CAJ | 학술논문

准确的极短期预报技术能够提高对船舶摇荡运动敏感的海洋特种作业安全性和效率。自回归（auto-regressive，AR）预报模型由于其自适应性强、计算效率高而被广泛应用于船舶运动的极短期预报研究。但该模型基于平稳随机假设，因而在非平稳船舶运动的极短期预报中存在困难。针对非平稳船舶运动极短期预报，文章提出一种基于AR-EMD方法的扩展AR模型，称为EMD-AR预报模型。其中，AR-EMD方法是指在经验模态分解（empirical mode decomposition，EMD）的过程中，采用AR预报的方法处理端点效应问题。 EMD-AR预报模型将非平稳信号分解成若干平稳的固有模态函数分量及余项，然后对各个分量分别用AR模型预报，得到最终的预报结果，以此克服非平稳性对AR预报模型的影响。研究基于船舶试验数据将EMD-AR模型与线性AR模型、非线性支持向量机回归（support vector regression，SVR）预报模型进行对比分析，结果表明，AR-EMD方法能够有效处理船舶运动非平稳性对AR预报模型的影响，提高该模型的预报精度，且EMD-AR模型预报性能较线性AR模型和非线性SVR模型更优。
준학적겁단기예보기술능구제고대선박요탕운동민감적해양특충작업안전성화효솔。자회귀（auto-regressive，AR）예보모형유우기자괄응성강、계산효솔고이피엄범응용우선박운동적겁단기예보연구。단해모형기우평은수궤가설，인이재비평은선박운동적겁단기예보중존재곤난。침대비평은선박운동겁단기예보，문장제출일충기우AR-EMD방법적확전AR모형，칭위EMD-AR예보모형。기중，AR-EMD방법시지재경험모태분해（empirical mode decomposition，EMD）적과정중，채용AR예보적방법처리단점효응문제。 EMD-AR예보모형장비평은신호분해성약간평은적고유모태함수분량급여항，연후대각개분량분별용AR모형예보，득도최종적예보결과，이차극복비평은성대AR예보모형적영향。연구기우선박시험수거장EMD-AR모형여선성AR모형、비선성지지향량궤회귀（support vector regression，SVR）예보모형진행대비분석，결과표명，AR-EMD방법능구유효처리선박운동비평은성대AR예보모형적영향，제고해모형적예보정도，차EMD-AR모형예보성능교선성AR모형화비선성SVR모형경우。
Accurate short-term prediction of ship motions allows better improvements in safety and con-trol quality in ship motion sensitive maritime operations. Inspired by the high adaptive and effective nature of auto-regressive (AR) model, it was widely studied in substantial papers concerning short-term prediction of ship motion. However, it suffers theoretical difficulty when the ship motion becomes non-stationary. In this paper, an extended AR model designated as EMD-AR for non-stationary ship motion forecast is developed by using AR-EMD technique. Where, AR-EMD technique refers to empirical mode decomposition (EMD) applying AR prediction method in boundary extension. EMD-AR model overcomes the non-stationarity in ship motion by decomposing the complex ship motion data into a couple of simple intrinsic mode functions (IMFs) and residual. Each sub-compo-nent is predicted individually, and predictions are then aggregated to attain the final results. Com-parative study with linear AR model and nonlinear support vector regression (SVR) model employing model testing ship motion data was conducted. The results show that AR-EMD is effective in han-dling the negative effect on the prediction accuracy resulting from non-stationarity in ship motion and EMD-AR model produces better prediction compared to AR and SVR models.