Aristotle University Of Thessaloniki (AUTH)
Ευφυές σύστημα για τη διάγνωση βλαβών στα μηχανικά υποσυστήματα του γεωργικού ελκυστήρα
Abstract
dc:descriptionThe 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 accelerometers that were placed at selected positions of the gearbox. The results of the system evaluation were considered highly satisfactory and confirmed in an absolute way the objectives of this Thesis.
Degree
thesis:*- Grantor dc:publisher
- Aristotle University Of Thessaloniki (AUTH)
- Year dc:date
- 2015
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Kateris, Dimitrios
- Κατέρης, Δημήτριος
Subjects
dc:subject × 12Rights
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/36075