Aircraft Engine Run-to-Failure Dataset under Real Flight Conditions for Prognostics and Diagnostics
Abstract
:1. Introduction
2. Data Description
2.1. CMAPSS Model
2.2. Flight Data
2.3. Data Records
3. Methods
- Define flight conditions. Real flight conditions as recorded on board of a commercial jet (i.e., NASA DASHlink [22] data) are taken as input to an engine simulator.
- Impose degradation. Degradation of the engine components is imposed at each flight.
- Simulation of a degraded flight. Complete flight covering climb, cruise and descend conditions is simulated with the CMAPSS dynamical model [23].
- Flight until failure. As a result of the degradation of the engines’ components, the health state of the engine decreases. The simulation of full flights (steps 1–3) with increasing degradation continues until the health index of the engine has reached zero i.e., ; which defines the end-of-life.
- Add sensor noise. Sensor noise is added to the simulated data to account for the variability of real sensor readings.
3.1. Degradation Model
3.2. Health Condition
3.3. Sensor Noise
3.4. Technical Validation
3.4.1. Examination of the Flight Profiles
3.4.2. Examination of the Degradation Trajectories
3.4.3. Examination of the Transition Times
4. Usage Notes
4.1. Prognostics Problem
Evaluation Metric
4.2. Diagnostics Problem
5. Discussion
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Goebel, K.; Daigle, M.; Saxena, A.; Roychoudhury, I.; Sankararaman, S. Prognostics: The Science of Making Predictions; Createspace Independent Publishing Platform: Scotts Valley, CA, USA, 2017. [Google Scholar]
- Fink, O.; Wang, Q.; Svensén, M.; Dersin, P.; Lee, W.J.; Ducoffe, M. Potential, challenges and future directions for deep learning in prognostics and health management applications. Eng. Appl. Artif. Intell. 2020, 92, 103678. [Google Scholar]
- Lei, Y.; Li, N.; Guo, L.; Li, N.; Yan, T.; Lin, J. Machinery health prognostics: A systematic review from data acquisition to RUL prediction. Mech. Syst. Signal Process. 2018, 104, 799–834. [Google Scholar]
- Hu, C.; Youn, B.D.; Wang, P.; Yoon, J.T. Ensemble of data-driven prognostic algorithms for robust prediction of remaining useful life. Reliab. Eng. Syst. Saf. 2012, 103, 120–135. [Google Scholar]
- Zhang, C.; Lim, P.; Qin, A.K.; Tan, K.C. Multiobjective deep belief networks ensemble for remaining useful life estimation in prognostics. IEEE Trans. Neural Netw. Learn. Syst. 2016, 28, 2306–2318. [Google Scholar] [PubMed]
- Booyse, W.; Wilke, D.N.; Heyns, S. Deep digital twins for detection, diagnostics and prognostics. Mech. Syst. Signal Process. 2020, 140, 106612. [Google Scholar]
- Da Costa, P.R.d.O.; Akcay, A.; Zhang, Y.; Kaymak, U. Remaining useful lifetime prediction via deep domain adaptation. Reliab. Eng. Syst. Saf. 2020, 195, 106682. [Google Scholar]
- Eker, Ö.F.; Camci, F.; Jennions, I.K. Major challenges in prognostics: Study on benchmarking prognostic datasets. In Proceedings of the 1st European Conference of the Prognostics and Health Management Society 2012, Dresden, Germany, 3–6 July 2012; Volume 3, p. 8. [Google Scholar]
- Prognostics Center of Excellence—Data Repository. 2020. Available online: https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository/ (accessed on 23 April 2019).
- Saxena, A.; Goebel, K. PHM08 Challenge Data Set. 2008. Available online: https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository/ (accessed on 23 April 2019).
- Saxena, A.; Goebel, K.; Simon, D.; Eklund, N. Damage propagation modeling for aircraft engine run-to-failure simulation. In Proceedings of the 2008 International Conference on Prognostics and Health Management, Denver, CO, USA, 6–9 October 2008; pp. 1–9. [Google Scholar] [CrossRef]
- Li, X.; Ding, Q.; Sun, J.Q. Remaining useful life estimation in prognostics using deep convolution neural networks. Reliab. Eng. Syst. Saf. 2018, 172, 1–11. [Google Scholar]
- Yang, H.; Zhao, F.; Jiang, G.; Sun, Z.; Mei, X. A Novel Deep Learning Approach for Machinery Prognostics Based on Time Windows. Appl. Sci. 2019, 9, 4813. [Google Scholar] [CrossRef] [Green Version]
- De Oliveira da Costa, P.R.; Akcay, A.; Zhang, Y.; Kaymak, U. Attention and long short-term memory network for remaining useful lifetime predictions of turbofan engine degradation. Int. J. Progn. Health Manag. 2019, 10, 034. [Google Scholar]
- Listou Ellefsen, A.; Bjørlykhaug, E.; Æsøy, V.; Ushakov, S.; Zhang, H. Remaining useful life predictions for turbofan engine degradation using semi-supervised deep architecture. Reliab. Eng. Syst. Saf. 2019, 183, 240–251. [Google Scholar] [CrossRef]
- Remaining Useful Life Prediction of Airplane Engine Based on PCA–BLSTM. Sensors 2020, 20, 4537. [CrossRef]
- Shi, Z.; Chehade, A. A dual-LSTM framework combining change point detection and remaining useful life prediction. Reliab. Eng. Syst. Saf. 2021, 205, 107257. [Google Scholar] [CrossRef]
- Wu, J.; Hu, K.; Cheng, Y.; Zhu, H.; Shao, X.; Wang, Y. Data-driven remaining useful life prediction via multiple sensor signals and deep long short-term memory neural network. ISA Trans. 2020, 97, 241–250. [Google Scholar] [PubMed]
- Xia, T.; Song, Y.; Zheng, Y.; Pan, E.; Xi, L. An ensemble framework based on convolutional bi-directional LSTM with multiple time windows for remaining useful life estimation. Comput. Ind. 2020, 115, 103182. [Google Scholar]
- Zhao, C.; Huang, X.; Li, Y.; Yousaf Iqbal, M. A Double-Channel Hybrid Deep Neural Network Based on CNN and BiLSTM for Remaining Useful Life Prediction. Sensors 2020, 20, 7109. [Google Scholar] [CrossRef]
- Xie, Z.; Du, S.; Lv, J.; Deng, Y.; Jia, S. A Hybrid Prognostics Deep Learning Model for Remaining Useful Life Prediction. Electronics 2020, 10, 39. [Google Scholar] [CrossRef]
- DASHlink—Flight Data For Tail 687. 2012. Available online: https://c3.nasa.gov/dashlink/resources/664/ (accessed on 23 January 2019).
- Frederick, D.K.; Decastro, J.A.; Litt, J.S. User’s Guide for the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS); Technical Report; NASA: Washington, DC, USA, 2007.
- Kobayashi, T.; Simon, D.L. Evaluation of an Enhanced Bank of Kalman Filters for In-Flight Aircraft Engine Sensor Fault Diagnostics. J. Eng. Gas Turbines Power 2005, 127, 497–504. [Google Scholar] [CrossRef] [Green Version]
- Borguet, S.; Leónard, O. A Generalised Likelihood Ratio Test for Adaptive Gas Turbine Health Monitoring. In Proceedings of the ASME Turbo Expo 2008: Power for Land, Sea, and Air, Berlin, Germany, 9–13 June 2008. [Google Scholar] [CrossRef]
- Tian, Y.; Arias Chao, M.; Kulkarni, C.; Goebel, K.; Fink, O. Real-Time Model Calibration with Deep Reinforcement Learning. arXiv 2020, arXiv:2006.04001. [Google Scholar]
- Arias Chao, M.; Kulkarni, C.; Goebel, K.; Fink, O. Fusing Physics-based and Deep Learning Models for Prognostics. arXiv 2020, arXiv:2003.00732. [Google Scholar]
- Willard, J.; Jia, X.; Xu, S.; Steinbach, M.; Kumar, V. Integrating Physics-Based Modeling with Machine Learning: A Survey. arXiv 2020, arXiv:2003.04919. [Google Scholar]
1 | DS08 is provided in five separate files i.e., DS08a-DS08e for easier handling. |
2 | i.e., altitude = 20 Kft, flight match number = 0.7, and throttle–resolver angle = 100%. |
Flight Class | Flight Length [h] | Number of Flights [#] |
---|---|---|
1 | 1 to 3 | 18 |
2 | 3 to 5 | 149 |
3 | >5 | 185 |
Name | # Units | Flight Classes | Failure Modes | Fan | LPC | HPC | HPT | LPT | Size | |||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
E | F | E | F | E | F | E | F | E | F | |||||
DS01 | 10 | 1, 2, 3 | 1 | ✓ | 7.6 M | |||||||||
DS02 | 9 | 1, 2, 3 | 2 | ✓ | ✓ | ✓ | 6.5 M | |||||||
DS03 | 15 | 1, 2, 3 | 1 | ✓ | ✓ | ✓ | 9.8 M | |||||||
DS04 | 10 | 2, 3 | 1 | ✓ | ✓ | 10.0 M | ||||||||
DS05 | 10 | 1, 2, 3 | 1 | ✓ | ✓ | 6.9 M | ||||||||
DS06 | 10 | 1, 2, 3 | 1 | ✓ | ✓ | ✓ | ✓ | 6.8 M | ||||||
DS07 | 10 | 1, 2, 3 | 1 | ✓ | ✓ | 7.2 M | ||||||||
DS08 | 54 | 1, 2, 3 | 1 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ | 35.6 M |
Development Data () | |
---|---|
Name | Description |
W_dev | Scenario descriptors—w |
X_s_dev | Measurements— |
X_v_dev | Virtual sensor— |
T_dev | Health Parameters— |
Y_dev | [in cycles] |
A_dev | Auxiliary data |
Test Data () | |
Name | Description |
W_test | Scenario descriptors -w |
X_s_test | Measurements— |
X_v_test | Virtual sensor— |
T_test | Health Parameters— |
Y_test | [in cycles] |
A_test | Auxiliary data |
Variables Name | |
Name | Description |
W_var | w variables |
X_s_var | variables |
X_v_var | variables |
T_var | variables |
A_var | Auxiliary variables |
# | Symbol | Description | Units |
---|---|---|---|
1 | alt | Altitude | ft |
2 | Mach | Flight Mach number | - |
3 | TRA | Throttle–resolver angle | % |
4 | T2 | Total temperature at fan inlet | °R |
# | Symbol | Description | Units |
---|---|---|---|
1 | Wf | Fuel flow | pps |
2 | Nf | Physical fan speed | rpm |
3 | Nc | Physical core speed | rpm |
4 | T24 | Total temperature at LPC outlet | °R |
5 | T30 | Total temperature at HPC outlet | °R |
6 | T48 | Total temperature at HPT outlet | °R |
7 | T50 | Total temperature at LPT outlet | °R |
8 | P15 | Total pressure in bypass-duct | psia |
9 | P2 | Total pressure at fan inlet | psia |
10 | P21 | Total pressure at fan outlet | psia |
11 | P24 | Total pressure at LPC outlet | psia |
12 | Ps30 | Static pressure at HPC outlet | psia |
13 | P40 | Total pressure at burner outlet | psia |
14 | P50 | Total pressure at LPT outlet | psia |
# | Symbol | Description | Units |
---|---|---|---|
1 | T40 | Total temp. at burner outlet | °R |
2 | P30 | Total pressure at HPC outlet | psia |
3 | P45 | Total pressure at HPT outlet | psia |
4 | W21 | Fan flow | pps |
5 | W22 | Flow out of LPC | lbm/s |
6 | W25 | Flow into HPC | lbm/s |
7 | W31 | HPT coolant bleed | lbm/s |
8 | W32 | HPT coolant bleed | lbm/s |
9 | W48 | Flow out of HPT | lbm/s |
10 | W50 | Flow out of LPT | lbm/s |
11 | SmFan | Fan stall margin | – |
12 | SmLPC | LPC stall margin | – |
13 | SmHPC | HPC stall margin | – |
14 | phi | Ratio of fuel flow to Ps30 | pps/psi |
# | Symbol | Description | Units |
---|---|---|---|
1 | fan_eff_mod | Fan efficiency modifier | - |
2 | fan_flow_mod | Fan flow modifier | - |
3 | LPC_eff_mod | LPC efficiency modifier | - |
4 | LPC_flow_mod | LPC flow modifier | - |
5 | HPC_eff_mod | HPC efficiency modifier | - |
6 | HPC_flow_mod | HPC flow modifier | - |
7 | HPT_eff_mod | HPT efficiency modifier | - |
8 | HPT_flow_mod | HPT flow modifier | - |
9 | LPT_eff_mod | LPT efficiency modifier | - |
10 | LPT_flow_mod | HPT flow modifier | - |
# | Symbol | Description | Units |
---|---|---|---|
1 | unit | Unit number | - |
2 | cycle | Flight cycle number | - |
3 | Fc | Flight class | - |
4 | Health state | - |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Arias Chao, M.; Kulkarni, C.; Goebel, K.; Fink, O. Aircraft Engine Run-to-Failure Dataset under Real Flight Conditions for Prognostics and Diagnostics. Data 2021, 6, 5. https://doi.org/10.3390/data6010005
Arias Chao M, Kulkarni C, Goebel K, Fink O. Aircraft Engine Run-to-Failure Dataset under Real Flight Conditions for Prognostics and Diagnostics. Data. 2021; 6(1):5. https://doi.org/10.3390/data6010005
Chicago/Turabian StyleArias Chao, Manuel, Chetan Kulkarni, Kai Goebel, and Olga Fink. 2021. "Aircraft Engine Run-to-Failure Dataset under Real Flight Conditions for Prognostics and Diagnostics" Data 6, no. 1: 5. https://doi.org/10.3390/data6010005
APA StyleArias Chao, M., Kulkarni, C., Goebel, K., & Fink, O. (2021). Aircraft Engine Run-to-Failure Dataset under Real Flight Conditions for Prognostics and Diagnostics. Data, 6(1), 5. https://doi.org/10.3390/data6010005