Loading...

Fuzzy ANN Approach to Support Independent Failures of Rotary Equipment Based on Vibration, Temperature Parameters-Case Study: A Centrifugal Pump in offshore Industry

Fouladi Vanda, Mohammad | 2013

607 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: English
  3. Document No: 44134 (58)
  4. University: Sharif University of Technology, International Campus, Kish Island
  5. Department: Science and Engineering
  6. Advisor(s): Ghaemi Osgouie, Kambiz; Ebrahimi Pour, Vahid
  7. Abstract:
  8. Pump operating problems may be either hydraulic or mechanical and there is interdependence between the failure diagnoses of these two categories. Consequently, a correct diagnosis of a pump failure needs to consider many symptoms including hydraulic or mechanical causes. Nonlinear, time-varying behavior, and imprecise measurement information of the systems makes it difficult to deal with pump failures with precise mathematical equations, while human operators with the aid of their practical experience can handle these complex situations, with only a set of imprecise linguistic if-then rules and imprecise system states, but this procedure is time consuming and needs the knowledge of human experts and experienced maintenance personnel. The purpose of this study is to provide a correct and timely diagnosis mechanism of pump failures by knowledge acquisition through a fuzzy rule-based neural network which could approximate human reasoning. The proposed system by: (1) reduction of human error, (2) reduction of repair time (3) creation of expert knowledge which could be used for training (4) reduction of unnecessary expenditures for upgrades and finally, (5) reduction of maintenance costs, will improve the maintenance process. The novelty of this work is the knowledge acquisition (the extraction of linguistic rules) through the interactive impact of the critical failure modes on the both hydraulic and mechanical operating parameters including flow rate, discharge pressure, efficiency, vibration , liquid and bearing temperature. The proposed approach is tested and applied to a centrifugal pump at an offshore oil industry
  9. Keywords:
  10. Neural Networks ; Centrifugal Pumps ; Diagnosis ; Failure Modes ; Fuzzy Rule-Base

 Digital Object List

 Bookmark

No TOC