基于神经网络和群智能优化算法的生产过程预警技术及其应用
|
摘要
预警技术是在警情发生之前对其进行预测,发出预警信号的过程。将预警技术应用于生产过程中,能有效地提高系统对异常工况的响应速度,及早发现异常,有效降低未来的可能损失,对安全生产起着重要的作用。
在研究分析了文化算法、混沌理论和粒子群优化算法整体框架和关键参数的基础上提出了两种混合算法：改进型文化粒子群优化算法(Culture-MPSO)和改进型混沌粒子群优化算法(Chaos-MPSO)来优化预警模型的参数。Culture-MPSO算法将文化算法和粒子群优化算法融合,一方面在文化算法的主群体空间加入PSO算法进行寻优,并对PSO算法中的关键参数进行改进,如惯性权重,另一方面增加了衡量进化方向好坏的指标,使算法的接受规则更具有自适应性。Chaos-MPSO算法将混沌理论和粒子群优化算法融合,一方面对PSO算法中几个关键的参数做出了改进,如惯性权重；另一方面在PSO算法的全局极值点的领域范围内引入混沌搜索技术进行二次搜索,增加了算法的局部搜索能力,使算法收敛速度更高效。
在实现生产过程预警的过程中,本文提出了两种模型：预警级别模型和软测量模型。预警级别模型是将预警的等级作为神经网络的输出,是一个离散输出模型；软测量模型是将预警的关键参数作为神经网络的输出,是一个连续输出模型。分别对这两种模型进行了仿真实验,最后将这两种模型结合,对神经网络的预警结果进行综合判断。
仿真实验结果表明：RBF网络模型相比BP网络以及Elman网络,在相同条件下可以得到更好的拟合效果和预测效果；Culture-MPSO算法和Chaos-MPSO算法比传统优化算法搜索性能更优,搜索速度更快,相比而言,Chaos-MPSO算法比Culture-MPSO算法具有更优的优化性能；将预警级别模型和软测量模型相结合,对生产工况的运行状态综合判断,提高了对工况运行状态预报的正确率。
将上述群智能优化算法和神经网络建模方法应用于裂解反应过程,建立综合预警模型,实现了对裂解反应过程异常工况提前预报的目的,防患于未然。
Early warning technology is that forecast the abnormal situation and send a warning signal before it occurs. Using early warning technology can improve the response speed of abnormal situation and find it before it occurs, and can reduce the future possible loss effectively. Early warning technology plays an important role in safety production.
Two hybrid algorithms (Culture-MPSO and Chaos-MPSO) were proposed to optimal the parameters of RBF-NN. Culture-MPSO algorithm fusions cultural algorithm and particle swarm optimization algorithm. On the one hand, Culture-MPSO uses PSO to optimal the population space of CA, and continuously improves the parameters of PSO, such as inertia weight. On the other hand, the accept rules of Culture-MPSO are more adaptive because of increasing a parameter to measure evolution direction. Chaos-MPSO algorithm fusions chaos theory and particle swarm optimization algorithm. On the one hand, Chaos-MPSO continuously improves the parameters of PSO, such as inertia weight. On the other hand, Chaos-MPSO uses chaos theory to find the better extreme value nearby the current global extreme value. This algorithm is more efficient and has good effect to optimal the early warning model.
Two models were proposed, including warning level model and soft sensor model. Warning level model has three warming levels, which is a discrete output model. Soft sensor model takes the key parameter as the output of neural network, which is a continuous output model. Many experiments have done to simulation the two kinds of models, then the two models are combined to decisive the warning level.
Under the same conditions, simulation results shows that:compared with BP network and Elman networks, RBF network shows better fitting and predictive result; Culture-MPSO algorithm and Chaos-MPSO algorithm have better search performance and faster search speed than the traditional optimization algorithms, and Chaos-MPSO algorithm is better than Culture-MPSO algorithm; the two models were combined to decisive the warning level, which has improved the correct rate of the early warning model.
Using the above intelligent optimization algorithms and neural network modeling method, and setting up a comprehensive early alarming model, which can predict the abnormal situation of process timely and prevent it occurs.
在研究分析了文化算法、混沌理论和粒子群优化算法整体框架和关键参数的基础上提出了两种混合算法：改进型文化粒子群优化算法(Culture-MPSO)和改进型混沌粒子群优化算法(Chaos-MPSO)来优化预警模型的参数。Culture-MPSO算法将文化算法和粒子群优化算法融合,一方面在文化算法的主群体空间加入PSO算法进行寻优,并对PSO算法中的关键参数进行改进,如惯性权重,另一方面增加了衡量进化方向好坏的指标,使算法的接受规则更具有自适应性。Chaos-MPSO算法将混沌理论和粒子群优化算法融合,一方面对PSO算法中几个关键的参数做出了改进,如惯性权重；另一方面在PSO算法的全局极值点的领域范围内引入混沌搜索技术进行二次搜索,增加了算法的局部搜索能力,使算法收敛速度更高效。
在实现生产过程预警的过程中,本文提出了两种模型：预警级别模型和软测量模型。预警级别模型是将预警的等级作为神经网络的输出,是一个离散输出模型；软测量模型是将预警的关键参数作为神经网络的输出,是一个连续输出模型。分别对这两种模型进行了仿真实验,最后将这两种模型结合,对神经网络的预警结果进行综合判断。
仿真实验结果表明：RBF网络模型相比BP网络以及Elman网络,在相同条件下可以得到更好的拟合效果和预测效果；Culture-MPSO算法和Chaos-MPSO算法比传统优化算法搜索性能更优,搜索速度更快,相比而言,Chaos-MPSO算法比Culture-MPSO算法具有更优的优化性能；将预警级别模型和软测量模型相结合,对生产工况的运行状态综合判断,提高了对工况运行状态预报的正确率。
将上述群智能优化算法和神经网络建模方法应用于裂解反应过程,建立综合预警模型,实现了对裂解反应过程异常工况提前预报的目的,防患于未然。
Early warning technology is that forecast the abnormal situation and send a warning signal before it occurs. Using early warning technology can improve the response speed of abnormal situation and find it before it occurs, and can reduce the future possible loss effectively. Early warning technology plays an important role in safety production.
Two hybrid algorithms (Culture-MPSO and Chaos-MPSO) were proposed to optimal the parameters of RBF-NN. Culture-MPSO algorithm fusions cultural algorithm and particle swarm optimization algorithm. On the one hand, Culture-MPSO uses PSO to optimal the population space of CA, and continuously improves the parameters of PSO, such as inertia weight. On the other hand, the accept rules of Culture-MPSO are more adaptive because of increasing a parameter to measure evolution direction. Chaos-MPSO algorithm fusions chaos theory and particle swarm optimization algorithm. On the one hand, Chaos-MPSO continuously improves the parameters of PSO, such as inertia weight. On the other hand, Chaos-MPSO uses chaos theory to find the better extreme value nearby the current global extreme value. This algorithm is more efficient and has good effect to optimal the early warning model.
Two models were proposed, including warning level model and soft sensor model. Warning level model has three warming levels, which is a discrete output model. Soft sensor model takes the key parameter as the output of neural network, which is a continuous output model. Many experiments have done to simulation the two kinds of models, then the two models are combined to decisive the warning level.
Under the same conditions, simulation results shows that:compared with BP network and Elman networks, RBF network shows better fitting and predictive result; Culture-MPSO algorithm and Chaos-MPSO algorithm have better search performance and faster search speed than the traditional optimization algorithms, and Chaos-MPSO algorithm is better than Culture-MPSO algorithm; the two models were combined to decisive the warning level, which has improved the correct rate of the early warning model.
Using the above intelligent optimization algorithms and neural network modeling method, and setting up a comprehensive early alarming model, which can predict the abnormal situation of process timely and prevent it occurs.
引文
[1]杨尔辅,胡益锋,周强等.乙烯生产过程建模及控制和优化技术综述[J].石油化工自动化,2002,2,1-6.
[2]McCulloch W S, Pitts W H. A logical calculus of the ideas immanent in nervous activity[J]. Bulletin of Mathematical Biophysics,1943, (5):115-133.
[3]Hebb D 0. The Organization of Behavior[M]. New York:Wiley,1949.
[4]Rosenblatt F. The perception:A probabilistic model for information storage and organization in the brain[J]. Psychological Review,1958, (65):386-458.
[5]Widrow B, Hoff M E. Adaptive Switching Circuits[M]. New York:IRE,1960,94-104.
[6]Minsky M, Papert S. Perceptions[M]. Cambridge:MIT Press,1969.
[7]Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagation error[J]. Nature,1986, (323):533-536.
[8]杨金城,胡春.裂解深度神经网络控制系统的研究[J].仪表及自动化,2005,20(2)：40-42.
[9]谢承泮.神经网络发展综述[J].科技情报开发与经济,2006,16(12)：148-150.
[10]黄海燕,顾幸生.基于文化算法的神经网络及其在建模中的应用[J].控制与决策,2008,23(4)：214-217.
[11]杨尔辅.工业裂解过程动力学建模与软测量技术研究[M].北京,清华大学自动化系,2001.
[12]王东生,曹磊.混沌、分形及其应用[M].合肥：中国科学技术大学出版社,1995.
[13]Coryn A L, Bailer-jones, David J C. A recurrent network for modeling dynamical system[J]. Network:Computer in Neural Systems,1998(9),531-547.
[14]Zhifeng Chen, Peide Qian. Application of PSO-RBF Neural Network in Network Intrusion Detection[J]. Third International Symposium on Intelligent Information Technology Application,2009,362-364.
[15]俞金寿.工业过程先进控制[M].北京：中国石化出版社,2002.
[16]Kennedy J, Eberhart R C. A discrete binary version of the particle swarm algorithm[A]. IEEE Service Center, Proceeding of the IEEE Conference on Systems, Man, and Cybernetics[C], Piscataway. NJ:IEEE Press,1997,4104-4109.
[17]Hashler M, Mazzini G, Lek M O, et al. Scanning the special issue on application of nonlinear dynamics to electronic and information engineering[A]. Proceedings of the IEEE[C],2002,90(5):631-640.
[18]Robinson J, Rahmat-Samii Y. Particle swarm optimization in electromagnetic [J]. IEEE Trans. On Antennas and Propagation,2004,52(2):397-407.
[19]Shi Y, Eberhart R C. Empirical study of particle swarm optimization[A]. Proceeding of the IEEE Congress on Evolutionary Computation[C], Piscataway, NJ:IEEE Press,1999, 1945-1950.
[20]Shi Y, Eberhart R C. Fuzzy adaptive particle swarm optimization[A]. The IEEE Congress on Evolutionary Computation[C], San Francisco:IEEE Press,2001,101-106.
[21]Eberhart R C, Shi Y. Tracking and optimizing dynamic systems with particle swarm[A]. The IEEE Congress on Evolutionary Computation[C], San Francisco:IEEE Press,2001, 94-100.
[22]陈贵敏,贾建援,韩琪.粒子群优化算法的惯性权重递减策略研究[J].西安交通大学学报,2006,40(1)：53-56.
[23]Eberhart R C, Shi Y. Comparing Inertia Weights and Constriction Factors in Particle Swarm Optimization[A]. Proc. CFC 2000[C], San Diego, CA,2000,84-88.
[24]莫愿斌,陈德钊,胡上序.混沌粒子群算法及其在生化过程动态优化中的应用[J].化工学报,2006,57(9)：2123-2127.
[25]Li X, Dam K H. Comparing particle swarms for tracking extreme in dynamic environments [A]. Congress on Evolutionary Computation[C],2003,1772-1779.
[26]Parrott D, Li X. A particle swarm model for tracking multiple peeks in a dynamic environment using speciation[A]. Congress on Evolutionary Computation[C],2004, 98-103.
[27]Peer E, van den Bergh F, Engelbrecht A. Using Neighborhoods with the Guaranteed Convergence PSO[J]. Swarm Intelligence Symposium. Piscataway, New Jersey, USA, IEEE Service Center,2003,235-242.
[28]van den Bergh F. An Analysis of Particle Swarm Optimizers[D], PhD Thesis. Department of Computer Science, University of Pretoria, South Africa,2002.
[29]van den Bergh F, Engelbrecht A. A new locally convergent particle swarm optimizer[A]. Proceedings of the IEEE Conference on Systems[C], Man, Cybernetics, Hammamet, Tunisia,2002.
[30]Clerc M. Particle Swarm Optimization[M]. London:ISTE Publishing Company,2006.
[31]Lovbjerg M, Rasmussen T K, et al. Hybrid particle swarm optimization with breeding and subpopulations[A]. IEEE International Conference on Evolutionary Computation[C], SanDieego,2000.
[32]Higashi N, Iba H. Particle swarm optimization with Gaussian mutation[J]. Proc of the IEEE Swarm Intelligence Symposium. Indianapolis:IEEE Inc,2003,72-79.
[33]高鹰,谢胜利.基于模拟退火的粒子群优化算法[J].计算机工程与应用,2004,1：47-50.
[34]Meng H J, Zhang P, Wu R Y. A hybrid particle swarm algorithm with embedded chaotic search[A]. IEEE Conference on Cybernetics and Intelligent Systems[C],2004,367-371.
[35]Liu L J, Cai Z X, Chen H. Immunity clone algorithm with particle swarm evolution[J]. Cent South University Technology,2006,1,703-706.
[36]高鹰.谢胜利.免疫粒子群优化算法[J].计算机工程与应用,2004,41(6)：4-6.
[37]Holden N, Freitas A. A hybrid particle swarm/ant colony algorithm for the classification of hierarchical biological data[J]. Swarm Intelligence Symposium,2005. Proceedings 2005 IEEE Volume, Issue,8-10 June 2005,100-107.
[38]李炳宇,萧蕴诗,吴启迪.一种基于粒子群算法求解优化问题的混合算法[J].控制与决策,2004,19(7)：804-806.
[39]Mikki S, Kishk A. Investigation of the quantum particle swarm optimization technique for electromagnetic applications[J]. Antennas and Propagation Society International Symposium,2005 IEEE Volume 2A,3-8 July 2005,45-48.
[40]Sun J, Feng B, Xu W. Particle swarm optimization with particles having quantum behavior [C]. IEEE Proc of Congress on Evolutionary Computation[A],2004.
[41]Van den Bergh F, Engelbrecht A. Training product unit networks using cooperative particle swarm optimizers[A]. Proc of the Third Genetic and Evolutionary Computation Conference[C], San Francisco, USA,2001.
[42]van den Bergh F, Engelbrecht A. Cooperative learning in neural networks using particle swarm optimizers[J]. South African Computation,2000,11(26):84-90.
[43]Potter M A, de Jong K A. A cooperative evolutionary approach to function optimization[A]. The Third Parallel Problem Solving From Nature[C], Berlin:Springer-Verlag,1994, 249-257.
[44]Caponetto R, Fortuna L, Fazzino S, et al. Chaotic Sequences to Improve the Performance of Evolutionary Algorithms[J]. IEEE Trans on Evolut Comput,2003,7(3):289-304.
[45]Al-kazemi B, Moan C K. Training feed forward neural networks using multi-phase particle swarm optimization[A]. Proceedings of the 9th International Conference on Neural Information Processing[C],2002,5:2615-2619.
[46]Bliss L. Selecting artificial neural net work inputs using particle swarm optimization[J]. Dissertation Pace University, USA,2003.
[47]Fukuyama Y. State estimation and optimal setting of voltage regulator in distribution systems[J]. IEEE Power Engineering Society Winter Meeting,2001,930-935.
[48]Zheng Y, Ma L, et al. Robust PID controller design using particle swarm optimizer[J]. Proceedings of IEEE International Symposium on Intelligence Control,2003,974-979.
[49]Zhang Xiaoming, Ning Guangliang. An improved RBF network on-line learning algorithm[J]. Second International Symposium on Information Science and Engineering, 2009,547-552.
[50]Zeng Qingwei, Xu Zhihai, Wu Jian. Prediction of Electricity Consumption Based on Genetic Algorithm-RBF Neural Network[J]. IEEE,2010,339-342.
[51]黄曦,邹安全.基于BP神经网络的企业财务危机组合预警研究[J].经济与管理研究.2009,5：87-91.
[52]黄继鸿,雷战波,凌超.经济预警方法研究综述[J].系统工程,2003,21(2)：64-70.
[53]X Yao, Y Liu and G Lin. Evolutionary programming made faster[J]. IEEE Transactions on Evolutionary Computation,1999,3(2),82-102.
[54]高飞,童恒庆.基于改进粒子群优化算法的混沌系统参数估计方法[J].物理学报,2006,55(2)：577-582.
[55]Salman A, Engelbrecht A and Omran M. Empirical analysis of self-adaptive differential evolution[J]. European Journal of Operational Research,2007,183:785-804.
[56]Liu B, Wang L, Jin Y H, et al. Improved particle swarm optimization combined with chaos[J]. Chaos, Solitons and Fractals,2005,25:1261-1271.
[57]Yoshida H, Kawata K, Fukuyama Y, et al. A particle swarm optimization for reactive power and votage control considering voltage stability[A]. Proceedings Intel Conf on Intelligent System Application to Power Systems[C],1999,117-121.
[58]Moody J, Darken C. Fast learning in networks of locally tuned processing units[J]. Neural Computation,1989,1(2):281-294.
[59]Chen S, Cowan C F, Grant P M. Orthogonal least squares learning algorithms for radial basis function networks[J]. IEEE Trans, On Neural Networks,1991,2(2):302-309.
[60]Kenendy J, Eberhart R C. Particle swarm optimization[A]. IEEE International Conference on Neural Networks[C],1995,1942-1948.
[61]Salman A, Ahmad I, Al-Madani S. Particle swarm optimization for task assignment problem[J]. Microprocessors and Microsystems,2002,26,363-371.
[62]Parsopoulos K E, Vrahatis M N. Recent approaches to global optimization problems through particle swarm optimization[J]. Natural Computing,2002,1,235-306.
[63]Zheng Y L, Ma L H, Zhang L Y. et al. On the convergence analysis and parameter selection in particle swarm optimization[A]. Proceedings of the Second International Conference on Machine Learning and Cybernetics[C],2003,1802-1807.
[64]Saleem.S.M. Knowledge-Based Solution to Dynamic Optimization Problems Using Cultural Algorithms[D]. PhD thesis. Wayne State University, Detroit, Michigan,2001.
[65]Shinin Zhu, Robert G. Reynolds. Fuzzy Cultural Algorithms with Evolutionary Programming [J]. Evolutionary Programming VII.1998,1447,209-218.
[66]R.L. Becerra, C.A.Coello Coello. A Cultural Algorithm with Differential Evolution to Solve Constrained Optimization Problems[J]. IBERAMIA,2004, LNAI 3315,881-890.
[67]崔红梅,朱庆保.粒子群算法的参数选择及收敛性分析[J].计算机工程与应用,2007,43(23)：89-91.
[68]王丽,王晓凯.一种非线性改变惯性权重的粒子群优化算法[J].计算机工程与应用,2003,43(4)：47-48.
[69]王启付,王战江,王收亭.一种动态改变惯性权重的粒子群优化算法[J].中国机械工程,2005,16(11)：945-948.
[70]刘建华,樊晓平,瞿志华.一种惯性权重动态调整的新型粒子群优化算法[J].计算机 工程与应用,2007,43(7)：68-70.
[71]黄海燕,顾幸生,刘漫丹.求解约束优化问题的文化算法研究[J].自动化学报,33(10)：1115-1120.
[72]Reynolds R G. An Introduction to Cultural Algorithms[A]. Proceedings of the 3th Annual Conference on Evolutionary Programming[C], San Diego, California,1994.
[73]刘漫丹.文化基因算法(Memetic Algorithm)研究进展[J].控制理论与应用,2007,26(11)：1-5.
[74]刘漫丹,齐仲纪.基于文化算法的生产过程建模方法[J].计算机与应用化学,2007,24(9)：1205-1208.
[75]齐仲纪,刘漫丹.基于文化算法的新型Elman网络的过程建模方法[J].华东理工大学学报,200834(5)：745-750.
[76]齐仲纪,刘漫丹.文化算法研究[J].计算机技术与应用,2008,18(5)：126-129.
[77]Xidong Jin, Robert G. Reynolds. Using Knowledge-Based Evolutionary Computation to Solve Nonlinear Constraint Optimization Problems:a Cultural Algorithm Approach[A]. In 1999 Congress on Evolutionary Computation[C], Washington D.C.1999,7,1672-1678.
[78]Robert G. Reynolds. An Introduction to Cultural Algorithms. Proceedings of the Third Annual Conference on Evolutionary Programming[J]. World Scientific, River Edge, New Jersey,1994,131-139.
[79]Shinin Zhu. Fuzzy Cultural Algorithms with Evolutionary Programming for Real-Valued Function Optimization[D]. PhD thesis. Wayne State University, Detroit, Michigan,1998.
[80]Chanjin Chung, Robert G. Reynolds. Knowledge-based Self-adaptation in Evolutionary Search[J]. International Journal of Pattern Recognition and Artificial Intelligence.2000, 14(1):19-33.
[81]Chanjin Chung, Robert G. Reynolds. Function Optimization Using Evolutionary Programming with Self-Adaptive Cultural Algorithms[A]. Proceedings of the First Asian-Pacific Conference on Simulated Evolution and Learning[C], Taejon, Korea,1996, 11,21-28.
[82]Elena Zannoni. Cultural Algorithms with Genetic Programming:Learning to Control the Program Evolution Process[D]. PhD thesis. Wayne State University, Detroit, Michigan. 1996.
[83]Chanjin Chung, Robert G. Culturing Evolution Strategies to Support the Exploration of Novel Environments by an Intelligent Robotic Agent[J]. Evolutionary Programming VII, 1998,14(47):219-228.
[84]Iacoban R, Robert G. Reynolds, Brewster.J. Cultural Swarms:Modeling the Impact of Culture on Social Interaction and Problem Solving[A]. Proceedings of IEEE Swarm Intelligence Symposium[C], Indianapolis, Indiana, USA,2003,205-211.
[85]王东生,曹磊.混沌、分形及其应用[M].合肥：中国科学技术大学出版社,1995.
[86]王兴元.复杂非线性系统中的混沌[M].北京：电子工业出版社,2003.
[87]韩敏.混沌时间序列预测理论与方法[M].北京：中国水利水电出版社,2007.
[88]李辉.混沌数字通信[M].北京：清华大学出版社,2006.
[89]李兵,蒋慰孙.混沌优化算法及其应用[J].控制理论与应用,1997,14(4)：613-615.
[90]赵俊,陈建军.混沌粒子群优化的模糊神经PID控制器设计[J].西安电子科技大学学报,2008,35(1)：54-59.
[2]McCulloch W S, Pitts W H. A logical calculus of the ideas immanent in nervous activity[J]. Bulletin of Mathematical Biophysics,1943, (5):115-133.
[3]Hebb D 0. The Organization of Behavior[M]. New York:Wiley,1949.
[4]Rosenblatt F. The perception:A probabilistic model for information storage and organization in the brain[J]. Psychological Review,1958, (65):386-458.
[5]Widrow B, Hoff M E. Adaptive Switching Circuits[M]. New York:IRE,1960,94-104.
[6]Minsky M, Papert S. Perceptions[M]. Cambridge:MIT Press,1969.
[7]Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagation error[J]. Nature,1986, (323):533-536.
[8]杨金城,胡春.裂解深度神经网络控制系统的研究[J].仪表及自动化,2005,20(2)：40-42.
[9]谢承泮.神经网络发展综述[J].科技情报开发与经济,2006,16(12)：148-150.
[10]黄海燕,顾幸生.基于文化算法的神经网络及其在建模中的应用[J].控制与决策,2008,23(4)：214-217.
[11]杨尔辅.工业裂解过程动力学建模与软测量技术研究[M].北京,清华大学自动化系,2001.
[12]王东生,曹磊.混沌、分形及其应用[M].合肥：中国科学技术大学出版社,1995.
[13]Coryn A L, Bailer-jones, David J C. A recurrent network for modeling dynamical system[J]. Network:Computer in Neural Systems,1998(9),531-547.
[14]Zhifeng Chen, Peide Qian. Application of PSO-RBF Neural Network in Network Intrusion Detection[J]. Third International Symposium on Intelligent Information Technology Application,2009,362-364.
[15]俞金寿.工业过程先进控制[M].北京：中国石化出版社,2002.
[16]Kennedy J, Eberhart R C. A discrete binary version of the particle swarm algorithm[A]. IEEE Service Center, Proceeding of the IEEE Conference on Systems, Man, and Cybernetics[C], Piscataway. NJ:IEEE Press,1997,4104-4109.
[17]Hashler M, Mazzini G, Lek M O, et al. Scanning the special issue on application of nonlinear dynamics to electronic and information engineering[A]. Proceedings of the IEEE[C],2002,90(5):631-640.
[18]Robinson J, Rahmat-Samii Y. Particle swarm optimization in electromagnetic [J]. IEEE Trans. On Antennas and Propagation,2004,52(2):397-407.
[19]Shi Y, Eberhart R C. Empirical study of particle swarm optimization[A]. Proceeding of the IEEE Congress on Evolutionary Computation[C], Piscataway, NJ:IEEE Press,1999, 1945-1950.
[20]Shi Y, Eberhart R C. Fuzzy adaptive particle swarm optimization[A]. The IEEE Congress on Evolutionary Computation[C], San Francisco:IEEE Press,2001,101-106.
[21]Eberhart R C, Shi Y. Tracking and optimizing dynamic systems with particle swarm[A]. The IEEE Congress on Evolutionary Computation[C], San Francisco:IEEE Press,2001, 94-100.
[22]陈贵敏,贾建援,韩琪.粒子群优化算法的惯性权重递减策略研究[J].西安交通大学学报,2006,40(1)：53-56.
[23]Eberhart R C, Shi Y. Comparing Inertia Weights and Constriction Factors in Particle Swarm Optimization[A]. Proc. CFC 2000[C], San Diego, CA,2000,84-88.
[24]莫愿斌,陈德钊,胡上序.混沌粒子群算法及其在生化过程动态优化中的应用[J].化工学报,2006,57(9)：2123-2127.
[25]Li X, Dam K H. Comparing particle swarms for tracking extreme in dynamic environments [A]. Congress on Evolutionary Computation[C],2003,1772-1779.
[26]Parrott D, Li X. A particle swarm model for tracking multiple peeks in a dynamic environment using speciation[A]. Congress on Evolutionary Computation[C],2004, 98-103.
[27]Peer E, van den Bergh F, Engelbrecht A. Using Neighborhoods with the Guaranteed Convergence PSO[J]. Swarm Intelligence Symposium. Piscataway, New Jersey, USA, IEEE Service Center,2003,235-242.
[28]van den Bergh F. An Analysis of Particle Swarm Optimizers[D], PhD Thesis. Department of Computer Science, University of Pretoria, South Africa,2002.
[29]van den Bergh F, Engelbrecht A. A new locally convergent particle swarm optimizer[A]. Proceedings of the IEEE Conference on Systems[C], Man, Cybernetics, Hammamet, Tunisia,2002.
[30]Clerc M. Particle Swarm Optimization[M]. London:ISTE Publishing Company,2006.
[31]Lovbjerg M, Rasmussen T K, et al. Hybrid particle swarm optimization with breeding and subpopulations[A]. IEEE International Conference on Evolutionary Computation[C], SanDieego,2000.
[32]Higashi N, Iba H. Particle swarm optimization with Gaussian mutation[J]. Proc of the IEEE Swarm Intelligence Symposium. Indianapolis:IEEE Inc,2003,72-79.
[33]高鹰,谢胜利.基于模拟退火的粒子群优化算法[J].计算机工程与应用,2004,1：47-50.
[34]Meng H J, Zhang P, Wu R Y. A hybrid particle swarm algorithm with embedded chaotic search[A]. IEEE Conference on Cybernetics and Intelligent Systems[C],2004,367-371.
[35]Liu L J, Cai Z X, Chen H. Immunity clone algorithm with particle swarm evolution[J]. Cent South University Technology,2006,1,703-706.
[36]高鹰.谢胜利.免疫粒子群优化算法[J].计算机工程与应用,2004,41(6)：4-6.
[37]Holden N, Freitas A. A hybrid particle swarm/ant colony algorithm for the classification of hierarchical biological data[J]. Swarm Intelligence Symposium,2005. Proceedings 2005 IEEE Volume, Issue,8-10 June 2005,100-107.
[38]李炳宇,萧蕴诗,吴启迪.一种基于粒子群算法求解优化问题的混合算法[J].控制与决策,2004,19(7)：804-806.
[39]Mikki S, Kishk A. Investigation of the quantum particle swarm optimization technique for electromagnetic applications[J]. Antennas and Propagation Society International Symposium,2005 IEEE Volume 2A,3-8 July 2005,45-48.
[40]Sun J, Feng B, Xu W. Particle swarm optimization with particles having quantum behavior [C]. IEEE Proc of Congress on Evolutionary Computation[A],2004.
[41]Van den Bergh F, Engelbrecht A. Training product unit networks using cooperative particle swarm optimizers[A]. Proc of the Third Genetic and Evolutionary Computation Conference[C], San Francisco, USA,2001.
[42]van den Bergh F, Engelbrecht A. Cooperative learning in neural networks using particle swarm optimizers[J]. South African Computation,2000,11(26):84-90.
[43]Potter M A, de Jong K A. A cooperative evolutionary approach to function optimization[A]. The Third Parallel Problem Solving From Nature[C], Berlin:Springer-Verlag,1994, 249-257.
[44]Caponetto R, Fortuna L, Fazzino S, et al. Chaotic Sequences to Improve the Performance of Evolutionary Algorithms[J]. IEEE Trans on Evolut Comput,2003,7(3):289-304.
[45]Al-kazemi B, Moan C K. Training feed forward neural networks using multi-phase particle swarm optimization[A]. Proceedings of the 9th International Conference on Neural Information Processing[C],2002,5:2615-2619.
[46]Bliss L. Selecting artificial neural net work inputs using particle swarm optimization[J]. Dissertation Pace University, USA,2003.
[47]Fukuyama Y. State estimation and optimal setting of voltage regulator in distribution systems[J]. IEEE Power Engineering Society Winter Meeting,2001,930-935.
[48]Zheng Y, Ma L, et al. Robust PID controller design using particle swarm optimizer[J]. Proceedings of IEEE International Symposium on Intelligence Control,2003,974-979.
[49]Zhang Xiaoming, Ning Guangliang. An improved RBF network on-line learning algorithm[J]. Second International Symposium on Information Science and Engineering, 2009,547-552.
[50]Zeng Qingwei, Xu Zhihai, Wu Jian. Prediction of Electricity Consumption Based on Genetic Algorithm-RBF Neural Network[J]. IEEE,2010,339-342.
[51]黄曦,邹安全.基于BP神经网络的企业财务危机组合预警研究[J].经济与管理研究.2009,5：87-91.
[52]黄继鸿,雷战波,凌超.经济预警方法研究综述[J].系统工程,2003,21(2)：64-70.
[53]X Yao, Y Liu and G Lin. Evolutionary programming made faster[J]. IEEE Transactions on Evolutionary Computation,1999,3(2),82-102.
[54]高飞,童恒庆.基于改进粒子群优化算法的混沌系统参数估计方法[J].物理学报,2006,55(2)：577-582.
[55]Salman A, Engelbrecht A and Omran M. Empirical analysis of self-adaptive differential evolution[J]. European Journal of Operational Research,2007,183:785-804.
[56]Liu B, Wang L, Jin Y H, et al. Improved particle swarm optimization combined with chaos[J]. Chaos, Solitons and Fractals,2005,25:1261-1271.
[57]Yoshida H, Kawata K, Fukuyama Y, et al. A particle swarm optimization for reactive power and votage control considering voltage stability[A]. Proceedings Intel Conf on Intelligent System Application to Power Systems[C],1999,117-121.
[58]Moody J, Darken C. Fast learning in networks of locally tuned processing units[J]. Neural Computation,1989,1(2):281-294.
[59]Chen S, Cowan C F, Grant P M. Orthogonal least squares learning algorithms for radial basis function networks[J]. IEEE Trans, On Neural Networks,1991,2(2):302-309.
[60]Kenendy J, Eberhart R C. Particle swarm optimization[A]. IEEE International Conference on Neural Networks[C],1995,1942-1948.
[61]Salman A, Ahmad I, Al-Madani S. Particle swarm optimization for task assignment problem[J]. Microprocessors and Microsystems,2002,26,363-371.
[62]Parsopoulos K E, Vrahatis M N. Recent approaches to global optimization problems through particle swarm optimization[J]. Natural Computing,2002,1,235-306.
[63]Zheng Y L, Ma L H, Zhang L Y. et al. On the convergence analysis and parameter selection in particle swarm optimization[A]. Proceedings of the Second International Conference on Machine Learning and Cybernetics[C],2003,1802-1807.
[64]Saleem.S.M. Knowledge-Based Solution to Dynamic Optimization Problems Using Cultural Algorithms[D]. PhD thesis. Wayne State University, Detroit, Michigan,2001.
[65]Shinin Zhu, Robert G. Reynolds. Fuzzy Cultural Algorithms with Evolutionary Programming [J]. Evolutionary Programming VII.1998,1447,209-218.
[66]R.L. Becerra, C.A.Coello Coello. A Cultural Algorithm with Differential Evolution to Solve Constrained Optimization Problems[J]. IBERAMIA,2004, LNAI 3315,881-890.
[67]崔红梅,朱庆保.粒子群算法的参数选择及收敛性分析[J].计算机工程与应用,2007,43(23)：89-91.
[68]王丽,王晓凯.一种非线性改变惯性权重的粒子群优化算法[J].计算机工程与应用,2003,43(4)：47-48.
[69]王启付,王战江,王收亭.一种动态改变惯性权重的粒子群优化算法[J].中国机械工程,2005,16(11)：945-948.
[70]刘建华,樊晓平,瞿志华.一种惯性权重动态调整的新型粒子群优化算法[J].计算机 工程与应用,2007,43(7)：68-70.
[71]黄海燕,顾幸生,刘漫丹.求解约束优化问题的文化算法研究[J].自动化学报,33(10)：1115-1120.
[72]Reynolds R G. An Introduction to Cultural Algorithms[A]. Proceedings of the 3th Annual Conference on Evolutionary Programming[C], San Diego, California,1994.
[73]刘漫丹.文化基因算法(Memetic Algorithm)研究进展[J].控制理论与应用,2007,26(11)：1-5.
[74]刘漫丹,齐仲纪.基于文化算法的生产过程建模方法[J].计算机与应用化学,2007,24(9)：1205-1208.
[75]齐仲纪,刘漫丹.基于文化算法的新型Elman网络的过程建模方法[J].华东理工大学学报,200834(5)：745-750.
[76]齐仲纪,刘漫丹.文化算法研究[J].计算机技术与应用,2008,18(5)：126-129.
[77]Xidong Jin, Robert G. Reynolds. Using Knowledge-Based Evolutionary Computation to Solve Nonlinear Constraint Optimization Problems:a Cultural Algorithm Approach[A]. In 1999 Congress on Evolutionary Computation[C], Washington D.C.1999,7,1672-1678.
[78]Robert G. Reynolds. An Introduction to Cultural Algorithms. Proceedings of the Third Annual Conference on Evolutionary Programming[J]. World Scientific, River Edge, New Jersey,1994,131-139.
[79]Shinin Zhu. Fuzzy Cultural Algorithms with Evolutionary Programming for Real-Valued Function Optimization[D]. PhD thesis. Wayne State University, Detroit, Michigan,1998.
[80]Chanjin Chung, Robert G. Reynolds. Knowledge-based Self-adaptation in Evolutionary Search[J]. International Journal of Pattern Recognition and Artificial Intelligence.2000, 14(1):19-33.
[81]Chanjin Chung, Robert G. Reynolds. Function Optimization Using Evolutionary Programming with Self-Adaptive Cultural Algorithms[A]. Proceedings of the First Asian-Pacific Conference on Simulated Evolution and Learning[C], Taejon, Korea,1996, 11,21-28.
[82]Elena Zannoni. Cultural Algorithms with Genetic Programming:Learning to Control the Program Evolution Process[D]. PhD thesis. Wayne State University, Detroit, Michigan. 1996.
[83]Chanjin Chung, Robert G. Culturing Evolution Strategies to Support the Exploration of Novel Environments by an Intelligent Robotic Agent[J]. Evolutionary Programming VII, 1998,14(47):219-228.
[84]Iacoban R, Robert G. Reynolds, Brewster.J. Cultural Swarms:Modeling the Impact of Culture on Social Interaction and Problem Solving[A]. Proceedings of IEEE Swarm Intelligence Symposium[C], Indianapolis, Indiana, USA,2003,205-211.
[85]王东生,曹磊.混沌、分形及其应用[M].合肥：中国科学技术大学出版社,1995.
[86]王兴元.复杂非线性系统中的混沌[M].北京：电子工业出版社,2003.
[87]韩敏.混沌时间序列预测理论与方法[M].北京：中国水利水电出版社,2007.
[88]李辉.混沌数字通信[M].北京：清华大学出版社,2006.
[89]李兵,蒋慰孙.混沌优化算法及其应用[J].控制理论与应用,1997,14(4)：613-615.
[90]赵俊,陈建军.混沌粒子群优化的模糊神经PID控制器设计[J].西安电子科技大学学报,2008,35(1)：54-59.