基于Fast-RVM的在线软测量预测模型

doi:10.11949/j.issn.0438-1157.20150566

化工学报 ›› 2015, Vol. 66 ›› Issue (11): 4540-4545.DOI: 10.11949/j.issn.0438-1157.20150566

基于Fast-RVM的在线软测量预测模型

许玉格, 刘莉, 曹涛

华南理工大学自动化科学与工程学院, 广东广州 510640

收稿日期:2015-05-06 修回日期:2015-07-20 出版日期:2015-11-05 发布日期:2015-11-05
通讯作者: 许玉格
基金资助:
国家自然科学基金项目(61473121);广州市珠江科技新星项目(2011J2200084);华南理工大学中央高校基本科研业务费专项基金项目(2014ZZ0027)。

On-line soft measuring model based on Fast-RVM

XU Yuge, LIU Li, CAO Tao

School of Automation Science and Engineering, South China University of Technology, Guanzhou 510640, Guangdong, China

Received:2015-05-06 Revised:2015-07-20 Online:2015-11-05 Published:2015-11-05
Supported by:
supported by the National Natural Science Foundation of China (61473121).

摘要/Abstract

摘要：

生化需氧量(biochemical oxygen demand,BOD)是评价水质好坏和污水处理效果的关键指标之一。由于污水生化处理过程复杂,在线仪表维护困难,生化需氧量无法得到快速精确地测量。针对这一问题,提出了一种基于Fast-RVM的在线软测量回归模型来实时在线预测出水指标BOD。该模型采用基于贝叶斯框架的相关向量机来在线预测输出指标,并且引入快速边际似然算法来加快模型的更新速度。通过污水数据的仿真实验,结果表明该在线模型的预测精度高于离线模型,泛化能力强,模型在线更新的快速性尤为突出,能较好地实现污水处理中出水水质的实时在线预测。

关键词: Fast-RVM算法, 在线建模, 软测量, 预测, 污水处理

Abstract:

Biochemical oxygen demand (BOD) is a significant indicator to evaluate the effluent quality in wastewater treatment process. Complex wastewater treatment process and high requirement for instrument maintenance make it very difficult to obtain BOD quickly and accurately. In order to solve this problem, a novel BOD on-line soft measuring model based on fast variable relevance vector machine (Fast-RVM) is proposed in this paper. Relevance vector machine algorithm with Bayesian framework is used to build up predictive model and fast marginal likelihood algorithm is applied to accelerate updating speed of the model. Simulation experiments show that the real-time on-line prediction performance and generalization ability are better by using the proposed model than those of off-line model. The online updating speed is particularly outstanding. These experimental results verify that the proposed method is very suitable for real-time on-line prediction of effluent quality in the wastewater treatment process.

Key words: Fast-RVM algorithm, on-line modeling, soft measurement, prediction, wastewater treatment process

中图分类号:

TP273

许玉格, 刘莉, 曹涛. 基于Fast-RVM的在线软测量预测模型[J]. 化工学报, 2015, 66(11): 4540-4545.

XU Yuge, LIU Li, CAO Tao. On-line soft measuring model based on Fast-RVM[J]. CIESC Journal, 2015, 66(11): 4540-4545.

参考文献 19

[1]	Huang Daoping (黄道平), Liu Yiqi (刘乙奇), Li Yan (李艳). Research and application of soft measurement in the sewage treatment process [J]. CIESC Journal (化工学报), 2011,62 (1): 56-64.
[2]	Guo Nan (郭楠), Qiao Junfei (乔俊飞). Research of BOD soft measuring instrument based on neural network [D]. Beijing: Beijing University of Technology, 2014.
[3]	Chen Zhaobo (陈兆波), Ren Yueming (任月明). Sewage Treatment Plant Measurement, Automatic Control and Fault Diagnosis (污水处理厂测量、自动控制与故障诊断) [M]. Beijing: Chemical Industry Press, 2009, 16-18.
[4]	Tian Yi (田奕), Qiao Junfei (乔俊飞). Neural network soft measurement of BOD based on genetic algorithm [J]. Computer Technology and Development (计算机技术与发展), 2009, 19 (3): 127-133.
[5]	Li Guihong (李贵宏), Zheng Hua (郑华). Application of artificial neural net work in wastewater treatment//Second International Conference on Information Science and Engineering, ICISE 2010 [C]. Hangzhou, 2010: 4373-4375.
[6]	Chen Zhiming (陈志明). Wastewater treatment prediction based on chao GA optimization LS-SVM//Proceedings of the 2011 Chinese Control and Decision Conference, CCDC 2011 [C]. Guizhou, 2011: 4013-4016.
[7]	Yang Baolei (杨鲍蕾). Prediction system of sewage outflow COD based on LS-SVM//Proceedings of the Second International Conference on Intelligent Control and Information Processing, ICICIP 2011 [C]. Hangzhou, 2011: 399-402.
[8]	Ran Weili (冉维丽), Qiao Junfei (乔俊飞). BOD soft-measuring approach based on PCA time-delay neural network [J]. Transaction of China Electrotechnical Society (电工技术学报), 2004, 19 (12): 78-82.
[9]	Su Shuhui (苏书惠), Zhang Shaode (张绍德), Tan Jinghui (谭敬辉). Research of waste water soft-measuring approach based on support vector machine [J]. Automation & Instrumentation (自动化与仪表), 2009, (6): 6-9.
[10]	Pani A K, Mohanta H K. Application of support vector regression, fuzzy inference and adaptive neuro fuzzy inference techniques for online monitoring of cement fitness. [J]. Powder Technology, 2014, 264: 484-497.
[11]	Tipping M E. Sparse Bayesian learning and the relevance vector machine [J]. Journal of Machine Learning Research, 2001, 1 (3): 211-244.
[12]	Michael E Tipping, Anita Faul. Fast marginal likelihood maximization for sparse Bayesian models//Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics [C]. Key West, 2003.
[13]	Xu Jiping (许继平), Chen Chen (陈晨), Liu Zaiwen (刘载文), Wang Xiaoyi (王小艺). Research on BOD online detection instrument based on the theory of soft instrument [J]. Control Engineering of China (控制工程), 2010, 17: 101-108.
[14]	Zhang Xiuju (张秀菊), An Huan (安焕), Zhao Wenrong (赵文荣), Zhang Qinling (张琴玲). Application of waste water prediction based on support vector machine [J]. Chinese Rural Water Conservancy and Hydroelectric Power (中国农村水利水电), 2015, (1): 85-89.
[15]	Xu Yuge (许玉格), Cao Tao (曹涛), Luo Fei (罗飞). The prediction of effluent quality of waste water treatment based on relevance vector machine [J]. Journal of South China University of Technology: Natural Science Edition (华南理工大学学报: 自然科学版), 2014, 42 (5): 111-117.
[16]	Wang Huazhong (王华忠), Yu Jinshou (俞金寿). Research on kernel function and its application in soft measurement modeling [J]. Automation & Instrumentation (自动化与仪表), 2004, 25 (10): 22-25.
[17]	Masuda Kazuaki. Global optimization of point search by equilibrium search of gradient dynamical system [J]. Electronic and Communication in Japan, 2008, 91 (1): 19-31.
[18]	Su Jieqiong, Wang Xuan, Liang Yong. GA-based support vector machine model for the predictor for the monthly reservoir storage [J]. Journal of Hydrologic Engineering, 2014, 19: 1430-1437.
[19]	Thomas Buchgraber, Dmitriy Shutin, Vincent Poor H. A sliding-window online fast variable sparse Bayesian learning algorithm//2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) [C]. 2011: 2128-2133.

基于Fast-RVM的在线软测量预测模型

On-line soft measuring model based on Fast-RVM

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]	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.
[3]	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.
[4]	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.
[5]	邵伟明, 韩文学, 宋伟, 杨勇, 陈灿, 赵东亚. 基于分布式贝叶斯隐马尔可夫回归的动态软测量建模方法[J]. 化工学报, 2023, 74(6): 2495-2502.
[6]	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.
[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]	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.
[10]	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.
[11]	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.
[12]	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.
[13]	任嘉辉, 刘豫, 刘朝, 刘浪, 李莹. 基于分子指纹和拓扑指数的工质临界温度理论预测[J]. 化工学报, 2022, 73(4): 1493-1500.
[14]	吴子睿, 孙瑞, 石凌峰, 田华, 王轩, 舒歌群. CO₂混合工质的气液相平衡的混合规则对比与预测研究[J]. 化工学报, 2022, 73(4): 1483-1492.
[15]	汪森林, 李照志, 邵应娟, 钟文琪. 超临界二氧化碳垂直管内传热恶化数值模拟研究[J]. 化工学报, 2022, 73(3): 1072-1082.