基于梯度增强回归树算法的磨浆过程打浆度软测量模型
|
摘要
基于梯度增强回归树(GBRT)的方法建立打浆度预测模型。采集实际工业环境中磨浆过程变量(如流量,纸浆浓度和磨浆机功率)和原料性质,包括原料纤维形态和浆料性质作为模型输入,所有输入变量数据来源于造纸厂。在实时数据上检验模型精度,均方误差为RMSE~k=0.9948。对比支持向量机(SVM)打浆度模型,GBRT打浆度模型时间复杂度更低。
A soft sensing method for beating degree modeling method is proposed based on the gradient boosting regression tree(GBRT) algorithm. In the model structure process, the refining process variables(including flow rate, pulp concentration, and refiner power) and the raw material properties(including fiber morphology and stock properties) are selected as model input. All the data of these input parameters are collected from a real-world paper mill. The model accuracy is tested by the real-time data, the mean square error of the soft sensing results is RMSE~k = 0.9948. Compared with the support vector machine(SVM) model, the proposed GBRT model has lower time complexity.
A soft sensing method for beating degree modeling method is proposed based on the gradient boosting regression tree(GBRT) algorithm. In the model structure process, the refining process variables(including flow rate, pulp concentration, and refiner power) and the raw material properties(including fiber morphology and stock properties) are selected as model input. All the data of these input parameters are collected from a real-world paper mill. The model accuracy is tested by the real-time data, the mean square error of the soft sensing results is RMSE~k = 0.9948. Compared with the support vector machine(SVM) model, the proposed GBRT model has lower time complexity.
引文
[1] 樊慧明, 李嘉禾, 郭鸣凤. 国家环保新政策与造纸行业面临的挑战[J]. 造纸科学与技术, 2018, 37(03):72-79. DOI:10.19696/j.issn1671-4571.2018.3.016
[2] 刘焕彬. 新时代下我国造纸工业发展与创新驱动的几点思考——在2017广东省造纸学会年会上的报告(提纲)[J]. 造纸科学与技术, 2018, 37(01):1-5. DOI:10.19696/j.issn1671-4571.2018.01.001
[3] BANAVATH H N, BHARDWAJ N K, RAY A K. A comparative study of the effect of refining on charge of various pulps[J]. Bioresource Technology, 2011, 102(6): 4544-4551. DOI: 10.1016/j.biortech.2010.12.109
[4] DING J, CHAI T, AFSHAR P, et al. MLP-based nonlinear modelling for energy saving in forming section of paper machines[C]//Proceedings of the World Congress on Intelligent Control and Automation (WCICA). 2012. DOI:10.1109/WCICA.2012. 6358268
[5] FRIEDMAN J H. Stochastic gradient boosting[J]. Computational Statistics & Data Analysis, 2002, 38(4): 367-378. DOI: 10.1016/S0167-9473(01)00065-2
[6] ELITH J, LEATHWICK J R, HASTIE T. A working guide to boosted regression trees[J]. Journal of Animal Ecology, 2008, 77(4): 802-813. DOI: 10.1111/j.1365-2656.2008.01390.x
[7] YE J, CHOW J-H, CHEN J, et al. Stochastic gradient boosted distributed decision trees[C]//Proceeding of the 18th ACM conference on Information and knowledge management-CIKM'09. New York, New York, USA: ACM Press, 2009: 2061. DOI: 10.1145/1645953.1646301
[8] ZHANG Y, HAGHANI A. A gradient boosting method to improve travel time prediction[J]. Transportation Research Part C, 2015, 58: 308-324. DOI: 10.1016/j.trc.2015.02.019
[9] DE'ATH G. Boosted trees for ecological modeling and prediction[J]. Ecology, 2007, 88(1): 243-251. DOI: 10.1890/0012-9658(2007)88[243:BTFEMA]2.0.CO;2
[10] TOUZANI S, GRANDERSON J, FERNANDES S. Gradient boosting machine for modeling the energy consumption of commercial buildings[J]. Energy and Buildings, Elsevier, 2018, 158: 1533-1543. DOI: 10.1016/J.ENBUILD.2017.11.039
[11] PERSSON C, BACHER P, SHIGA T, et al. Multi-site solar power forecasting using gradient boosted regression trees[J]. Solar Energy, 2017, 150: 423-436. DOI: 10.1016/j.solener.2017.04.066
[12] Qi C, CHEN Q, FOURIE A, et al. Pressure drop in pipe flow of cemented paste backfill: Experimental and modeling study[J]. Powder Technology, 2018, 333: 9-18. DOI: 10.1016/J.POWTEC.2018.03.070
[13] NIETO P J G, GARCIA-GONZALO E, ARBAT G, et al. Pressure drop modelling in sand filters in micro-irrigation using gradient boosted regression trees[J]. Biosystems Engineering, 2018, 171: 41-51. DOI: 10.1016/j.biosystemseng. 2018.04.011
[14] TERVASKANTO M, IKONEN E, AHVENLAMPI T. Refiner quality control in a CTMP plant[C]// IEEE International Conference on Control & Automation. IEEE, 2010. DOI: 10.1109/ICCA.2009.5410443
[15] KOHAVI R. A study of cross-validation and bootstrap for accuracy estimation and model selection[C]// Proceedings of the 14th international joint conference on Artificial intelligence-Volume 2. Morgan Kaufmann Publishers Inc.1995.
[2] 刘焕彬. 新时代下我国造纸工业发展与创新驱动的几点思考——在2017广东省造纸学会年会上的报告(提纲)[J]. 造纸科学与技术, 2018, 37(01):1-5. DOI:10.19696/j.issn1671-4571.2018.01.001
[3] BANAVATH H N, BHARDWAJ N K, RAY A K. A comparative study of the effect of refining on charge of various pulps[J]. Bioresource Technology, 2011, 102(6): 4544-4551. DOI: 10.1016/j.biortech.2010.12.109
[4] DING J, CHAI T, AFSHAR P, et al. MLP-based nonlinear modelling for energy saving in forming section of paper machines[C]//Proceedings of the World Congress on Intelligent Control and Automation (WCICA). 2012. DOI:10.1109/WCICA.2012. 6358268
[5] FRIEDMAN J H. Stochastic gradient boosting[J]. Computational Statistics & Data Analysis, 2002, 38(4): 367-378. DOI: 10.1016/S0167-9473(01)00065-2
[6] ELITH J, LEATHWICK J R, HASTIE T. A working guide to boosted regression trees[J]. Journal of Animal Ecology, 2008, 77(4): 802-813. DOI: 10.1111/j.1365-2656.2008.01390.x
[7] YE J, CHOW J-H, CHEN J, et al. Stochastic gradient boosted distributed decision trees[C]//Proceeding of the 18th ACM conference on Information and knowledge management-CIKM'09. New York, New York, USA: ACM Press, 2009: 2061. DOI: 10.1145/1645953.1646301
[8] ZHANG Y, HAGHANI A. A gradient boosting method to improve travel time prediction[J]. Transportation Research Part C, 2015, 58: 308-324. DOI: 10.1016/j.trc.2015.02.019
[9] DE'ATH G. Boosted trees for ecological modeling and prediction[J]. Ecology, 2007, 88(1): 243-251. DOI: 10.1890/0012-9658(2007)88[243:BTFEMA]2.0.CO;2
[10] TOUZANI S, GRANDERSON J, FERNANDES S. Gradient boosting machine for modeling the energy consumption of commercial buildings[J]. Energy and Buildings, Elsevier, 2018, 158: 1533-1543. DOI: 10.1016/J.ENBUILD.2017.11.039
[11] PERSSON C, BACHER P, SHIGA T, et al. Multi-site solar power forecasting using gradient boosted regression trees[J]. Solar Energy, 2017, 150: 423-436. DOI: 10.1016/j.solener.2017.04.066
[12] Qi C, CHEN Q, FOURIE A, et al. Pressure drop in pipe flow of cemented paste backfill: Experimental and modeling study[J]. Powder Technology, 2018, 333: 9-18. DOI: 10.1016/J.POWTEC.2018.03.070
[13] NIETO P J G, GARCIA-GONZALO E, ARBAT G, et al. Pressure drop modelling in sand filters in micro-irrigation using gradient boosted regression trees[J]. Biosystems Engineering, 2018, 171: 41-51. DOI: 10.1016/j.biosystemseng. 2018.04.011
[14] TERVASKANTO M, IKONEN E, AHVENLAMPI T. Refiner quality control in a CTMP plant[C]// IEEE International Conference on Control & Automation. IEEE, 2010. DOI: 10.1109/ICCA.2009.5410443
[15] KOHAVI R. A study of cross-validation and bootstrap for accuracy estimation and model selection[C]// Proceedings of the 14th international joint conference on Artificial intelligence-Volume 2. Morgan Kaufmann Publishers Inc.1995.