Rolling bearings are key components in the power transmission system of naval ships, and their operating status directly afects the reliability and safety of the ship power system. Aiming at the problems of complex operating environment, non-linear and non-stationary vibration signals, and weak early fault characteristics of naval ship equipment, this paper studies the virtual measurement method for rolling bearing faults of naval ships. A fault virtual measurement model fusing convolutional neural network (CNN) and long short-term memory (LSTM) network is constructed. The CNN is used to extract the local impactfeatures of vibration signals, and the LSTM network is adopted to model the temporal evolution law of fault features, so as to realize the end-to-end mapping from vibration signals to bearingfault status. An experimental dataset is built based on the vibration data of ship rotating machinery, and the modelperformance is verified through model comparison experiments, noise robustness tests and early fault detection experiments. The experimental results show that the proposed model outperforms the comparison models such as support vector machine (SVM), CNN and LSTM in terms offault diagnosis accuracy, anti-noise performance and early fault identification ability, with a diagnosis accuracy of92.1%. The research results demonstrate that the proposed method can achieve high-precision virtual measurement of the health status of key components in ship power systems.

Qiaona Zhang, Xiaojing Liu, Jiayi Kong, Yushan Du. Research on Virtual Measurement Method for Ship Rolling Bearing Faults Based on CNN-LSTM. Academic Journal of Engineering and Technology Science (2026), Vol. 9, Issue 3: 51-57. https://doi.org/10.25236/AJETS.2026.090307.

[1] Lianyou Lai, Weijian Xu,Zhongzhe Song.A Novel Fault Diagnosis Method for Rolling Bearings Based on Spectral Kurtosis and LS-SVM[J].Electronics,2025,14(14):2790.

[2] Sujit Kumar,Bam Bahadur Sinha.Enhanced Fault Diagnosis of Rolling Bearings with Noise Filtering and Neural Networks[J].Journal of Vibration Engineering & Technologies, 2025, 13(6):4111-4124.

[3] Xin Li,Ziming Kou,Cong Han,Shuai Huang.Deep clustering domain adaptation for fault diagnosis of rolling bearings in mining belt conveyors[J].Measurement,2025,248:116878.

[4] Zhenrong Ma,Ying Zhang.A study on rolling bearing fault diagnosis using RIME-VMD.[J] Scientific reports,2025,15(1):4712.

[5] Xianze Li,Guopeng Zhu,Aijun Hu,Lei Xing,Ling Xiang.A meta-learning method based on meta-feature enhancementfor bearingfault identification under few-sample conditions[J].Mechanical Systems and Signal Processing,2025,226:112370.

[6] Wang Wei,Yu Yang,Luo Simin,Liu Wenlin,Tang Wei,Ye Yuanbo.Distribution Line Longitudinal Protection Method Based on Virtual Measurement Current Restraint[J].Energy Engineering, 2024, 121(2):315-337.

[7] Kuznetsov V. I.,Kalashnikov S. D.,Nagovitsyna A. N..Simulation of an Autonomous Navigation Method for Determining the Orbit and Orientation ofSpacecraft from Virtual Measurements ofStellar Zenith Distances[J].Cosmic Research,2022,60(6):469-475.

[8] Kenji Nagata,Yoh-ichi Mototake,Rei Muraoka,Takehiko Sasaki, Masato Okada.Bayesian Spectral Deconvolution Based on Poisson Distribution: Bayesian Measurement and Virtual Measurement Analytics (VMA).[J].CoRR,2018,abs/1812.05501

[9] Liang Xidong, Zhang Sihua, Lin Chengsen, Ding Ziwei, Zhang Chaofan. Research on TBM Tunneling Position Prediction Model Based on Optimized Deep Learning Algorithm[J]. Coal Engineering, 2026, 1-13.

[10] Cai Aiting, Su Junlin, Dai Kun, Zhao Han, Wang Jiayi. Kick Prediction Based on Long Short-Term Memory Network and Random Forest[J]. Drilling Fluid & Completion Fluid, 2025, 1-9.

[11] Liu Jie, Yang Kaipeng, Ge Qin, Li Xiaoyu, Yang Jiale, Xi Dong, Jiang Dexun, Li Mo. An Optimized Reduction Model for River Water Pollution Based on Data-Driven Theory[J]. China Environmental Science, 2026, 1-11.

[12] Ma Yanfeng, Li Jinyuan, Wang Zijian, Zhao Shuqiang, Guo Runsheng. Regional Equivalent Inertia Evaluation Method for Renewable Energy Power Systems Based on Measurement Data[J]. Transactions of China Electrotechnical Society, 2024, 39(17): 5406-5421.

[13] Li Li, Zhang Yaxuan, Yu Qingyun. Review and Prospects of Virtual Metrology Technology for Manufacturing Processes[J]. Information and Control, 2023, 52(04): 417-431+482.