Uncertainty-Aware Prognosis via Deep Gaussian Process

被引:26
作者
Biggio, Luca [1 ,2 ]
Wieland, Alexander [1 ]
Chao, Manuel Arias [1 ]
Kastanis, Iason [2 ]
Fink, Olga [1 ]
机构
[1] Swiss Fed Inst Technol, CH-8093 Zurich, Switzerland
[2] Ctr Suisse Elect & Microtech CSEM, CH-2002 Neuchatel, Switzerland
关键词
Uncertainty; Global Positioning System; Predictive models; Standards; Bayes methods; Gaussian processes; Neural networks; Deep Gaussian processes; remaining useful life estimation; uncertainty quantification; REMAINING USEFUL LIFE; NEURAL-NETWORK; PREDICTION;
D O I
10.1109/ACCESS.2021.3110049
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The task of predicting how long a certain industrial asset will be able to operate within its nominal specifications is called Remaining Useful Life (RUL) estimation. Efficient methods of performing this task promise to drastically transform the world of industrial maintenance, paving the way for the so-called Industry 4.0 revolution. Given the abundance of data resulting from the advent of the digitalization era, Machine Learning (ML) models are the ideal candidates for tackling the RUL estimation problem in a fully data-driven fashion. However, given the safety-critical nature of maintenance operations on industrial assets, it's crucial that such ML-based methods be designed such that their levels of transparency and reliability are maximized. Modern ML algorithms, however, are often employed as black-box methods, which do not provide any clue regarding the confidence level associated with their output. In this paper, we address this limitation by investigating the performance of a recently proposed class of algorithms, Deep Gaussian Processes, which provide uncertainty estimates associated with their RUL prediction, yet retain the expressive power of modern ML techniques. Contrary to standard approaches to uncertainty quantification, such methods scale favourably with the size of the available datasets, allowing their usage in the "big data" setting. We perform a thorough evaluation and comparison of several variants of DGPs applied to RUL predictions. The performance of the algorithms is evaluated on the NASA N-CMAPSS (New Commercial Modular Aero-Propulsion System Simulation) dataset for aircraft engines. The results show that the proposed methods are able to yield very accurate RUL predictions along with sensible uncertainty estimates, providing more reliable solutions for (safety-critical) real-life industrial applications.
引用
收藏
页码:123517 / 123527
页数:11
相关论文
共 50 条
[41]   Uncertainty-aware structural damage warning system using deep variational composite neural networks [J].
Eltouny, Kareem A. ;
Liang, Xiao .
EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS, 2023, 52 (11) :3345-3368
[42]   GPyro: uncertainty-aware temperature predictions for additive manufacturing [J].
Sideris, Iason ;
Crivelli, Francesco ;
Bambach, Markus .
JOURNAL OF INTELLIGENT MANUFACTURING, 2023, 34 (01) :243-259
[43]   Uncertainty-aware Cross-Entropy for Semantic Segmentation [J].
Landgraf, Steven ;
Hillemann, Markus ;
Wursthorn, Kira ;
Ulrich, Markus .
ISPRS ANNALS OF THE PHOTOGRAMMETRY, REMOTE SENSING AND SPATIAL INFORMATION SCIENCES: VOLUME X-2-2024, 2024, :129-136
[44]   Uncertainty-Aware Gaze Tracking for Assisted Living Environments [J].
Her, Paris ;
Manderle, Logan ;
Dias, Philipe A. ;
Medeiros, Henry ;
Odone, Francesca .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 32 :2335-2347
[45]   Uncertainty-Aware Guided Volume Segmentation [J].
Prassni, Joerg-Stefan ;
Ropinski, Timo ;
Hinrichs, Klaus .
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2010, 16 (06) :1358-1365
[46]   Uncertainty-Aware Principal Component Analysis [J].
Goertler, Jochen ;
Spinner, Thilo ;
Streeb, Dirk ;
Weiskopf, Daniel ;
Deussen, Oliver .
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2020, 26 (01) :822-831
[47]   Uncertainty-Aware Authentication Model for IoT [J].
Heydari, Mohammad ;
Mylonas, Alexios ;
Katos, Vasilis ;
Balaguer-Ballester, Emili ;
Altaf, Amna ;
Tafreshi, Vahid Heydari Fami .
COMPUTER SECURITY, ESORICS 2019, 2020, 11980 :224-237
[48]   Doubly Intention Learning for Cold-start Recommendation with Uncertainty-aware Stochastic Meta Process [J].
Liu, Huafeng ;
Zhou, Mingjie ;
Jing, Liping ;
Ng, Michael K. .
PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, :6212-6222
[49]   Uncertainty-aware Simulation of Adaptive Systems [J].
Jezequel, Jean-Marc ;
Vallecillo, Antonio .
ACM TRANSACTIONS ON MODELING AND COMPUTER SIMULATION, 2023, 33 (03)
[50]   Load Uncertainty-Aware Economic Dispatch [J].
Rawal, Keerti ;
Ahmad, Aijaz .
2023 IEEE PES 15TH ASIA-PACIFIC POWER AND ENERGY ENGINEERING CONFERENCE, APPEEC, 2023,