基于小波变换与改进时间序列模型的船舶升沉运动预测方法

doi:10.3976/j.issn.1002-4026.20240019

山东科学 ›› 2024, Vol. 37 ›› Issue (6): 1-11.doi: 10.3976/j.issn.1002-4026.20240019

• 海洋科技与装备 • 下一篇

基于小波变换与改进时间序列模型的船舶升沉运动预测方法

刘志臻¹^,²(), 黄鲁蒙²^,³^,^*(), 孙亚鹏¹^,², 张颖³, 刘振东³

1.天水电气传动研究所集团有限公司,甘肃天水 741020
2.大型电气传动系统与装备技术国家重点实验室,甘肃天水 741020
3.中国石油大学(华东) 机电工程学院,山东青岛 266580

收稿日期:2024-01-25 出版日期:2024-12-20 发布日期:2024-12-05
通信作者: *黄鲁蒙,男,博士,讲师,硕士生导师,研究方向为海洋工程装备、控制工程。E-mail:20170057@upc.edu.cn,Tel:18953273368
作者简介:刘志臻(1986—),男,高级工程师,研究方向为油气装备设计及自动化。E-mail:liuzzqq@126.com
基金资助:
大型电气传动系统与装备技术国家重点实验室(天水电气传动研究所集团有限公司)开放基金课题(SKLLDJ032022004);山东省重点研发计划(重大科技创新工程)项目(2022CXGC020402);国家重点研发计划(2021YFB3401400)

Ship heave motion prediction method based on wavelet transform and improved time series model

LIU Zhizhen¹^,²(), HUANG Lumeng²^,³^,^*(), SUN Yapeng¹^,², ZHANG Ying³, LIU Zhendong³

1. Tianshui Electric Transmission Research Institute Group Co., Ltd., Tianshui 741020, China
2. State Key Laboratory of Large Electric Drive System and Equipment Technology, Tianshui 741020, China
3. College of Mechanical and Electrical Engineering, China University of Petroleum (East China), Qingdao 266580, China

Received:2024-01-25 Online:2024-12-20 Published:2024-12-05

摘要/Abstract

摘要：

船舶升沉运动信号的检测滞后严重影响了海洋升沉补偿系统性能,通过对升沉运动进行准确预测可以有效改善系统的稳定性和实时性。为了提高预测模型的实用性,设计了自回归时间序列模型,具有计算效率高、编程简单的特点。在此基础上为了进一步解决该模型对非平稳复杂海况和预测时长适应性差的问题,引入小波多尺度分析方法,形成了一种基于小波变换与改进自回归的组合预测模型,通过对历史数据进行分解变换、重构、子序列预测及预测数据合成实现了对升沉运动的在线多步预测。对平稳随机波形和船舶实测非平稳波形的理论测试与实验结果表明:该组合模型具有良好的预测性能,能有效减少由于升沉运动信号检测滞后而引起的海洋升沉补偿系统控制误差。

关键词: 海洋工程, 升沉补偿, 时间序列预测, 小波变换

Abstract:

Lag in detecting ship heave motion signals severely affects the performance of ocean heave compensation systems. Therefore, accurate heave motion prediction can effectively improve the stability and real-time performance of these systems. To improve the engineering practicability of a heave motion prediction model, we designed an autoregressive time-series model featuring high calculation efficiency, simple programing, and a small accumulation error. Moreover, to further address the poor adaptability of the model to nonlinear and nonstationary complex sea conditions and long-term predictions, we developed a combined prediction model based on wavelet transform and improved autoregression using the wavelet multiscale analysis method and achieved online multistep prediction of heave motions by decomposing and transforming historical data, reconstructing sub-sequence prediction, and forecasting data synthesis. Finally, theoretical testing and experiments were conducted on stationary random waveforms and nonstationary waveforms measured on ships. The analysis results show that the combined model exhibits good prediction performance and can effectively reduce the control error of the ocean heave compensation system caused by the lag in the heave motion signal detection.

Key words: ocean engineering, heave compensation, time-series prediction, wavelet transformation

中图分类号:

TE58

刘志臻, 黄鲁蒙, 孙亚鹏, 张颖, 刘振东. 基于小波变换与改进时间序列模型的船舶升沉运动预测方法[J]. 山东科学, 2024, 37(6): 1-11.

LIU Zhizhen, HUANG Lumeng, SUN Yapeng, ZHANG Ying, LIU Zhendong. Ship heave motion prediction method based on wavelet transform and improved time series model[J]. Shandong Science, 2024, 37(6): 1-11.

图/表 12

图1

图2

表1

图3

图4

图5

图6

图7

表2

图8

图9

图10

参考文献 21

[1]	李欢, 樊春明, 李鹏, 等. 浮式波浪补偿装置研究及发展建议[J]. 石油机械, 2022, 50(2): 53-58. DOI: 10.16082/j.cnki.issn.1001-4578.2022.02.008.
[2]	WOODACRE J K, BAUER R J, IRANI R. Hydraulic valve-based active-heave compensation using a model-predictive controller with non-linear valve compensations[J]. Ocean Engineering, 2018, 152: 47-56. DOI: 10.1016/j.oceaneng.2018.01.030.
[3]	LIU Z D, ZHANG Y T, YU X G, et al. Study on the control strategies of offshore drilling crown-block heave compensation system with compound cylinders[J]. IEEE Access, 2020, 8: 149270-149281. DOI: 10.1109/access.2020.3015720.
[4]	CHEN S L, XIE P, LIAO J H, et al. NMPC-PID control of secondary regulated active heave compensation system for offshore crane[J]. Ocean Engineering, 2023, 287: 115902. DOI: 10.1016/j.oceaneng.2023.115902.
[5]	ZINAGE S, SOMAYAJULA A. Deep reinforcement learning based controller for active heave compensation[J]. IFAC-PapersOnLine, 2021, 54(16): 161-167. DOI: 10.1016/j.ifacol.2021.10.088.
[6]	黄鲁蒙, 张彦廷, 孙选建, 等. 海洋浮式钻井液压绞车升沉补偿系统设计[J]. 石油学报, 2017, 38(9): 1091-1098. DOI: 10.7623/syxb201709011.
[7]	LI S Z, WEI J H, GUO K, et al. Nonlinear robust prediction control of hybrid active-passive heave compensator with extended disturbance observer[J]. IEEE Transactions on Industrial Electronics, 2017, 64(8): 6684-6694. DOI: 10.1109/tie.2017.2698358.
[8]	HE Y H, ZHAO Y X, HAN X, et al. Functional risk-oriented health prognosis approach for intelligent manufacturing systems[J]. Reliability Engineering & System Safety, 2020, 203: 107090. DOI: 10.1016/j.ress.2020.107090.
[9]	DUAN W Y, HAN Y, HUANG L M, et al. A hybrid EMD-SVR model for the short-term prediction of significant wave height[J]. Ocean Engineering, 2016, 124: 54-73. DOI: 10.1016/j.oceaneng.2016.05.049.
[10]	JIANG H, DUAN S L, HUANG L M, et al. Scale effects in AR model real-time ship motion prediction[J]. Ocean Engineering, 2020, 203: 107202. DOI: 10.1016/j.oceaneng.2020.107202.
[11]	KHAN A, BIL C, MARION K E. Ship motion prediction for launch and recovery of air vehicles[C]//Proceedings of OCEANS 2005 MTS/IEEE. Washington, DC, USA: IEEE, 2005:2795-801. DOI: 10.1109/oceans.2005.1640198.
[12]	SHI B H, XIAN L, WU Q P, et al. Active heave compensation prediction research for deep sea homework crane based on KPSO-SVR[C]//Proceedings of the 33rd Chinese Control Conference. Nanjing: IEEE, 2014: 977-982. DOI: 10.1109/chicc.2014.6896273.
[13]	HUANG L M, DENG X G, BO Y C, et al. Evolutionary optimization assisted delayed deep cycle reservoir modeling method with its application to ship heave motion prediction[J]. ISA Transactions, 2022, 126: 638-648. DOI: 10.1016/j.isatra.2021.08.020.
[14]	ZHANG R. Statistical analysis of the non-stationary binomial AR(1) model with change point[J]. Applied Mathematical Modelling, 2023, 118: 152-165. DOI: 10.1016/j.apm.2023.01.032.
[15]	刘自强, 王效岳, 白如江. 基于时间序列模型的研究热点分析预测方法研究[J]. 情报理论与实践, 2016, 39(5): 27-33. DOI: 10.16353/j.cnki.1000-7490.2016.05.006.
[16]	YE F, YUAN Y B. A modified stochastic model for LS+AR hybrid method and its application in polar motion short-term prediction[J]. Geodesy and Geodynamics, 2024, 15(1): 100-105. DOI: 10.1016/j.geog.2023.05.005.
[17]	陈是扦, 彭志科, 周鹏. 信号分解及其在机械故障诊断中的应用研究综述[J]. 机械工程学报, 2020, 56(17): 91-107. DOI: 10.3901/JME.2020.17.091.
[18]	白润才, 柴森霖, 刘光伟, 等. 基于Mallat算法与ARMA模型的露天矿卡车故障率预测[J]. 中国安全科学学报, 2018, 28(10): 31-37. DOI: 10.16265/j.cnki.issn1003-3033.2018.10.006.
[19]	赵紫龙. 基于小波分解的差分灰色神经网络-AR模型及其在地铁隧道沉降预测中应用研究[J]. 测绘通报, 2020(S1): 99-103. DOI: 10.13474/j.cnki.11-2246.2020.0523.
[20]	高迪驹, 潘康凯, 王天真. 混合动力船舶负载功率预测模型研究[J]. 控制工程, 2019, 26(2): 362-367. DOI: 10.14107/j.cnki.kzgc.161443.
[21]	张彦廷, 黄鲁蒙, 陈国明, 等. 深水钻井补偿绞车的节能机理及解耦控制方案研究[J]. 中国石油大学学报(自然科学版), 2017, 41(4): 124-131. DOI: 10.3969/j.issn.1673-5005.2017.04.016.

预测步数	随机波			实测波
预测步数	δ_MAE/m	δ_RMSE/m	J_D	δ_MAE/m	δ_RMSE/m	J_D
1	0.000 1	0.000 2	0.999 8	0.035 0	0.056 3	0.902 0
3	0.007 1	0.008 3	0.990 4	0.150 2	0.210 5	0.572 5
5	0.047 7	0.055 9	0.935 0	0.230 1	0.303 2	0.332 5

预测步数	δ_MAE/m	δ_RMSE/m	J_D
1	0.000 2	0.000 3	0.999 3
3	0.005 6	0.007 9	0.94 2
5	0.015 5	0.020 2	0.955 0

基于小波变换与改进时间序列模型的船舶升沉运动预测方法

Ship heave motion prediction method based on wavelet transform and improved time series model

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 21

相关文章 3

Metrics

本文评价

推荐阅读 0

[1]	刘霏，谷文静，王公堂，万洪林. 基于BP神经网络的虹膜图像质量分类方法[J]. 山东科学, 2015, 28(2): 108-112.
[2]	孙克渠,许娴,李筠,葛修军,马培明,黄晨阳，李传柱. 连云港海域海水盐度长期变化特征[J]. J4, 2014, 27(2): 30-33.
[3]	程岩, 任国兴, 成文. 一维小波的信号处理在海水中总有机碳测量中的应用研究[J]. J4, 2011, 24(1): 6-9.