基于ANFIS模型隧道交通量预测研究

Research of Tunnel Traffic Volume Prediction Based on ANFIS Model

交通量预测作为隧道通风照明控制节能的一个重要环节,对通风控制可以实现超前控制,从而节省部分电能,因此针对如何实现准确的交通量预测提出一种基于TakagiSugeno模型的ANFIS自适应模糊神经推理系统,它是以历史数据作为输入数据,利用模糊系统和神经系统相结合的优势对隧道小时交通量进行高精度的预测,利用Matlab软件建立ANFIS预测模型,作为对比,同时利用小波神经网络预测方法对同样数据进行训练,再对两种不同的预测性能加以对比分析,结果表明ANFIS(自适应神经模糊推理系统)的方法预测精度更高,有一定的现实意义。

Traffic volume prediction is an important link of energy saving for tunnel ventilation lighting control,which can realize advance control of ventilation control,thus saving a part of electric energy,so puts forward a new method based on Takagi-sugeno model to realize traffic forecast accurately. ANFIS Adaptive Fuzzy Neural inference system,which takes historical data as input data,uses the advantage of combination of fuzzy system and neural network to predict the traffic volume of tunnels in high precision,using the Matlab software to set up the ANFIS forecast model,using the Wavelet neural network prediction method to train the same data,and comparing the two different prediction performances. The results show that the method of ANFIS（Adaptive Neuro-fuzzy inference system） has a higher precision and has some practical significance.