To address the core challenges arising from data distribution heterogeneity and strong noise interference induced by multi-operating-condition switching in aero-engines, as well as the gradient vanishing, excessive memory consumption, and insufficient generalization under complex operating conditions inherent in conventional deep networks for long-sequence remaining useful life (RUL) prediction, this paper proposes an aero-engine RUL prediction method that integrates multi-dimensional data preprocessing with an attention-enhanced deep equilibrium network. First, a multi-dimensional preprocessing pipeline comprising operating condition clustering, Z-Score grouped normalization, random forest feature selection, and exponential moving average temporal smoothing is constructed to purify and denoise degradation features under complex operating conditions, thereby mitigating the distribution shift caused by multi-operating-condition switching at the data level. Subsequently, built upon the deep equilibrium network framework, a dual-input attention mechanism is designed to achieve collaborative enhancement of temporal features and hidden layer states; an Anderson acceleration solver is introduced to optimize the convergence of fixed-point iterations; and a Bayesian regression module is incorporated to quantify the uncertainty of prediction results. These designs simultaneously alleviate long-sequence gradient vanishing and memory overload at their source while substantially improving the model's adaptability to complex operating conditions and prediction reliability. Simulation experiments are conducted on the NASA C-MAPSS aero-engine dataset. Ablation studies verify the necessity and synergistic benefits of the three core components: the dual-input attention mechanism, the Anderson acceleration solver, and data smoothing. Compared with 12 state-of-the-art RUL prediction methods, the proposed method achieves the best performance on FD001, FD002, and FD004 and ranks among the top on FD003; particularly on the complex multi-operating-condition datasets FD002 and FD004, the RMSE is reduced to as low as 11.91 and 11.97, respectively, demonstrating significant advantages. To further validate the cross-domain generalization capability and engineering adaptability, the proposed method is transferred to the N-CMAPSS high-fidelity aero-engine simulation dataset, where it maintains stable and excellent prediction performance across all 8 sub-datasets of graded complexity, fully demonstrating its generalization capability and reliability in complex engineering scenarios. The proposed method achieves the collaborative optimization of RUL prediction accuracy and computational efficiency within a purely data-driven paradigm, exhibiting superior robustness and generalization under both single- and complex multi-operating conditions, and can provide reliable technical support for aero-engine predictive maintenance.
[1]成心怡, 张琪, 郑建飞, 等.考虑非平稳特征的滚动轴承健康指标构建方法[J].哈尔滨工程大学学报, 2026, (06):1-10
[2]王昱, 杨晓庆, 李硕, 等.基于时空融合的航空发动机预测[J].振动与冲击, 2025, 44(16):318-328
[3]韩淞宇, 邵海东, 姜洪开, 等.基于提升卷积神经网络的航空发动机高速轴承智能故障诊断[J].航空学报, 2022, 43(09):158-171
[4]Zhao K, Jia Z, Jia F, et al.Multi-scale integrated deep self-attention network for predicting remaining useful life of aero-engine[J].Engineering Applications of Artificial Intelligence, 2023, 120:105860-
[5]吴嘉俊, 苏春, 张玉茹.基于双重自注意力机制和长短时记忆网络的剩余寿命预测[J].系统工程与电子技术, 2024, 46(06):1986-1994
[6]Li N, Wang M, Lei Y, et al.Remaining useful life prediction of lithium-ion battery with nonparametric degradation modeling and incomplete data[J].Reliability Engineering & System Safety, 2025, 256:110721-
[7]Wang F, Tang S, Sun X, et al.Remaining useful life prediction based on nonlinear random coefficient regression model with fusing failure time data[J].Journal of Systems Engineering and Electronics, 2023, 34(1):247-258
[8]郭晓静, 徐晓慧, 郭佳豪.基于改进GRU的航空发动机寿命预测自注意力优化算法[J].航空动力学报, 2024, 39(12):447-457
[9]李浩, 王卓健, 李哲, 等.基于堆栈自编码器和DeepAR的航空发动机剩余寿命预测[J].推进技术, 2022, 43(11):72-80
[10]王欣, 黄佳琪, 孟天宇, 等.多特征注意力的航空发动机剩余寿命预测模型[J].航空工程进展, 2023, 14(02):73-80
[11]Bai S, Kolter J Z, Koltun V.Deep equilibrium models[J].Advances in neural information processing systems, 2019, 32:-
[12]Bai S, Koltun V, Kolter J Z.Multiscale deep equilibrium models[J].Advances in neural information processing systems, 2020, 33:5238-5250
[13]Biau G, Scornet E.A random forest guided tour[J].Test, 2016, 25(2):197-227
[14]Shi P, Jia T, Xu X, et al.A generative dual-input model based on architectural computational optimization and multi-attention mechanism for remaining useful life prediction[J].Reliability Engineering & System Safety, 2025, :111777-
[15]Mullachery V, Khera A, Husain A..Bayesian neural networks[J].arXiv prep, 2018, :-
[16]Krishna K, Murty M N.Genetic K-means algorithm[J].IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 1999, 29(3):433-439
[17]Kim T, Solanki V S, Baraiya H J, et al.A smart,sensible agriculture system using the exponential moving average model[J].Symmetry, 2020, 12(3):457-
[18]Peng Y, Deng B, Zhang J, et al.Anderson acceleration for geometry optimization and physics simulation[J].ACM Transactions on Graphics (TOG), 2018, 37(4):1-14
[19]Y?ld?r?m U, Af?er H.Linear methods for predictive maintenance: The case of NASA C-MAPSS datasets[J].Applied Sciences, 2025, 15(18):9945-
[20]刘赟, 张琪, 杨立浩.Adam、PSO优化DBN的非协作式敌我识别系统作战效能评估方法[J].火箭军工程大学学报, 2025, 39(04):124-136
[21]王通，熊涛理.基于改进Adam-DBN的油井工况诊断方法[J].沈阳工业大学学报, 2023, 45(3):330-335
[22]Gal Y, Ghahramani Z.Dropout as a bayesian approximation: Representing model uncertainty in deep learning[J].international conference on machine learning. PMLR, 2016, :1050-1059
[23]Chen J, Li D, Huang R, et al.Aero-engine remaining useful life prediction method with self-adaptive multimodal data fusion and cluster-ensemble transfer regression[J].Reliability Engineering & System Safety, 2023, 234:109151-
[24]Mo Y, Wu Q, Li X, et al.Remaining useful life estimation via transformer encoder enhanced by a gated convolutional unit[J].Journal of Intelligent Manufacturing, 2021, 32(7):1997-2006
[25]Zhang J, Li X, Tian J, et al.An integrated multi-head dual sparse self-attention network for remaining useful life prediction[J].Reliability Engineering & System Safety, 2023, 233:109096-
[26]Li Y, Chen Y, Hu Z, et al.Remaining useful life prediction of aero-engine enabled by fusing knowledge and deep learning models[J].Reliability Engineering & System Safety, 2023, 229:108869-
[27]Xiang S, Li P, Huang Y, et al.Single gated RNN with differential weighted information storage mechanism and its application to machine RUL prediction[J].Reliability Engineering & System Safety, 2024, 242:109741-
[28]Xiang S, Zheng X, Miao J, et al.Dynamic Self-Learning neural network and its application for rotating equipment RUL prediction[J].IEEE Internet of Things Journal, 2024, :-
[29]曲桂娴, 刘冬阳, 杨旭, 等.基于传感器时序信息增强的剩余寿命预测方法[J].航空学报, 2025, 46(17):231634-
[30]章东平, 王大为, 何数技, 等.基于跨维度特征融合的航空发动机寿命预测[J].浙江大学学报：工学版, 2025, 59(7):1504-1513
[31]王昱, 张哲成, 杨晓庆.基于MTCN和双重注意力的航空发动机RUL预测[J].电子测量与仪器学报, 2025, 39(11):142-151
[32]许丹阳, 尚洁, 蒋琛, 等.基于自适应时空图卷积网络的航空发动机剩余寿命预测[J].计算机集成制造系统, 2025, 31(06):2165-2177
[33]Li D, Chen J, Huang R, et al.Sensor-aware CapsNet: Towards trustworthy multisensory fusion for remaining useful life prediction[J].Journal of Manufacturing Systems, 2024, 72:26-37
[34]Zhang Y, Su C, Wu J, et al.Trend-augmented and temporal-featured Transformer network with multi-sensor signals for remaining useful life prediction[J].Reliability Engineering & System Safety, 2024, 241:109662-
[35]Xu Z, Zhang Y, Miao Q.An attention-based multi-scale temporal convolutional network for remaining useful life prediction[J].Reliability Engineering & System Safety, 2024, 250:110288-
[36]Shi J, Zhong J, Zhang Y, et al.A dual attention LSTM lightweight model based on exponential smoothing for remaining useful life prediction[J].Reliability Engineering & System Safety, 2024, 243:109821-
CJA