Applying the feature of analyzing the chaotic characteristics of nonlinear dynamic system of chaos theory, the railway coal dispatched volume time series was analyzed. On the base of Takens phase space reconstruction, C-C method was used to calculate embedding time-delay and embedding window , G-P method was used to calculate the embedding dimension, and then Small-data method was used to calculate the maximum Lyapunov exponent of railway coal dispatched volume time series. The Lyapunov exponent was used to analyze the chaotic characteristics of the time series. The analytical results show as the following: the growth amount and growth rate of railway coal dispatched volume have chaotic characteristics, but the coal dispatched volume doesn’t. The maximum Lyapunov exponent method and BP neural network were separately used to forecast the growth amount and growth rate of railway coal dispatched volume from 1st January 1999 to 26th June 2012. The result shows that the predicted data using maximum Lyapunov exponent method is anastomotic with the real data. The maximum Lyapunov exponent method is better than BP neural network in predicting. The maximum Lyapunov exponent method is useful in railway coal dispatched volume prediction.