Prognostics and Health Management

Prognostics and Health Management

Traditional reliability analysis considers population characteristics in reliability analysis by modeling a life distribution of historical units. This traditional approach only provides an overall reliability estimate that takes the same value for the entire population. In engineering practice, we are often more interested in investigating the reliability information of a specific unit under its actual use condition in order to determine the advent of a failure and prevent the failure from occurring. Recently, prognostics and health management (PHM) has emerged as a key technology to overcome the limitations of traditional reliability analysis. PHM focuses on utilizing sensory signals acquired from an engineered system to monitor the health condition and predict the remaining useful life of the system over its life-time. This health information provides an advance warning of potential failures and a window of opportunity for implementing measures to avert these failures. In this research area, I developed new techniques and approaches that enable optimal design of sensor networks for fault detection, effective extraction of health-relevant information from sensory signals, and robust prediction of remaining useful life.

Publications


Health Sensing

  1. Wang P., Youn B.D., Hu C., Ha J.M., and Jeon B., “A Probabilistic Detectability-Based Sensor Network Design Method for System Health Monitoring and Prognostics,” Journal of Intelligent Material Systems and Structures, DOI: 10.1177/1045389X14541496, 2014. [ DOI ]
  2. Wang P., Youn B.D., and Hu C., “A Generic Sensor Network Design Framework Based on a Detectability Measure,” ASME International Design Engineering Technical Conferences & Computers and Information in Engineering Conference (IDETC/CIE), Aug 15-18 2010, Montreal, Quebec, Canada.
  3. Wang P., Youn B.D., and Hu C., “A Probabilistic Detectability-Based Structural Sensor Network Design Methodology for Prognostics and Health Management,” Annual Conference of the Prognostics and Health Management (PHM) Society 2010, Oct 10-16 2010, Portland, OR.

Health Reasoning

  1. Youn B.D., Park K.M., Hu C.,Yoon, J.T., and Bae Y.C., “Statistical Health Reasoning of Power Generator Stator Windings against Moisture Absorption,” Submitted, IEEE Transactions on Power Systems.
  2. Tamilselvan P., Wang P., and Hu C., “Health Diagnostics Using Multi-Attribute Classification Fusion,” Engineering Applications of Artificial Intelligence, v32, p192–202, 2014. [ DOI ]
  3. Hu C.,Wang P., Youn B.D., and Lee W.R., “Copula-Based Statistical Health Grade System against Mechanical Faults of Power Transformers,” IEEE Transactions on Power Delivery, v27, n4, p1809–1819, 2012. [ DOI ]
  4. Youn B.D., Park K.M., Hu C.,Yoon, J.T., and Bae Y.C., “Health Diagnostics of Water-Cooled Power Generator Stator Windings Using a Directional Mahalanobis Distance (DMD),” 2013 IEEE International Conference on Prognostics and Health Management (PHM), Jun 24-27, 2013, Gaithersburg, MD. (Chair of Medical Equipment PHM Session)
  5. Tamilselvan P., Wang P., and Hu C., “Design of a Robust Classification Fusion Platform for Structural Health Diagnostics,” ASME International Design Engineering Technical Conferences & Computers and Information in Engineering Conference (IDETC/CIE), Aug 4-7, 2013, Portland, OR.
  6. Hu C.,Youn B.D., and Kim T.J., “Statistical Health Grade System against Mechanical Failures of Power Transformers,” AnnualConference of the Prognostics and Health Management (PHM) Society 2012, Sep 23-27 2012, Minneapolis, MN. (Conducted presentation)

Health Prognostics

  1. Hu C., and Youn B.D., Kim T.J., “Semi-Supervised Learning with Co-Training for Data-Driven Prognostics,” Submitted,  Mechanical Systems and Signal Processing, 2014.
  2. Xi Z., Wang P., Rong Jing, and Hu C.,“A Copula-Based Sampling Method for Data-Driven Prognostics,” Reliability Engineering and System Safety, DOI: 10.1016/j.ress.2014.06.014, 2014. [ DOI ]
  3. Hu C.,Youn B.D., and Wang P., “Ensemble of Data-Driven Prognostic Algorithms for Robust Prediction of Remaining Useful Life,” Reliability Engineering and System Safety,v103, p120–135, 2012. [ DOI ]
  4. Wang P., Youn B.D., and Hu C.,“A Generic Probabilistic Framework for Structural Health Prognostic and Uncertainty Management,” Mechanical Systems and Signal Processing, v28, p622–637, 2012. [ DOI ]
  5. Xi Z., Jing R., Wang P., and Hu C., “A Copula-based Sampling Method for Data-driven Prognostics and Health Management,” ASME International Design Engineering Technical Conferences & Computers and Information in Engineering Conference (IDETC/CIE), Aug 4-7, 2013, Portland, OR. (ASME Design Automation Conference (DAC) Best Paper Award, 2013)
  6. Hu C.,Youn B.D., and Kim T.J., “Semi-Supervised Learning with Co-Training for Data-Driven Prognostics,” 2012 IEEE International Conference on Prognostics and Health Management (PHM), Jun 18-21 2012, Denver, CO. (IEEE PHM 2012 Best Paper Award; Invited as Panelist of PHM Design Techniques & Algorithms Panel)
  7. Hu C.,Youn B.D., Wang P., and Yoon, J.T., “An Ensemble Approach for Robust Data-Driven Prognostics,” ASME International Design Engineering Technical Conferences & Computers and Information in Engineering Conference (IDETC/CIE), Aug 12-15 2012, Chicago, DC. (Top Ten Best Papers and PHM Session Best Paper)
  8. Hu C.,Youn B.D., and Kim T.J., “Semi-Supervised Learning with Co-Training for Data-Driven Prognostics,” ASME International Design Engineering Technical Conferences & Computers and Information in Engineering Conference (IDETC/CIE), Aug 28-31 2011, Washington, DC. (Conducted presentation)
  9. Hu C.,Youn B.D., and Wang P., “Ensemble of Data-Driven Prognostic Algorithms with Weight Optimization and K-Fold Cross Validation,” ASME International Design Engineering Technical Conferences & Computers and Information in Engineering Conference (IDETC/CIE), Aug 15-18 2010, Montreal, Quebec, Canada. (Conducted presentation)
  10. Hu C.,Youn B.D., and Wang P., “Ensemble of Data-Driven Prognostic Algorithms with Weight Optimization and K-Fold Cross Validation,” Annual Conference of the Prognostics and Health Management (PHM) Society 2010, Oct 10-16 2010, Portland, OR. (PHM Best Paper Nomination, 2010)