【作者】 彭尚军；

【导师】 赵忠杰；

【作者基本信息】 长安大学 ， 交通信息工程及控制， 2007， 硕士

【摘要】 公路隧道通风系统具有很强的非线形特征,传统的线性控制理论难以获得精确的数学模型,因此,模糊控制等现代控制方法成为公路隧道通风控制的趋势,但模糊控制存在隶属函数、控制规则难以确定的问题。本文将具有强大学习能力的神经网络融合到模糊控制系统中,研究了公路隧道通风的模糊神经控制方法。解决了模糊控制系统本身的学习和适应能力差、模糊变量各语言值隶属函数,控制规则不能随着环境参数(如交通量、基准排放量等)的改变而自动调整和修改等问题。针对公路隧道通风模糊控制系统,参考了最优规则排序无关,在此基础上修改控制规则,获得了较优的规则库,与常规试凑法相比,大大节省了调整时间,同时利用等价结构的模糊神经网络模型,使其与规则库更好的匹配,反复调整隶属函数和修改控制规则,获得最佳模糊组合。并且建立了隧道小时交通量预测模型,可以获得任意给定交通量预测模型下的最佳模糊组合,从而实现了最优控制。提出基于模糊神经网络模型的隧道通风控制方法,能自动修改规则库和调整隶属函数,与单纯的模糊控制方法相比,提高了控制系统的自动化程度,提前预测未来的交通状况,节省了调整时间,降低了电能消耗。更多还原

【Abstract】 The road tunnel ventilation system has strong non-linear characteristic and it is difficult to gain the precise mathematical model by using the traditional linear control theory, therefore, the modem control methods such as the fuzzy control become the trend for the road tunnel ventilation control. However, there are some difficulties with the establishment of the fuzzy membership functions and the rule base. The paper use Fuzzy Neural Network Control (FNNC) system to improve the method of tunnel ventilation control. Solved the problems such as Fuzzy Logical Control system’s lacking of learning and adaptive ability, the membership functions of the fuzzy variables cannot be changed, the fuzzy logical rules cannot be modified automatically when environmental variables such as traffic model, average exhaust, etc, are changed.In view of the fuzzy control system of tunnel ventilation, on the basis of the best rule sorting independence, logical rules are modified and the optimized rules are gained. It takes much less time to regulate rules by using the above method than the traditional one. And established the tunnel hour traffic volume forecast model, in addition, membership functions are adjusted by using fuzzy neural network based on Back Propagation (BP) algorithm, so they match for the rules better and a more reasonable fuzzy combination is got. Then the final optimized fuzzy combination based on any specific traffic volume forecast model is gained. The FNNC system can modify the logical rules and regulate the parameters of membership functions automatically. Compared with the FLC system, the control process becomes more automatic, the time and the energy consumption becomes less.更多还原