1.East China Electric Power Test & Research Institute,China Datang Corporation Science and Technology General Research Institute Co. ,LTD. ,Hefei 230031,Anhui,China
2.Institutes of Physical Science and Information Technology,Anhui University,Hefei 230601,Anhui,China
To improve the feature extraction and prediction ability of gate recurrent unit (GRU) for time series, we propose a performance parameter prediction method based on a multi-scale wavelet kernel network and a hybrid attention-gated recurrent network (mWKN-HAGRU). First, the scaling parameters of the wavelet kernel function ware adjusted to extract hidden state information from multiple dimensions, providing rich feature inputs for subsequent predictive models. Then, a hybrid attention gate recurrent unit (HAGRU) is designed, where temporal local attention can learn the long-term dependence between sequences and quantitatively characterize the influence of different features on the prediction performance.This can effectively capture the information interactions between features and comprehensively characterize the spatial correlation and evolution laws between different sequences. Finally, experimental results on a real marine diesel engine dataset showed that the proposed method significantly improved the predictive performance of the key performance parameters of the cooling water system.
长短期记忆网络(Long Short Term Memory,LSTM)被广泛用于处理具有时间依赖性的序列数据,Liu等[7]将LSTM模型用于预测船舶柴油机冷却水系统的排气温度。Han等[8]结合LSTM和前馈神经网络(Feedforward Neural Network,FNN)的特征提取[9],准确预测了不同故障类型的剩余使用寿命。文献[10]选取多个敏感监测参数作为输入数据,并提出一种改进的堆叠门控循环单元循环神经网络(Gate Recurrent Unit Recurrent Neural Network,GRU-RNN)的新方法。尽管上述方法能够在一定程度上提升预测的精度,但无法全面刻画时序间在长时间尺度上的依赖关系以及空间尺度上的演变规律,难以满足对序列进行中长期准确预测的实际需求。
CHENGC, HUON X, XUS Q, et al. Fault diagnosis for high-speed train traction systems based on MLCCA[J]. Control Engineering of China, 2024, 31(7): 1163-1168. DOI: 10.14107/j.cnki.kzgc.20220926 (Ch ).
[3]
NANDHINIS, PARTHASARATHYS, SARAVANANS. An efficient optimal hybrid SVELM based monitoring and forecasting the engine operations for safety standards[J]. Expert Systems with Applications, 2024, 238: 121679. DOI: 10.1016/j.eswa.2023.121679 .
[4]
WANGR H, CHENH, GUANC. Random convolutional neural network structure: An intelligent health monitoring scheme for diesel engines[J]. Measurement, 2021, 171: 108786. DOI: 10.1016/j.measurement.2020.108786 .
[5]
ZHANGZ Z, SONGW, LIQ Q. Dual-aspect self-attention based on transformer for remaining useful life prediction[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 2505711. DOI: 10.1109/TIM.2022.3160561 .
[6]
LIUL, SONGX, ZHOUZ T. Aircraft engine remaining useful life estimation via a double attention-based data-driven architecture[J]. Reliability Engineering & System Safety, 2022, 221: 108330. DOI: 10.1016/j.ress.2022.108330 .
[7]
WANGR H, CHENH, GUANC. DPGCN model: A novel fault diagnosis method for marine diesel engines based on imbalanced datasets[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 72: 3504011. DOI: 10.1109/TIM.2022.3228002 .
[8]
LIUB, GANH B, CHEND, et al. Research on fault early warning of marine diesel engine based on CNN-BiGRU[J]. Journal of Marine Science and Engineering, 2023, 11(1): 56. DOI: 10.3390/jmse11010056 .
[9]
HANP H, ELLEFSENA L, LIG Y, et al. Fault prognostics using LSTM networks: Application to marine diesel engine[J]. IEEE Sensors Journal, 2021, 21(22): 25986-25994. DOI: 10.1109/JSEN.2021.3119151 .
YAOY, TONGJ R, GAOJ, et al. Monitoring and fault diagnosis method of complex industrial process based on DLPPCA-SVM[J]. Control and Decision, 2022, 37(5): 1402-1408. DOI: 10.13195/j.kzyjc.2020.1614(Ch ).
[12]
XIAM, SHAOH D, MAX D, et al. A stacked GRU-RNN-based approach for predicting renewable energy and electricity load for smart grid operation[J]. IEEE Transactions on Industrial Informatics, 2021, 17(10): 7050-7059. DOI: 10.1109/TII.2021.3056867 .
[13]
LIT F, ZHAOZ B, SUNC, et al. WaveletKernelNet: An interpretable deep neural network for industrial intelligent diagnosis[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2022, 52(4): 2302-2312. DOI: 10.1109/TSMC.2020.3048950 .
HANM, LIJ B, XUM L, et al. Fault prognosis of marine diesel engine with working state transition based on EIIKF[J]. Acta Automatica Sinica, 2019, 45(5): 920-926. DOI: 10.16383/j.aas.2018.c170457 (Ch ).
[16]
LÜS G, YANGL, YANGQ. Research on the applications of infrared technique in the diagnosis and prediction of diesel engine exhaust fault[J]. Journal of Thermal Science, 2011, 20(2): 189-194. DOI: 10.1007/s11630-011-0456-7 .
[17]
ZHANGJ X, LIS Y. Air quality index forecast in Beijing based on CNN-LSTM multi-model[J]. Chemosphere, 2022, 308: 136180. DOI: 10.1016/j.chemosphere.2022.136180 .
[18]
MEIP, LIM, ZHANGQ, et al. Prediction model of drinking water source quality with potential industrial-agricultural pollution based on CNN-GRU-Attention[J]. Journal of Hydrology, 2022, 610: 127934. DOI: 10.1016/j.jhydrol.2022.127934 .