Loading...

Fault Diagnosis of Crack Growth in Power Transmission Systems, using Neural Network

Delavari, Mohammad Mohsen | 2016

1043 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: English
  3. Document No: 48666 (58)
  4. University: Sharif University of Technology, International Campus, Kish Island
  5. Department: Science and Engineering
  6. Advisor(s): Selk Ghafari, Ali; Khayyat, Amir Ali Akbar
  7. Abstract:
  8. Nowadays, industrial companies deal with a wide range of serious problems in the field of power transmission maintenance and also fault detection. A large amount of money and time is spent on these issues in order to solve them; consequently, there is an essential need for this subject. In this thesis, in order to tackle those major issues which were referred above, an artificial neural network is trained with only one hidden layer. Also, a suitable database for training an efficient neural network is needed. Thus, a one-stage gearbox system with appropriate degrees of freedom is used to set up referred database. In this system, a crack is imposed to a tooth of spur gear with different sizes in three individual cases. Moreover, an appropriate dynamic model of the system under investigation is derived using bond graph approach. The dynamic model is simulated in order to gain the displacement of pinion in a specific direction, which shows the effect of imposed crack on the system under investigation. Next, the database is developed based on the parameters which affect fault characteristics. In pervious works, the neural network was sensitive just for two or three basic parameters, but in this thesis seven essential and fundamental parameters that have effect on the crack growth and also system dynamic response, are taken into consideration. As a result, the neural network is trained with acceptable performance and after that it is tested by two different crack sizes and the results are good with negligible error
  9. Keywords:
  10. Fault Detection ; Gearbox ; Bond Graph ; Dynamics Models ; Crack ; Neural Network ; Power Transmission System

 Digital Object List

 Bookmark

...see more