BROWSE

Special Graduate Schools Graduate School of Science and Technology Department of Industrial Engineering 3. Theses(Master)

Neural Network-based Prediction of Aluminum Extrusion Process Parameters

DC Field Value Language
dc.contributor.advisorWang, Gi Nam-
dc.contributor.authorBajimaya, Sachin Man-
dc.date.accessioned2018-11-08T07:16:52Z-
dc.date.available2018-11-08T07:16:52Z-
dc.date.issued2008-02-
dc.identifier.other6920-
dc.identifier.urihttps://dspace.ajou.ac.kr/handle/2018.oak/5445-
dc.description학위논문(석사)----아주대학교 일반대학원 :산업공학과,2008. 2-
dc.description.tableofcontents1 Introduction = 1 2 Background = 3 3 Indirect Extrusion Process = 4 3.1 Definition = 4 3.2 Interdependence Between Extrusion Variables = 6 4 Neural Network = 8 4.1 Definition = 8 4.2 Network architecture = 10 4.2.1 Number of layers and neurons in each layer = 11 4.2.2 Connections between neurons and their strengths = 13 4.2.3 Transfer function = 15 4.3 Operation of the back-propagation network = 17 4.4 Limitations of Neural Networks = 19 5 Methodology and Implementation = 20 5.1 Development of Neural Network Model = 21 5.1.1 Model Architecture = 21 5.1.2 Data Division and Preprocessing = 22 5.1.3 Training = 25 6 Results and Discussion = 27 7 Conclusion = 30 References = 31-
dc.language.isoeng-
dc.publisherThe Graduate School, Ajou University-
dc.rights아주대학교 논문은 저작권에 의해 보호받습니다.-
dc.titleNeural Network-based Prediction of Aluminum Extrusion Process Parameters-
dc.title.alternativeSachin Man Bajimaya-
dc.typeThesis-
dc.contributor.affiliation아주대학교 일반대학원-
dc.contributor.alternativeNameSachin Man Bajimaya-
dc.contributor.department일반대학원 산업공학과-
dc.date.awarded2008. 2-
dc.description.degreeMaster-
dc.identifier.localId566397-
dc.identifier.urlhttp://dcoll.ajou.ac.kr:9080/dcollection/jsp/common/DcLoOrgPer.jsp?sItemId=000000006920-
dc.subject.keywordNeural-
dc.subject.keywordNetwork-based-
dc.subject.keywordAluminum-
dc.subject.keywordExtrusion-
dc.subject.keywordParameters-
dc.description.alternativeAbstractThe objective of this research is to estimate realistic principal extrusion process parameters by means of artificial neural network. Conventionally, finite element analysis is used to derive extrusion process parameters. However, the finite element analysis of the extrusion model does not consider the manufacturing process constraints in its modeling. Therefore, the process parameters obtained through such an analysis remains highly theoretical. Alternatively, process development in industrial extrusion is to a great extent based on trial and error and often involves full-size experiments, which are both expensive and time-consuming. The artificial neural network-based estimation of the extrusion process parameters prior to plant execution helps to make the actual extrusion operation more efficient because more realistic parameters may be obtained. And so, it bridges the gap between simulation results and the parameters required by a real manufacturing execution system. In this work, the feasibility of making use of neural networks to predict realistic principal extrusion process parameters is studied. In the course, a suitable neural network is designed which is trained using an appropriate learning algorithm. The network so trained is used to predict the extrusion process parameters and finally, the predicting performance of the network is evaluated.-
Appears in Collections:
Special Graduate Schools > Graduate School of Science and Technology > Department of Industrial Engineering > 3. Theses(Master)
Files in This Item:
There are no files associated with this item.
Show simple item record

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

  • License
    sherpa_romeo
    sherpa_juliet
STATISTICS
Total Visit :3,747,942
Total Download :1,818
Today View :25,600

AJOU

AJOU Central Library Repository는 국립중앙도서관 OAK 보급사업으로 구축되었습니다.

Browse

OAK Portal LOGIN