Follow us: Facebook LinkedIn Twitter Google + Weibo Join SMC

Diagnostics and Prognostics

TC Leadership

Imad H. Makki

TC Co-Chair

Imad H. Makki (This email address is being protected from spambots. You need JavaScript enabled to view it.)
Ford Motor Company



Karolos Grigoriadis

TC Co-Chair

Karolos Grigoriadis (This email address is being protected from spambots. You need JavaScript enabled to view it.)
University of Houston, TX, USA

Matthew Franchek

TC Co-Chair

Matthew Franchek (This email address is being protected from spambots. You need JavaScript enabled to view it.)
University of Houston, TX, USA




Our Goal

There is an increasing demand for complex systems to become safer and more reliable. This requirement extends beyond the normally accepted safety-critical systems, such as, nuclear reactors, power plants aircraft where safety is of paramount importance, to more common everyday systems, such as, vehicle fuelling and exhaust systems and medical devices where the system reliability and performance is vital. Diagnostics and Prognostics (D&P) methods are used to provide such systems with intelligent and reliable capabilities to assess the presence, location and severity of a fault (of faults), as well as, the ability of the system to retain robust and reliable functionality in the presence of the fault.

Information synthesis (IS) is an approach to diagnosing and prognosticating physical systems. It is an on-line adaptive model based parameter estimation technique where the model structure and the parameters of the model are determined using system identification techniques. IS can be used for fault detection, isolation and identification, and the solution is attractive for diagnostics and prognostics since the algorithm performs automatic calibrations, and compresses a large amount of system health information into the IS model coefficients. Using an on-line adaptive model based technique, IS can be efficiently used to determine the health of the system under operation. In the presence of a fault, the input-output relationship of the system differs from that of the healthy system, and adapting the model structure of the healthy system to the faulty system can capture this difference.

In addition, IS could be based on more intelligent control methods which include pattern recognition, real time data classification & clustering (ideal for diagnostics applications), Neural Networks (NN) and Support Vector Machine (SVM), Fuzzy Systems (FS), and machine learning algorithms. Humans are good at generalizing from experience. Computers excel at following explicit instructions over and over. SVM, FS, & NN can bridge this gap by modeling and summarizing the data, identifying and predicting abnormal behaviors, and providing health (diagnostics) information which lead to improved robustness and fault tolerance due to network redundancy and adaptation to unknown situations.

The main advantage of this model-based approach is the ability to incorporate physical understanding of the system for system monitoring. One important benefit of the information synthesis solution is that it can account for the aging of a system and system to system variation due to its online adaptive feature. Furthermore, the possibility of false detections is reduced and fault identification is possible due to the system health information contained in the model coefficients, resulting in a more robust, reliable, and a cost effective system.

The goal of this technical committee is to provide a forum to exchange ideas and solutions among researchers, professional engineers, and faculty working in the area of diagnostics and prognostics. This is achieved by organizing SMC co-sponsored conferences, workshops, and publications. Additionally, we aim to create a venue where academia and industry individuals can virtually meet to discuss real-life and challenging problems and provide suitable solutions which impact the quality, life, performance, and cost of the applications and product.

Recent Activities

  • Promoting innovative research and active academic-industry collaboration in the area of Diagnostics and Prognostics.
  • Establishing a special interest group in Diagnostics and Prognostics and related fields.
  • Encouraging IEEE members to collaborate in research in the area of Diagnostics and Prognostics and other relevant fields.
  • Organizing special sessions in IEEE/SMC conferences.
  • Co-organizing SMC Technically-sponsored conferences.

Join Us

  • Interact with scientists, academics, and engineers who are actively working in the area of Diagnostics and Prognostics and its applications to many aspects of our lives, i.e., nuclear reactors, avionics, automotive, and medical devices.
  • Participate in interesting conferences and workshops to exchange research ideas and results with scientists, academics, and engineers.
  • Promote IS and Diagnostics and Prognostics and their various applications.
  • Interact, collaborate and meet with colleagues from different regions of the world.

Members

  • Dimitar Filev, Ford Research & Advanced Engineering
  • Giscard Kfoury, Lawrence Technological University
  • Hassene Jammoussi, Ford Research & Advanced Engineering
  • James Kerns, Lawrence Technological University
  • Kimball Williams, IEEE SEM
  • Mahmoud Abou-Nasr, Ford Research & Advanced Engineering
  • Mohamad Berri, Ford CAE & Software Engineering
  • Pankaj Kumar, Ford Research & Advanced Engineering
  • Ryan Baker, Ford Research & Advanced Engineering
  • Timothy Feldkamp, Ford Research & Advanced Engineering
  • Ratna Babu Chuinnam, Wayne State University
  • Philip Chen, University of Makao
  • Janos Grantner, Western Michigan University
  • Plamen Angelov, Lancaster University
  • Ferat Sahin, Rochester University of Technology
  • Hao Ying, Wayne State University

 


Back to top