Center for Intelligent Maintenance Systems Proposal #1127924 Proposal #1127922

This proposal seeks funding for the Center for Center for Intelligent Maintenance Systems sites at the University of Cincinnati and the Missouri Institute of Science and Technology. Funding Requests for Fundamental Research are authorized by an NSF approved solicitation, NSF 10-601. The solicitation invites I/UCRCs to submit proposals for support of industry-defined fundamental research.

Prognosis of industrial systems and the management of their health based on system data typically requires significant analysis and design prior to implementation of an effective detection and management system. The proposed work seeks to accelerate the process of collection and assessment of data in order to reduce the life cycle of Prognosis and Health Management (PHM) research. The work plans to explore a framework with unified systematic methods to ensure the precision of Remaining Useful Life (RUL) estimations that are essential for effective health management.

The proposed work promises to significantly improve methods to estimate the usable lifetime of industrial equipment, thus enabling efficient maintenance of operating production systems and reducing overall cost. 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 by virtue of the framework to be established by the work. The center will involve graduate students, teachers and undergraduates in the work emphasizing involvement of minority and female students.

Project Report

The project goal is to predict and proactively avoid faults in mechanical, industrial systems and machines. Such early warning would benefit US companies by reducing maintenance costs since repairs would be done only when needed. Moreover, it would prevent potentially catastrophic failures and allow performance optimization of the machinery. For example, when air-conditioning system becomes clogged its effectiveness reduces; it leads to higher energy bills and unnecessary carbon emissions. The project developed novel tools for rapid development of prognostics agents for industrial systems and machines. The tools are employed to develop software that monitors the particular system, detects abnormal behavior, identifies the type of faults, and predicts time-to-failure. This is a model-based approach where physical model of the system is employed to detect faulty (abnormal) operation, identify fault type and root-cause, and predict time-to-failure. Moreover, it is capable of identifying multiple simultaneous faults and does not require prior fault data. The develop prognostics methodology is able to learn new faults on-line. Moreover, the mathematical analysis demonstrates correctness of the fault estimations. The prognostics tools have been demonstrated for a set of industrial applications including heating-ventilation and air conditioning (HVAC) system, pneumatic piston pump, and robotic manipulator. The results have been validated using data from hardware testbeds. Moreover, the project provided invaluable opportunities for young engineers and future US workers and inventors to engage in the cutting-edge research. The team included two female graduate students with one graduating during the course of the project. We have successfully worked with National Instruments company to create LabView based tools that can be rapidly deployed on embedded devices such as CompactRIO monitoring and control platform. Future plans are to commercialize the tools and strengthen competitiveness of US companies through added intelligent maintenance capabilities both in manufacturing processes and as a feature of final products.

National Science Foundation (NSF)
Division of Industrial Innovation and Partnerships (IIP)
Standard Grant (Standard)
Application #
Program Officer
Lawrence A. Hornak
Project Start
Project End
Budget Start
Budget End
Support Year
Fiscal Year
Total Cost
Indirect Cost
Missouri University of Science and Technology
United States
Zip Code