Bayesian Networks for Inverse Inference in Manufacturing Bayesian Networks

Avadhut Sardeshmukh, S. Reddy, BP Gautham, Amol Joshi
{"title":"Bayesian Networks for Inverse Inference in Manufacturing Bayesian Networks","authors":"Avadhut Sardeshmukh, S. Reddy, BP Gautham, Amol Joshi","doi":"10.1109/ICMLA.2017.00-91","DOIUrl":null,"url":null,"abstract":"Physics based simulations of manufacturing processes are used for prediction of material properties and defects in a number of industrial applications. However, a practising engineer often requires the solution to an \"inverse problem\" - prediction of inputs for the desired outcome. The inverse problem is usually solved by constrained optimisation. Extensive simulation during optimisation is avoided through response surfaces constructed from simulations. But the design space is often so large that even with response surfaces, optimisation might not be possible. Moreover, these problems are typically ill-posed, so discriminative models such as artificial neural networks do not work well. In this paper, we investigate the application of conditional linear Gaussian Bayesian networks to address the inverse problem with multi-pass wire drawing process as a case study. We propose an approach to systematically find all solutions and rank them according to their likelihood.","PeriodicalId":6636,"journal":{"name":"2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"13 1","pages":"626-631"},"PeriodicalIF":0.0000,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICMLA.2017.00-91","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

Abstract

Physics based simulations of manufacturing processes are used for prediction of material properties and defects in a number of industrial applications. However, a practising engineer often requires the solution to an "inverse problem" - prediction of inputs for the desired outcome. The inverse problem is usually solved by constrained optimisation. Extensive simulation during optimisation is avoided through response surfaces constructed from simulations. But the design space is often so large that even with response surfaces, optimisation might not be possible. Moreover, these problems are typically ill-posed, so discriminative models such as artificial neural networks do not work well. In this paper, we investigate the application of conditional linear Gaussian Bayesian networks to address the inverse problem with multi-pass wire drawing process as a case study. We propose an approach to systematically find all solutions and rank them according to their likelihood.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
制造贝叶斯网络中的逆推理贝叶斯网络
在许多工业应用中,基于物理的制造过程模拟用于预测材料性能和缺陷。然而,一个执业工程师经常需要解决一个“逆问题”——预测预期结果的输入。逆问题通常通过约束优化来解决。通过模拟构建响应面,避免了优化过程中大量的模拟。但设计空间往往太大,即使有响应面,优化也可能无法实现。此外,这些问题通常是病态的,因此像人工神经网络这样的判别模型不能很好地工作。本文以条件线性高斯贝叶斯网络为例,研究了其在多道次拉丝过程逆问题中的应用。我们提出了一种方法来系统地找到所有的解决方案,并根据它们的可能性对它们进行排序。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Tree-Structured Curriculum Learning Based on Semantic Similarity of Text Direct Multiclass Boosting Using Base Classifiers' Posterior Probabilities Estimates Predicting Psychosis Using the Experience Sampling Method with Mobile Apps Human Action Recognition from Body-Part Directional Velocity Using Hidden Markov Models Realistic Traffic Generation for Web Robots
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1