Romano Patrick – ICSL

RomanoPatrick.JPG Office:
Room 227,
Intelligent Systems Control laboratory (ICSL)
Manufacturing Research Center (MaRC)
Georgia Institute of Technology
813 Ferst Drive, N.W.
Atlanta, Georgia 30332-0560 U.S.A.

Telephone: +1(404) 894-4130
Fax: +1(404) 894-3971
email: romano.patrick@gatech.edu

About

Romano Patrick is a PhD student in the School of Electrical and Computer Engineering at Georgia Tech performing research to develop model-based techniques for diagnosing and prognosticating dynamical engineering systems. His work is being performed under advisement from Dr. George Vachtsevanos (School of Electrical and Computer Engineering) and Dr. Aldo Ferri (School of Mechanical Engineering).

Romano previously earned degrees from the Georgia Institute of Technology (MBA), The University of Texas at Arlington (Master of Science in Electrical Engineering) and Universidad Panamericana, Guadalajara campus (Bachelor of Science in Electromechanical Engineering).

His work experience includes several teaching positions ranging from technical institutes to graduate-level college courses, work for several years as a research and development engineer for a company developing novel electronic security systems, two years performing applied research and development for local industry at the Automation and Robotics Research Institute in Fort Worth, Texas, and, as of today, nearly three years as a Graduate Research Assistant at Georgia Tech providing support for machine diagnosis prognosis projects.

Romano is married to a beautiful Mexican lady (seen in the picture) and they currently live in Atlanta, Georgia.

Research

Romano Patrick’s research addresses the development of Model-based Diagnosis and Prognosis techniques for engineering systems. The objective of this work is to develop a framework for integrating models, simulation and experimental data in order to diagnose incipient failure modes and prognosticate the remaining useful life of critical machine components. His research is currently being applied to the main rotor transmission of a helicopter, and although the helicopter example is used to illustrate the methodology, it is expected that, by appropriately adapting modules, such architecture can be applied to a variety of similar engineering systems.

In recent years a paradigm shift has been introduced in the way critical systems are maintained and operated in order to ensure their safety, availability and reliability. Focus is on technologies to monitor, process on-line real-time data, and detect and predict the remaining useful life of failing components or subsystems. The military and industrial sectors are recognizing the importance of such Condition-Based Maintenance (CBM) or Prognostic and Health Management (PHM) technologies, and they are actively pursuing their development and implementation. This proposed research addresses a significant component of CBM or PHM.

The methodology proposed by Romano Patrick’s research is tested and validated initially through simulation, but also through comparison to data obtained from actual helicopters in operation and ground truth data from a test cell employing a prototypical helicopter gearbox. The experimental testing on the helicopter provides vibration data collected through a number of accelerometers mounted on the frame of the transmission gearbox, while one of the test cell experiments is also able to provide damage progression measures. The proposed architecture consists of several modules with the following key elements:

  • Vibration signature analysis and extraction of descriptive vibratory features.
  • Vibration signature characterization and modeling that incorporates system-specific parameters and effects (e.g. noise), and determination of vibration changes induced by a fault.
  • Finite Element Analysis of a gearbox component (utilizing ANSYS software package) under varying operating conditions to determine the effect of different extents of damage.
  • Use of an empirical model and considerations for characterizing fracture progression, including adaptations of the famous Paris’ law of crack growth and load cycle shape considerations.

The integrated model-based diagnostic and prognostic architecture is evaluated by defining appropriate performance metrics, and comparison with other means of performing diagnostics and prognostics, as opposed to the model-based method, is also conducted to demonstrate the effectiveness of the approach. Expected contributions of this work include:

  • A model-based fault diagnosis and failure prognosis methodology for a dynamic large-scale mechanical system.
  • A “reverse engineering” approach for generating vibration data through a modeling framework as well as fault features or condition indicators.
  • Utilization of the vibration model of a faulted planetary gear transmission to classify descriptive system parameters into fault-sensitive and fault-insensitive parameters.
  • Guidelines for integration of the model-based architecture into prognostic algorithms aimed at determining the remaining useful life of failing components.
  • Characterization of vibration signals for a class of complex rotary systems through model-based techniques to arrive at descriptive fault features or condition indicators and for a better understanding of certain physics of failure mechanisms.

A brief description of the main thrust of Romano Patrick’s Ph.D. research can be found in the section of this site covering Model-based Diagnosis and Prognosis.

Publications

Journal Articles
  • B. Wu, A. Saxena, R. Patrick, and G. Vachtsevanos, “Vibration Monitoring for Fault Diagnosis of Helicopter Planetary Gears” submitted to IEEE transactions on Automation Science and Engineering
Conference Papers

-Romano Patrick. October 20, 2006