WANG Xiao-nong, LI Jian-guo, HE Yun-peng
（School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China）
Abstract：Based on grey neural network and particle swarm optimization algorithm, an automated stereo garage decision model is proposed to solve the problems of long waiting queue and low efficiency of automated parking garage. The gray neural network is used to forecast the stay time of the vehicle and particle swarm optimization algorithm is used to allocate the parking spaces in the stereo garage. The proposed stereo garage mathematical model is established on condition that vehicle arrival interval obeys Poisson distribution. The performance of stereo garage is evaluated by the average waiting time, average waiting queue length, average service time and average energy consumption of the customers. By comparing the efficiency indexes of the existing model based on near-distribution principle and the proposed model based on gray neural network and particle swarm algorithm, it is proved that the proposed model based on gray neural network and particle swarm algorithm is effective in improving the efficiency of garage operation and reducing the energy consumption of garage.
Key words：stereo garage; parking space allocation; particle swarm algorithm; grey neural network algorithm; near-distribution principle
CLD number：U491.7; TP274 Document code：A
Article ID：1674-8042（2019）04-0369-010 doi：10.3969/j.issn.1674-8042.2019.04.009
References
［1］Xia T, Zhe B. Research on access scheduling of lifting and traversing cubic garage. Logistics Technology, 2015, 34(24)： 138-140.
［2］Lv H Z, Zhang L Y, Lian Z Z. Design of control algorithm for intelligent access vehicle. Software Engineer, 2015, 18 (12)： 52-53.
［3］Sun J Y, Wei Y H. Study on optimization of access control of automatic stereo garage. Logistics Technology, 2015, 34 (11)： 296-298.
［4］Pan Y F. Study on the ranking and cost optimization of automated stereo garage. Journal of Shanghai University of Electric Power, 2001, (1)： 27-31.
［5］Yang X F, Xiao H. Comparative analysis of access strategy of automated stereo garage. Machine Manufacturing and Automation, 2004, (5)： 47-49.
［6］Zuo W H, Jiang D J. Queuing and efficiency analysis of stereo garage. Journal of Chongqing Jiaotong University (Natural Science Edition), 2015, (4)： 113-116.
［7］Wei L. Based on the roadway stacking stereo garage vehicle access strategy algorithm. Chongqing: Chongqing University, 2014: 17-34.
［8］Kuo P H, Krishnamurthy A, Malmborg C J. Design models for unit load storage and retrieval systems using autonomous vehicle technology and resource conserving storage and dwell point policies. Applied Mathematical Modelling, 2007: 312332-2346.
［9］Fukunari M, Malmborg C J.An efficient cycle time model for autonomous vehicle storage and retrieval systems. International Journal of Production Research, 2008: 463167-3184.
［10］Liang Y. Research on queueing model and scheduling optimization of automated stereo garage. Lanzhou: Lanzhou Jiaotong University, 2017: 12-19.
［11］Li X, Zhu Y M. Modeling and simulation of dynamic placement allocation in automated stereoscopic warehouse. Logistic Technology, 2016, 39(3)： 131-136.
［12］Lu Y. Gray prediction model research and its application. Hangzhou: Zhejiang Technology University, 2014: 15-26.
［13］Fan Z Y. BP neural network model and learning algorithm. Software Guide, 2011, (7)： 66-68.
［14］Huang L. BP neural network algorithm improvement and application research. Chongqing: Chongqing Normal University, 2008: 23-36.
［15］Yang W, Fu W P, Wang W. Based on multi-color set and particle swarm optimization of warehouse location in stereo warehouse. Mechanical Science and Technology, 2012, 31(4)： 648-651.
［16］Huang T A, Sheng J G, Xu H Y, et al. Improved simplified particle swarm optimization algorithm. Computer Simulation, 2013, 30(2)： 327-330.
［17］Li Y L. Based on multi-objective particle swarm algorithm optimization and its application. Nangjing: Southwest Jiaotong University, 2014: 26-37.
立体车库车位分配模型与仿真分析
王小农， 李建国， 贺云鹏
（兰州交通大学 自动化与电气工程学院， 甘肃 兰州 730070）
摘 要: 采用一种基于灰色神经网络和粒子群算法的自动化立体车库决策模型， 以解决自动化立体车库车位分配时顾客排队过长和出入库效率低等问题。 灰色神经网络实现车辆库内停留时间的预测， 粒子群算法用于入库车辆车位优化分配。 假设车辆到达时间间隔服从泊松分布的情况下建立立体车库数学模型， 并采用顾客平均等待时间、 平均等待队长、 平均服务时间以及平均能耗作为立体车库效率指标评价立体车库性能。 分别编制就近分配原则和基于灰色神经网络和粒子群算法下车位分配仿真程序， 比较其效率指标可以看出， 基于灰色神经网络和粒子群算法的车位分配方法在提高车库运行效率和降低车库运行能耗方面更有效。
关键词: 立体车库； 车位分配； 粒子群算法； 灰色神经网络算法； 就近分配原则
引用格式： WANG Xiao-nong, LI Jian-guo, HE Yun-peng. Stereo garage parking space allocation model and simulation analysis. Journal of Measurement Science and Instrumentation, 2019, 10（4）： 369-378. ［doi： 10.3969／j.issn.1674-8042.2019.04.009］
【full text view]
