中文摘要：

针对短时交通流的延迟性、随机性和周期性特征,采用灰关联分析和分数阶累加生成方法建立了带时滞和周期特征的分数阶累加灰色新模型.针对短时交通流的延迟性,将短时交通流数据拆分成参考时间序列和对应的比较时间序列,进行关联度分析,得到计算时滞值的方法.针对短时交通流的随机性和周期性,利用分数阶累加生成方法,并引入tan（kp）为发展系数,sin（kp）为输入变量,建立了短时交通流的分数阶GM（1,1｜tan（kp）,sin（kp））模型,给出了模型参数的最小二乘估计和周期性参数与分数阶阶数的优化求解算法.最后将模型应用于长沙市芙蓉区某交叉路口的交通流建模及预测中,并与常规的五种模型进行了对比分析,结果表明,模型能较为准确地反映交通流的实际情况,且有较高的预测精度和较为稳定的结果.

英文摘要：

Using the grey correlation analysis and fractional accumulated generation method,this paper builds a new grey model with fractional order accumulate for three characteristics of short-term traffic flow time lag,randomness and periodicity.For the time lag of shortterm traffic flow,it breaks the short-term traffic flow data into reference-time sequences and comparing time sequences and analyses them to get a method of counting lag value.And for the randomness and periodicity of short-term traffic flow,it gives the least square estimation of model parameters and the optimization algorithm of periodic parameters and fractional orders by fractional order accumulate generation method,also introducing tan（kp）as development coefficient and sin（kp） as input variable and building a fractional order GM（1,1｜ tan（kp）,sin（kp）） model of short-term traffic flow.Finally,this paper applies the model to the traffic flow modeling and forecasting of an intersection in Furong,Changsha,and analyses five conventional models contrastively.It turns out that this model can reflect the actual situations well,has higher accuracy of the prediction and stable results.