-world applications. In many practical applications, data collection may be insufficient or even unavailable for applying data-driven PHM methods, while in some other applications the system is too complex for physics-based modeling. As a consequence the coupled model research is proposed to investigate advantages and limitations of both approaches to eventually establish a more effective and robust systematic PHM approach that closely integrates fundamental methodologies of both sides through which weakness from either single approach can be compensated by strength of the other side. This research, which focuses on a methodology and technical framework for coupled models, provides a comprehensive guideline on how to collect and assess the degradation data in a short time period. The developed framework combines the significant benefits of both the data-driven model and physical based model in previous prognostic research. The unified approach is used to improve the precision of the RUL estimation. Thus, the research is a cornerstone toward the goal of rapid, low-cost prognostics and more proactive maintenance. The Center's research on coupled models is ahead of the curve in that the focus on cyber-physical systems (CPS) (which the coupled model approach can be used to generate) has only recently begun. Not only does this place the Center at the forefront of this research area, but it also aligns the Center with other advanced concepts such as Industry 4.0, on which the Center has recently written a conference paper titled Service Innovation and Smart Analytics for Industry 4.0 and Big Data Environment, published in Procedia CIRP, Volume 16, 2014, Pages 3-8. In the past year, the IMS Center has taken initial steps to transferring our already developed technologies and methodologies in manufacturing, to become useful tools in the healthcare industry, and to develop new innovations, software and intelligent systems to improve the quality of information for healthcare providers and individuals alike. The availability of this information will impact the accuracy of health diagnoses, care, treatment decisions, and fitness and activity data, thus improving overall outcomes. With its current efforts, the Center has specifically targeted the areas of assisted living safety and rehabilitation, as well as fitness and health data acquisition and analytics. It is believed that the inclusion of domain knowledge and physical models would aid the data-based and statistical models that are being considered for the health care applications. The use of the coupled model approach for health care applications will be explored in more detail in future studies.
