Intelligent system for fault diagnosis in agricultural tractor mechanical subsystems

Abstract

The aim of this Thesis is the development of a prototype intelligent fault - failure diagnosis system (design and implementation). Both the development and confirmation were performed in an agricultural tractor mechanical gearbox. The system was based on this particular idea: When fault occurs at a single bearing of a gearbox, this leads to the replacement of all of its bearings even though they are still operational. This way the repair costs raise to an unreasonably high level. This intelligent system was developed to diagnose quickly and with a great accuracy faults and failures at any of the agricultural tractor mechanical subsystem. It is also able to diagnose at which bearing exactly the fault occurs, so that the repair of it is selective and the maintenance costs reduced. The system is based on the performance of either one or two Bayesian Multilayer Perceptron Neural Network with Automatic Relevance Determination, MLP-ARD, which combine data from monoaxial and triaxial accelero ...
show more

All items in National Archive of Phd theses are protected by copyright.

DOI
10.12681/eadd/36075
Handle URL
http://hdl.handle.net/10442/hedi/36075
ND
36075
Alternative title
Ευφυές σύστημα για τη διάγνωση βλαβών στα μηχανικά υποσυστήματα του γεωργικού ελκυστήρα
Author
Kateris, Dimitrios (Father's name: Lambros)
Date
2015
Degree Grantor
Aristotle University Of Thessaloniki (AUTH)
Committee members
Μόσχου Δημήτριος
Τσατσαρέλης Κωνσταντίνος
Βουγιούκας Σταύρος
Τσιάφης Ιωάννης
Μπότσαρης Παντελής
Γράβαλος Ιωάννης
Κωτσόπουλος Θωμάς
Discipline
Agricultural and Veterinary SciencesOther Agricultural Sciences
Keywords
Neural networks; Fault diagnosis; Βearings; condition monitoring
Country
Greece
Language
Greek
Description
357 σ., im., tbls., fig., ch., ind.
Usage statistics
VIEWS
Concern the unique Ph.D. Thesis' views for the period 07/2018 - 07/2023.
Source: Google Analytics.
ONLINE READER
Concern the online reader's opening for the period 07/2018 - 07/2023.
Source: Google Analytics.
DOWNLOADS
Concern all downloads of this Ph.D. Thesis' digital file.
Source: National Archive of Ph.D. Theses.
USERS
Concern all registered users of National Archive of Ph.D. Theses who have interacted with this Ph.D. Thesis. Mostly, it concerns downloads.
Source: National Archive of Ph.D. Theses.
Related items (based on users' visits)