Probabilistic Interval Prediction of Ship Roll Motion Using Multi-Resolution Decomposition and Non-Parametric Kernel Density Estimation

Abstract

The prediction of ship roll motion is important for the safety of marine vessels and the efficiency of offshore operations. This study aims to address the issues of low prediction accuracy and incapability to illustrate the uncertainty of ship roll motion in traditional deterministic prediction models. Thus, a probabilistic interval prediction scheme for ship roll motion is established utilizing the novel data preprocessing strategy and non-parametric kernel density estimation (KDE). The novel data preprocessing method based on multi-resolution decomposition and reconstruction strategy is used to reduce the non-stationarity of the time series and number of mode components. This method is also utilized to extract trends from the mode components for preserving more effective information. Accordingly, the dynamic recurrent neural network is adopted to enable the identification and deterministic prediction of reconstruction data for ship roll motion. The deterministic prediction values of ship motion status can be obtained by reconstructing the predicted outcomes of the mode components. Non-parametric KDE is applied to predict the fluctuation range of ship roll status by combining deterministic prediction results. The feasibility and effectiveness of the probability prediction scheme are exhibited through the measured data of M.V. YuKun. Results show that the deterministic prediction accuracy of the proposed scheme is superior to those of traditional deterministic prediction models, with maximum improvements of 22.7% and 27.5% for single-and multi-step prediction accuracies, respectively. The minimum prediction interval coverage probability at the 85% confidence level is 98%. The reliable fluctuation range of ship roll can be realized through the non-parametric KDE, which can offer more effective reference information for ship operators. The proposed model not only satisfies the requirements of deterministic prediction accuracy but also produces reliable uncertainty estimates of ship roll motion status.

Keywords

Ship roll motion probabilistic prediction / Data preprocessing strategy / Neural network / Non-parametric kernel density estimation

References

[1] AfsharK, BigdeliN. Data analysis and short term load forecasting in Iran electricity market using singular spectral analysis (SSA). Renew Energ, 2011, 36(5): 2620-2627

[2] AnXL, JiangDX, ZhaoMH, LiuC. Short-term prediction of wind power using EMD and chaotic theory. Commun Nonlinear Sci Numer Simulat, 2012, 17(2): 1036-1042

[3] ChungJC, BienZ, KimYS. A note on ship-motion prediction based on wave-excitation input estimation. IEEE J Oceanic Eng, 1990, 15(3): 244-250

[4] DingSF, MaQ, ZhouL, HanS, DongWB. Multipoint heave motion prediction method for ships based on the PSO-TGCN model. China Ocean Eng, 2023, 37(6): 1022-1031

[5] DuanWY, HuangLM, HanY, ZhangYH, HuangS. A hybrid AR-EMD-SVR model for the short-term prediction of nonlinear and non-stationary ship motion. J Zhejiang Univ-Sc A (Appl Phys Eng), 2015, 16(7): 562-576

[6] ElmanJL. Finding structure in time. Cognitive Sci, 1990, 14(2): 179-211

[7] ElmanJL. Learning and development in neural networks: The importance of starting small. Cognition, 1993, 48(1): 71-99

[8] FossenTIHandbook of marine craft hydrodynamics and motion control, 2011, Chichester, West Sussex, United Kingdom, John Wiley & Sons Ltd

[9] FuHX, GuZQ, WangYC. Ship pitch prediction based on Bi-ConvLSTM-CA model. J Mar Sci Eng, 2022, 10(7): 840

[10] GaoN, HuAK, HouLX, ChangX. Real-time ship motion prediction based on adaptive wavelet transform and dynamic neural network. Ocean Eng, 2023, 280: 114466

[11] GengXY, LiYB, SunQ. A novel short-term ship motion prediction algorithm based on EMD and adaptive PSO-LSTM with the sliding window approach. J Mar Sci Eng, 2023, 11: 466

[12] GramackiANonparametric kernel density estimation and its computational aspects, 2018, Cham, Switzerland, Springer International Publishing

[13] HanLQ, ShiYArtificial neural network theory and application, 2023, Beijing, China, China Machine Press

[14] HarveyA, OryshchenkoV. Kernel density estimation for time series data. Int J Forecasting, 2012, 28(1): 3-14

[15] HuangLM, DuanWY, HanY, ChenYS. A review of short-term prediction techniques for ship motions in seaway. J Ship Mech, 2014, 18(12): 1534-1542

[16] HuangNE, ShenZ, LongSR, WuMC, ShihHH, ZhengQA, YenNC, TungCC, LiuHH. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc R Soc London Ser A Math Phys Eng Sci, 1998, 454(1971): 903-995

[17] JiangH, DuanSL, HuangLM, HanY, YangH, MaQW. Scale effects in AR model real-time ship motion prediction. Ocean Eng, 2020, 203: 107202

[18] KwiatkowskiD, PhillipsPCB, SchmidtP, ShinY. Testing the null hypothesis of stationarity against the alternative of a unit root. J Econometrics, 1992, 54(1): 159-178

[19] LiGY, KawanB, WangH, ZhangHX. Neural-network-based modelling and analysis for time series prediction of ship motion. Ship Technol Res, 2017, 64(1): 30-39

[20] LiL, WangTT, YinHR, NiuJ, LiangYB, HeJN, MiaoSH. Point-interval joint prediction method of dissolved gas volume fraction in transformer oil based on GWO-LSTM and NKDE. High Volt Appar, 2022, 58(11): 88-97

[21] LiMW, GengJ, HanDF, ZhengTJ. Ship motion prediction using dynamic seasonal RvSVR with phase space reconstruction and the chaos adaptive efficient FOA. Neurocomputing, 2016, 174: 661-680

[22] LiMW, XuDY, GengJ, HongWC. A ship motion forecasting approach based on empirical mode decomposition method hybrid deep learning network and quantum butterfly optimization algorithm. Nonlinear Dyn, 2022, 107: 2447-2467

[23] LiSQ, LiuXM, LinAJ. Fractional frequency hybrid model based on EEMD for financial time series forecasting. Commun Nonlinear Sci Numer Simulat, 2020, 89: 105281

[24] LiXM, HanZW, ZhaoTY, ZhangJL, XueD. Modeling for indoor temperature prediction based on time-delay and Elman neural network in air conditioning system. J Build Eng, 2021, 33: 101854

[25] LinZ, YangQ, GuoZQ, LiJ. An improved Autoregressive method with Kalman Filtering Theory for vessel motion predication. Int J Intell Eng Syst, 2011, 4(4): 11-18

[26] LuoQF, LiJ, ZhouYQ, LiaoL. Using spotted hyena optimizer for training feedforward neural networks. Cogn Syst Res, 2020, 65: 1-16

[27] MaoZY, ZhaoY, ZhaoJX, ShaoLH, ZuoH. A dual-channel ultra-short-term ship motion prediction model using temporal convolutional network, frequency-enhanced channel attention and informer. Phy Fluids, 2025, 37(2): 022145

[28] MiXW, LiuH, LiYF. Wind speed prediction model using singular spectrum analysis, empirical mode decomposition and convolutional support vector machine. Energ Convers Manage, 2019, 180: 196-205

[29] MorenoSR, dos Santos CoelhoL. Wind speed forecasting approach based on singular spectrum analysis and adaptive neuro fuzzy inference system. Renew Energ, 2018, 126: 736-754

[30] PengXY, ZhangB, ZhouHG. An improved particle swarm optimization algorithm applied to long short-term memory neural network for ship motion attitude prediction. T I Meas Control, 2019, 41(15): 4462-4471

[31] PengXY, ZhaoXR, WeiNX, XieN. AR algorithm for extremely short-term prediction of large ship’s motion. Ship Eng, 2001, 5: 5-7

[32] QiuXPNeural networks and deep learning, 2020, Beijing, China, China Machine Press

[33] ReisJ, BatistaP, OliveiraP, SilvestreC. Discrete-time Kalman filter for heave motion estimation. Ocean Eng, 2023, 277: 114240

[34] SongCY, ZhangXK, ZhangGQ. Attitude prediction of ship coupled heave-pitch motions using nonlinear innovation via fullscale test data. Ocean Eng, 2022, 264: 112524

[35] SunQ, TangZ, GaoJP, ZhangGC. Short-term ship motion attitude prediction based on LSTM and GPR. Appl Ocean Res, 2022, 118: 102927

[36] SuhermiN, Suhartono, PrastyoDD, AliB. Roll motion prediction using a hybrid deep learning and ARIMA model. Proced Comput Sci, 2018, 144: 251-258

[37] TarkhanehO, ShenHF. Training of feedforward neural networks for data classification using hybrid particle swarm optimization, Mantegna Lévy flight and neighborhood search. Heliyon, 2019, 5(4): e01275

[38] WangYC, DouYB, YangZQ, FuHX. Ship pitch prediction method based on LSTMC and multi-head attention. Ocean Eng, 2024, 309: 118236

[39] WangYC, WangH, ZouDX, FuHX. Ship roll prediction algorithm based on Bi-LSTM-TPA combined model. J Mar Sci Eng, 2021, 9(4): 387

[40] WeiYY, ChenZZ, ZhaoC, ChenX. Deterministic ship roll forecasting model based on multi-objective data fusion and multilayer error correction. Appl Soft Comput, 2023, 132: 109915

[41] WeiYY, ChenZZ, ZhaoC, TuYH, ChenX, YangR. A BiLSTM hybrid model for ship roll multi-step forecasting based on decomposition and hyperparameter optimization. Ocean Eng, 2021, 242: 110138

[42] WeiYY, ChenZZ, ZhaoC, ChenX, HeJH, ZhangCY. A three-stage multi-objective heterogeneous integrated model with decomposition-reconstruction mechanism and adaptive segmentation error correction method for ship motion multi-step prediction. Adv Eng Inform, 2023, 56: 101954

[43] WuZH, HuangNE. Ensemble empirical model decomposition: A noise assisted data analysis method. Adv Adapt Data Anal, 2009, 1(1): 1-41

[44] XiaJD, ZhengWL, WangZH, LiJ. Short-term prediction of ship motion attitude based on EMD-LSTM. Comput Digit Eng, 2022, 50(7): 1434-1438

[45] YangY, YuDJ, ChengJS. A roller bearing fault diagnosis method based on EMD energy entropy and ANN. Journal of Sound and Vibration, 2006, 294(1-2): 269-277

[46] YinJC, ZouZJ, XuF. On-line prediction of ship roll motion during maneuvering using sequential learning RBF neural networks. Ocean Eng, 2013, 61: 139-147

[47] YinJC, PerakisNA, WangN. A real-time ship roll motion prediction using wavelet transform and variable RBF network. Ocean Eng, 2018, 160: 10-19

[48] YinJC, ZouZJ, XuF, WangNN. Online ship roll motion prediction based on grey sequential extreme learning machine. Neurocomputing, 2014, 129: 168-174

[49] YuCJ, LiYL, ZhangMJ. An improved wavelet transform using singular spectrum analysis for wind speed forecasting based on Elman Neural Network. Energ Convers Manage, 2017, 148: 895-904

[50] YuanPY, ZhaoWG, ZhaoY. Intelligent prediction algorithm of ship roll and pitch motion based on SSA-optimized BiLSTM network. Ocean Eng, 2025, 320: 120331

[51] ZambomAZ, DiasR. A review of kernel density estimation with applications to econometrics. Int Economet Rev, 2013, 5(1): 20-42

[52] ZhangB, WangS, DengLW, JiaMQ, XuJZ. Ship motion attitude prediction model based on IWOA-TCN-Attention. Ocean Eng, 2023, 272: 113911

[53] ZhangB, PengXY, GaoJ. Ship motion attitude prediction based on ELM-EMD-LSTM integrated model. J Ship Mech, 2020, 24(11): 1413-1421

[54] ZhangGY, TanF, WuYX. Ship motion attitude prediction based on an adaptive dynamic particle swarm optimization algorithm and bidirectional LSTM Neural Network. IEEE Access, 2020, 8: 90087-90098

[55] ZhangT, ZhengXQ, LiuMX. Multiscale attention-based LSTM for ship motion prediction. Ocean Eng, 2021, 230(13): 109066

[56] ZhangXL, LuXM, JiaRS, KanST. Micro-seismic signal denoising method based on variational mode decomposition and energy entropy. J China Coal Soc, 2018, 43(2): 356-363

[57] ZhouBW, MaXJ, LuoYH, YangDS. Wind power prediction based on LSTM networks and nonparametric kernel density estimation. IEEE Access, 2019, 7: 165279-165292

[58] ZhouL, DuanYX, RenZR, AnS. Active heave compensation control system and motion prediction research. J Huazhong Univ of Sci & Tech (Natural Science Edition), 2021, 49(3): 98-104

RIGHTS & PERMISSIONS

Harbin Engineering University and Springer-Verlag GmbH Germany, part of Springer Nature