Prediction models of the number of end-of-life vehicles in China

Prediction along with future trend analysis of the volume of end-of-life vehicles (ELVs) has a great impact on the execution of regulations and formulation of policies in China. To deal with such issues, this work investigates the historical data of their major influence factors including production volume, sale volume, vehicle count, turnover of highway freight, passenger turnover, GDP and income of per urban resident. Moreover, based on obtained main factors and historical data of ELV volume in China, its prediction models are established by multiple linear regressions (MLR), neural networks (NN) and optimized NN based on genetic algorithm (GA-NN) methods. In addition, a numerical example is given to illustrate the proposed models and the effectiveness of the proposed methods.