This proposal seeks funding for the Center for Intelligent Maintenance Systems studies conducted by the University of Cincinnati site (lead), the Missouri University of Science and Technology site and the University of Michigan site. Funding Requests for Fundamental Research are authorized by an NSF approved solicitation, NSF 10-507. The solicitation invites I/UCRCs to submit proposals for support of industry-defined fundamental research.
The proposed research focuses on methods for controlling and evaluating the quality of data used in prognostic applications of system health and indicating when maintenance is needed. The proposal is well conceived, well organized, and the goals and objectives of the research are presented well. The tasks to be accomplished over the two years are clearly outlined, as well as which of the cooperating institutions will carry out the work.
The proposed research answers a significant research question raised by the industrial partners. For many companies assuring the quality of datasets before actually performing prognostics can avoid unnecessary investment in redundant prognostics analysis due to poor quality datasets. Assured data quality will improve prognostics results, which leads to better maintenance decisions and significant cost saving. The IMS Center has actively involved minority and female graduate students and has provided a number of Research Experience for Teachers and Undergraduates (RET and REU) projects.
This collaborative project has investigated a systematic approach for evaluating the data collection and pre-processing of experimental datasets in order to support development of the prognostics applications. Our investigation focuses on two main categories of approaches for pre-analysis of datasets:data-driven and model-based ones. To make use of the strengths of both approaches, the Team has studied the significance of the proposed evaluation metrics and new methods of quantitative assessment of experimental datasets to support the prognostics framework. The project, which focuses on methods for assessing a dataset before investing significant resources on analysis, contributes to the Prognostics and Health Management (PHM) field in that it provides systematic guidelines on how to collect and evaluate datasets. The systematic framework integrates comprehensive quantitative metrics for data validation and verification in the data collection, pre-analysis and reconstruction stages to assure data quality for prognostics purposes. These metrics are utilized to enhance the previously developed QFD (Quality Function Deployment) –based selection tool to prioritize prognostic algorithms. Additionally, this research provides an important step toward the goal of autonomous data validation and verification. Through the broad IAB support and collaboration with our industry partners, the project answered a significant research question raised by our industrial partners that "what are meaningful tests or indicators that can measure the quality of a dataset for prognostics applications." For many companies, assuring the quality of datasets before actually performing prognostics can avoid unnecessary investment in redundant prognostics analysis due to poor quality datasets. Assured data quality will improve prognostics results, which leads to better maintenance decisions and significant cost saving. As we have been inspired by relevant research in other fields such as data-mining, biostatistics, and signal processing, the outcome of this research could potentially impact those fields as well. The IMS Center has actively involved minority and female graduate students and has provided a number of Research Experience for Teachers and Undergraduates (RET and REU) projects. This research project will continue those efforts. In addition, the close collaborative component of this research will provide an opportunity of university researchers to work closely with their industry counterparts.
