Reliability estimation of washing machine spider assembly via classification
- Authors
- Gorguluarslan, Recep; Kim, Eui-Soo; Choi, Seung-Kyum; Choi, Hae-Jin
- Issue Date
- Jun-2014
- Publisher
- SPRINGER LONDON LTD
- Keywords
- Probabilistic neural network; Latin hypercube sampling; Front loading washingmachine; Reliability
- Citation
- INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, v.72, no.9-12, pp 1581 - 1591
- Pages
- 11
- Journal Title
- INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
- Volume
- 72
- Number
- 9-12
- Start Page
- 1581
- End Page
- 1591
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/12171
- DOI
- 10.1007/s00170-014-5745-3
- ISSN
- 0268-3768
1433-3015
- Abstract
- This paper presents a study on the reliability estimation of the spider assembly of the front loading washing machine. To achieve the analytical certification of the current design of the spider assembly of the washing machine, fatigue life test, finite element analysis, physical experimentation, and a classification processes were conducted. First, the conventional finite element analysis and fatigue life analysis were conducted and their simulation results have been validated by physical experiments in this research. The probability of failure is estimated by a classification process. Specifically, the probabilistic neural network classifier is incorporated into the simulation process to reduce the number of finite element analysis calculations while ensuring the prediction accuracy of the failure probability. Based on the estimated failure probability and other structural analysis results, the margin of the performance of the spider assembly is fully identified.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > School of Mechanical Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/12171)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.