Research On Passenger Performance-oriented Bus Rapid Transit System

Bus Rapid Transit(BRT) is an effective means to solve the problems of urban traffic congestion,environmental pollution and waste of resources.However,the BRT system in China’s development time is shorter,in addition to a few cities,many cities in the development of BRT in the demonstration guide role.Therefore,this paper chooses BRT passenger performance index from the perspective of passengers,and uses the improved evaluation model to study the evaluation of passenger performance-oriented BRT system.Through the horizontal comparison between cities,this paper realizes the performance supervision of public finance into BRT system For the government pointed out that the public financial investment BRT system construction and operation of the focus,but also for the completion of the BRT system to provide a highly efficient assessment of the city.This paper reviews the domestic and foreign research on BRT system performance evaluation and fuzzy neural network integration methods.On this basis,the composition and function of BRT system are based on the performance of different subjects.The analysis of the performance indicators to integrate the most concerned about the passengers BRT three criteria 7 indicators,constitute the evaluation index system.At the same time,based on the fuzzy evaluation method and the advantages and disadvantages of the neural network,it is proposed to improve the evaluation model with the idea of integration.Then,the evaluation steps and data processing methods of fuzzy BP neural network are proposed,and the virtual sample generation technique is proposed to solve the problem of insufficient training samples.Finally,based on the performance indicators data of Guangzhou,Hangzhou,Changzhou and Jinan,the basic data are processed by data normalization,virtual sample generation and fuzzy evaluation,and the training samples of neural network are obtained.Finally,through the test sample,complete the verification,draw the relevant conclusions.Finally,the indicators selected in this paper can reflect the performance concerns of passengers,and the improved fuzzy BP neural network model can be more objective and efficient to complete the calculation of performance evaluation.The use of virtual sample generation technology to expand the sample to ensure that the characteristics of the original sample,and improve the generalization of neural networks,in other cities similar projects in the promotion.First,the fuzzy BP neural network model is an improved method based on the fuzzy evaluation method and the neural network integration.In this paper,the model is improved and the data of other cities are used to train and tested.The fuzzy neural network model is based on the fuzzy evaluation method and the neural network.Verify the availability of the model.Secondly,for neural network performance,too large or too few training samples will affect the generalization of neural networks and adaptability.This paper proposes a virtual sample generation technique based on perturbation idea to expand the sample,not only can the generalization ability of the neural network,but also can effectively avoid falling into the local minimum.