Impacts of Technology Advancements on CBM+

Abstract

Condition based maintenance (CBM) is a maintenance philosophy that offers opportunity to improve the reliability and availability of high value assets, while also having potential to reduce the labor and cost of maintenance. A key enabler of CBM is Health and Usage Monitoring Systems (HUMS), which actively collect and analyze asset data during operation to facilitate CBM. Adoption of HUMS for commercial and Department of Defense (DoD) vehicles, particularly ground vehicles, has been slow. Additionally, the rapidly changing technology landscape provides a moving target for CBM implementation. For this project, Rochester Institute of Technology (RIT) will evaluate rapidly emerging technologies, including deep learning and additive manufacturing for repair, and will research how these technologies impact CBM and HUMS deployment. Further, the project will also look at the potential impact of evolving hardware, communications, and algorithm technologies on design and implementation approaches for HUMS. The proposed research is broken into three thrusts: 1) Gear Health Management, 2) Vehicle CBM, and 3) Additive Manufacturing (AM) repair. The Gear Health Management thrust will leverage deep learning technologies and fusion of vibration and oil analysis data to provide improved anomaly detection and prognostics capability. The project will evaluate recent advances in deep learning and leverage state-of-the-art development frameworks as a means to improve anomaly detection. Additionally, RIT will investigate probabilistic methods to fuse vibration and fluid monitoring features to enhance the anomaly detection and prognostic capability. A demonstration of the advanced prognostic techniques, utilizing vibration and fluid monitoring data, applied to a planetary gear set is anticipated. This improved anomaly detection will be beneficial to increase the failure detection horizon and accuracy, reducing operations and maintenance risks. Vehicle CBM and HUMS implementation is limited by uncertainty in technology stability and performance, as well as return on investment. This thrust will develop a technology assessment framework that evaluates the impact of anticipated technology advances on HUMS system design and performance. The framework will include the ability to assess changes in algorithm, computer, and communications technologies against the selected system design approach. RIT will then integrate selected technology solutions to evaluate framework performance. The resulting framework will provide a method for evaluating HUMS system design attributes with respect to performance and return on investment over the long term. The final research thrust will reduce the barriers to AM based repair. Currently, AM repair is often limited by lack of knowledge of material properties or final component requirements. This project will develop a framework to facilitate AM decision making through targeted collection of design intent and informed by CBM/HUMS data for the component to be repaired. A repository of AM repair property data will also be developed to support the framework. The resulting framework will enable decisions for cost effective depot repair of additional components through AM processes. Together, these research thrusts will inform interactions that affect deployment of Condition Based Maintenance capabilities for vehicles, from the standpoint of HUMS system design, through advanced data analysis and prognostics, and including additive repair based maintenance

Document Details

Document Type
DoD Grant Award
Publication Date
Jul 10, 2018
Source ID
N000141812339

Entities

People

  • Michael Thurston

Organizations

  • Office of Naval Research
  • Rochester Institute of Technology
  • United States Navy

Tags

Readers

  • Defense Technology Research and Development.
  • Fault Tolerant Diagnosis of Black and White Balloon Isolation Tests Using ¥.
  • Life Cycle Cost Analysis

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy