基于改进PSO-ARIMA模型的船舶纵摇角度预测

针对自回归移动平均(auto regressive moving average,ARMA)模型在船舶纵摇角度预测时不具有普遍适用性问题,提出使用自回归综合移动平均(auto regressive integrated moving average,ARIMA)模型进行纵摇角度预测,并采用改进粒子群优化(particle swarm optimization,PSO)算法对模型定阶。对纵摇角度值序列数据进行平稳性检验和差分运算,确定ARIMA模型的适用性;采用具有针对性适应度评价函数的PSO算法进行模型定阶,并优化PSO算法的权重计算方法。通过仿真对比验证本文所提方法的科学性和有效性。仿真结果表明:采用改进PSO算法进行模型定阶的方法能够有效提升模型的预测精度,具有更好的预测效果。

Prediction of ship pitch angle based on improved PSO-ARIMA model

In view of the fact that the auto regressive moving average (ARMA) model is not of the universal applicability when predicting the ship pitch angle, an auto regressive integrated moving average (ARIMA) model is proposed for predicting the ship pitch angle, and an improved particle swarm optimization (PSO) algorithm is adopted to determine the model order. For the pitch angle value series, the stationarity test and difference operation of the data are performed to determine the applicability of the ARIMA model. The PSO algorithm with a targeted fitness evaluation function is used to determine the model order, and the weight calculation method of the PSO algorithm is optimized. The scientificity and effectiveness of the method proposed in this paper is verified through the simulation. The simulation results show that the method using the improved PSO algorithm determining the model order can effectively improve the prediction accuracy of the model and makes the model have better prediction effect.