基于粒子蜂群算法优化的多支持向量机软测量建模方法研究
|
摘要
软测量技术是一种新型的智能检测技术,在工业过程测控系统中具有非常广阔的应用前景。在软测量技术体系中,软测量建模理论的研究是其中的热点之一,直接关系到软测量的成功与否。为了解决传统软测量建模方法中存在的适用范围小、精度低等问题,本文针对存在多种工况状态的软测量对象,研究了一种基于粒子蜂群算法优化的多支持向量机软测量建模方法,并成功建立了铝电磁铸轧过程中铝带坯晶粒度的软测量模型,从而验证了该方法的有效性。
首先,介绍了软测量技术的基本原理,并进行了文献综述,分析了软测量建模理论的研究趋势,指出了软测量建模过程中所面临的主要问题。
其次,针对样本数据的合理聚类问题,研究了一种基于减法聚类改进的模糊C-均值聚类算法,并在两组数据集上进行了仿真试验,试验结果证实了该算法具有稳定性高、计算量小等优点。随后,在介绍支持向量机回归建模基本理论的基础上,研究了一种基于模糊聚类的多支持向量机软测量建模方法,给出了其详细的建模流程及模型应用流程。
然后,针对支持向量机的参数优化问题,提出了一种新型的粒子蜂群优化算法,将粒子群算法中的全局指导机制与人工蜂群算法的基本结构进行了有机融合。通过大量的仿真试验,证实了该优化算法具有收敛速度快、收敛率高等优点。
最后,针对铝电磁铸轧过程中铝带坯晶粒度的检测难题,将软测量技术引入其中,建立了铝带坯晶粒度的多支持向量机软测量模型,并进行了仿真试验分析。试验结果表明,该模型较之传统单模型,具有更强的鲁棒性和更好的预测性能。
Soft sensor technology is a novel type of intelligent measurement technology. It has a very broad application prospects in the industrial process measurement and control system. In the soft sensor technology system, the theoretical study of the soft sensor modeling is one of the hot one. The traditional soft sensor modeling methods have some disadvantages. For example, narrow scope of use, low precision and so on. In the paper, for the soft sensor object with a variety of working conditions, a multiple support vector machines soft sensor modeling based on particle bee colony optimization algorithm is researched. And then, in order to prove the effectiveness of the method, the aluminum strip's grain size soft sensor model is established successfully in the process of aluminum electromagnetic casting.
Firstly, the basic principle of soft sensor technology is introduced. Through the literature review, the research trend of soft sensor modeling theory is analyzed. At the same time, some major matters are indicated in the process of soft sensor modeling.
Secondly, in order to solve the problem of data clustering, an improved fuzzy C-means clustering based on the subtractive clustering is researched. Two data sets are simulated and analyzed by using the algorithm. The results show that the improved algorithm has many advantages, including greater stability, less computation, and so on. Soon afterwards, the support vector regression modeling basic theory is elaborated. Based on the above research, a multiple support vector machines soft sensor modeling method based on fuzzy clustering is researched. The detailed model building process and the model application process is introduced.
Then, in order to solve the support vector machines parameters optimization problem, a novel particle bee colony optimization algorithm is proposed. In the algorithm, the global guidance mechanism of PSO and the basic structure of artificial bee colony algorithm are combined organically. Through a large number of simulation experiments, some advantages are confirmed, including faster convergence speed, higher convergence rate, and so on.
Finally, in order to solve the measurement problem of aluminum strip's grain size in the process of aluminum electromagnetic casting, the soft sensor technology is used. The multiple support vector machines soft sensor model of aluminum strip's grain size is established. The simulation results show that, compared with the traditional single model, the model has more robust and better prediction performance.
首先,介绍了软测量技术的基本原理,并进行了文献综述,分析了软测量建模理论的研究趋势,指出了软测量建模过程中所面临的主要问题。
其次,针对样本数据的合理聚类问题,研究了一种基于减法聚类改进的模糊C-均值聚类算法,并在两组数据集上进行了仿真试验,试验结果证实了该算法具有稳定性高、计算量小等优点。随后,在介绍支持向量机回归建模基本理论的基础上,研究了一种基于模糊聚类的多支持向量机软测量建模方法,给出了其详细的建模流程及模型应用流程。
然后,针对支持向量机的参数优化问题,提出了一种新型的粒子蜂群优化算法,将粒子群算法中的全局指导机制与人工蜂群算法的基本结构进行了有机融合。通过大量的仿真试验,证实了该优化算法具有收敛速度快、收敛率高等优点。
最后,针对铝电磁铸轧过程中铝带坯晶粒度的检测难题,将软测量技术引入其中,建立了铝带坯晶粒度的多支持向量机软测量模型,并进行了仿真试验分析。试验结果表明,该模型较之传统单模型,具有更强的鲁棒性和更好的预测性能。
Soft sensor technology is a novel type of intelligent measurement technology. It has a very broad application prospects in the industrial process measurement and control system. In the soft sensor technology system, the theoretical study of the soft sensor modeling is one of the hot one. The traditional soft sensor modeling methods have some disadvantages. For example, narrow scope of use, low precision and so on. In the paper, for the soft sensor object with a variety of working conditions, a multiple support vector machines soft sensor modeling based on particle bee colony optimization algorithm is researched. And then, in order to prove the effectiveness of the method, the aluminum strip's grain size soft sensor model is established successfully in the process of aluminum electromagnetic casting.
Firstly, the basic principle of soft sensor technology is introduced. Through the literature review, the research trend of soft sensor modeling theory is analyzed. At the same time, some major matters are indicated in the process of soft sensor modeling.
Secondly, in order to solve the problem of data clustering, an improved fuzzy C-means clustering based on the subtractive clustering is researched. Two data sets are simulated and analyzed by using the algorithm. The results show that the improved algorithm has many advantages, including greater stability, less computation, and so on. Soon afterwards, the support vector regression modeling basic theory is elaborated. Based on the above research, a multiple support vector machines soft sensor modeling method based on fuzzy clustering is researched. The detailed model building process and the model application process is introduced.
Then, in order to solve the support vector machines parameters optimization problem, a novel particle bee colony optimization algorithm is proposed. In the algorithm, the global guidance mechanism of PSO and the basic structure of artificial bee colony algorithm are combined organically. Through a large number of simulation experiments, some advantages are confirmed, including faster convergence speed, higher convergence rate, and so on.
Finally, in order to solve the measurement problem of aluminum strip's grain size in the process of aluminum electromagnetic casting, the soft sensor technology is used. The multiple support vector machines soft sensor model of aluminum strip's grain size is established. The simulation results show that, compared with the traditional single model, the model has more robust and better prediction performance.
引文
[1]梁倩,吕勇哉.基于HGA优化RBF网络的污水总氮软测量[J].计算机仿真,2008,25(7)：137-140.
[2]王学武,顾幸生,刘卓倩,等.基于PSO-BP神经网络的催化裂化C3含量软测量模型[J].系统仿真学报,2009,21(4)：973-976.
[3]朱红求,阳春华,桂卫华.基于模糊LS-SVM的净化过程钴离子浓度软测量[J].仪器仪表学报,2009,30(6)：1224-1227.
[4]徐海霞.多模型软测量建模方法研究及其在生物发酵过程中的应用[D].南京：江苏大学,2009.
[5]李昂.基于SVM的常压塔石脑油干点软测量建模研究[D].哈尔滨：哈尔滨工业大学,2008.
[6]傅永峰.软测量建模方法研究及其工业应用[D].杭州：浙江大学,2007.
[7]Jennifer Yick, Biswanath Mukherjee, Dipak Ghosal. Wireless sensor network survey [J]. Computer Networks,2008,52(12):2292-2330.
[8]Riky Subrata, Albert Y. Zomaya, Bjorn Landfeldt. Cooperative power-aware scheduling in grid computing environments [J]. Journal of Parallel and Distributed Computing,2010,70(2):84-91.
[9]张彬,杨为民,吴智勇,等.基于径向基函数神经网络的乙苯催化脱氢转化率的软测量应用[J].化工进展,2009,28(4)：588-591.
[10]赵露平.基于自适应混合模型的萃取过程软测量研究与应用[D].沈阳：东北大学,2009.
[11]乔弘,周黎辉,潘卫华,等.基于参数自适应SVR的火电厂热工参数软测量[J].华北电力大学学报,2008,35(2)：94-97.
[12]Brosillow C, Joseph B, Martin T. Inferential Control of Process[J]. AIChE. J., 1978,24(3):485-509.
[13]Lakhmi Jain, Anna Maria Fanelli. Recent Advances in Artificial Neural Networks Design and Applications[M]. Boca Raton, USA:CRC Press,2000.
[14]阚晓旭,金晓明.RBF多模型神经网络软测量技术在湿法磷酸生产中的应用[J].化工自动化及仪表,2006,33(1)：64-66.
[15]梁倩,吕勇哉.基于HGA优化RBF网络的污水总氮软测量[J].计算机仿真,2008,25(7)：137-140.
[16]J.C.B. Gonzaga, L.A.C. Meleiro, C. Kiang, et al. ANN-based soft-sensor for real-time process monitoring and control of an industrial polymerization process[J]. Computers & Chemical Engineering,2009,33(1):43-49.
[17]M. Shakil, M. Elshafei, M.A. Habib, et al. Soft sensor for NOx and O2 using dynamic neural networks[J]. Computers & Electrical Engineering,2009,35(4): 578-586.
[18]A. Jimenez, G. Beltran, M.P. Aguilera, et al. A sensor-software based on artificial neural network for the optimization of olive oil elaboration process[J]. Sensors and Actuators B:Chemical,2008,129(2):985-990.
[19]周长,张杰,吕文祥.基于Bootstrap多神经网络的软测量方法[J].控制工程,2009,16(4)：475-477.
[20]闫晶.基于MEDO粒子群算法的流量软测量RBF网络优化研究[D].秦皇岛：燕山大学,2009.
[21]Xue-feng Yan. Hybrid artificial neural network based on BP-PLSR and its application in development of soft sensors[J]. Chemometrics and Intelligent Laboratory Systems,2010,103(2):152-159.
[22]Javier Fernandez de Canete, Pablo del Saz-Orozco, Salvador Gonzalez-Perez. Application of adaptive neurofuzzy control using soft sensors to continuous distillation[J]. Computer Aided Chemical Engineering,2008, (25):465-470.
[23]叶涛.基于机器学习的软测量技术理论与应用[D].广州：华南理工大学,2007.
[24]Min Woo Lee, Sung Hun Hong, Hyeoksun Choi, et al. Real-time remote monitoring of small-scaled biological wastewater treatment plants by a multivariate statistical process control and neural network-based software sensors[J]. Process Biochemistry,2008,43(10):1107-1113.
[25]赵正虎,李华.基于QPSO优化RBF网络的稀土萃取组分含量软测量[J].电子质量,2010,(11)：1-2.
[26]Vapnik V. The Nature of Satistic Learning Theory[M]. New York:Cambridge University Press,1999.
[27]李修亮,苏宏业,褚健.基于在线聚类的多模型软测量建模方法[J].化工学报,2007,58(11)：2834-2839.
[28]Guohai Liu, Dawei Zhou, Haixia Xu, et al. Model optimization of SVM for a fermentation soft sensor[J]. Expert Systems with Applications,2010,37(4): 2708-2713.
[29]P. Jain, I. Rahman, B.D. Kulkarni. Development of a Soft Sensor for a Batch Distillation Column Using Support Vector Regression Techniques[J]. Chemical Engineering Research and Design,2007,85(2):283-287.
[30]杨妍,陈如清,俞金寿.基于混沌最小二乘支持向量机的软测量建模[J].华东理工大学学报(自然科学版),2009,35(6)：902-906.
[31]Jenny Terzic, C.R. Nagarajah, Muhammad Alamgir. Fluid level measurement in dynamic environments using a single ultrasonic sensor and Support Vector Machine (SVM)[J]. Sensors and Actuators A:Physical,2010,161(1-2): 278-287.
[32]R. Noori, A.R. Karbassi, A. Moghaddamnia, et al. Assessment of input variables determination on the SVM model performance using PCA, Gamma test, and forward selection techniques for monthly stream flow prediction[J]. Journal of Hydrology,2011,401(3-4):177-189.
[33]林碧华,顾幸生.基于差分进化算法-最小二乘支持向量机的软测量建模[J].化工学报,2008,59(7)：1681-1685.
[34]张淑宁,王福利,何大阔,等.基于多最小二乘支持向量机的草酸钴粒度软测量[J].仪器仪表学报,2010,31(9)：2081-2087.
[35]Fabien Chauchard, Jenny Svensson, Johan Axelsson, et al. Localization of embedded inclusions using detection of fluorescence:Feasibility study based on simulation data, LS-SVM modeling and EPO pre-processing[J]. Chemometrics and Intelligent Laboratory Systems,2008,91(1):34-42.
[36]Zhi-gang Su, Pei-hong Wang, Jiong Shen, et al. Multi-model strategy based evidential soft sensor model for predicting evaluation of variables with uncertainty[J]. Applied Soft Computing,2011,11(2):2595-2610.
[37]吕丛.基于支持向量回归的水力旋流器溢流粒度软测量[D].沈阳：东北大学,2009.
[38]张斌.一种改进的约简支持向量机及其在锌净化过程软测量中的应用[D].长沙：中南大学,2010.
[39]S. Khatibisepehr, B. Huang, F. Ibrahim, et al. Data-based modeling and prediction of cytotoxicity induced by contaminants in water resources [J]. Computational Biology and Chemistry,2011, (1):136-147.
[40]Ji Huang, Yu-cheng Bo, Hui-yuan Wang. Electromechanical equipment state forecasting based on genetic algorithm-support vector regression[J]. Expert Systems with Applications,2011,38(7):8399-8402.
[41]杜文莉,官振强,钱锋.一种基于时序误差补偿的动态软测量建模方法[J].化工学报,2010,61(2)：439-443.
[42]李炜,章寅.异类多模型动态融合软测量方法研究与应用[J].化工自动化及仪表,2010,37(8)：42-45.
[43]张健.提高制浆蒸煮过程纸浆Kappa值软测量精度的研究[D].广州：华南理工大学,2004.
[44]李艳.制浆蒸煮过程纸浆卡伯值软测量技术研究与应用[D].广州：华南理工大学,2003.
[45]李川.真空净油机喷雾蒸发及软测量技术研究[D].重庆：重庆大学,2007.
[46]李勇刚.基于智能集成模型的苛性比值与溶出率软测量及应用研究[D].长沙：中南大学,2004.
[47]任青松.基于软测量的铝电磁铸轧过程控制系统研究[D].长沙：中南大学,2007.
[48]王云飞.基于支持向量机的铝电磁铸轧系统软测量模型研究[D].长沙：中南大学,2008.
[49]凌玉华,杨欣荣,李海娜,等.铝电磁铸轧带坯晶粒度软测量建模及优化[C].2009年中国智能自动化会议论文集,2009：1085-1093.
[50]赵谦.基于SVM的铝带坯晶粒度软测量模型的研究[D].长沙：中南大学,2009.
[51]郭燕萍.基于多神经网络融合的铝带坯晶粒度软测量技术的研究[D].长沙：中南大学,2010.
[52]梁朝霞.球磨机负荷检测软测量建模方法的研究[D].沈阳：东北大学,2008.
[53]姜丽.模糊C均值聚类的理论与应用研究[D].杭州：浙江工商大学,2010.
[54]康家银,纪志成,龚成龙.一种核模糊C均值聚类算法及其应用[J].仪器仪表学报,2010,31(7)：1657-1663.
[55]孙志海,孔万增,朱善安.视频目标定位的减法聚类改进算法[J].浙江大学学报(工学版),2010,44(3)：458-462.
[56]杜喆.几类支持向量机变型算法的研究[D].西安：西安电子科技大学,2009.
[57]霍明.短期负荷预测的支持向量机模型参数优化方法研究[D].长沙：湖南大学,2009.
[58]肖先锋.基于支持向量机的铝粉细粉率软测量[D].大连,大连理工大学,2009.
[59]张煜东,吴乐南,奚吉,等.进化计算研究现状[J].电脑开发与应用,2009,22(12)：933-937.
[60]A. Colorni, M. Dorigo, V. Maniezzo, et al. Distributed optimization by ant colonies[A]. In:Proceedings of the 1st European Conference on Artificial Life[C]. Paris, France:Elsevier Publishing,1991:134-142.
[61]J. Kennedy, R.C. Eberhart. Particle Swarm optimization[A]. In:Proceedings of International Conference on Neural Networks[C]. Piscataway, NJ:IEEE Service Center,1995:1942-1948.
[62]J. Kennedy, R.C. Eberhart, Y.H. Shi. Swarm Intelligence[M]. San Francisco, USA:Morgan Kaufmann Publishers,2001.
[63]D. Karaboga. An idea based on honey bee swarm for numerical optimiza-tion[R]. Erciyes:Erciyes University, Engineering Faculty, Computer Engineering Department,2005.
[64]D. Karaboga, B. Basturk. A powerful and efficient algorithm for numerical function optimization—artificial bee colony (ABC) algorithm[J]. Journal of Global Optimization,2007, (39):459-471.
[65]D. Karaboga, B. Basturk. On the performance of artificial bee colony (ABC) algorithm[J]. Applied Soft Computing,2008, (8):687-697.
[66]D. Karaboga, B. Akay. A comparative study of Artificial Bee Colony algorithm[J]. Applied Mathematics and Computation,2009, (14):108-132.
[67]V. Tereshko. Reaction—diffusion model of a honeybee colony's foraging behaviour[A]. In:Proceedings of the Parallel Problem Solving from Nature VI Conference, Lecture Notes in Computer Science[C]. Birmingham, UK: Springer-Verlag,2000,1917:807-816.
[68]钟掘.铝合金的超常铸轧制备[J].中国有色金属学报,2004,14(1)：147-153.
[69]沈海鸥.铸轧带坯晶粒粗大的原因分析及对策[J].有色金属加工,2009,38(5)：20-22.
[70]郭运涛,毛大恒.铝带坯电磁快速铸轧换相周期选取的探讨[J].轻合金加工技术,2005,33(3)：17-20.
[71]刘同娟,郭键,刘军.MATLAB建模、仿真与应用[M].北京：中国电力出版社,2009.
[2]王学武,顾幸生,刘卓倩,等.基于PSO-BP神经网络的催化裂化C3含量软测量模型[J].系统仿真学报,2009,21(4)：973-976.
[3]朱红求,阳春华,桂卫华.基于模糊LS-SVM的净化过程钴离子浓度软测量[J].仪器仪表学报,2009,30(6)：1224-1227.
[4]徐海霞.多模型软测量建模方法研究及其在生物发酵过程中的应用[D].南京：江苏大学,2009.
[5]李昂.基于SVM的常压塔石脑油干点软测量建模研究[D].哈尔滨：哈尔滨工业大学,2008.
[6]傅永峰.软测量建模方法研究及其工业应用[D].杭州：浙江大学,2007.
[7]Jennifer Yick, Biswanath Mukherjee, Dipak Ghosal. Wireless sensor network survey [J]. Computer Networks,2008,52(12):2292-2330.
[8]Riky Subrata, Albert Y. Zomaya, Bjorn Landfeldt. Cooperative power-aware scheduling in grid computing environments [J]. Journal of Parallel and Distributed Computing,2010,70(2):84-91.
[9]张彬,杨为民,吴智勇,等.基于径向基函数神经网络的乙苯催化脱氢转化率的软测量应用[J].化工进展,2009,28(4)：588-591.
[10]赵露平.基于自适应混合模型的萃取过程软测量研究与应用[D].沈阳：东北大学,2009.
[11]乔弘,周黎辉,潘卫华,等.基于参数自适应SVR的火电厂热工参数软测量[J].华北电力大学学报,2008,35(2)：94-97.
[12]Brosillow C, Joseph B, Martin T. Inferential Control of Process[J]. AIChE. J., 1978,24(3):485-509.
[13]Lakhmi Jain, Anna Maria Fanelli. Recent Advances in Artificial Neural Networks Design and Applications[M]. Boca Raton, USA:CRC Press,2000.
[14]阚晓旭,金晓明.RBF多模型神经网络软测量技术在湿法磷酸生产中的应用[J].化工自动化及仪表,2006,33(1)：64-66.
[15]梁倩,吕勇哉.基于HGA优化RBF网络的污水总氮软测量[J].计算机仿真,2008,25(7)：137-140.
[16]J.C.B. Gonzaga, L.A.C. Meleiro, C. Kiang, et al. ANN-based soft-sensor for real-time process monitoring and control of an industrial polymerization process[J]. Computers & Chemical Engineering,2009,33(1):43-49.
[17]M. Shakil, M. Elshafei, M.A. Habib, et al. Soft sensor for NOx and O2 using dynamic neural networks[J]. Computers & Electrical Engineering,2009,35(4): 578-586.
[18]A. Jimenez, G. Beltran, M.P. Aguilera, et al. A sensor-software based on artificial neural network for the optimization of olive oil elaboration process[J]. Sensors and Actuators B:Chemical,2008,129(2):985-990.
[19]周长,张杰,吕文祥.基于Bootstrap多神经网络的软测量方法[J].控制工程,2009,16(4)：475-477.
[20]闫晶.基于MEDO粒子群算法的流量软测量RBF网络优化研究[D].秦皇岛：燕山大学,2009.
[21]Xue-feng Yan. Hybrid artificial neural network based on BP-PLSR and its application in development of soft sensors[J]. Chemometrics and Intelligent Laboratory Systems,2010,103(2):152-159.
[22]Javier Fernandez de Canete, Pablo del Saz-Orozco, Salvador Gonzalez-Perez. Application of adaptive neurofuzzy control using soft sensors to continuous distillation[J]. Computer Aided Chemical Engineering,2008, (25):465-470.
[23]叶涛.基于机器学习的软测量技术理论与应用[D].广州：华南理工大学,2007.
[24]Min Woo Lee, Sung Hun Hong, Hyeoksun Choi, et al. Real-time remote monitoring of small-scaled biological wastewater treatment plants by a multivariate statistical process control and neural network-based software sensors[J]. Process Biochemistry,2008,43(10):1107-1113.
[25]赵正虎,李华.基于QPSO优化RBF网络的稀土萃取组分含量软测量[J].电子质量,2010,(11)：1-2.
[26]Vapnik V. The Nature of Satistic Learning Theory[M]. New York:Cambridge University Press,1999.
[27]李修亮,苏宏业,褚健.基于在线聚类的多模型软测量建模方法[J].化工学报,2007,58(11)：2834-2839.
[28]Guohai Liu, Dawei Zhou, Haixia Xu, et al. Model optimization of SVM for a fermentation soft sensor[J]. Expert Systems with Applications,2010,37(4): 2708-2713.
[29]P. Jain, I. Rahman, B.D. Kulkarni. Development of a Soft Sensor for a Batch Distillation Column Using Support Vector Regression Techniques[J]. Chemical Engineering Research and Design,2007,85(2):283-287.
[30]杨妍,陈如清,俞金寿.基于混沌最小二乘支持向量机的软测量建模[J].华东理工大学学报(自然科学版),2009,35(6)：902-906.
[31]Jenny Terzic, C.R. Nagarajah, Muhammad Alamgir. Fluid level measurement in dynamic environments using a single ultrasonic sensor and Support Vector Machine (SVM)[J]. Sensors and Actuators A:Physical,2010,161(1-2): 278-287.
[32]R. Noori, A.R. Karbassi, A. Moghaddamnia, et al. Assessment of input variables determination on the SVM model performance using PCA, Gamma test, and forward selection techniques for monthly stream flow prediction[J]. Journal of Hydrology,2011,401(3-4):177-189.
[33]林碧华,顾幸生.基于差分进化算法-最小二乘支持向量机的软测量建模[J].化工学报,2008,59(7)：1681-1685.
[34]张淑宁,王福利,何大阔,等.基于多最小二乘支持向量机的草酸钴粒度软测量[J].仪器仪表学报,2010,31(9)：2081-2087.
[35]Fabien Chauchard, Jenny Svensson, Johan Axelsson, et al. Localization of embedded inclusions using detection of fluorescence:Feasibility study based on simulation data, LS-SVM modeling and EPO pre-processing[J]. Chemometrics and Intelligent Laboratory Systems,2008,91(1):34-42.
[36]Zhi-gang Su, Pei-hong Wang, Jiong Shen, et al. Multi-model strategy based evidential soft sensor model for predicting evaluation of variables with uncertainty[J]. Applied Soft Computing,2011,11(2):2595-2610.
[37]吕丛.基于支持向量回归的水力旋流器溢流粒度软测量[D].沈阳：东北大学,2009.
[38]张斌.一种改进的约简支持向量机及其在锌净化过程软测量中的应用[D].长沙：中南大学,2010.
[39]S. Khatibisepehr, B. Huang, F. Ibrahim, et al. Data-based modeling and prediction of cytotoxicity induced by contaminants in water resources [J]. Computational Biology and Chemistry,2011, (1):136-147.
[40]Ji Huang, Yu-cheng Bo, Hui-yuan Wang. Electromechanical equipment state forecasting based on genetic algorithm-support vector regression[J]. Expert Systems with Applications,2011,38(7):8399-8402.
[41]杜文莉,官振强,钱锋.一种基于时序误差补偿的动态软测量建模方法[J].化工学报,2010,61(2)：439-443.
[42]李炜,章寅.异类多模型动态融合软测量方法研究与应用[J].化工自动化及仪表,2010,37(8)：42-45.
[43]张健.提高制浆蒸煮过程纸浆Kappa值软测量精度的研究[D].广州：华南理工大学,2004.
[44]李艳.制浆蒸煮过程纸浆卡伯值软测量技术研究与应用[D].广州：华南理工大学,2003.
[45]李川.真空净油机喷雾蒸发及软测量技术研究[D].重庆：重庆大学,2007.
[46]李勇刚.基于智能集成模型的苛性比值与溶出率软测量及应用研究[D].长沙：中南大学,2004.
[47]任青松.基于软测量的铝电磁铸轧过程控制系统研究[D].长沙：中南大学,2007.
[48]王云飞.基于支持向量机的铝电磁铸轧系统软测量模型研究[D].长沙：中南大学,2008.
[49]凌玉华,杨欣荣,李海娜,等.铝电磁铸轧带坯晶粒度软测量建模及优化[C].2009年中国智能自动化会议论文集,2009：1085-1093.
[50]赵谦.基于SVM的铝带坯晶粒度软测量模型的研究[D].长沙：中南大学,2009.
[51]郭燕萍.基于多神经网络融合的铝带坯晶粒度软测量技术的研究[D].长沙：中南大学,2010.
[52]梁朝霞.球磨机负荷检测软测量建模方法的研究[D].沈阳：东北大学,2008.
[53]姜丽.模糊C均值聚类的理论与应用研究[D].杭州：浙江工商大学,2010.
[54]康家银,纪志成,龚成龙.一种核模糊C均值聚类算法及其应用[J].仪器仪表学报,2010,31(7)：1657-1663.
[55]孙志海,孔万增,朱善安.视频目标定位的减法聚类改进算法[J].浙江大学学报(工学版),2010,44(3)：458-462.
[56]杜喆.几类支持向量机变型算法的研究[D].西安：西安电子科技大学,2009.
[57]霍明.短期负荷预测的支持向量机模型参数优化方法研究[D].长沙：湖南大学,2009.
[58]肖先锋.基于支持向量机的铝粉细粉率软测量[D].大连,大连理工大学,2009.
[59]张煜东,吴乐南,奚吉,等.进化计算研究现状[J].电脑开发与应用,2009,22(12)：933-937.
[60]A. Colorni, M. Dorigo, V. Maniezzo, et al. Distributed optimization by ant colonies[A]. In:Proceedings of the 1st European Conference on Artificial Life[C]. Paris, France:Elsevier Publishing,1991:134-142.
[61]J. Kennedy, R.C. Eberhart. Particle Swarm optimization[A]. In:Proceedings of International Conference on Neural Networks[C]. Piscataway, NJ:IEEE Service Center,1995:1942-1948.
[62]J. Kennedy, R.C. Eberhart, Y.H. Shi. Swarm Intelligence[M]. San Francisco, USA:Morgan Kaufmann Publishers,2001.
[63]D. Karaboga. An idea based on honey bee swarm for numerical optimiza-tion[R]. Erciyes:Erciyes University, Engineering Faculty, Computer Engineering Department,2005.
[64]D. Karaboga, B. Basturk. A powerful and efficient algorithm for numerical function optimization—artificial bee colony (ABC) algorithm[J]. Journal of Global Optimization,2007, (39):459-471.
[65]D. Karaboga, B. Basturk. On the performance of artificial bee colony (ABC) algorithm[J]. Applied Soft Computing,2008, (8):687-697.
[66]D. Karaboga, B. Akay. A comparative study of Artificial Bee Colony algorithm[J]. Applied Mathematics and Computation,2009, (14):108-132.
[67]V. Tereshko. Reaction—diffusion model of a honeybee colony's foraging behaviour[A]. In:Proceedings of the Parallel Problem Solving from Nature VI Conference, Lecture Notes in Computer Science[C]. Birmingham, UK: Springer-Verlag,2000,1917:807-816.
[68]钟掘.铝合金的超常铸轧制备[J].中国有色金属学报,2004,14(1)：147-153.
[69]沈海鸥.铸轧带坯晶粒粗大的原因分析及对策[J].有色金属加工,2009,38(5)：20-22.
[70]郭运涛,毛大恒.铝带坯电磁快速铸轧换相周期选取的探讨[J].轻合金加工技术,2005,33(3)：17-20.
[71]刘同娟,郭键,刘军.MATLAB建模、仿真与应用[M].北京：中国电力出版社,2009.