在线KPLS建模方法及在磨机负荷参数集成建模中的应用

汤健; 柴天佑; 余文; 赵立杰

doi:10.3724/SP.J.1004.2013.00471

在线KPLS建模方法及在磨机负荷参数集成建模中的应用

doi: 10.3724/SP.J.1004.2013.00471

汤健^1,2,
柴天佑^1,3,,
余文⁴,
赵立杰⁵

1.
东北大学流程工业综合自动化国家重点实验室沈阳 110004, 中国;
2.
中国人民解放军92941部队葫芦岛 125001, 中国;
3.
东北大学自动化研究中心沈阳 110004, 中国;
4.
墨西哥国立理工大学高级研究中心(CINVESTAV-IPN) 墨西哥 07360, 墨西哥;
5.
沈阳化工大学信息工程学院沈阳 110142, 中国

详细信息

通讯作者:
柴天佑

计量
- 文章访问数: 1665
- HTML全文浏览量: 80
- PDF下载量: 1604
- 被引次数: 0
出版历程
- 收稿日期: 2012-05-13
- 修回日期: 2013-01-22
- 刊出日期: 2013-05-20

On-line KPLS Algorithm with Application to Ensemble Modeling Parameters of Mill Load

TANG Jian^1,2,
CHAI Tian-You^{1,3
,},
YU Wen⁴,
ZHAO Li-Jie⁵

1.
State Key Laboratory of Synthetical Automation for Process Industries (Northeastern University), Shenyang 110004, China;
2.
Unit 92941, PLA, Huludao 125001, China;
3.
Research Center of Automation, Northeastern University, Shenyang 110004, China;
4.
Departamento de Control Automatico, CINVESTAV-IPN, Av.IPN 2508, México D.F. 07360, México;
5.
College of Information Engineering, Shenyang University of Chemical Technology, Shenyang 110142, China

摘要

摘要: 针对过程非线性、基于历史数据构建的离线模型泛化性差以及基于滑动窗口和每样本递推更新的在线建模方法难以均衡建模精度和建模速度等问题, 提出了一种在线核偏最小二乘(On-line kernel partial least squares, OLKPLS)建模方法. 该方法依据新样本与建模样本间的近似线性依靠(Approximate linear dependence, ALD)值和代表工业过程特性漂移幅度的阈值, 选择有价值样本更新KPLS模型, 并采用合成数据和Benchmark平台数据对该方法进行了仿真验证. 针对基于离线历史数据建立的融合多传感器信息的磨机负荷参数集成模型难以适应磨矿过程时变特性的问题, 提出了基于OLKPLS和在线自适应加权融合算法的在线集成建模方法, 并通过实验球磨机的实际运行数据仿真验证了方法的有效性.
- 核偏最小二乘 /
- 近似线性依靠 /
- 模型更新条件 /
- 在线建模 /
- 集成建模
Abstract: Industrial processes have the characters of strong nonlinearity, and soft sensor models constructed based on historical data have low generalization. Normally used moving window and sample recursive updating on-line modeling approach can not obtain a trade off between the modeling accuracy and the modeling speed. To aim at these problems, a novel on-line kernel partial least squares (OLKPLS) algorithm is proposed in this paper. The approximate linear dependence (ALD) value between the new sample and the modeling samples is calculated. According to the threshold value that represents the concept drift amplitude of the industrial process, only new samples satisfy the ALD condition to update the KPLS model. Synthetic data and benchmark data are used to validate this approach. To aim at the multi-sensor information fusion ensemble model of mill load parameters based on off-line historical data, an on-line ensemble modeling approach based on OLKPLS and on-line adaptive weighting fusion algorithm are proposed, which are validated using the simulation results based on operating data of the laboratory ball mill.
- Kernel partial least squares (KPLS) /
- approximate linear dependence (ALD) /
- model's updating condition /
- on-line modeling /
- ensemble modeling

HTML全文

参考文献(47)

[1]	Chai Tian-You, Ding Jin-Liang, Wang Hong, Su Chun-Yi. Hybrid intelligent optimal control method for operation of complex industrial processes. Acta Automatica Sinica, 2008, 34(5): 505-515 (柴天佑, 丁进良, 王宏, 苏春翌. 复杂工业过程运行的混合智能优化控制方法. 自动化学报, 2008, 34(5): 505-515)
[2]	[2] Zhou P, Chai T Y, Wang H. Intelligent optimal-setting control for grinding circuits of mineral processing process. IEEE Transactions on Automation Science and Engineering, 2009, 6(4): 730-743
[3]	Zhou Ping, Chai Tian-You. Intelligent monitoring and control of mill load for grinding processes. Control Theory Applications, 2008, 25(6): 1095-1099 (周平, 柴天佑. 磨矿过程磨机负荷的智能监测与控制. 控制理论与应用, 2008, 25(6): 1095-1099)
[4]	[4] Tham M T, Montague G A, Morris A J, Lant P A. Soft-sensors for process estimation and inferential control. Journal of Process Control, 1991, 1(1): 3-14
[5]	[5] Kadlec P, Gabrys B, Strand S. Data-driven soft sensors in the process industry. Computers and Chemical Engineering, 2009, 33(4): 795-814
[6]	[6] Liu J L. On-line soft sensor for polyethylene process with multiple production grades. Control Engineering Practice, 2007, 15(7): 769-778
[7]	[7] Tang J, Chai T Y, Zhao L J, Yu W, Yue H. Soft sensor for parameters of mill load based on multi-spectral segments PLS sub-models and on-line adaptive weighted fusion algorithm. Neurocomputing, 2012, 78(1): 38-47
[8]	[8] Rosipal R, Trejo L J. Kernel partial least squares regression in reproducing kernel Hilbert space. Journal of Machine Learning Research, 2002, 2(1): 97-123
[9]	[9] Kadlec P, Grbic R, Gabrys B. Review of adaptation mechanisms for data-driven soft sensors. Computers Chemical Engineering, 2011, 35(1): 1-24
[10]	Gallagher N B, Wise B M, Butler S W, White D D Jr, Barna G G. Development and benchmarking of multivariate statistical process control tools for a semiconductor etch process: improving robustness through model updating. In: Proceedings of the 1997 Advanced Control of Chemical Processes. Banff, Canada: IEEE, 1997. 78-83
[11]	Wold S. Exponentially weighted moving principal components analysis and projections to latent structures. Chemometrics and Intelligent Laboratory Systems, 1994, 23(1): 149-161
[12]	Li W H, Yue H H, Valle-Cervantes S, Qin S J. Recursive PCA for adaptive process monitoring. Journal of Process Control, 2000, 10(5): 471-486
[13]	Elshenawy L M, Yin S, Naik A S, Ding S X. Efficient recursive principal component analysis algorithms for process monitoring. Industrial and Engineering Chemistry Research, 2010, 49(1): 252-259
[14]	Qin S J. Recursive PLS algorithms for adaptive data modeling. Computers Chemical Engineering, 1998, 22(4-5): 503-514
[15]	Wang X, Kruger U, Irwin G W. Process monitoring approach using fast moving window PCA. Industrial and Engineering Chemistry Research, 2005, 44(5): 5691-5702
[16]	Pan T, Shan Y, Wu Z T, Chen Z H, Li P Z. MWPLS method applied to the waveband selection of NIR spectroscopy analysis for brix degree of sugarcane clarified juice. In: Proceedings of the 3rd International Conference on Measuring Technology and Mechatronics Automation. Shanghai, China: IEEE, 2011. 671-674
[17]	Cauwenberghs G, Poggio T. Incremental and decremental support vector machine learning. In: Proceedings of the 2001 in Advances in Neural Information Processing Systems. Granada, Spain: IEEE, 2001. 409-415
[18]	Laskov P, Gehl C, Krger S, Mller K R. Incremental support vector learning: analysis, implementation and applications. Journal Machine Learning Research, 2006, 7(1): 1909-1936
[19]	Karasuyama M, Takeuchi I. Multiple incremental decremental learning of support vector machines. IEEE Transactions on Neural Networks, 2010, 21(7): 1048-1059
[20]	Yu W. Nonlinear system identification using discrete-time recurrent neural networks with stable learning algorithms. Information Sciences, 2004, 158: 131-147
[21]	Cong Q M, Chai T Y. Cascade process modeling with mechanism-based hierarchical neural networks. International Journal of Neural Systems, 2010, 20(1): 1-11
[22]	Wang W, Chai T Y, Yu W, Wang H, Su C Y. Modeling component concentrations of sodium aluminate solution via Hammerstein recurrent neural networks. IEEE Transactions on Control System Technology, 2012, 20(4): 971-982
[23]	Wang X, Kruger U, Lennox B. Recursive partial least squares algorithms for monitoring complex industrial processes. Control Engineering Practice, 2003, 11(6): 613-632
[24]	Jin H D, Lee Y H, Lee G, Han C H. Robust recursive principal component analysis modeling for adaptive monitoring. Industrial and Engineering Chemistry Research, 2006, 45(2): 696-703
[25]	Choi S W, Martin E B, Morris A J, Lee I B. Adaptive multivariate statistical process control for monitoring time-varying processes. Industrial and Engineering Chemistry Research, 2006, 45(9): 3108-3118
[26]	He X B, Yang Y P. Variable MWPCA for adaptive process monitoring. Industrial and Engineering Chemistry Research, 2008, 47(2): 419-427
[27]	Engel Y, Mannor S, Meir R. The kernel recursive least-squares algorithm. IEEE Transactions on Signal Processing, 2004, 52(8): 2275-2285
[28]	Yu W. Fuzzy modelling via on-line support vector machines. International Journal of Systems Science, 2010, 41(11): 1325-1335
[29]	Tang J, Yu W, Zhao L J, Yue H, Chai T Y. Modeling of operating parameters for wet ball mill by modified GA-KPLS. In: Proceedings of the 3rd International Workshop on Advanced Computational Intelligence. Suzhou, China: IEEE, 2010. 282-287
[30]	Qin Z M, Liu J Z, Zhang L Y, Gu J J. Online learning algorithm for sparse kernel partial least squares. In: Proceedings of the 5th IEEE Conference on Industrial Electronics and Applications. Taichung, Taiwan, China: IEEE, 2010. 1790-1794
[31]	Tang J, Yu W, Chai T Y, Zhao L J. On-line principal component analysis with application to process modeling. Neurocomputing, 2012, 82(1): 167-178
[32]	Tang J, Zhao L J, Yu W, Chai T Y, Yue H. Modified recursive partial least squares algorithm with application to modeling parameters of ball mill load. In: Proceedings of the 30th Chinese Control Conference. Yantai, China: IEEE, 2011. 5277-5282
[33]	Tang J, Chai T Y, Yu W, Zhao L J. Feature extraction and selection based on vibration spectrum with application to estimating the load parameters of ball mill in grinding process. Control Engineering Practice, 2012, 20(10): 991-1004
[34]	Dietterieg T. Machine-learning research: four current directions. The Artificial Intelligence Magazine, 1998, 18(1): 97-136
[35]	Hansen L K, Salamon P. Neural network ensembles. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(10): 993-1001
[36]	Ho T K. The random subspace method for constructing decision forests. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(8): 832-844
[37]	Rodriguez J J, Kuncheva L I, Alonso C J. Rotation forest: a new classifier ensemble method. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(10): 1619-1630
[38]	Yu E Z, Cho S Z. Ensemble based on GA wrapper feature selection. Computers Industrial Engineering, 2006, 51(1): 111-116
[39]	Viney N R, Bormann H, Breuer L, Bronstert A, Croke B F W, Frede H, Grff T, Hubrechts L, Huisman J A, Jakeman A J, Kite G E, Lanini J, Leavesley G, Lettenmaier D P, Lindstrm G, Seibert J, Sivapalan M, Willems P. Assessing the impact of land use change on hydrology by ensemble modelling (LUCHEM) II: ensemble combinations and predictions. Advances in Water Resources, 2009, 32(2): 147-158
[40]	Perrone M P, Cooper L N. When Networks Disagree: Ensemble Methods for Hybrid Neural Networks, Technical Report A121062, Institute for Brain and Neural Systems, Brown University, 1993
[41]	Zhou Z H, Wu J X, Tang W. Ensembling neural networks: many could be better than all. Artificial Intelligence, 2002, 137(1-2): 239-263
[42]	Zhang Chun-Xia, Zhang Jiang-She. A survey of selective ensemble learning algorithms. Chinese Journal of Computers, 2011, 34(8): 1399-1410 (张春霞, 张讲社. 选择性集成学习算法综述. 计算机学报, 2011, {\bf 34}(8): 1399-1410)
[43]	Tang Jian, Chai Tian-You, Zhao Li-Jie, Yue Heng, Zheng Xiu-Ping. Ensemble modeling for parameters of ballmill load in grinding process based on frequency spectrum of shell vibration. Control Theory Applications, 2012, 29(2): 183-191 (汤健, 柴天佑, 赵立杰, 岳恒, 郑秀萍. 基于振动频谱的磨矿过程球磨机负荷参数集成建模方法. 控制理论与应用, 2012, 29(2): 183-191)
[44]	Tang J, Chai T Y, Yu W, Zhao L J. Ball mill load estimation of the grinding process based on selective multi-source information fusion. IEEE Transactions on Automation Science and Engineering, to be published
[45]	Yue H, Qin S J. Reconstruction-based fault identification using a combined index. Industrial and Engineering Chemistry Research, 2001, 40(20): 4403-4414
[46]	Yeh I C. Modeling of strength of high performance concrete using artificial neural networks. Cement and Concrete Research, 1998, 28(12): 1797-1808
[47]	Tang J, Zhao L J, Zhou J W, Yue H, Chai T Y. Experimental analysis of wet mill load based on vibration signals of laboratory-scale ball mill shell. Minerals Engineering, 2010, 23(9): 720-730