为提高船舶交通流量预测精度,综合考虑季节、气候等因素,通过分析历史流量数据,在线性增长模型的基础上构建了考虑周期性波动因素的船舶交通流量预测改进模型,并运用贝叶斯估计和预测方法求解模型,提出了基于时序数据预测船舶交通流量的预测方法.实例验证表明,较传统线性增长模型,新模型更符合交通流量的实际情况,月流量预测结果的平均绝对误差下降了3.56%,标准差下降了3.79%.因此,新的预测方法用于船舶交通流量预测是有效的. In order to improve the accuracy of forecasting traffic flow of ships, an improved traffic flow forecasting model considering cyclical fluctuation was constructed by analyzing historical flow data and considering the seasonal and climatic factors. Based on the linear growth model, a Bayesian estimation And predictive method to solve the model, a forecasting method based on time series data is proposed to predict the traffic flow of the ship.Examples show that the new model is more in line with the actual traffic flow than the traditional linear growth model, and the average absolute error of the monthly flow forecast results decreases by 3.56 %, Standard deviation decreased by 3.79% Therefore, the new prediction method is effective for ship traffic flow prediction.