电梯交通流分析及电梯群控策略研究
|
摘要
在经济不断发展、科学技术日新月异的今天,电梯作为建筑物内的主要运输工具,已成为我们日常生活中一个不可缺少的重要组成部分。随着建筑物规模的扩大及电梯部数的增加,电梯客流呈现新的变化,随之对电梯群控系统的性能提出了更高的要求。因此,一方面需要对不断发展变化的电梯交通流进行调查研究,分析其规律特征,另一方面要求研究处理电梯交通流的群控策略。本文针对电梯群控系统中的一些关键问题进行了研究,其主要成果如下:
电梯交通流产生的理论和方法是深入研究电梯群控策略必须解决的关键问题。为了描述乘客分布,首次提出了电梯乘客起始-目标楼层(Origin-Destination, O-D)矩阵的概念。以交通流采集数据为基础,以热力学熵、信息熵理论为指导,建立极大熵模型,用以推算乘客O-D矩阵。极大熵模型的求解本质上是一个优化问题,首先提出了极大熵模型的拉格朗日乘子求解方法,该方法计算结果从实数解到整数解的推定中采用启发式搜索,得到的是次优解。为了对求解结果进行改进,经对遗传算法机制的深入思考,提出了一种启发式遗传算法求解方法,可以直接求得极大熵模型的最优解。基于乘客O-D矩阵,利用蒙特卡罗采样法进行客流仿真。随着交通测定的持续执行,利用极大熵模型可以产生持续的O-D交通流,建立乘客O-D交通流数据库,为群控系统的仿真试验奠定了数据基础。
电梯交通流预测是实现电梯交通模式识别和电梯群控系统的重要组成部分。针对该问题,提出了将历史数据和最新的客流数据相结合,利用小波支持向量机(WSVM)建立了电梯交通流预测模型,预测模型采用SMO算法进行训练。通过与自回归滑动平均(ARMA)模型、BP神经网络、高斯核支持向量机(GSVM)三种方法预测结果的比较,说明了WSVM提高了预测准确性和预测精度。
电梯交通模式识别是电梯群控系统的重要功能模块。为此,提出了基于高斯核粒子群K均值聚类算法的电梯交通模式识别方法。该方法以粒子群优化算法为框架,以适应度函数设计为核心。为了增强聚类算法的鲁棒性,采用高斯核距离替换欧氏距离设计适应度函数,利用M-估计的影响函数分析了聚类算法的鲁棒性。仿真实验表明该方法不需要任何先验知识就能达到准确分类的目的。粒子群K均值聚类算法需要调整的参数少,易于实现,计算速度快,且具有稳定的收敛特征,能很好满足群控系统实时性的要求。可作为电梯群控系统的一个模块,辅助电梯群控系统做出决策,以期提高电梯群控系统在各种交通状况下的服务性能。
针对强化学习应用于电梯调度时存在学习速度缓慢问题,本文采用CMAC网络建立基于先验知识的电梯群强化学习系统,一个方面是利用先验知识缩小强化学习算法要探索的状态空间,加快强化学习算法的收敛速度,另一个方面利用CMAC神经网络具有较好的在线增量学习能力以及收敛性快、不存在局部极小点的特点,从这两个方面对电梯群控调度进行优化,试验结果表明其有效性。
建立了电梯群控仿真环境,包括电梯群控仿真试验台(硬件设计)和电梯群控仿真系统(软件设计)。电梯群控试验台符合实际电梯群控系统的结构,可以满足电梯群控系统研究的需要。而电梯群控仿真系统为电梯群控策略的研究提供了仿真平台。在该仿真平台上进行了群控策略研究,结果表明基于交通模式识别,实现了各不同交通模式之间的合理调度。
With the development of economy and the advance of science and technology, elevators as the main vertical transportation tool in the buildings have been an indispensable part in our daily life. As the size of building enlarging and the number of installed elevators increasing, elevator traffic flow takes on new changes and then the high quality of elevator group control system (EGCS) is required. Hence, on the one hand, elevator traffic flow need to be surveyed to analyze the pattern, on the other hand, it needs studying the group control strategy to handle the elevator traffic flow. The dissertation investigates some key technology of EGCS, and the main contribution is as follows:
The theory and method of elevator traffic flow generation is a key problem to further study the elevator group control strategies. In order to describe the passenger distribution, the concept of the elevator passenger origin-destination (O-D) matrix is first put forward. Based on t elevator traffic data collected, in terms of the theory of thermodynamics entropy and information entropy, the maximizing entropy model is constructed to estimate the elevator passenger O-D matrix. The model is solved using Lagrange multiplier method and heuristic genetic algorithm respectively. The computational example shows that GA is significantly superior to the Lagrange multiplier method. Based on the passenger O-D matrix estimated, the Mento Carlo sampling method is utilized to simulation traffic flow. With the traffic measure executed continuously, the O-D flow is generated using the model and set up the O-D database. Elevator group simulation test is executed based on the O-D database.
Elevator traffic prediction is the basis of elevator traffic pattern recognition and the important component of EGCS. To this question, wavelet support vector machines (WSVM) is presented to construct elevator traffic flow prediction model by combining the historical data and recent passenger data. The prediction model is trained by SMO algorithm. The simulation showed that the prediction result not only retains the tendency of historical data but also tracking the passenger flow change in time. Through the comparison of prediction results by BP neural network, ARMA and GSVM methods, it is showed that the WSVM can increase the prediction accuracy and preciseness.
Elevator traffic pattern recognition is the important functional module. A new method of elevator traffic pattern recognition based on Gaussian kernel particle swarm optimization K-means clustering algorithm (GKPSOKCA) is proposed. In order to enhance the robustness of the clustering algorithm, fitness function is devised by Gaussian kernel metric replacing the Euclidean distance. The robustness of the clustering algorithm is analyzed using the influence function of M-estimator. Simulation shows that the GKPSOKCA can classify elevator traffic patterns precisely without any prior knowledge. Compared with IEKCA, GKPSOKCA needs less parameters to determine, can be easily implemented, and has stable convergence characteristic with good computational efficiency. Elevator traffic pattern recognition with GKPSOKCA can be used as a module in EGCS and assist EGCS in making decisions in order that EGCS improves the service performance under different traffic situations.
Reinforcement learning system based on prior knowledge applying to elevator group control dispatching is significantly enhancing the convergent speed of reinforcement learning. The dissertation uses the CMAC network to build the elevator group reinforcement learning system. On the one hand, addition of prior knowledge can reduce the state space explored by reinforcement learning algorithm, and enhance the convergent speed of reinforcement learning. On the other hand, CMAC network has the good online incremental learning capability and good convergent speed, and hasn’t local minima. From the two sides, the elevator group dispatching is optimized. The simulation result verified its effectiveness.
Lastly, the elevator group control simulation environment is designed, including elevator group control test-bed and elevator group control simulation system. Elevator group control test-bed conforms to the real EGCS structure and can satisfy the need for study on the EGCS. Elevator group control simulation system provides the simulation platform for the study on group control strategy. Based on the simulation platform, simulation study of group control strategy is executed and the results showed that reasonable dispatching is implemented among different traffic flow pattern based on traffic pattern recognition.
电梯交通流产生的理论和方法是深入研究电梯群控策略必须解决的关键问题。为了描述乘客分布,首次提出了电梯乘客起始-目标楼层(Origin-Destination, O-D)矩阵的概念。以交通流采集数据为基础,以热力学熵、信息熵理论为指导,建立极大熵模型,用以推算乘客O-D矩阵。极大熵模型的求解本质上是一个优化问题,首先提出了极大熵模型的拉格朗日乘子求解方法,该方法计算结果从实数解到整数解的推定中采用启发式搜索,得到的是次优解。为了对求解结果进行改进,经对遗传算法机制的深入思考,提出了一种启发式遗传算法求解方法,可以直接求得极大熵模型的最优解。基于乘客O-D矩阵,利用蒙特卡罗采样法进行客流仿真。随着交通测定的持续执行,利用极大熵模型可以产生持续的O-D交通流,建立乘客O-D交通流数据库,为群控系统的仿真试验奠定了数据基础。
电梯交通流预测是实现电梯交通模式识别和电梯群控系统的重要组成部分。针对该问题,提出了将历史数据和最新的客流数据相结合,利用小波支持向量机(WSVM)建立了电梯交通流预测模型,预测模型采用SMO算法进行训练。通过与自回归滑动平均(ARMA)模型、BP神经网络、高斯核支持向量机(GSVM)三种方法预测结果的比较,说明了WSVM提高了预测准确性和预测精度。
电梯交通模式识别是电梯群控系统的重要功能模块。为此,提出了基于高斯核粒子群K均值聚类算法的电梯交通模式识别方法。该方法以粒子群优化算法为框架,以适应度函数设计为核心。为了增强聚类算法的鲁棒性,采用高斯核距离替换欧氏距离设计适应度函数,利用M-估计的影响函数分析了聚类算法的鲁棒性。仿真实验表明该方法不需要任何先验知识就能达到准确分类的目的。粒子群K均值聚类算法需要调整的参数少,易于实现,计算速度快,且具有稳定的收敛特征,能很好满足群控系统实时性的要求。可作为电梯群控系统的一个模块,辅助电梯群控系统做出决策,以期提高电梯群控系统在各种交通状况下的服务性能。
针对强化学习应用于电梯调度时存在学习速度缓慢问题,本文采用CMAC网络建立基于先验知识的电梯群强化学习系统,一个方面是利用先验知识缩小强化学习算法要探索的状态空间,加快强化学习算法的收敛速度,另一个方面利用CMAC神经网络具有较好的在线增量学习能力以及收敛性快、不存在局部极小点的特点,从这两个方面对电梯群控调度进行优化,试验结果表明其有效性。
建立了电梯群控仿真环境,包括电梯群控仿真试验台(硬件设计)和电梯群控仿真系统(软件设计)。电梯群控试验台符合实际电梯群控系统的结构,可以满足电梯群控系统研究的需要。而电梯群控仿真系统为电梯群控策略的研究提供了仿真平台。在该仿真平台上进行了群控策略研究,结果表明基于交通模式识别,实现了各不同交通模式之间的合理调度。
With the development of economy and the advance of science and technology, elevators as the main vertical transportation tool in the buildings have been an indispensable part in our daily life. As the size of building enlarging and the number of installed elevators increasing, elevator traffic flow takes on new changes and then the high quality of elevator group control system (EGCS) is required. Hence, on the one hand, elevator traffic flow need to be surveyed to analyze the pattern, on the other hand, it needs studying the group control strategy to handle the elevator traffic flow. The dissertation investigates some key technology of EGCS, and the main contribution is as follows:
The theory and method of elevator traffic flow generation is a key problem to further study the elevator group control strategies. In order to describe the passenger distribution, the concept of the elevator passenger origin-destination (O-D) matrix is first put forward. Based on t elevator traffic data collected, in terms of the theory of thermodynamics entropy and information entropy, the maximizing entropy model is constructed to estimate the elevator passenger O-D matrix. The model is solved using Lagrange multiplier method and heuristic genetic algorithm respectively. The computational example shows that GA is significantly superior to the Lagrange multiplier method. Based on the passenger O-D matrix estimated, the Mento Carlo sampling method is utilized to simulation traffic flow. With the traffic measure executed continuously, the O-D flow is generated using the model and set up the O-D database. Elevator group simulation test is executed based on the O-D database.
Elevator traffic prediction is the basis of elevator traffic pattern recognition and the important component of EGCS. To this question, wavelet support vector machines (WSVM) is presented to construct elevator traffic flow prediction model by combining the historical data and recent passenger data. The prediction model is trained by SMO algorithm. The simulation showed that the prediction result not only retains the tendency of historical data but also tracking the passenger flow change in time. Through the comparison of prediction results by BP neural network, ARMA and GSVM methods, it is showed that the WSVM can increase the prediction accuracy and preciseness.
Elevator traffic pattern recognition is the important functional module. A new method of elevator traffic pattern recognition based on Gaussian kernel particle swarm optimization K-means clustering algorithm (GKPSOKCA) is proposed. In order to enhance the robustness of the clustering algorithm, fitness function is devised by Gaussian kernel metric replacing the Euclidean distance. The robustness of the clustering algorithm is analyzed using the influence function of M-estimator. Simulation shows that the GKPSOKCA can classify elevator traffic patterns precisely without any prior knowledge. Compared with IEKCA, GKPSOKCA needs less parameters to determine, can be easily implemented, and has stable convergence characteristic with good computational efficiency. Elevator traffic pattern recognition with GKPSOKCA can be used as a module in EGCS and assist EGCS in making decisions in order that EGCS improves the service performance under different traffic situations.
Reinforcement learning system based on prior knowledge applying to elevator group control dispatching is significantly enhancing the convergent speed of reinforcement learning. The dissertation uses the CMAC network to build the elevator group reinforcement learning system. On the one hand, addition of prior knowledge can reduce the state space explored by reinforcement learning algorithm, and enhance the convergent speed of reinforcement learning. On the other hand, CMAC network has the good online incremental learning capability and good convergent speed, and hasn’t local minima. From the two sides, the elevator group dispatching is optimized. The simulation result verified its effectiveness.
Lastly, the elevator group control simulation environment is designed, including elevator group control test-bed and elevator group control simulation system. Elevator group control test-bed conforms to the real EGCS structure and can satisfy the need for study on the EGCS. Elevator group control simulation system provides the simulation platform for the study on group control strategy. Based on the simulation platform, simulation study of group control strategy is executed and the results showed that reasonable dispatching is implemented among different traffic flow pattern based on traffic pattern recognition.
引文
[1]朱昌明.电梯的技术发展趋势[J].工程机械与维修, 2001, 2: 38-39.
[2] Johnston B. Project spotlight: Taipei 101: The experience[J]. Elevator World, 2006, 54(6): 126-132.
[3]刚宪约.曳引电梯系统动态理论及动力学参数优化方法研究[博士论文].杭州:浙江大学, 2005.
[4] Barney G C, Dos Santos S M. Elevator Traffic Analysis, Design and Control(2nd) [M]. London: IEE Peter Peregrinus, 1985.
[5]傅武军.超高速电梯轿厢横向振动控制研究[博士论文].上海:上海交通大学, 2007.
[6] Barney G C. Elevator traffic handbook: Theory and Practice [M]. London; New York: Spon Press, 2003.
[7]三菱电气AI2200电梯监控系统介绍, 2007. In: http:// www.mitsubishi -elevator. com/innovations/control_system_b.html#pagetop.
[8] Peters R D. Vertical transportation planning in buildings[Dissertation]. West London: Brunel University, 1998.
[9] So A, Cheng G, Suen W and Leung A. Elevator performance Evaluation in two numbers[J]. Elevator World, 2005, 53(1): 102-105.
[10] Courtney R G., Davidson P J. A survey of passenger traffic in two buildings[R]. Watford: Building Research Establishment, 1994.
[11] Peters R D, Haddon J. Lift Passenger Traffic Patterns: Applications, Current Knowledge and Measurement[J]. Elevator World, 2000, 48(9): 87-88, 90, 92, 94.
[12] Elevate软件官方网站, 2008. In:http://elevateontheweb.peters-research.com
[13] Barney G C. Traffic design benchmarks standard templates[J]. Elevator World, 2005, 53(2): 79-82.
[14]李中华,朱燕飞,李春华,毛宗源.基于人工免疫聚类算法的电梯交通流分析[J].华南理工大学学报(自然科学版), 2003, 31(12): 26-29.
[15] Powell B A. Important issues in up-peak traffic handling[A]. In: Proceedings of the 1992 International Conferences on Elevator Technologies[C]. Amsterdam, 1992:207-218.
[16] So A T P, Yu J K L. Dynamic zoning based supervisory control for elevators[A]. In: Proceedings of the 1999 IEEE international conference on control applications[C]. Hawai’i, 1999: 1591-1596.
[17] So A T P, Chan W L. Comprehensive dynamic zoning algorithms[J]. Elevator World, 1997, 45(9): 99-103.
[18] So A T P, Chan W L. Intelligent supervisory control for lifts: dynamic zoning[J]. Building Serv Eng Res Technol., 2001, 22(1): 14-33.
[19]宗群,罗欣宇,王振世.电梯上高峰动态规划分区控制方法的研究[J].控制与决策, 2002, 17(增刊): 781-784.
[20]宗群,王振世,尚晓光.电梯上高峰模式下动态分区算法的研究[J].系统工程与电子技术, 2001, 23(12): 97-100.
[21]李中华,毛宗源,郑日荣,等.基于人工免疫算法的电梯交通动态分区的优化[J].华南理工大学学报, 2004, 32(10): 46-50.
[22]郑延军,张惠侨,叶庆泰,等.电梯动态分区算法及其遗传算法研究[J].计算机工程与应用, 2001, 37(22): 142-144, 148.
[23]杨祯山,邵诚.电梯群控技术的现状与发展方向[J].控制与决策, 2005, 20(12): 1321-1331.
[24] Crites R H, Barto A G. Elevator group control using multiple reinforcement learning agents[J]. Machine learning, 1998, 33(2): 235-262.
[25] Ujihara H, Tsuji S. The revolutionary AI-2100 elevator group control system and the new intelligent option series[J]. Mitsubishi Electric Advance, 1998, 12(45): 5-8.
[26]李东,王伟,邵诚.电梯群控智能系统与智能控制技术[J].控制与决策, 2001, 16(5): 513-517.
[27]宗群,曹燕飞,曲照伟.电梯群控系统中智能控制方法[J].电气传动, 1998, (3): 25-28, 34.
[28]张筠莉,杨祯山.论人工智能技术在智能大厦电梯交通控制中的应用[J].城市智能建筑系统, 2001(6): 42-48.
[29] Umeda Y, Uetani K, Ujihara H, et al. Fuzzy theory and intelligent options[J]. Elevator World, 1989, 37(7): 86-91.
[30] Kim C B, Seong K A, Lee-Kwang H. Design and Implementation of a Fuzzy Elevator Group Control System[J]. IEEE Transactions on Systems, Man andCybernetics-part A: Systems and Humans, 1998, 28(3): 277-287.
[31] Amano M, Yamazaki M, Ikejima H. The latest elevator group supervisory control system[A]. In: ed. Barney G C, Elevator Technology 6[C]. London, 1995: 88-95.
[32] Kubo S, Nakai S, et al. Elevator group control system with a fuzzy neural network model[A]. In: ed. Barney G C, Elevator Technology 6[C]. London, 1995: 11-20.
[33] Fujino A, Tobita T, Segawa K, et al. An Elevator Group Control System with Floor-Attribute Control Method and System Optimization Using Genetic Algorithms[J]. IEEE Transactions on Industrial Electronics, 1997, 44(4): 546-552.
[34] Tobita T, Fujino A, Segawa K, et al. A parameter tuning method using genetic algorithms for an elevator group control system[A]. In: Proceedings of the 1996 IEEE IECON 22nd International Conference on Industrial Electronics, Control, and Instrumentation[C]. Taipei, 1996: 823-828.
[35] Fujino A, Tobita, T, Yoneda K. An online tuning method for multiobjective control of elevator group[A]. In: Proceedings of the 1992 International Conference on Industrial Electronics, Control, Instrumentation, and Automation,‘Power Electronics and Motion Control’[C]. San Diego, CA, USA, 1992 : 795–800.
[36] Tapio Yyni, Jari Ylinen. Evolutionary bi-objective optimization in the elevator car routing problem[J]. European Journal of Operational Research, 2006, 169(3): 960-977.
[37] Tapio Yyni, Jari Ylinen. Genetic algorithm in elevator car routing problem[A]. In: Proceedings of the Genetic Evolutionary Computation Conference 2001[C]. San Francisco, 2001: 1413-1422.
[38]万健如,李保海.群控电梯改进型遗传算法最佳派梯方法[J].起重运输机械, 2005, (4): 50-54.
[39] Cortes P, Larraneta J, Onieva L. A Genetic Algorithm for Controlling Elevator Group Systems[C]. Lecture Notes in Computer Science(LNCS 2687). Berlin: Springer-Verlag, 2003: 313-320.
[40] Kim J H, Moon B R. Adaptive Elevator Group Control with Cameras[J]. IEEE Transactions on Industrial Electronics, 2001, 48(2):377-382.
[41] Takahashi S, Kita H, Suzuki H, et al. Simulation-based Optimization of a Controller for Multi-car Elevators Using a Genetic Algorithm for Noisy Fitness Function[A]. In: The 2003 congress on evolutionary computation-CEC 2003[C]. Canberra, Australia,2003, vol(3): 1582-1587.
[42] Beielstein T, Ewald C P, Markon S. Optimal Elevator Group Control by Evolution Strategies[C]. GECCO 2003, LNCS 2724: 963-1974.
[43] Muna Hamdi, Mulvaney D J. Priorised A* search in real-time elevator dispatching[J]. Control Engineering Practice, 2007, 15: 219-230.
[44]高阳,陈世福,陆鑫.强化学习研究综述[J].自动化学报, 2004, 30(1): 87-100.
[45]李伟,何雪松,叶庆泰,等.基于先验知识的强化学习系统[J].上海交通大学学报, 2004, 38(8): 1362-1365.
[46] Powell B A, Stanley J, et al. Elevator Dispatching Employing Hall Call Assignment Based on Fuzzy Response Time Logic[P]. United States: No.5668356, 1997.9.
[47] Whitehall B L, Sirag D J, et al. Elevator Control Neural Network[P]. United States: No.5672853, 1997.9.
[48]上海三菱电梯有限公司群控技术介绍,2007. In: http:// www.smec-cn.com/ technology4.asp
[49] Miconic 10TM控制系统介绍,迅达电梯有限公司,2007. In: http://www. schindler.com/group_index/group_tech/group_tech_dc.htm
[50] Siikonen M L. Elevator Group Control with Artificial Intelligence[R]. Research Reports, Helsinki University of Technology Systems Analysis Lab, 1997.
[51]华升富士达电梯有限公司电梯群管理控制系统介绍,2007. In:http://www. fujitec.com.cn/qglkzxt.htm
[52]林勇,柴远利,黄永宣.基于广义最小二乘模型的动态交通OD矩阵估计[J].系统工程理论与实践, 2004, 24(1): 136-144.
[53] Zong Q, Shang X G, Yue Y J. Simulating traffic flow generator based on elevator traffic probability simulation model[J]. Elevator World, 2004, 52(4): 130-133.
[54]郑延军,张惠侨,叶庆泰,等.电梯群控系统客流分析与仿真[J].计算机工程与应用, 2001,37(22): 139-141.
[55]王炜,邓卫,杨琪,等.公路网络规划建设与管理方法(第二版)[M].北京:科学出版社, 2006.
[56]段进宇,缪立新,江见鲸.由路段交通流量反估出行OD矩阵技术的应用[J].清华大学学报(自然科学版), 2000, 40(6): 123-126.
[57]陈森发,周振国,于栋华.一种动态OD矩阵估计算法的理论及应用[J].东南大学学报,自然科学版, 2003, 33(1): 106-110.
[58] Fisk C S. On combining maximum entropy trip matrix estimation with user optimal assignment[J]. Transportation Research, 1988, 22B: 66-79.
[59] Wong S C, Tong C O. Estimation of time-dependent origin-destination matrices for transit networks[J]. Transportation Research B, 1998, 32(1): 35-48.
[60] Van Zuylen H J, Willumsen L G. The most likely trip matrix estimated from traffic counts[J]. Transportation Research, 1980, 14B: 281-293.
[61] Bell M G H. The real time estimation of origin-destination flows in the presence of platoon dispersion[J]. Transportation Research, 1991, 25B: 115-125.
[62] Nauyen S. Estimating origin-destination matrix from observed flows[A]. In: M. Florian (Ed.), Transportation Planning Models[C]. Amsterdam: Elsevier Science Publishers, 1984: 363-380.
[63] Watling D P. Maximum likelihood estimation of an origin-destination matrix from a partial registration plate survey[J]. Transportation Research, 1994, 28: 289-314.
[64]丁以中.贝叶斯-交通流均衡模型:一种由交通量观测估计O-D流的有效方法[J].系统工程理论与实践, 1996, 16(6): 50-57.
[65]孙光辉.信息熵与不确定性[J].青岛大学学报, 2000, 13(3): 50-51.
[66]孟庆生.关于Shannon熵的本质及其应用[M].北京:气象出版社, 1988.
[67] Chapman T G. Entropy as a measure of hydrologic data uncertainty and model performance[J]. Journal of Hydrology, 1986, 85: 111-126.
[68]姜丹.信息论与编码[M].合肥:中国科技大学出版社, 2001: 18-22, 102-105.
[69] Schneider M H, Zenios S A. A comparative study of algorithms for matrix balancing[J]. Operations Research, 1990, 38(3): 439-455.
[70]姚新,陈国良,徐惠敏,等.进化算法研究进展[J].计算机学报,1995,18(9): 694-706.
[71] Vignaux G. A, Michalewicz Z A. Genetic Algorithm for the Linear Transportation Problem[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1991, 21(2): 445-452.
[72]上海三菱电梯公司群控技术介绍. In: http://www.smec-cn.com/ technology4.asp.
[73] Thangabelu, Kandasamy. Optimized“up-peak”elevator channeling system with predicted traffic volume equalized sector assignments[P]. United States: No.4846311, 1989.
[74] Kameli, Nader. Predictor Elevator for Traffic During Peak Conditions[P]. UnitedStates: No.5276295, 1994.
[75]宗群,岳有军.电梯群控系统交通流的预测方法[J].系统工程与电子技术, 2001, 23(7): 103-105.
[76] Zong Q, Yue Y, Cao Y, et al. Application of Intelligence Forecasting Method in Traffic Analysis of EGCS[J]. Transactions of Tianjin University, 6(1), 2000: 18-21.
[77]宗群,孙志明,童玲.一种电梯交通流多模式预测方法的研究[J].信息与控制, 2006, 35(1): 93-102.
[78]黄敏,崔宝同,顾树生.基于小波神经网络的电梯交通流预测[J].控制与决策, 2006, 21(5): 589-592.
[79] Wan J, Jin X, Liu Y, et al. Elevator traffic-flow prediction based on wavelet network. Elevator World, 2007, 55(12): 132-137.
[80] Li X, Tong L, Zong Q. ARMA model for elevator traffic flow forecasting[J]. Elevator World, 53(8), 2005:83-87.
[81] Vapnik V. The Nature of Statistical Learning Theory[M]. New York: Springer, 1995.
[82] Vapnik V. Statistical Learning Theory[M]. New York: Wiley, 1998.
[83]张莉,周伟达,焦李成.尺度核函数支撑矢量机[J].电子学报, 2002, 30(4): 527-529.
[84] Zhang Li, Zhou Weida, Jiao Licheng. Wavelet Support Vector Machine[J]. IEEE Transactions on Systems, Man, and Cybernetics-Part B: Cybernetics, 2004, 34(1): 34-39.
[85] Müller K R, Smola A J, R?tsch G, et al. Predicting Time Series with Support Vector Machines[A]. In: Advances in Kernel Methods-Support Vector learning[C]. Cambridge, MA: MIT Press, 1999: 243-254.
[86]李元诚,李波,方廷健.基于小波支持向量机的非线性组合预测方法研究[J].信息与控制, 2004, 33(3): 303-306, 324.
[87] Scholkof B, Smola A. Learning with kernels: support vector machines, Regularization, Optimization, and Beyond [M]. Cambridge: MIT Press, 2002.
[88] Smola A, Scholkof B. A tutorial on support vector regression[J]. Statistics and Computing, 14(3), 2004: 199-222.
[89] Platt J C. Fast training of support vector machines using sequential minimal optimization[A]. In: Scholkopf B, Burges C, Smola A, eds. Advances in Kernel Methods: Support Vector Machines[C]. Cambridge: MIT Press, 1998: 185-208.
[90] Flake G W, Lawrence S. Efficient SVM regression training with SMO[J]. Machine Learning Special Issue on SVMs, 2000, 46(1~3): 271-290.
[91]张浩然,韩正之.回归支持向量机的改进序列最小优化学习算法[J].软件学报, 2003, 14(12): 2006-2013.
[92] Matin M. On-line support vector machines for function approximation[R]. Technical Report, LSI-02-11-R. Catalunya: Department of Software, Univesitat Politecnica Catalunta, 2002.
[93] Sydney C K, Chu C K Y, Lin S S. Hospital lift system simulator: A performance elevator-predictor [J]. European Journal of Operational Research, 2003, 146: 156-180.
[94]宗群.虚拟环境下智能电梯群控调度方法的研究[博士论文].天津:天津大学, 2003.
[95] Albert T P, Beebe J R, Chan W L, et al. Elevator Traffic Pattern Recognition by Artificial Neural Network [A]. In: Proc of 1995 Elevcon 1995 Elevator Engineers Conference[C]. Hong Kong: Int Association of Elevator Engineers, 1995: 122-131.
[96]宗群,尚晓光,岳有军,等.电梯群控系统的交通模式识别[J].控制与决策, 2001, 16(2): 163-166.
[97]宗群,尚晓光,严明,等.基于模糊神经网络的电梯系统交通模式识别[J].系统工程学报, 2001, 16(6): 418-424.
[98]唐桂忠,张广明. GA模糊神经网络在电梯群控交通流识别中的应用[J].微处理机,2005, 5: 49-52.
[99]许玉格,罗飞.新型电梯群控系统交通模式识别方法[J].控制理论与应用, 2005, 22(12): 900-904.
[100]李中华,朱燕飞,李春华,等.基于人工免疫聚类算法的电梯交通流分析[J].华南理工大学学报(自然科学版), 2003, 31(12): 26~29.
[101] Tang G Z, Zhang G M, Zhu W. EGCS Traffic-Pattern Identification[J]. Elevator World, 2005, 53(12): 116-120.
[102]刘靖明,韩丽川,侯立文.基于粒子群的K均值聚类算法[J].系统工程理论与实践, 2005, 25(6): 54-58.
[103] Van der Merwe D W, Engelbrecht A P. Data Clustering Using Particle Swarm Optimization[A]. In: The 2003 Congress on Evolutionary Computation[C]. Canberra, 2003: 215-220.
[104]杨维,李岐强.粒子群优化算法综述[J].中国工程科学, 2004, 6(5): 87-94.
[105] Wu K L, Yang M S. Alternative C-means Clustering Algorithms [J]. Pattern Recognition, 2002, 35(10): 2267-2278.
[106] Walter Rudin著,赵慈庚,蒋铎译.数学分析原理(第3版) [M].北京:机械工业出版社,2004.
[107] Cristianini N, Taylor J S. An introduction to support vector machines and other kernel-based learning methods[M]. Cambridge: Cambridge University Press, 2000.
[108] Lee D, Baek S, Sung K. Modified K-means algorithm for vector quantizer design[J]. IEEE Signal Processing Letters, 1997, 4(1): 2-4.
[109] Higashi N, Iba Hitoshi. Particle swarm optimization with Gaussian mutation[A]. In: Proceedings of the IEEE Swarm Intelligence Symposium [C]. Indianapolis, Indiana, USA, 2003: 72-79.
[110] Hampel F R, Ronchetti E M, Rousseeuw P J, et al. Robust Statistics-The approach based on influence functions [M]. New York: John Wiley and Sons, Wiley series in probability and mathematical statistics, 1986.
[111] Brand M, Nikovski D. Decision-theoretic group elevator scheduling[R]. Mistubishi Electric Corp, 2003. In: http://www.merl.com/papers/docs/TR2003-61.pdf
[112]高阳,胡景凯,王本年,等.基于CMAC网络强化学习的电梯群控调度[J].电子学报, 2007,35(2):362-365.
[113] Sutton R S, Barto A G. Reinforcement learning: An Introduction[M]. Cambridge: MIT Press, 1998.
[114] Maclin R, Shavlik J W. Incorporating advice into agents that learn from reinforcements[A]. In: Proceedings of the 12th national conference on artificial intelligence[C]. Seattle, WA: MIT Press, 1994: 694-699.
[115] Riberiro C H C. Embedding a Priori Knowledge in Reinforcement Learning[J]. Journal of Intelligent and Robotic Systems, 1998, 21: 51-71.
[116] Pascal Garcia. A New Way to Introduce Knowledge into Reinforcement Learning[A]. In: N. Lavrac et al. (Eds:), ECML 2003, LNAI 2837[C]. Berlin: Springer-Verlag, 2003: 157-168.
[117]杜春侠.多智能体系统具有先验知识的Q学习算法[J].清华大学学报, 2005, 45(7): 981-984.
[118] Kaelbling L P, Stanley J. Rosenschein. Action and Planning in Embedded Agents[J].Robotics and Autonomous Systems, 1991, 6(1): 35-48.
[119] Kaelbling L P. Reinforcement learning: A survey[J]. Journal of Artificial Intelligence Research, 1996, 4: 237-285.
[120]李伟.工程应用中强化学习方法研究[博士论文].上海:上海交通大学, 2005.
[121] Watkins C J C H, Doya K. Technical note: Q-learning[J]. Machine Learning, 1992, 8(3/4): 279-292.
[122] Tsitsiklis J N, Roy B V. An analysis of temporal difference learning with function approximation[J]. IEEE Transactions on Automatic Control, 1997, 42(5): 674-690.
[123] Baird L C. Residual algorithms: reinforcement learning with function approximation[A]. In: Proceedings of the 12th international conference on machine learning(ICML95)[C]. Tahoe City, California, USA, 1995: 30-37.
[124] Sutton R S. Generalization in reinforcement learning: successful examples using sparse coarse coding[A]. In: Advances in neural information processing systems [C]. Cambridge: MIT Press, 1996: 1038-1044.
[125]陆鑫,高阳,李宁,等.基于神经网络的强化学习算法研究[J].计算机研究与发展,2002, 39(8): 981-985.
[126] Boyan J, Moore A. Generalization in reinforcement learning: safely approximating the value functions[A]. In: Tesauro et al (eds.), Neural Information Processing Systems 7[C]. Cambridge, MA: The MIT Press, 1995: 369-376.
[127] Albus J S. A new approach to manipulator control: The cerebellar model articulation controller(cmac) [J]. Journal of Dynamic Systems, Measurement, and Control, 1975, 97(3): 220-227.
[128] Miller W T, et al. CMAC: An associative neural networks alternative to backpropagation[C]. In: Proceedings of The IEEE, 1990, 78(10): 1561-1567.
[129] Almeida P E M, Simoes M G. Parametric CMAC Networks: Fundamentals and applications of a fast convergence neural structure[J]. IEEE Transactions on Industry Applications, 2003, 39(5): 1551-1557.
[130] Barto A G, Mahadevan S. Recent advances in hierarchical reinforcement learning[J]. Discrete Event Dynamic Systems: Theory and Applications, 2003, 13: 41-77.
[131] Dietterich T G. Hierarchical reinforcement learning with the MAXQ value function decomposition[J]. Journal of Artificial Intelligence Research, 2000, 13: 227-303.
[132] Bao G, Cassandras C G, et al. Elevator dispatchers for down peak traffic[R]. Boston:ECE Department Technical Report, University of Massachusetts, 1994.
[133] Lustig A. Lift simulation program[J]. Elevator World, 1986, 34(3): 74-79.
[134] Siikonen M L. Elevator traffic simulation[J]. Simulation, 1993, 61(4): 257-267.
[135] Siikonen M L, Susi T, Hakonen H. Passenger traffic flow simulation in tall buildings[J]. Elevator World, 2001, 49(8): 117-123.
[136] Zong Q, Xue L, Wang Z. Virtual simulation environments of elevator group control systems[J]. Elevator World, 2001, 49(12): 90-93.
[137]宗群,尚晓光,岳有军,等.电梯群控系统虚拟仿真环境设计[J].制造业自动化, 1999, 21(5): 24-25, 31.
[138]宗群,王维佳,刘文静.电梯群控与监视系统实验平台的研究.实验室研究与探索, 2005, 24(增刊): 291-294.
[139]李中华,朱燕飞,李春华,等.面向对象的电梯群控系统仿真平台开发与实现[J].计算机仿真, 2005, 22(2): 156-159, 170.
[140]李中华,毛宗源.基于Matlab的多速度模式电梯群控系统模型仿真[J].系统仿真学报, 2005, 17(8): 1997-2000.
[141]许玉格,罗飞.基于细胞自动机的电梯群控系统建模及其面向对象实现[J].计算机工程与应用, 2004, 11: 40-42, 63.
[142]许玉格,罗飞,曹建忠.目的层预约的模糊神经网络电梯群控策略[J].华南理工大学学报(自然科学版), 2007, 35(1). 13-18.
[143]罗飞,许玉格,曹建忠.基于目的层预约的电梯群控系统建模与控制[J].控制与决策, 2006, 21(10): 1159-1162.
[144] Bi X, Zhu C, Ye Q. The development of elevator group control simulation testbed[J]. Elevator World, 2003, 51(12): 97-102.
[145] Bi Xiaoliang, Zhu Changming, Ye Qingtai. A GA-based approach to the multi-objective optimization problem in elevator group control system[J]. Elevator World, 2004, 52(6): 58, 59, 61-63.
[146]毕晓亮,李伟,朱昌明,叶庆泰.电梯群控系统多目标控制策略[J].上海交通大学学报, 2004, 38(8):1366-1368.
[147] Peters R D. Ideal lift kinematics-Complete equations for plotting optimum motion[J]. Elevator World, 1996, 44(4): 110-113.
[148]毕晓亮,朱昌明,叶庆泰.电梯服务系统仿真设计[J].上海交通大学学报, 2003, 37(11): 1736-1742.
[2] Johnston B. Project spotlight: Taipei 101: The experience[J]. Elevator World, 2006, 54(6): 126-132.
[3]刚宪约.曳引电梯系统动态理论及动力学参数优化方法研究[博士论文].杭州:浙江大学, 2005.
[4] Barney G C, Dos Santos S M. Elevator Traffic Analysis, Design and Control(2nd) [M]. London: IEE Peter Peregrinus, 1985.
[5]傅武军.超高速电梯轿厢横向振动控制研究[博士论文].上海:上海交通大学, 2007.
[6] Barney G C. Elevator traffic handbook: Theory and Practice [M]. London; New York: Spon Press, 2003.
[7]三菱电气AI2200电梯监控系统介绍, 2007. In: http:// www.mitsubishi -elevator. com/innovations/control_system_b.html#pagetop.
[8] Peters R D. Vertical transportation planning in buildings[Dissertation]. West London: Brunel University, 1998.
[9] So A, Cheng G, Suen W and Leung A. Elevator performance Evaluation in two numbers[J]. Elevator World, 2005, 53(1): 102-105.
[10] Courtney R G., Davidson P J. A survey of passenger traffic in two buildings[R]. Watford: Building Research Establishment, 1994.
[11] Peters R D, Haddon J. Lift Passenger Traffic Patterns: Applications, Current Knowledge and Measurement[J]. Elevator World, 2000, 48(9): 87-88, 90, 92, 94.
[12] Elevate软件官方网站, 2008. In:http://elevateontheweb.peters-research.com
[13] Barney G C. Traffic design benchmarks standard templates[J]. Elevator World, 2005, 53(2): 79-82.
[14]李中华,朱燕飞,李春华,毛宗源.基于人工免疫聚类算法的电梯交通流分析[J].华南理工大学学报(自然科学版), 2003, 31(12): 26-29.
[15] Powell B A. Important issues in up-peak traffic handling[A]. In: Proceedings of the 1992 International Conferences on Elevator Technologies[C]. Amsterdam, 1992:207-218.
[16] So A T P, Yu J K L. Dynamic zoning based supervisory control for elevators[A]. In: Proceedings of the 1999 IEEE international conference on control applications[C]. Hawai’i, 1999: 1591-1596.
[17] So A T P, Chan W L. Comprehensive dynamic zoning algorithms[J]. Elevator World, 1997, 45(9): 99-103.
[18] So A T P, Chan W L. Intelligent supervisory control for lifts: dynamic zoning[J]. Building Serv Eng Res Technol., 2001, 22(1): 14-33.
[19]宗群,罗欣宇,王振世.电梯上高峰动态规划分区控制方法的研究[J].控制与决策, 2002, 17(增刊): 781-784.
[20]宗群,王振世,尚晓光.电梯上高峰模式下动态分区算法的研究[J].系统工程与电子技术, 2001, 23(12): 97-100.
[21]李中华,毛宗源,郑日荣,等.基于人工免疫算法的电梯交通动态分区的优化[J].华南理工大学学报, 2004, 32(10): 46-50.
[22]郑延军,张惠侨,叶庆泰,等.电梯动态分区算法及其遗传算法研究[J].计算机工程与应用, 2001, 37(22): 142-144, 148.
[23]杨祯山,邵诚.电梯群控技术的现状与发展方向[J].控制与决策, 2005, 20(12): 1321-1331.
[24] Crites R H, Barto A G. Elevator group control using multiple reinforcement learning agents[J]. Machine learning, 1998, 33(2): 235-262.
[25] Ujihara H, Tsuji S. The revolutionary AI-2100 elevator group control system and the new intelligent option series[J]. Mitsubishi Electric Advance, 1998, 12(45): 5-8.
[26]李东,王伟,邵诚.电梯群控智能系统与智能控制技术[J].控制与决策, 2001, 16(5): 513-517.
[27]宗群,曹燕飞,曲照伟.电梯群控系统中智能控制方法[J].电气传动, 1998, (3): 25-28, 34.
[28]张筠莉,杨祯山.论人工智能技术在智能大厦电梯交通控制中的应用[J].城市智能建筑系统, 2001(6): 42-48.
[29] Umeda Y, Uetani K, Ujihara H, et al. Fuzzy theory and intelligent options[J]. Elevator World, 1989, 37(7): 86-91.
[30] Kim C B, Seong K A, Lee-Kwang H. Design and Implementation of a Fuzzy Elevator Group Control System[J]. IEEE Transactions on Systems, Man andCybernetics-part A: Systems and Humans, 1998, 28(3): 277-287.
[31] Amano M, Yamazaki M, Ikejima H. The latest elevator group supervisory control system[A]. In: ed. Barney G C, Elevator Technology 6[C]. London, 1995: 88-95.
[32] Kubo S, Nakai S, et al. Elevator group control system with a fuzzy neural network model[A]. In: ed. Barney G C, Elevator Technology 6[C]. London, 1995: 11-20.
[33] Fujino A, Tobita T, Segawa K, et al. An Elevator Group Control System with Floor-Attribute Control Method and System Optimization Using Genetic Algorithms[J]. IEEE Transactions on Industrial Electronics, 1997, 44(4): 546-552.
[34] Tobita T, Fujino A, Segawa K, et al. A parameter tuning method using genetic algorithms for an elevator group control system[A]. In: Proceedings of the 1996 IEEE IECON 22nd International Conference on Industrial Electronics, Control, and Instrumentation[C]. Taipei, 1996: 823-828.
[35] Fujino A, Tobita, T, Yoneda K. An online tuning method for multiobjective control of elevator group[A]. In: Proceedings of the 1992 International Conference on Industrial Electronics, Control, Instrumentation, and Automation,‘Power Electronics and Motion Control’[C]. San Diego, CA, USA, 1992 : 795–800.
[36] Tapio Yyni, Jari Ylinen. Evolutionary bi-objective optimization in the elevator car routing problem[J]. European Journal of Operational Research, 2006, 169(3): 960-977.
[37] Tapio Yyni, Jari Ylinen. Genetic algorithm in elevator car routing problem[A]. In: Proceedings of the Genetic Evolutionary Computation Conference 2001[C]. San Francisco, 2001: 1413-1422.
[38]万健如,李保海.群控电梯改进型遗传算法最佳派梯方法[J].起重运输机械, 2005, (4): 50-54.
[39] Cortes P, Larraneta J, Onieva L. A Genetic Algorithm for Controlling Elevator Group Systems[C]. Lecture Notes in Computer Science(LNCS 2687). Berlin: Springer-Verlag, 2003: 313-320.
[40] Kim J H, Moon B R. Adaptive Elevator Group Control with Cameras[J]. IEEE Transactions on Industrial Electronics, 2001, 48(2):377-382.
[41] Takahashi S, Kita H, Suzuki H, et al. Simulation-based Optimization of a Controller for Multi-car Elevators Using a Genetic Algorithm for Noisy Fitness Function[A]. In: The 2003 congress on evolutionary computation-CEC 2003[C]. Canberra, Australia,2003, vol(3): 1582-1587.
[42] Beielstein T, Ewald C P, Markon S. Optimal Elevator Group Control by Evolution Strategies[C]. GECCO 2003, LNCS 2724: 963-1974.
[43] Muna Hamdi, Mulvaney D J. Priorised A* search in real-time elevator dispatching[J]. Control Engineering Practice, 2007, 15: 219-230.
[44]高阳,陈世福,陆鑫.强化学习研究综述[J].自动化学报, 2004, 30(1): 87-100.
[45]李伟,何雪松,叶庆泰,等.基于先验知识的强化学习系统[J].上海交通大学学报, 2004, 38(8): 1362-1365.
[46] Powell B A, Stanley J, et al. Elevator Dispatching Employing Hall Call Assignment Based on Fuzzy Response Time Logic[P]. United States: No.5668356, 1997.9.
[47] Whitehall B L, Sirag D J, et al. Elevator Control Neural Network[P]. United States: No.5672853, 1997.9.
[48]上海三菱电梯有限公司群控技术介绍,2007. In: http:// www.smec-cn.com/ technology4.asp
[49] Miconic 10TM控制系统介绍,迅达电梯有限公司,2007. In: http://www. schindler.com/group_index/group_tech/group_tech_dc.htm
[50] Siikonen M L. Elevator Group Control with Artificial Intelligence[R]. Research Reports, Helsinki University of Technology Systems Analysis Lab, 1997.
[51]华升富士达电梯有限公司电梯群管理控制系统介绍,2007. In:http://www. fujitec.com.cn/qglkzxt.htm
[52]林勇,柴远利,黄永宣.基于广义最小二乘模型的动态交通OD矩阵估计[J].系统工程理论与实践, 2004, 24(1): 136-144.
[53] Zong Q, Shang X G, Yue Y J. Simulating traffic flow generator based on elevator traffic probability simulation model[J]. Elevator World, 2004, 52(4): 130-133.
[54]郑延军,张惠侨,叶庆泰,等.电梯群控系统客流分析与仿真[J].计算机工程与应用, 2001,37(22): 139-141.
[55]王炜,邓卫,杨琪,等.公路网络规划建设与管理方法(第二版)[M].北京:科学出版社, 2006.
[56]段进宇,缪立新,江见鲸.由路段交通流量反估出行OD矩阵技术的应用[J].清华大学学报(自然科学版), 2000, 40(6): 123-126.
[57]陈森发,周振国,于栋华.一种动态OD矩阵估计算法的理论及应用[J].东南大学学报,自然科学版, 2003, 33(1): 106-110.
[58] Fisk C S. On combining maximum entropy trip matrix estimation with user optimal assignment[J]. Transportation Research, 1988, 22B: 66-79.
[59] Wong S C, Tong C O. Estimation of time-dependent origin-destination matrices for transit networks[J]. Transportation Research B, 1998, 32(1): 35-48.
[60] Van Zuylen H J, Willumsen L G. The most likely trip matrix estimated from traffic counts[J]. Transportation Research, 1980, 14B: 281-293.
[61] Bell M G H. The real time estimation of origin-destination flows in the presence of platoon dispersion[J]. Transportation Research, 1991, 25B: 115-125.
[62] Nauyen S. Estimating origin-destination matrix from observed flows[A]. In: M. Florian (Ed.), Transportation Planning Models[C]. Amsterdam: Elsevier Science Publishers, 1984: 363-380.
[63] Watling D P. Maximum likelihood estimation of an origin-destination matrix from a partial registration plate survey[J]. Transportation Research, 1994, 28: 289-314.
[64]丁以中.贝叶斯-交通流均衡模型:一种由交通量观测估计O-D流的有效方法[J].系统工程理论与实践, 1996, 16(6): 50-57.
[65]孙光辉.信息熵与不确定性[J].青岛大学学报, 2000, 13(3): 50-51.
[66]孟庆生.关于Shannon熵的本质及其应用[M].北京:气象出版社, 1988.
[67] Chapman T G. Entropy as a measure of hydrologic data uncertainty and model performance[J]. Journal of Hydrology, 1986, 85: 111-126.
[68]姜丹.信息论与编码[M].合肥:中国科技大学出版社, 2001: 18-22, 102-105.
[69] Schneider M H, Zenios S A. A comparative study of algorithms for matrix balancing[J]. Operations Research, 1990, 38(3): 439-455.
[70]姚新,陈国良,徐惠敏,等.进化算法研究进展[J].计算机学报,1995,18(9): 694-706.
[71] Vignaux G. A, Michalewicz Z A. Genetic Algorithm for the Linear Transportation Problem[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1991, 21(2): 445-452.
[72]上海三菱电梯公司群控技术介绍. In: http://www.smec-cn.com/ technology4.asp.
[73] Thangabelu, Kandasamy. Optimized“up-peak”elevator channeling system with predicted traffic volume equalized sector assignments[P]. United States: No.4846311, 1989.
[74] Kameli, Nader. Predictor Elevator for Traffic During Peak Conditions[P]. UnitedStates: No.5276295, 1994.
[75]宗群,岳有军.电梯群控系统交通流的预测方法[J].系统工程与电子技术, 2001, 23(7): 103-105.
[76] Zong Q, Yue Y, Cao Y, et al. Application of Intelligence Forecasting Method in Traffic Analysis of EGCS[J]. Transactions of Tianjin University, 6(1), 2000: 18-21.
[77]宗群,孙志明,童玲.一种电梯交通流多模式预测方法的研究[J].信息与控制, 2006, 35(1): 93-102.
[78]黄敏,崔宝同,顾树生.基于小波神经网络的电梯交通流预测[J].控制与决策, 2006, 21(5): 589-592.
[79] Wan J, Jin X, Liu Y, et al. Elevator traffic-flow prediction based on wavelet network. Elevator World, 2007, 55(12): 132-137.
[80] Li X, Tong L, Zong Q. ARMA model for elevator traffic flow forecasting[J]. Elevator World, 53(8), 2005:83-87.
[81] Vapnik V. The Nature of Statistical Learning Theory[M]. New York: Springer, 1995.
[82] Vapnik V. Statistical Learning Theory[M]. New York: Wiley, 1998.
[83]张莉,周伟达,焦李成.尺度核函数支撑矢量机[J].电子学报, 2002, 30(4): 527-529.
[84] Zhang Li, Zhou Weida, Jiao Licheng. Wavelet Support Vector Machine[J]. IEEE Transactions on Systems, Man, and Cybernetics-Part B: Cybernetics, 2004, 34(1): 34-39.
[85] Müller K R, Smola A J, R?tsch G, et al. Predicting Time Series with Support Vector Machines[A]. In: Advances in Kernel Methods-Support Vector learning[C]. Cambridge, MA: MIT Press, 1999: 243-254.
[86]李元诚,李波,方廷健.基于小波支持向量机的非线性组合预测方法研究[J].信息与控制, 2004, 33(3): 303-306, 324.
[87] Scholkof B, Smola A. Learning with kernels: support vector machines, Regularization, Optimization, and Beyond [M]. Cambridge: MIT Press, 2002.
[88] Smola A, Scholkof B. A tutorial on support vector regression[J]. Statistics and Computing, 14(3), 2004: 199-222.
[89] Platt J C. Fast training of support vector machines using sequential minimal optimization[A]. In: Scholkopf B, Burges C, Smola A, eds. Advances in Kernel Methods: Support Vector Machines[C]. Cambridge: MIT Press, 1998: 185-208.
[90] Flake G W, Lawrence S. Efficient SVM regression training with SMO[J]. Machine Learning Special Issue on SVMs, 2000, 46(1~3): 271-290.
[91]张浩然,韩正之.回归支持向量机的改进序列最小优化学习算法[J].软件学报, 2003, 14(12): 2006-2013.
[92] Matin M. On-line support vector machines for function approximation[R]. Technical Report, LSI-02-11-R. Catalunya: Department of Software, Univesitat Politecnica Catalunta, 2002.
[93] Sydney C K, Chu C K Y, Lin S S. Hospital lift system simulator: A performance elevator-predictor [J]. European Journal of Operational Research, 2003, 146: 156-180.
[94]宗群.虚拟环境下智能电梯群控调度方法的研究[博士论文].天津:天津大学, 2003.
[95] Albert T P, Beebe J R, Chan W L, et al. Elevator Traffic Pattern Recognition by Artificial Neural Network [A]. In: Proc of 1995 Elevcon 1995 Elevator Engineers Conference[C]. Hong Kong: Int Association of Elevator Engineers, 1995: 122-131.
[96]宗群,尚晓光,岳有军,等.电梯群控系统的交通模式识别[J].控制与决策, 2001, 16(2): 163-166.
[97]宗群,尚晓光,严明,等.基于模糊神经网络的电梯系统交通模式识别[J].系统工程学报, 2001, 16(6): 418-424.
[98]唐桂忠,张广明. GA模糊神经网络在电梯群控交通流识别中的应用[J].微处理机,2005, 5: 49-52.
[99]许玉格,罗飞.新型电梯群控系统交通模式识别方法[J].控制理论与应用, 2005, 22(12): 900-904.
[100]李中华,朱燕飞,李春华,等.基于人工免疫聚类算法的电梯交通流分析[J].华南理工大学学报(自然科学版), 2003, 31(12): 26~29.
[101] Tang G Z, Zhang G M, Zhu W. EGCS Traffic-Pattern Identification[J]. Elevator World, 2005, 53(12): 116-120.
[102]刘靖明,韩丽川,侯立文.基于粒子群的K均值聚类算法[J].系统工程理论与实践, 2005, 25(6): 54-58.
[103] Van der Merwe D W, Engelbrecht A P. Data Clustering Using Particle Swarm Optimization[A]. In: The 2003 Congress on Evolutionary Computation[C]. Canberra, 2003: 215-220.
[104]杨维,李岐强.粒子群优化算法综述[J].中国工程科学, 2004, 6(5): 87-94.
[105] Wu K L, Yang M S. Alternative C-means Clustering Algorithms [J]. Pattern Recognition, 2002, 35(10): 2267-2278.
[106] Walter Rudin著,赵慈庚,蒋铎译.数学分析原理(第3版) [M].北京:机械工业出版社,2004.
[107] Cristianini N, Taylor J S. An introduction to support vector machines and other kernel-based learning methods[M]. Cambridge: Cambridge University Press, 2000.
[108] Lee D, Baek S, Sung K. Modified K-means algorithm for vector quantizer design[J]. IEEE Signal Processing Letters, 1997, 4(1): 2-4.
[109] Higashi N, Iba Hitoshi. Particle swarm optimization with Gaussian mutation[A]. In: Proceedings of the IEEE Swarm Intelligence Symposium [C]. Indianapolis, Indiana, USA, 2003: 72-79.
[110] Hampel F R, Ronchetti E M, Rousseeuw P J, et al. Robust Statistics-The approach based on influence functions [M]. New York: John Wiley and Sons, Wiley series in probability and mathematical statistics, 1986.
[111] Brand M, Nikovski D. Decision-theoretic group elevator scheduling[R]. Mistubishi Electric Corp, 2003. In: http://www.merl.com/papers/docs/TR2003-61.pdf
[112]高阳,胡景凯,王本年,等.基于CMAC网络强化学习的电梯群控调度[J].电子学报, 2007,35(2):362-365.
[113] Sutton R S, Barto A G. Reinforcement learning: An Introduction[M]. Cambridge: MIT Press, 1998.
[114] Maclin R, Shavlik J W. Incorporating advice into agents that learn from reinforcements[A]. In: Proceedings of the 12th national conference on artificial intelligence[C]. Seattle, WA: MIT Press, 1994: 694-699.
[115] Riberiro C H C. Embedding a Priori Knowledge in Reinforcement Learning[J]. Journal of Intelligent and Robotic Systems, 1998, 21: 51-71.
[116] Pascal Garcia. A New Way to Introduce Knowledge into Reinforcement Learning[A]. In: N. Lavrac et al. (Eds:), ECML 2003, LNAI 2837[C]. Berlin: Springer-Verlag, 2003: 157-168.
[117]杜春侠.多智能体系统具有先验知识的Q学习算法[J].清华大学学报, 2005, 45(7): 981-984.
[118] Kaelbling L P, Stanley J. Rosenschein. Action and Planning in Embedded Agents[J].Robotics and Autonomous Systems, 1991, 6(1): 35-48.
[119] Kaelbling L P. Reinforcement learning: A survey[J]. Journal of Artificial Intelligence Research, 1996, 4: 237-285.
[120]李伟.工程应用中强化学习方法研究[博士论文].上海:上海交通大学, 2005.
[121] Watkins C J C H, Doya K. Technical note: Q-learning[J]. Machine Learning, 1992, 8(3/4): 279-292.
[122] Tsitsiklis J N, Roy B V. An analysis of temporal difference learning with function approximation[J]. IEEE Transactions on Automatic Control, 1997, 42(5): 674-690.
[123] Baird L C. Residual algorithms: reinforcement learning with function approximation[A]. In: Proceedings of the 12th international conference on machine learning(ICML95)[C]. Tahoe City, California, USA, 1995: 30-37.
[124] Sutton R S. Generalization in reinforcement learning: successful examples using sparse coarse coding[A]. In: Advances in neural information processing systems [C]. Cambridge: MIT Press, 1996: 1038-1044.
[125]陆鑫,高阳,李宁,等.基于神经网络的强化学习算法研究[J].计算机研究与发展,2002, 39(8): 981-985.
[126] Boyan J, Moore A. Generalization in reinforcement learning: safely approximating the value functions[A]. In: Tesauro et al (eds.), Neural Information Processing Systems 7[C]. Cambridge, MA: The MIT Press, 1995: 369-376.
[127] Albus J S. A new approach to manipulator control: The cerebellar model articulation controller(cmac) [J]. Journal of Dynamic Systems, Measurement, and Control, 1975, 97(3): 220-227.
[128] Miller W T, et al. CMAC: An associative neural networks alternative to backpropagation[C]. In: Proceedings of The IEEE, 1990, 78(10): 1561-1567.
[129] Almeida P E M, Simoes M G. Parametric CMAC Networks: Fundamentals and applications of a fast convergence neural structure[J]. IEEE Transactions on Industry Applications, 2003, 39(5): 1551-1557.
[130] Barto A G, Mahadevan S. Recent advances in hierarchical reinforcement learning[J]. Discrete Event Dynamic Systems: Theory and Applications, 2003, 13: 41-77.
[131] Dietterich T G. Hierarchical reinforcement learning with the MAXQ value function decomposition[J]. Journal of Artificial Intelligence Research, 2000, 13: 227-303.
[132] Bao G, Cassandras C G, et al. Elevator dispatchers for down peak traffic[R]. Boston:ECE Department Technical Report, University of Massachusetts, 1994.
[133] Lustig A. Lift simulation program[J]. Elevator World, 1986, 34(3): 74-79.
[134] Siikonen M L. Elevator traffic simulation[J]. Simulation, 1993, 61(4): 257-267.
[135] Siikonen M L, Susi T, Hakonen H. Passenger traffic flow simulation in tall buildings[J]. Elevator World, 2001, 49(8): 117-123.
[136] Zong Q, Xue L, Wang Z. Virtual simulation environments of elevator group control systems[J]. Elevator World, 2001, 49(12): 90-93.
[137]宗群,尚晓光,岳有军,等.电梯群控系统虚拟仿真环境设计[J].制造业自动化, 1999, 21(5): 24-25, 31.
[138]宗群,王维佳,刘文静.电梯群控与监视系统实验平台的研究.实验室研究与探索, 2005, 24(增刊): 291-294.
[139]李中华,朱燕飞,李春华,等.面向对象的电梯群控系统仿真平台开发与实现[J].计算机仿真, 2005, 22(2): 156-159, 170.
[140]李中华,毛宗源.基于Matlab的多速度模式电梯群控系统模型仿真[J].系统仿真学报, 2005, 17(8): 1997-2000.
[141]许玉格,罗飞.基于细胞自动机的电梯群控系统建模及其面向对象实现[J].计算机工程与应用, 2004, 11: 40-42, 63.
[142]许玉格,罗飞,曹建忠.目的层预约的模糊神经网络电梯群控策略[J].华南理工大学学报(自然科学版), 2007, 35(1). 13-18.
[143]罗飞,许玉格,曹建忠.基于目的层预约的电梯群控系统建模与控制[J].控制与决策, 2006, 21(10): 1159-1162.
[144] Bi X, Zhu C, Ye Q. The development of elevator group control simulation testbed[J]. Elevator World, 2003, 51(12): 97-102.
[145] Bi Xiaoliang, Zhu Changming, Ye Qingtai. A GA-based approach to the multi-objective optimization problem in elevator group control system[J]. Elevator World, 2004, 52(6): 58, 59, 61-63.
[146]毕晓亮,李伟,朱昌明,叶庆泰.电梯群控系统多目标控制策略[J].上海交通大学学报, 2004, 38(8):1366-1368.
[147] Peters R D. Ideal lift kinematics-Complete equations for plotting optimum motion[J]. Elevator World, 1996, 44(4): 110-113.
[148]毕晓亮,朱昌明,叶庆泰.电梯服务系统仿真设计[J].上海交通大学学报, 2003, 37(11): 1736-1742.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |