摘要
针对BP神经网络识别电梯群控交通流量存在的缺陷,提出了基于遗传算法优化GA-BP模糊神经网络识别电梯群控系统交通流量的新模型。GA训练模糊BP神经网络能够克服网络建模中产生的局部极小的缺点,提高了电梯群控交通流量识别的准确性。最后利用Matlab软件对样本数据进行训练和测试。仿真结果表明所构造的识别模型预测误差非常小。
Its deficiency was revealed because of traffic pattern identification method of elevator group control system based on using BP neural network, and a new traffic patten identification model is proposed which is based on optimizing fuzzy neural network by genetic algorithm. The genetic algorithm is used to train fuzzy BP neural network, which can overcome the shortcoming of local minimum appeared while training the network, and the veracity of the whole traffic pattern identification model can be increased. At last, the sampled data were trained and tested Matlab software, and the simulation results indicate that the proposed identify model has very small error.
出处
《微电机》
北大核心
2008年第3期78-80,87,共4页
Micromotors
关键词
电梯群控
遗传算法
BP神经网络
模糊神经网络
Elevator group control system
Genetic algorithm
BP neural network
Fuzzy neural network
