Multiple kernel least square support vector machine model for prediction of cement clinker lime content

doi:10.11949/j.issn.0438-1157.20151598

Abstract

Abstract:

Aiming at the problem of how to accurately predict the cement clinker fCaO content, the traditional single kernel least squares support vector machine (LSSVM) is difficult to show the complex non-linear relation between the clinker fCaO content and corresponding variables exactly. Thus, the multiple kernel least square support vector machine (MKLSSVM) containing three kernel function is presented based on multiple kernel learning to avoid the influence of the single kernel function on the model accuracy. As a result of artificial selection the parameters of MKLSSVM is blindness and uncertainty. The random perturbation chaos particle swarm optimization (RPCPSO) algorithm is presented to get the best parameters of MKLSSVM. The cement clinker fCaO content model is built by using the RPCPSO algorithm to optimize the parameters of MKLSSVM. Simulation results indicated that the RPCPSO algorithm had a fast convergence speed, and the model had high precision and strong ability of power generalization. Thus, the model was valuable for practical application.

Key words: multiple kernel learning, least square support vector machine, model, optimization, algorithm, random perturbation

摘要：

针对水泥熟料游离氧化钙(fCaO)含量预测模型辨识的问题,考虑到单一核函数无法显著提高模型精度,采用多项式核函数、指数径向基核函数和高斯径向基核函数组合构建等价核的方法,建立了多核最小二乘支持向量机水泥熟料fCaO预测模型。同时,利用改进的粒子群优化算法对多核最小二乘支持向量机模型的6个待确定参数进行迭代寻优,避免了模型参数人工选取的盲目性。最后将基于改进粒子群的多核最小二乘支持向量机模型应用于熟料fCaO含量的实例仿真。结果表明,建立的水泥熟料fCaO含量预测模型精度高、泛化能力强。

关键词: 多核学习, 最小二乘支持向量机, 模型, 优化, 算法, 随机扰动

CLC Number:

TP183

ZHAO Pengcheng, LIU Bin, GAO Wei, ZHAO Zhibiao, WANG Meiqi. Multiple kernel least square support vector machine model for prediction of cement clinker lime content[J]. CIESC Journal, 2016, 67(6): 2480-2487.

赵朋程, 刘彬, 高伟, 赵志彪, 王美琪. 用于水泥熟料fCaO预测的多核最小二乘支持向量机模型[J]. 化工学报, 2016, 67(6): 2480-2487.

References 22

[1]	KAEWMANEE K, KRAMMART P, SUMRANWANICH T, et al. Effect of free lime content on properties of cement-fly ash mixtures [J]. Construction and Building Materials, 2013, 38: 829-836. DOI: 10.1016/j.conbuildmat.2012.09.035.
[2]	王秀莲, 孙旭晨, 王卓, 等. 基于局部PSO-LSSVM的水泥f-CaO测量方法研究 [J]. 控制工程, 2014, 21 (6): 807-811. DOI: 10.3969/j.issn.1671-7848.2014.06.003. WANG X L, SUN X C, WANG Z, et al. Measurement method research for cement f-CaO based on local PSO-LSSVM [J]. Contorl Engineering of China, 2014, 21 (6): 807-811. DOI: 10.3969/j.issn.1671-7848.2014.06.003.
[3]	LI W T, WANG D H, ZHOU X J, et al. An improved multi-source based soft sensor for measuring cement free lime content [J]. Information Sciences, 2015, 323: 94-105. DOI: 10.1016/j.ins.2015.06.035.
[4]	李大字, 刘方, 靳其兵. 自增长混合神经网络及其在燃料电池建模中的应用 [J]. 化工学报, 2015, 66 (1): 333-337. DOI: 10.11949/j.issn.0438-1157.20141431. LI D Z, LIU F, JIN Q B. Self-growing hybrid neural network and its application for fuel cell modelling [J]. CIESC Journal, 2015, 66 (1): 333-337. DOI: 10.11949/j.issn.0438-1157.20141431.
[5]	VAPNIK V N. An overview of statistical learning theory [J]. IEEE Trans. on Neural Networks, 1999, 10 (5): 988-999. DOI: 10.1109/72.788640.
[6]	SUYKENS J A K, VANDEWALLE J. Least squares support vector machines classifiers [J]. Neural Network Letters, 1999, 19 (3): 293-300. DOI: 10.1023/A:1018628609742.
[7]	SUYKENS J A K, VANDEWALLE J. Recurrent least squares support vector machines [J]. IEEE Trans. on Circuits and Systems, 2000, 47 (7): 1109-1114. DOI: 10.1109/81.855471.
[8]	ZHENG P P, FENG J, LI Z, et al. A novel SVD and LS-SVM combination algorithm for blind watermarking [J]. Neurocomputing, 2014, 142: 520-528. DOI: 10.1016/j.neucom.2014.04.005.
[9]	冯凯, 卢建刚, 陈金水. 基于最小二乘支持向量机的MIMO线性参数变化模型辨识及预测控制 [J]. 化工学报, 2015, 66 (1): 197-205. DOI: 10.11949/j.issn.0438-1157.20141636. FENG K, LU J G, CHEN J S. Identification and model predictive control of LPV models based on LS-SVM for MIMO system [J]. CIESC Journal, 2015, 66 (1): 197-205. DOI: 10.11949/j.issn.0438-1157.20141636.
[10]	CHEN T T, LEE S J. A weighted LS-SVM based learning system for time series forecasting [J]. Information Sciences, 2015, 299: 99-116. DOI: 10.1016/j.ins.2014.12.031.
[11]	刘瑞兰, 徐艳, 戎舟. 基于稀疏最小二乘支持向量机的软测量建模 [J]. 化工学报, 2015, 66 (4): 1402-1406. DOI: 10.11949/j.issn.0438-1157.20141392. LIU R L, XU Y, RONG Z. Modeling soft sensor based on sparse least square support vector machine [J]. CIESC Journal, 2015, 66 (4): 1402-1406. DOI: 10.11949/j.issn.0438-1157.20141392.
[12]	AIOLLI F, DONINI M. EasyMKL: a scalable multiple kernel learning algorithm [J]. Neurocomputing, 2015, 169: 215-224. DOI: 10.1016/j.neucom.2014.11.078.
[13]	汪洪桥, 孙富春, 蔡艳宁, 等. 多核学习方法 [J]. 自动化学报, 2010, 36 (8): 1037-1050. DOI: 10.3724/SP.J.1004.2010.01037. WANG H Q, SUN F C, CAI Y N, et al. On multiple kernel learning methods [J]. Acta Automatica Sinica, 2010, 36 (8): 1037-1050. DOI: 10.3724/SP.J.1004.2010.01037.
[14]	陈强, 任雪梅. 基于多核最小二乘支持向量机的永磁同步电机混沌建模及其实时在线预测 [J]. 物理学报, 2010, 59 (4): 2310-2318. DOI: 10.7498/aps.59.2310. CHEN Q, REN X M. Chaos modeling and real-time online prediction of permanent magnet synchronous motor based on multiple kernel least squares support vector machine [J]. Acta Physica Sinica, 2010, 59 (4): 2310-2318. DOI: 10.7498/aps.59.2310.
[15]	FOSSACECA J M, MAZZUCHI T A, SARKANI S. MARK-ELM: application of a novel multiple kernel learning framework for improving the robustness of network intrusion detection [J]. Expert Systems with Applications, 2015, 42 (8): 4062-4080. DOI: 10.1016/j.eswa.2014.12.040.
[16]	安剑奇, 陈易斐, 吴敏. 基于改进支持向量机的高炉一氧化碳利用率预测方法 [J]. 化工学报, 2015, 66 (1): 206-214. DOI: 10.11949/j.issn.0438-1157.20141482. AN J Q, CHEN Y F, WU M. A prediction method for carbon monoxide utilization ratio of blast furnace based on improved support vector regression [J]. CIESC Journal, 2015, 66 (1): 206-214. DOI: 10.11949/j.issn.0438-1157.20141482.
[17]	何巧乐, 崔国民, 许海珠. 基于新策略粒子群算法优化换热网络 [J]. 化工学报, 2014, 65 (S1): 391-397. DOI: 10.3939/j.issn.0438-1157.2014.zl.063. HE Q L, CUI G M, XU H Z. Particle swarm optimization with two new strategies for heat exchangers network synthesis [J]. CIESC Journal, 2014, 65 (S1): 391-397. DOI: 10.3939/j.issn.0438-1157.2014.zl.063.
[18]	NICKABADI A, EBADZADEH M M, SAFABAKHSH R. A novel particle swarm optimization algorithm with adaptive inertia weight [J]. Applied Soft Computing, 2011, 11 (4): 3658-3670. DOI: 10.1016/j.asoc.2011.01.037.
[19]	田中大, 高宪文, 石彤. 用于混沌时间序列预测的组合核函数最小二乘支持向量机 [J]. 物理学报, 2014, 63 (16): 70-80. DOI: 10.7498/aps.64.030506. TIAN Z D, GAO X W, SHI T. Combination kernel function least squares support vector machine for chaotic time series prediction [J]. Acta Physica Sinica, 2014, 63 (16): 70-80. DOI: 10.7498/aps.64.030506.
[20]	YAO X, LIU Y, LIN G M. Evolutionary programming made faster [J]. IEEE Trans. on Evolutionary Computation, 1999, 3 (2): 82-102. DOI: 10.1109/4235.771163.
[21]	YANG C H, TSAI S W, CHUANG L Y, et al. An improved particle swarm optimization with double-bottom chaotic maps for numerical optimization [J]. Applied Mathematics and Computation, 2012, 219 (1): 260-279. DOI: 10.1016/j.amc.2012.06.015.
[22]	SUN J, FANG W, PALADE V, et al. Quantum-behaved particle swarm optimization with Gaussian distributed local attractor point [J]. Applied Mathematics and Computation, 2011, 218 (7): 3763-3775. DOI: 10.1016/j.amc.2011.09.021.82.
[17]	何巧乐, 崔国民, 许海珠. 基于新策略粒子群算法优化换热网络[J]. 化工学报, 2014, 65(S1): 391-397. DOI: 10.3939/j.issn.0438-1157.2014.zl.063. HE Q L, CUI G M, XU H Z. Particle swarm optimization with two new strategies for heat exchangers network synthesis[J]. CIESC Journal, 2014, 65(S1): 391-397. DOI: 10.3939/j.issn.0438-1157.2014.zl.063.
[18]	NICKABADI A, EBADZADEH M M, SAFABAKHSH R. A novel particle swarm optimization algorithm with adaptive inertia weight[J]. Applied Soft Computing, 2011, 11(4): 3658-3670. DOI: 10.1016/j.asoc.2011.01.037.
[19]	田中大,高宪文,石彤. 用于混沌时间序列预测的组合核函数最小二乘支持向量机[J]. 物理学报, 2014, 63(16): 70-80. DOI: 10.7498/aps.64.030506. TIAN Z D, GAO X W, SHI T. Combination kernel function least squares support vector machine for chaotic time series prediction[J]. Acta Physica Sinica, 2014, 63(16): 70-80. DOI: 10.7498/aps.64.030506.
[20]	YAO X, LIU Y, LIN G M. Evolutionary programming made faster[J] , IEEE Trans. on Evolutionary Computation, 1999, 3(2): 82-102. DOI: 10.1109/4235.771163.
[21]	YANG C H, TSAI S W, CHUANG L Y, et al. An improved particle swarm optimization with double-bottom chaotic maps for numerical optimization[J]. Applied Mathematics and Computation, 2012, 219(1): 260-279. DOI: 10.1016/j.amc.2012.06.015.
[22]	SUN J, FANG W, PALADE V, et al. Quantum-behaved particle swarm optimization with Gaussian distributed local attractor point[J]. Applied Mathematics and Computation, 2011, 218(7): 3763-3775. DOI: 10.1016/j.amc.2011.09.021.