A digital twin-based fault early warning method for marine diesel engines based on multimodal information fusion

PDF(28694 KB)

Journal of Dalian Maritime University ›› 2026, Vol. 52 ›› Issue (1) : 65-78.

SUN Jiawen¹，REN Hongxiang^*1，YANG Xiao¹，WANG Delong¹，PAN Mingyang¹，WEI Dejian²

Author information +

History +

Abstract

To achieve accurate perception of the operational status and effective fault early warning of marine diesel engines, a multimodal digital twin method integrating mechanism simulation and sensor measurement information was proposed. This method introduced a performance degradation correction mechanism to construct a high-fidelity thermodynamic simulation model of diesel engines, designed a feature extraction network integrating multi-scale convolution and attention mechanisms, and accomplished deep feature extraction and cross-modal fusion of the two types of complementary information. Taking the deviation degree as the early warning index, the self-learning of performance parameter thresholds was realized combined with kernel density estimation, and a fault early warning mechanism with dynamic adaptability was constructed. The effectiveness and applicability of the proposed method under actual operating conditions were verified based on the operational data of the 9L34DF dual-fuel marine diesel engine.

Key words

marine diesel engine / multimodal information fusion / performance prediction / fault early warning / digital twin

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

SUN Jiawen, REN Hongxiang, YANG Xiao, WANG Delong, PAN Mingyang, WEI Dejian. A digital twin-based fault early warning method for marine diesel engines based on multimodal information fusion[J]. Journal of Dalian Maritime University. 2026, 52(1): 65-78

References

[1]LI Y B, GUO Z W, LI Z X, et al. Instantaneous angular speed-based fault diagnosis of multicylinder marine diesel engine using intrinsic multiscale dispersion entropy[J]. IEEE Sensors Journal, 2023, 23(9): 9523-9535.

[2]XU C Y, LI W Y, ZHAO Y. A novel fused narx-driven digital twin model for aeroengine gas path parameter prediction[J]. IEEE Transactions on Industrial Informatics, 2024, 20(4): 6280-6288.

[3]甘辉兵. LNG船推进系统建模与仿真研究[D]. 大连：大连海事大学, 2012.GAN H B. Modeling and simulation of LNG carrier propulsion system[D]. Dalian: Dalian Maritime University,2012.(in Chinese)

[4]WANG R H, CHEN H, GUAN C, et al. Research on the fault monitoring method of marine diesel engines based on the manifold learning and isolation forest[J]. Applied Ocean Research, 2021, 112: 102681.

[5]MILIOULIS K, BOLBOT V, THEOTOKATOS G. Model-based safety analysis and design enhancement of a marine LNG fuel feeding system[J]. Journal of Marine Science and Engineering, 2021, 9(1): 69.

[6]陈冬梅, 赵思恒, 魏承印, 等. 船舶柴油机状态监测及预测性维护研究及应用[J]. 中国机械工程, 2022, 33(10): 1162-1168.

CHEN D M, ZHAO S H, WEI C Y, et al. Research and applications of condition monitoring and predictive maintenance of marine diesel engines[J]. China Mechanical Engineering,2022,33(10):1162-1168.(in Chinese)

[7]QIN Y, ZHANG T S, QIAN Q, et al. Large model for rotating machine fault diagnosis based on a dense connection network with depthwise separable convolution[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 1-12.

[8]王新全, 孙培廷, 邹永久, 等. 基于GA-BP模型的船舶柴油机排气温度趋势预测[J]. 大连海事大学学报, 2015, 41(3): 73-76.

WANG X Q, SUN P T, ZOU Y J, et al. Prediction of marine main engine exhaust temperature changing trend based on GA-BP model[J]. Journal of Dalian Maritime University,2015,41(3):73-76.(in Chinese)

[9]宫文峰, 陈辉, WANG D W. 基于深度学习的船舶机械微小故障快速诊断方法[J]. 计算机集成制造系统, 2022, 28(9): 2852-2864.

GONG W F, CHEN H, WANG D W. Fast diagnosis method of incipient fault of marine machinery based on deep learning[J]. Computer Integrated Manufacturing Systems,2022,28(9):2852-2864.(in Chinese)

[10]陶飞, 刘蔚然, 张萌, 等. 数字孪生五维模型及十大领域应用[J]. 计算机集成制造系统, 2019, 25(1): 1-18.

TAO F, LIU W R, ZHANG M, et al. Five-dimension digital twin model and its ten applications[J]. Computer Integrated Manufacturing Systems,2019,25(1):1-18.(in Chinese)

[11]TSITSILONIS K M, THEOTOKATOS G, PATIL C, et al. Health assessment framework of marine engines enabled by digital twins[J]. International Journal of Engine Research, 2023, 24(7): 3264-3281.

[12]周宏根, 魏凯, 窦振寰, 等. 基于数字孪生的船用柴油机整机性能评估方法[J]. 船舶工程, 2022, 44(5): 82-89.

ZHOU H G, WEI K, DOU Z H, et al. Digital twin-based performance evaluation method for marine diesel engines[J]. Ship Engineering,2022,44(5):82-89.(in Chinese)

[13]景乾峰, 神和龙, 尹勇. 一种基于虚拟现实系统的船舶数字孪生框架[J]. 北京交通大学学报, 2020, 44(5): 117-124.

JING Q F, SHEN H L,YIN Y. A ship digital twin framework based on virtual reality system[J].Journal of Beijing Jiaotong University,2020,44(5):117-124.(in Chinese)

[14]HAUTALA S, MIKULSKI M, SDERNG E, et al. Toward a digital twin of a mid-speed marine engine: from detailed 1D engine model to real-time implementation on a target platform[J]. International Journal of Engine Research, 2023, 24(12): 4553-4571.

[15]JEON J, THEOTOKATOS G. A framework to assure the trustworthiness of physical model-based digital twins for marine engines[J]. Journal of Marine Science and Engineering, 2024, 12(4): 595.

[16]XU X A, LIN Y, YE C. Fault diagnosis of marine machinery via an intelligent data-driven framework[J]. Ocean Engineering, 2023, 289: 116302.

[17]邢致恺, 何怡刚, 姚其新. 基于多模态信息融合的变压器在线故障诊断方法[J]. 电子测量与仪器学报, 2024, 38(9): 95-103.

XING Z K, HE Y G, YAO Q X. Transformer online fault diagnosis method based on multi-modal information fusion[J].Journal of Electronic Measurement and Instrumentation, 2024, 38(9): 95-103.(in Chinese)

[18]THEOTOKATOS G, STOUMPOS S, BOLBOT V, et al. Simulation-based investigation of a marine dual-fuel engine[J]. Journal of Marine Engineering & Technology, 2020, 19(Sup.1): 5-16.

[19]ZHANG J K, WANG Z T, LI S Y, et al. A digital twin approach for gas turbine performance based on deep multi-model fusion[J]. Applied Thermal Engineering, 2024, 246: 122954.

[20]DONG Y T, JIANG H K, WU Z H, et al. Digital twin-assisted multiscale residual-self-attention feature fusion network for hypersonic flight vehicle fault diagnosis[J]. Reliability Engineering & System Safety, 2023, 235: 109253.

[21]TIAN H X, YANG L Z, JU B T. Spatial correlation and temporal attention-based LSTM for remaining useful life prediction of turbofan engine[J]. Measurement, 2023, 214: 112816.

[22]HU J, SHEN L, ALBANIE S, et al. Squeeze-and-excitation networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8): 2011-2023.

[23]董建伟, 曾鸿, 刘鑫龙, 等. 基于DBN-SVR的船舶主机排烟温度基线模型[J]. 大连海事大学学报, 2022, 48(2): 101-109.

DONG J W, ZENG H, LIU X L, et al. Exhaust gas temperature baseline model of main engine based on DBN-SVR[J]. Journal of Dalian Maritime University, 2022,48(2): 101-109.(in Chinese)

[24]王泷德. 基于改进极限学习机的船舶发动机故障诊断研究[D]. 大连：大连海事大学, 2023.

WANG L D. Research on fault diagnosis of marine engine based on improved extreme learning machine[J].Dalian: Dalian Maritime University,2023.(in Chinese)