Hybrid hot strip rolling force prediction using a bayesian trained artificial neural networ.pdf

下载文档

6
0
约2.18万字
约 5页
2017-04-06 发布于江苏
举报
版权申诉
保障服务

Hybrid hot strip rolling force prediction using a bayesian trained artificial neural networ.pdf

1、本文档共5页，可阅读全部内容。
2、有哪些信誉好的足球投注网站（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。
3、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。

Hybrid hot strip rolling force prediction using a bayesian trained artificial neural networ

American Journal of Applied Sciences 3 (6): 1885-1889, 2006 ISSN 1546-9239 ? 2006 Science Publications Corresponding Author: Abdelkrim Moussaoui, Department of Electronics, University of Guelma, BP 401, 24000, Algeria 1885 Hybrid Hot Strip Rolling Force Prediction using a Bayesian Trained Artificial Neural Network and Analytical Models 1Abdelkrim Moussaoui, 1Yacine Selaimia and 2Hadj Ahmed Abbassi 1Department of Electronics, University of Guelma, BP 401, 24000, Algeria 2Department of electronics, University of Annaba, BP 12, Annaba, 23000, Algeria Abstract: The authors discuss the combination of an Artificial Neural Network (ANN) with analytical models to improve the performance of the prediction model of finishing rolling force in hot strip rolling mill process. The suggested model was implemented using Bayesian Evidence based training algorithm. It was found that the Bayesian Evidence based approach provided a superior and smoother fit to the real rolling mill data. Completely independent set of real rolling data were used to evaluate the capacity of the fitted ANN model to predict the unseen regions of data. As a result, test rolls obtained by the suggested hybrid model have shown high prediction quality comparatively to the usual empirical prediction models. Key words: Hot rolling mill, neural networks modelling, bayesian evidence INTRODUCTION Recent years have seen attempts by a number of authors to utilise various artificial neural network (ANN) based models to help better predict the rolling force in a hot rolling strip mill[1-3]. The rationale here is that ANNs have the potential to provide a mechanism for dealing with multi-variate, often noisy and possibly non-linear data sets, where an exact analytic model is either intractable, or too time consuming to develop. The basic procedure is to use a database of measurements to train an ANN structure and then evaluate the predictive capacity of the built model on previ