터보팬의 잔여 유효 수명 예측을 위한 다수 소수 특징 추출 병렬 연결 합성곱 신경망
Parallel-connected convolutional neural network with minority and majority feature extraction for the estimation of the remaining useful life of turbofans
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The prediction of remaining useful life (RUL) plays a crucial role in assessing the condition of a machine before it completely fails, ensuring performance by the execution of preventive maintenance beforehand. Recently, various deep learning models have been frequently used for RUL estimation, and they have shown good performance. However, these deep learning models face several challenges such as inefficiency owing to the selection of complex preprocessing methods, overfitting owing to model complexity, and other unresolved issues. Therefore, this study proposes a new deep-learning-based approach to address these issues by constructing a novel structure that includes a simple preprocessing step, minority feature extraction module, and majority feature extraction module. First, it explains the relatively simple preprocessing and assumptions regarding the target data of an undefined training set. Second, we describe the design of a convolution-based model using minority and majority feature extraction modules created through 2D convolutional layers. This model can learn the relationships between minority and majority sensors over time. By connecting the modules in parallel, it aggregates various types of information using multiple features from a single dataset. Finally, we present various experiments on the proposed algorithm and compare it with the latest existing methods using the NASA C-MAPSS dataset.
Abstract
The prediction of remaining useful life (RUL) plays a crucial role in assessing the condition of a machine before it completely fails, ensuring performance by the execution of preventive maintenance beforehand. Recently, various deep learning models have been frequently used for RUL estimation, and they have shown good performance. However, these deep learning models face several challenges such as inefficiency owing to the selection of complex preprocessing methods, overfitting owing to model complexity, and other unresolved issues. Therefore, this study proposes a new deep-learning-based approach to address these issues by constructing a novel structure that includes a simple preprocessing step, minority feature extraction module, and majority feature extraction module. First, it explains the relatively simple preprocessing and assumptions regarding the target data of an undefined training set. Second, we describe the design of a convolution-based model using minority and majority feature extraction modules created through 2D convolutional layers. This model can learn the relationships between minority and majority sensors over time. By connecting the modules in parallel, it aggregates various types of information using multiple features from a single dataset. Finally, we present various experiments on the proposed algorithm and compare it with the latest existing methods using the NASA C-MAPSS dataset.
참고문헌 (24)
- O. Merkt,, "On the Use of Predictive Models for Improving the Quality of Industrial Maintenance : an Analytical Literature Review of Maintenance Strategies", 2019 Federated Conference on Computer Science and Information Systems (FedCSIS), pp.693~704 (2019)
- Kim, K., "A Study on the Improvement of the Safety Quality of Defence in Korea through the Survey ·Analysis of the Safety Quality System of the UK MOD", Proceedings of the 2020 spring conference of the Korean Society for Quality Management, pp.106~106 (2020)
- Sakib, N., "Challenges and Opportunities of Condition-based Predictive Maintenance : A Review", Procedia CIRP, 78, pp.267~272 (2018)
- Pintelon, L., "Maintenance: An Evolutionary Perspective", pp.21~48 (2008), Springer Science & Business Media
- S. J. Engel, "Prognostics, The Real Issues Involved With Predicting Life Remaining", 2000 IEEE Aerospace Conference. Proceedings, 6, pp.457~469 (2000)
- Ahmad, R., "An overview of time-based and condition-based maintenanace in industrial application", Computers & Industrial Engineering, 63(1), pp.135~149 (2012)
- Son, M., "A Study on the Reflection of Condition-Based Maintenance Requirement in the Defense Specification", Journal of Korean Society for Quality Management, 49(3), pp.269~279 (2021)
- Lee, J., "Probabilistic Prognostics and Health Management of Energy Systems", pp.9~32 (2017), Springer
- Serradilla, O., "Interpreting Remaining Useful Life estimations combining Explainable Artificial Intelligence and domain knowledge in industrial machinery", 2020 IEEE International Conference on Fuzzy Systems (2020)
- Wang, Y., "Remaining Useful Life Prediction using Deep Learning Approaches : A Review", Procedia manufacturing, 49, pp.81~88 (2020)
- Li, X., "Remaining useful life estimation in prognostics using deep convolution neural networks", Reliability Engineering & System Safety, 172, pp.1~11 (2018)
- Lin, R., "Remaining useful life prediction in prognostics using multi-scale sequence and Long Short-Term Memory network", Journal of computational science, 57, pp.1~11 (2022)
- Asif, O., "A Deep Learning Model for Remaining Useful Life Prediction of Aircraft Turbofan Engine on C-MAPSS Dataset", IEEE Access, 10, pp.95425~95440 (2022)
- Wang, J., "Remaining Useful Life Estimation in Prognostics Using Deep Bidirectional LSTM Neural Network", 2018Prognostics and System Health Management Conference, pp.1037~1042 (2019)
- Shcherbakov, M., "A Hybrid Deep Learning Framework for Intelligent Predictive Maintenance of Cyber-physical Systems", ACM Transactions on Cyber-Physical Systems, 6(2), pp.1~22 (2022)
- Hong, C. W., "Remaining Useful Life Prognosis for Turbofan Engine Using Explainable Deep Neural Networks with Dimensionality Reduction", Sensors, 20(22), pp.1~19 (2020)
- Kong, Z., "Convolution and Long Short-Term Memory Hybrid Deep Neural Networks for Remaining Useful Life Prognostics", Applied Sciences, 9(19), pp.1~18 (2019)
- Wang, L., "Dynamic predictive maintenance strategy for system remaining useful life prediction via deep learning ensemble method", Reliability Engineering & System Safety, 245, pp.1~12 (2024)
- Back, M., "Development of 2D CNN-based Model for Remaining Useful Life of Turbofan Engine", Proceedings of the autumn annual conference of IEIE, pp.261~263 (2023)
- Frederick, D, K., "User’s guide for the commercial modular aero-propulsion system simulation(C-MAPSS)", National Aeronautics and Space Administration, ~ (2007)
- Saxena, A., "Damage Propagation Modeling for Aircraft Engine Run-to-Failure Simulation", 2008 international conference on prognostics and health management, pp.1~9 (2008)
- Heimes, F. O., "Recurrent neural networks for remaining useful life estimation", 2008 international conference on prognostics and health management, pp.1~6 (2008)
- Sateesh Babu, G., "Deep convolutional neural network based regression approach for estimation of remaining useful life", Database Systems for Advanced Applications: 21st International Conference, pp.214~228 (2016)