Xiaosheng Li
ABSTRACT
The entire life cycle of an engine is an asymmetric process, and the characteristics of its internal components are different. It is of great significance to extract engine degradation features and build models for improving the RUL prediction of the main engine. In this paper, a RUL prediction method based on CBAM attention mechanism is designed. For long time series engine data, using Convolutional Neural Network (CNN) to extract features and share convolutional kernels can process high-dimensional data well. The purpose of adding a Gated Recurrent Unit (GRU) network is to use the GRU network to sequentially model the feature expressions extracted from the CNN network and learn the sequential correlation of data. Convolutional block attention module (CBAM) is introduced as a mechanism to reduce the influence of different data lengths on the final prediction by focusing on the channels and spaces. This paper validates the above prediction method on two different engine datasets. The prediction method can effectively mine the internal time and space dependence between multiple sensor data, improve the precision of RUL prediction, and prove that the method has good applicability and effectiveness.
- H. Oh, M. H. Azarian, M. Pecht, C. H. White, R. C. Sohaney, and E. Rhem. 2010. Physics-of-failure approach for fan PHM in electronics applications. Prognostics & System Health Management Conference. IEEE, pp.1-6.Google Scholar
- Salahshoor K, Mosallaei M, Bayat M. 2008. Centralized and decentralized process and sensor fault monitoring using data fusion based on adaptive extended Kalman filter algorithm. Measurement, 41(10): 1059-1076.Google ScholarCross Ref
- Ordonez, CelestinoSanchezLasheras, FernandoRoca-Pardinas, Javierde Cos Juez, Francisco Javier. 2019. A hybrid ARIMA-SVM model for the study of the remaining useful life of aircraft engines. Journal of Computational and Applied Mathematics, vol. 346, pp. 184-191.Google ScholarDigital Library
- Khelif R, Chebel-Morello B, Malinowski S, 2017. Direct Remaining Useful Life Estimation Based on Support Vector Regression. IEEE Transactions on Industrial Electronics, 64(3): 2276-2285.Google ScholarCross Ref
- Jiang Y, Zeng W, Shen J, Chu J. 2019. Prediction of remaining useful life of lithiumion battery based on convex optimization life parameter degradation mechanism model. Proc. CSU EPSA 2019, 31, 23- 28.Google Scholar
- Gao T, Li Y, Huang X, 2020. Data-Driven Method for Predicting Remaining Useful Life of Bearing Based on Bayesian Theory. Sensors, 21(1): 182.Google ScholarCross Ref
- Li H, Zhao W, Zhang Y, 2020. Remaining useful life prediction using multi-scale deep convolutional neural network. Applied Soft Computing, 89: 106113.Google ScholarDigital Library
- Wu R, Ma J.2019. An Improved LSTM Neural Network with Uncertainty to Predict Remaining Useful Life. 2019 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS). pp. 274-279.Google Scholar
- Wang B, Lei Y, Yan T, 2020. Recurrent convolutional neural network: A new framework for remaining useful life prediction of machinery. Neurocomputing, 379: 117-129.Google ScholarDigital Library
- Wang S, Zhang X, Gao D, 2018. A Remaining Useful Life Prediction Model Based on Hybrid Long-Short Sequences for Engines. 2018 IEEE International Conference on Intelligent Transportation Systems (ITSC). IEEE, pp. 1757-1762.Google ScholarDigital Library
- Babu G S, Zhao P, Li X L. 2016. Deep Convolutional Neural Network Based Regression Approach for Estimation of Remaining Useful Life. Springer, Cham, pp.214-228.Google Scholar
- Jayasinghe L, Samarasinghe T, Yuen C, 2019. Temporal Convolutional Memory Networks for Remaining Useful Life Estimation of Industrial Machinery: IEEE, 10.1109/ICIT.2019.8754956.Google Scholar
- Li X, Zhang W, Ma H, 2020. Data alignments in machinery remaining useful life prediction using deep adversarial neural networks. Knowledge-Based Systems, 197: 105843.Google ScholarCross Ref
- Hur K. 2020. Remaining Useful Life Prognosis for Turbofan Engine Using Explainable Deep Neural Networks with Dimensionality Reduction. Sensors, vol. 20, no. 22, p.6626.Google ScholarCross Ref
- ZhaoZ, Liang B, Wang X, 2017. Remaining useful life prediction of aircraft engine based on degradation pattern learning - ScienceDirect. Reliability Engineering & System Safety, 164: 74-83.Google ScholarCross Ref
- Cun Y L, Boser B, Denker J S, 1990. Handwritten digit recognition with a back-propagation network. Advances in neural information processing systems, 2(2): 396-404.Google Scholar
- Woo S, Park J, Lee J Y, 2018. CBAM: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV). pp: 3-19.Google ScholarDigital Library
- Cheng Yi, Zhu H, Wu J, 2022. Residual service life prediction method of mechanical equipment based on nested long and short term memory network. Science in China: Science of Technology, 52(01): 76-87.Google Scholar
- Li J, Jia Y, Zhang Z, 2021. Residual life prediction of aero engine based on fusion neural network[J]. Propulsion technology, 42(08): 1725-1734.Google Scholar
- Li H, Wang Z, Li Z. 2022. An enhanced CNN-LSTM remaining useful life prediction model for aircraft engine with attention mechanism[J]. PeerJ. Computer science, 8:e1084.Google Scholar
Index Terms
- Research on Remaining Useful Life Prediction of Dual-fuel Main EngineBased on CBAM Attention Mechanism
Recommendations
Remaining Useful Life Prediction of Bearing Based on Deep Perceptron Neural Networks
BDIOT '18: Proceedings of the 2018 2nd International Conference on Big Data and Internet of ThingsThe life assessment and prediction research of the bearing is the most important content of the bearing long life and high reliable research. A novel remaining useful life prediction of bearing model that is deep learning based on deep perceptron neural ...
Attention-based Gate Recurrent Unit for remaining useful life prediction in prognostics
AbstractAn essential process in prognostics and health management (PHM) is remaining useful life (RUL) prediction. The traditional Recurrent Neural Networks (RNNs) and their variants are not very efficient at solving the regression problems of RUL ...
Highlights- Propose a novel method for RUL predictions based on an attention-based GRU.
- Construct an Encoder–Decoder model that integrates GRU.
- The attention assigns weights and uses the feature information effectively.
- Comparisons with ...
AA-LSTM: An Adversarial Autoencoder Joint Model for Prediction of Equipment Remaining Useful Life
Advances in Knowledge Discovery and Data MiningAbstractRemaining Useful Life (RUL) prediction of equipment can estimate the time when equipment reaches the safe operating limit, which is essential for strategy formulation to reduce the possibility of loss due to unexpected shutdowns. This paper ...
Comments