多层反馈混沌神经网络及其在交叉口优化控制中的应用

Multi-layer Chaotic Neural Network with Feedback and Its Application in Urban Signal Intersection Optimization Control

研究城市交叉口交通控制信号优化配时问题。以Hopfield网络和混沌模型为基础,开发了多层反馈混沌神经网络,将其应用于城市交通控制信号配时优化,并开发了应用于优化计算的能量函数和车辆平均延误计算式;探讨了城市交通系统的混沌特性,并开发混沌定量判别算法。以广东某交叉路口为对象进行了仿真,结果表明:与传统的配时方法相比,采用所开发的多层反馈混沌神经网络进行优化配时,交叉路口车辆的平均延误可以平均减少25.1%,可以大大提高路口的通行效率。该网络也可以应用于其他对象的优化。

The issue about the optimal timing of urban traffic-signal was discussed. A multi-layer chaotic neural network with feedback （ML-CNN） was developed based on Hopfield network and chaos theory, it was effectively used in dealing with the optimal timing of urban traffic-signal. An energy function for the network and an equation for the average delay per vehicle for optimal computation were developed. The characteristics of chaos in traffic system were discussed, and then the models for distinguishing chaos were developed. Simulation research was carried out at the intersection in Jiangmen city in China, which indicates that urban traffic-signal timing optimization by using ML-CNN could reduce the average delay per vehicle at intersection by 25.1% comparing to that by using the conventional timing methods. The ML-CNN could also be used in other fields,