基于前向神经网络最佳派梯智能控制

Optimum Dispatch Control of Elevators Based on a Forward Neural Network

通过对安装在大楼内的多台电梯进行智能调度,可有效节约能源、提高电梯的使用效率、缩短乘客等候时间。按照以人为本的原则,基于前向神经网络控制方法,根据群控电梯的主要性能指标构造评价函数;通过比较每部电梯评价函数值的大小,实现最佳派梯控制。仿真运行结果表明了本方法的可行性。与常用的模糊控制方法相比,该方法可使候梯时间缩短,电梯起停次数减少,能源损耗降低,实际应用效果良好。

Intelligent control is performed for multiple-elevators, which could save more energy, improve the running efficiency and reduce the waiting time. Based on a forward neural network, an evaluation function is constructed according to the main performances of group controlled elevators. By comparing the evaluation function values of the elevators, the optimum dispatch control is realized. The results of simulation have proved the feasibility of this method and a satisfactory effect is gained in practical applications. Compared with conventional fuzzy control methods, this method is effective to shorten the waiting time, decrease the startup stop frequency and reduces the power loss.