基于模糊神经网络的电梯群控系统调度方法研究

Research of Dispatching Method in Elevator Group Control System Based on Fuzzy Neural Network

电梯群控系统是一个复杂的决策系统,具有多目标性、随机性和非线性等特点,难以采用精确的数学模型加以描述,因而传统的控制方法很难提高系统性能。将模糊控制技术与神经网络技术相结合,提出了一种能适应各种交通客流状况的调度方法,设计了各电梯响应呼梯信号的综合评价函数,通过神经网络的学习能力调整各评价因素(候梯时间、乘梯时间、能量消耗、拥挤度)的权重系数,从而确定最佳派梯方案。仿真实验结果表明,此方法能在各种交通客流状况下实现合理的电梯调度,验证了此方法的有效性。

It is a complex optimization system to elevator group control system （EGCS） with multi -objective, stochastic and nonlinear characteristics. It is hard to describe EGCS with exact mathematic model and to increase the capability of the system with traditional control method. The fuzzy control technology and neural network technology are combined in this paper and a dispatching method applied to various passenger traffic conditions is proposed. The comprehensive evaluation function of traffic signal is established and the right heavy of every evaluation factor （waiting time, riding time, energy consume, crowd degree） is studied by the neural network, so the elevator is dispatched optimally. The result of simulation shows that this method realizes reasonable elevator dispatching under various passenger traffic conditions and indicates the validity of this method.