摘要
介绍了应用两个模糊神经网络分两步进行电梯群控系统交通模式识别 ,提出了利用专家知识获取样本和训练网络的步骤。实际数据测试结果表明 ,该方法能准确地辨识出各种交通模式所占的比例 ,对群控器的派梯可起到很好的指导作用 ,从而提高电梯群控系统的服务性能。
The traffic pattern recognition method of an elevator group control systems is presented, in which fuzzy neural networks are employed. The method consists of feature extraction of the traffic pattern, determination of the network structures, and mixed learning of the network. The procedures of obtaining the training data by expert knowledge and training the fuzzy neural networks are put forward. Results of tests using real traffic data show that the ratio of various traffic modes can be accurately recognized. This method can instruct the group controller to optimize dispatch strategy and improve the service of the elevator group.
出处
《控制与决策》
EI
CSCD
北大核心
2001年第2期163-166,共4页
Control and Decision
基金
天津市自然科学基金重点基金项目!(99380 12 11)
