Life Cycle Identification Of Railway Passenger Transportation Products

In recent years, along with the rapid development of rapid transit railway and the gradual improvement of railway network, railway operation enterprises usher in an unprecedented development opportunity. In the passenger transportation market, railway operation enterprises have to confront the competition with road transportation, air transportation and so on. Ultimately, market competition is competition for products. Therefore, it has a great significance to study the life cycle of railway passenger transport products, identify the life cycle stage, lay down specific product strategy and improve the core competence of railway passenger transport products.First, this thesis simply expounds the theory and practice study trend of product life cycle identification at home and abroad, analyses merits and demerits of the relevant identify methods, and then put forwards the study thought and method of this paper. Secondly, describes the total concept of railway passenger transport product and the connotation of railway passenger transport product life cycle in detail, analyses the characteristics of the railway passenger transport product and product strategy in each stage of life cycle, and then draw forth the concept of railway passenger transport products life cycle identification. Detailed analyses influencing factors, and adopt thorough identification indexes of railway passenger transport products life cycle in the combination with the characteristics of railway passenger transport products. After that, combines Genetic Algorithm (GA) and Least Square Method, designs Hybrid Hierarchical Genetic Algorithm (HHGA) which would be learning algorithm of the Artificial Neural Network (ANN), establishes mathematical model of Radial Basis Function Neural Network (RBFNN) optimized by Hybrid Hierarchical Genetic Algorithm (HHGA). Optimizes the structure and parameters of the RBFNN by taking advantage of HHGA, reduces learning steps of the net and lowers errors of the output. At last, takes T2and Z18passenger train of Guangzhou Railway Group Changsha passenger traffic section for example, through comparative analyzing the mathematical model build in this paper with the RBFNN model not optimized by HGA. The results show that the RBFANN optimized by HGA is more accuracy than PNN which is not optimized. According to the identification results about Z18passenger train, put forwards relevant advice on product strategy for Changsha passenger traffic section.This paper consists of15figures,11tables and48references.