基于偏最小二乘法的纸张抗张强度预测模型

doi:10.3969/j.issn.0438-1157.2014.09.032

化工学报 ›› 2014, Vol. 65 ›› Issue (9): 3544-3551.DOI: 10.3969/j.issn.0438-1157.2014.09.032

基于偏最小二乘法的纸张抗张强度预测模型

李远华, 陶劲松, 李继庚, 刘焕彬

华南理工大学制浆造纸工程国家重点实验室, 广东广州 510640

收稿日期:2013-12-19 修回日期:2014-03-17 出版日期:2014-09-05 发布日期:2014-09-05
通讯作者: 陶劲松
基金资助:
2010广东省科技计划项目重大科技专项（2010A080801002）；华南理工大学制浆造纸工程国家重点实验室开放基金项目（201233）；2014中央高校基本科研业务费专项资金资助项目（2014ZZ0055）。

Building predicting model of paper tensile strength based on partial least-squares approach

LI Yuanhua, TAO Jingsong, LI Jigeng, LIU Huanbin

State Key Laboratory of Pulp and Paper Engineering, South China University of Technology, Guangzhou 510640, Guangdong, China

Received:2013-12-19 Revised:2014-03-17 Online:2014-09-05 Published:2014-09-05
Supported by:
supported by the Major Science and Technology Projects of Science and Technology in Guangdong (2010A080801002), the Fund of State Key Laboratory of Pulp and Paper Engineering, South China University of Technology (201233) and the Fundamental Research Funds for the Central Universities (2014ZZ0055).

摘要/Abstract

摘要： 为了解决抗张强度机理模型中参数难以测量、偏离工厂生产变量、实际指导关联性差的问题。以一瓦楞原纸生产线为研究对象，先通过经验分析筛选影响纸张抗张强度的生产过程变量，在收集对应变量的生产数据后，应用偏最小二乘法建立抗张强度预测模型并对重要影响变量进行分析。结果表明该模型具有较好精度，其皮尔逊相关系数r=0.732，均方根误差RMSE值为276 N·m^-1，平均相对误差MRE值为5.17%。同时得到了影响纸张抗张强度的6个重要生产过程变量，通过机理分析和现场验证，发现结果具有较好的现实吻合度。

关键词: 化学过程, 纸张抗张强度, 产品工程, 偏最小二乘法, 预测

Abstract: The problems existing in the mechanism models include difficulty in obtaining the parameters, and most of the parameters had little relationship with production which reduced its practicability. The partial least-squares method (PLS) was used to establish the model to predict paper strength based on a production line of a corrugated paper mill. By selecting parameters and their data aided with mechanism analysis, we built the model and obtained the key parameters. The results showed that the model had a good precision that its Pearson's value was 0.732, root mean square error (RMSE) was 276 N·m^-1, and mean relative error (MRE) was 5.17%. Besides, the model had a good analytical ability that the key elements could be interpreted very well from the mechanism angle.

Key words: chemical processes, paper sheet tensile strength, product engineering, partial least-squares, prediction

中图分类号:

TS75

李远华, 陶劲松, 李继庚, 刘焕彬. 基于偏最小二乘法的纸张抗张强度预测模型[J]. 化工学报, 2014, 65(9): 3544-3551.

LI Yuanhua, TAO Jingsong, LI Jigeng, LIU Huanbin. Building predicting model of paper tensile strength based on partial least-squares approach[J]. CIESC Journal, 2014, 65(9): 3544-3551.

参考文献 19

[1]	Chen Kefu (陈克复). Pulp and Paper Machinery and Equipment (制浆造纸机械与设备 (下)) [M]. Beijing: China Light Industry Press, 2003
[2]	Page D H. A theory for the tensile strength of paper[J]. Tappi Journal, 1969, 52 (4): 674-679
[3]	Garg P, Scott W. Potential application of predictive tensile strength models in paper manufacture (Ⅰ): Development of a predictive tensile strength model from the page equation//TAPPI Papermakers Conference Proceedings[C]. 2001
[4]	Anson S J I, Karademir A, Sampson W W. Specific contact area and the tensile strength of paper [J]. Appita Journal, 2006, 59 (4): 297-301
[5]	Westerlind Bo S, Arnesson P, Sandstorm P, et al. Engineering approach to page and shear-lag theory for predicting tensile strength of paper//61st Appita Annual Conference and Exhibition [C]. Gold Coast, 2007
[6]	Axelsson A. Fibre based models for predicting tensile strength of paper [D]. Finland: Luleå University of Technology, 2009: 32-65
[7]	Wang Baoyu (王宝玉). Study on the relationship between the chemical characteristics of wood fiber and paper sheet strength [D]. Guangzhou: South China University of Technology, 2011
[8]	Navita S, Kumar Ra. Articficial neural network modeling for tensile strength of paper in paper manufacturing process international [J]. Information Technology and Knowledge Management, 2011, 4 (2): 409-412
[9]	Wang Huiwen (王惠文). Partial Least-Squares Regression Method and Application (光纤传感技术与应用) [M]. Beijing: National Defense Industry Press, 2000: 123-202
[10]	Hu Yi (胡益), Wang Li (王丽), Ma Hehe (马贺贺). Online nonlinear process monitoring using kernel partial least squares [J]. CIESC Journal (化工学报), 2011, 62 (9): 2555-2562
[11]	Jia Runda (贾润达), Mao Zhizhong (毛志忠), Wang Fuli (王福利). KPLS model based product quality control for batch processes [J]. CIESC Journal (化工学报), 2013, 64 (4): 1332-1341
[12]	Wang Xiaoyong (汪小勇). Based on multivariate statistical projection method of soft measurement technology research industrial process [D]. Hangzhou: Zhejiang University, 2004
[13]	Chu Fei (褚菲), Wang Fuli (王福利), Wang Xiaogang (王小刚). Hybrid modeling method for performance prediction of multi-stage centrifugal compressor [J]. Chinese Journal of Scientific Instrument (仪器仪表学报), 2011, 32 (12): 2821-2827
[14]	Noraini Ibrahim, Antoni Wibowo. Partial least squares regression based variables selection for water level predictions [J]. American Journal of Applied Sciences, 2013, 10 (4): 322-330
[15]	Mihaleva V V, van Schalkwijk D B, de Graaf A A. A systematic approach to obtain validated partial least square models for predicting lipoprotein subclasses from serum NMR spectra [J]. Analytical Chemistry, 2014. 86 (1): 543-550
[16]	Pearson coefficient [DB/OL]. http://wiki.mbalib.com/wiki/Pearson coefficient
[17]	Liu Guixiong (刘桂雄), Lin Xuhong (林绪虹). Partial least-square regressive analysis and modeling of ultraweak photon emission of fish [J]. Journal of South China University of Technology (华南理工大学学报), 2006, 34 (11): 29-32
[18]	Wang Xueming (王学民). Statistical analysis methods and applications [D]. Shanghai: Shanghai University of Finance and Economics, 2010
[19]	Lu Qianhe (卢谦和). Paper Making Theory and Engineering [M]. Beijing: China Light Industry Press, 2007: 225-349

基于偏最小二乘法的纸张抗张强度预测模型

Building predicting model of paper tensile strength based on partial least-squares approach

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献 19

相关文章 15

编辑推荐

Metrics

本文评价

[1]	闫琳琦, 王振雷. 基于STA-BiLSTM-LightGBM组合模型的多步预测软测量建模[J]. 化工学报, 2023, 74(8): 3407-3418.
[2]	林典, 江国梅, 徐秀彬, 赵波, 刘冬梅, 吴旭. 硅基类液防原油黏附涂层的研制及其减阻性能研究[J]. 化工学报, 2023, 74(8): 3438-3445.
[3]	尹刚, 李伊惠, 何飞, 曹文琦, 王民, 颜非亚, 向禹, 卢剑, 罗斌, 卢润廷. 基于KPCA和SVM的铝电解槽漏槽事故预警方法[J]. 化工学报, 2023, 74(8): 3419-3428.
[4]	郭雨莹, 敬加强, 黄婉妮, 张平, 孙杰, 朱宇, 冯君炫, 陆洪江. 稠油管道水润滑减阻及压降预测模型修正[J]. 化工学报, 2023, 74(7): 2898-2907.
[5]	李艳辉, 丁邵明, 白周央, 张一楠, 于智红, 邢利梅, 高鹏飞, 王永贞. 非常规服役超临界锅炉的微纳尺度腐蚀动力学模型建立及应用[J]. 化工学报, 2023, 74(6): 2436-2446.
[6]	于源, 陈薇薇, 付俊杰, 刘家祥, 焦志伟. 几何相似涡流空气分级机环形区流场变化规律研究及预测[J]. 化工学报, 2023, 74(6): 2363-2373.
[7]	张中秋, 李宏光, 石逸林. 基于人工预测调控策略的复杂化工过程多任务学习方法[J]. 化工学报, 2023, 74(3): 1195-1204.
[8]	吴心远, 刘奇磊, 曹博渊, 张磊, 都健. Group2vec：基于无监督机器学习的基团向量表示及其物性预测应用[J]. 化工学报, 2023, 74(3): 1187-1194.
[9]	胡月, 马守骏, 蹇锡高, 翁志焕. 新型聚芳醚腈固化邻苯二甲腈树脂的研究[J]. 化工学报, 2023, 74(2): 871-882.
[10]	陈家辉, 杨鑫泽, 陈顾中, 宋震, 漆志文. 以离子液体密度为例的分子性质预测模型建模方法探讨[J]. 化工学报, 2023, 74(2): 630-641.
[11]	赵亚静, 胡激江, 介素云, 李伯耿. HTPB引入方式对不饱和树脂改性效果的影响[J]. 化工学报, 2023, 74(2): 883-892.
[12]	史克年, 郑景元, 钱宇, 杨思宇. 基于马尔可夫链的蒸汽动力系统两阶段随机规划[J]. 化工学报, 2023, 74(2): 807-817.
[13]	杨静, 林振康, 汤君, 樊铖, 孙克宁. 电池系统的故障特征以及多故障的诊断与识别[J]. 化工学报, 2022, 73(8): 3394-3405.
[14]	周新杰, 王建林, 艾兴聪, 随恩光, 王汝童. 基于IDPC-RVM的多模态间歇过程质量变量在线预测[J]. 化工学报, 2022, 73(7): 3120-3130.
[15]	李淼, 赵虹, 姜标, 陈思远, 闫龙. 煤制乙炔关键中间体BaC₂合成的热力学分析[J]. 化工学报, 2022, 73(5): 1908-1919.