A fuzzy method for predicting the demand for rail freight transportation

摘要

The demand for rail freight transportation is a continuosly changing process over space and time and is affected by many quantitative and qualitative factors. In order to develop a more rational transport planning process to be followed by railway organisations, there is a need to accurately forecast freight demand under a dynamic and uncertain environment.. In conventional linear regression analysis, the deviations between the observed and the estimated values are supposed to be due to observation errors. In this paper, taking a different perspective, these deviations are regarded as the non-random uncertainties associated with forecasting issues.The details of fuzzy linear regression method are put forward and discussed in the paper. Based on an analyzes of the characteristics of the rail transportation problem, the proposed model was successfully applied to a real example from China.The results of that application are also presented here.