{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T23:02:22Z","timestamp":1778886142437,"version":"3.51.4"},"reference-count":33,"publisher":"ASME International","issue":"3","funder":[{"DOI":"10.13039\/100004704","name":"BMW of North America","doi-asserted-by":"publisher","award":["2010394"],"award-info":[{"award-number":["2010394"]}],"id":[{"id":"10.13039\/100004704","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,9,1]]},"abstract":"<jats:p>This paper presents the use of subassembly models instead of the entire assembly model to predict assembly quality defects at an automotive original equipment manufacturer (OEM). Specifically, artificial neural networks (ANNs) were used to predict assembly time and market value from assembly models. These models were converted into bipartite graphs from which 29 graph complexity metrics were extracted to train 18,900 ANN prediction models. The size of the training set, order of the bipartite graph, selection of training set, and defect type were experimentally studied. With a training size of 28 parts, an interpolation focused training set selection with a second-order graph seeding ensured that 70% of all predictions were within 100% of the target value. The study shows that with an increase in training size and careful selection of training sets, assembly defects can be predicted reliably from subassemblies' complexity data.<\/jats:p>","DOI":"10.1115\/1.4037179","type":"journal-article","created":{"date-parts":[[2017,7,3]],"date-time":"2017-07-03T16:34:53Z","timestamp":1499099693000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":12,"title":["Evaluating the Use of Artificial Neural Networks and Graph Complexity to Predict Automotive Assembly Quality Defects"],"prefix":"10.1115","volume":"17","author":[{"given":"Apurva","family":"Patel","sequence":"first","affiliation":[{"name":"Mechanical Engineering, Clemson University, Clemson, SC 29634-0921 e-mail:"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"Andrews","sequence":"additional","affiliation":[{"name":"Mechanical Engineering, Clemson University, Clemson, SC 29634-0921 e-mail:"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joshua D.","family":"Summers","sequence":"additional","affiliation":[{"name":"Professor Mechanical Engineering, Clemson University, Clemson, SC 29634-0921 e-mail:"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erin","family":"Harrison","sequence":"additional","affiliation":[{"name":"Assembly Planning, BMW Manufacturing Co., LLC, Greer, SC 29651 e-mail:"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joerg","family":"Schulte","sequence":"additional","affiliation":[{"name":"Liaison Office, BMW Manufacturing Co., LLC, Greer, SC 29651 e-mail:"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M.","family":"Laine Mears","sequence":"additional","affiliation":[{"name":"Professor Automotive Engineering, Clemson University, Clemson, SC 29634 e-mail:"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"33","published-online":{"date-parts":[[2017,7,26]]},"reference":[{"key":"2019100315501306000_bib1","volume-title":"Engineering Design: A Systematic Approach","year":"2007"},{"key":"2019100315501306000_bib2","volume-title":"The Mechanical Design Process","year":"2010"},{"key":"2019100315501306000_bib3","volume-title":"Theory of Technical Systems","year":"1988"},{"issue":"3","key":"2019100315501306000_bib4","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1115\/1.2829466","article-title":"An Axiomatic Framework for Engineering Design","volume":"121","year":"1999","journal-title":"ASME J. Mech. Des."},{"issue":"3","key":"2019100315501306000_bib5","first-page":"63","article-title":"The House of Quality","volume":"66","year":"1988","journal-title":"Harv. Bus. Rev."},{"key":"2019100315501306000_bib6","volume-title":"Engineering Design","year":"2013"},{"key":"2019100315501306000_bib7","volume-title":"The Engineering Design of Systems","year":"2009"},{"key":"2019100315501306000_bib8","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2014-34186","article-title":"A Case Study of Configuration Management Methods in a Major Automotive OEM","volume-title":"ASME","year":"2014"},{"key":"2019100315501306000_bib9","article-title":"Engineering Change Management\u2014Verification, Validation and Testing Planning Tool Development","year":"2014"},{"issue":"1","key":"2019100315501306000_bib10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00163-003-0031-7","article-title":"Change and Customisation in Complex Engineering Domains","volume":"15","year":"2004","journal-title":"Res. Eng. Des."},{"issue":"5","key":"2019100315501306000_bib11","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1115\/1.1765117","article-title":"Predicting Change Propagation in Complex Design","volume":"126","year":"2004","journal-title":"ASME J. Mech. Des."},{"key":"2019100315501306000_bib12","article-title":"Review of the Design Tools and Methods to Predict Change Propagation Pathways","year":"2012"},{"issue":"4","key":"2019100315501306000_bib13","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1007\/s00163-012-0132-2","article-title":"Reasons for Change Propagation: A Case Study in an Automotive OEM","volume":"23","year":"2012","journal-title":"Res. Eng. Des."},{"issue":"2","key":"2019100315501306000_bib14","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/s00163-010-0097-y","article-title":"Engineering Change: An Overview and Perspective on the Literature","volume":"22","year":"2010","journal-title":"Res. Eng. Des."},{"key":"2019100315501306000_bib15","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/ICMA.2010.21","article-title":"Assembly Time Modeling Through Connective Complexity Metrics","volume-title":"ICMA","year":"2010"},{"key":"2019100315501306000_bib16","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2011-47481","article-title":"Complexity as a Surrogate Mapping Between Function Models and Market Value","volume-title":"ASME","year":"2011"},{"key":"2019100315501306000_bib17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-44989-0_36","article-title":"Using Graph Complexity Connectivity Method to Predict Information From Design Representations\u2014A Comparative Study","volume-title":"Design Computing and Cognition\u201916","year":"2016"},{"key":"2019100315501306000_bib18","first-page":"1095","article-title":"Precision Analysis of the Graph Complexity Connectivity Method: Assembly and Function Model","year":"2016"},{"issue":"2","key":"2019100315501306000_bib19","doi-asserted-by":"publisher","first-page":"21003","DOI":"10.1115\/1.4026293","article-title":"Comparison of Graph Generation Methods for Structural Complexity Based Assembly Time Estimation","volume":"14","year":"2014","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"key":"2019100315501306000_bib20","doi-asserted-by":"crossref","first-page":"777","DOI":"10.1007\/978-3-642-30817-8_76","article-title":"Complexity Connectivity Metrics\u2014Predicting Assembly Times With Low Fidelity Assembly CAD Models","volume-title":"Smart Product Engineering","year":"2013"},{"key":"2019100315501306000_bib21","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2012-70995","article-title":"Representation: Extracting Mate Complexity From Assembly Models to Automatically Predict Assembly Times","volume-title":"ASME","year":"2012"},{"issue":"5","key":"2019100315501306000_bib22","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1016\/S0731-7085(99)00272-1","article-title":"Basic Concepts of Artificial Neural Network (ANN) Modeling and Its Application in Pharmaceutical Research","volume":"22","year":"2000","journal-title":"J. Pharm. Biomed. Anal."},{"key":"2019100315501306000_bib23","article-title":"Comparative Study of Representation Structures for Modeling Function and Behavior of Mechanical Devices","volume-title":"ASME","year":"2001"},{"key":"2019100315501306000_bib24","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2010-28561","article-title":"Complexity Metrics for Directional Node-Link System Representations: Theory and Applications","volume-title":"ASME","year":"2010"},{"key":"2019100315501306000_bib25","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2011-47530","article-title":"Evaluation and Comparison of Two Design for Assembly Methods: Subjectivity of Information","volume-title":"ASME","year":"2011"},{"key":"2019100315501306000_bib26","first-page":"96","article-title":"Adaptive Switching Circuits","volume-title":"Int. J. Commun. Network. Syst. Sci.","year":"1960"},{"key":"2019100315501306000_bib27","first-page":"318","article-title":"Learning Internal Representations by Error Propagation","volume-title":"Parallel Distributed Processing: Explorations in the Microstructure of Cognition","year":"2013"},{"issue":"1","key":"2019100315501306000_bib28","doi-asserted-by":"publisher","first-page":"11005","DOI":"10.1115\/1.4025809","article-title":"Manufacturing Assembly Time Estimation Using Structural Complexity Metric Trained Artificial Neural Networks","volume":"14","year":"2014","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"key":"2019100315501306000_bib29","doi-asserted-by":"crossref","first-page":"777","DOI":"10.1007\/978-3-642-30817-8_76","article-title":"Complexity Connectivity Metrics-Predicting Assembly Times With Abstract Assembly Models","volume-title":"Smart Product Engineering","year":"2013"},{"issue":"1","key":"2019100315501306000_bib30","doi-asserted-by":"publisher","first-page":"11004","DOI":"10.1115\/1.4025808","article-title":"Assembly Time Estimation: Assembly Mate Based Structural Complexity Metric Predictive Modeling","volume":"14","year":"2014","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"key":"2019100315501306000_bib31","doi-asserted-by":"publisher","DOI":"10.1080\/0951192X.2012.684706","article-title":"Assembly Time Modelling Through Connective Complexity Metrics","volume":"26","year":"2013","journal-title":"Int. J. Comput. Integr. Manuf."},{"key":"2019100315501306000_bib32","first-page":"1","article-title":"Higher Order Interactions: Product and Configuration Study on DSM Saturation","volume-title":"ICED","year":"2015"},{"key":"2019100315501306000_bib33","first-page":"1137","article-title":"A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection","volume-title":"IJCAI","year":"1995"}],"container-title":["Journal of Computing and Information Science in Engineering"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/doi\/10.1115\/1.4037179\/6102691\/jcise_017_03_031017.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/doi\/10.1115\/1.4037179\/6102691\/jcise_017_03_031017.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,3]],"date-time":"2019-10-03T19:50:18Z","timestamp":1570132218000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article\/doi\/10.1115\/1.4037179\/371033\/Evaluating-the-Use-of-Artificial-Neural-Networks"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7,26]]},"references-count":33,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2017,9,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4037179","relation":{},"ISSN":["1530-9827","1944-7078"],"issn-type":[{"value":"1530-9827","type":"print"},{"value":"1944-7078","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,7,26]]},"article-number":"031017"}}