关键词: 交通运输工程, 自适应滤波, 预测模型, 迭代运算, 港口吞吐量, 校正

Abstract: In order to effectively forecast the throughput of Dalian port, an adaptive filtering algorithm was introduced. By use of MATLAB simulation model, a future port throughput prediction model was established, which included the experimental simulation process, technical principles and theoretical models. The prediction results were obtained by an improved adaptive filtering algorithm. Combined with setting different amplification levels, different degrees of correction were performed. The results indicate that: through the small error set by the model, four weights are selected and the best weight is obtained by iterative operation, and then it is applied to the next group of data for prediction. The research shows that the variance and standard deviation of the prediction value of port throughput obtained by the improved adaptive filtering algorithm are respectively improved from 0.019 899 and 0.141 064 before improvement to 0.008 172 and 0.090 399 after improvement, which indicates that the proposed model can effectively predict the port throughput in the following years.

Key words: traffic and transportation engineering, adaptive filtering, prediction model, iterative operation, port throughput, correction