This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
An Efficient Machine Learning Algorithm for Valve Fault Detection
Technical Paper
2022-01-0163
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
Multi-level Miller-cycle Dynamic Skip Fire (mDSF) is a combustion engine technology that improves fuel efficiency by deciding on each cylinder-event whether to skip (deactivate) the cylinder, fire with low (Miller) charge, or fire with a high (Power) charge. In an engine with two intake and two exhaust valves per cylinder, skipping can be accomplished by deactivating all valves, while firing with a reduced charge is accomplished by deactivating one of the intake valves.
This new ability to modulate the charge level introduces new failure modes. The first is a failure to reactivate the single, high-charge intake valve, which results in a desired High Fire having the air intake of a Low Fire. The second is a failure to deactivate the single intake valve, which results in a Low Fire having the air intake of a High Fire. Reliably detecting these two faults has proven challenging for classical techniques that se measured MAP (Manifold Absolute Pressure) and/or crank angle acceleration to identify characteristic features of the failures. However, the fault detection problem proves to be very tractable using machine learning techniques like artificial neural networks and logistic regression. This paper presents a computationally efficient machine learning model for fault detection in an mDSF engine using a three-class Logistic Regression solution based on commonly available engine controller signals. Training and testing accuracy exceeded 98% based on steady-state engine dyno data with valve faults induced at a 1% rate. The model requires about 100 multiply and accumulate operations each cylinder-event.
Authors
Topic
Citation
Serrano, J., Ortiz-Soto, E., Chen, S., Chien, L. et al., "An Efficient Machine Learning Algorithm for Valve Fault Detection," SAE Technical Paper 2022-01-0163, 2022, https://doi.org/10.4271/2022-01-0163.Also In
References
- Stabinsky , M. , Albertson , W. , Tuttle , J. , Kehr , D. et al. Active Fuel Managementā¢ Technology: Hardware Development on a 2007 GM 3.9L V-6 OHV SI Engine SAE Technical Paper 2007-01-1292 2007 https://doi.org/10.4271/2007-01-1292.
- Falkowski , A. , McElwee , M. , and Bonne , M. Design and Development of the DaimlerChrysler 5.7L HEMIĀ® Engine MultiDisplacement Cylinder Deactivation System SAE Technical Paper 2004-01-2106 2004 https://doi.org/10.4271/2004-01-2106.
- Wilcutts , M. , Switkes , J. , Shost , M. , and Tripathi , A. Design and Benefits of Dynamic Skip Fire Strategies for Cylinder Deactivated Engines SAE Int. J. Engines 6 1 2013 278 288 https://doi.org/10.4271/2013-01-0359
- Serrano , J. , Routledge , G. , Lo , N. , Shost , M. et al. Methods of Evaluating and Mitigating NVH when Operating an Engine in Dynamic Skip Fire SAE Int. J. Engines 7 3 2014 1489 1501 https://doi.org/10.4271/2014-01-1675
- Younkins , M. , Ortiz-Soto , E. , Wilcutts , M. , Fuerst , J. , and Rayl , A. Dynamic Skip Fire: New Technologies for Innovative Propulsion Systems 39th eInternational Vienna Motor Symposium 2018
- Chen , S. , Schiffgens , H.J. , Wang , R. , and Scassa , M. Reduced Emissions and Consumption of Diesel Engines through Dynamic Cylinder Deactivation MTZ Worldwide 81 July-August 2020 60 64 10.1007/s38313-020-0246-2
- Ortiz-Soto , E. and Younkins , M. Advanced Cylinder Deactivation with Miller Cycle MTZ Worldwide 80 May 2019 58 63 10.1007/s38313-019-0032-1
- Ortiz-Soto , E. , Yang , X. , Van Ess , J. , Owlia , S. et al. Controls and Hardware Development of Multi-Level Miller Cycle Dynamic Skip Fire (mDSF) Technology SAE Int. J. Adv. & Curr. Prac. in Mobility 3 4 2021 1810 1823 https://doi.org/10.4271/2021-01-0446
- Chen , S.K. , Chien , L.-C. , Nagashima , M. , Van Ess , J. et al. Misfire Detection in a Dynamic Skip Fire Engine SAE Int. J. Engines 8 2 2015 https://doi.org/10.4271/2015-01-0210
- Chen , S. , Mandal , A. , Chien , L. , and Ortiz-Soto , E. Machine Learning for Misfire Detection in a Dynamic Skip Fire Engine SAE Int. J. Engines 11 6 965 976 2018 https://doi.org/10.4271/2018-01-1158
- Mandal , A. , Arvanitis , A. , Chen , S. , Chien , L. et al. Vibration Rating Prediction Using Machine Learning in a Dynamic Skip Fire Engine SAE Int. J. Adv. & Curr. Prac. in Mobility 1 4 2019 1491 1501 https://doi.org/10.4271/2019-01-1054
- Vaughan , A. and Bohac , S.V. Real-Time, Adaptive Machine Learning for Non-Stationary, Near Chaotic Gasoline Engine Combustion Time Series Neural Networks 2015 http://dx.doi.org/10.1016/j.neunet.2015.04.007
- LeCun , Y. , Matan , O. , Boser , B. , Denker , J.S. , et al. Handwritten Zip Code Recognition with Multilayer Networks Proceedings of the 10th International Conference on Pattern Recognition 1990 2 35 40 10.1109/ICPR.1990.119325
- Krizhevsky , A. , Sutskever , I. , and Hinton , G.E. ImageNet Classification with Deep Convolutional Neural Networks Communications ACM 60 6 84 90 2017 10.1145/3065386
- Rosenblatt , F. The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain Psychological Review 65 6 December 1958 386 408 10.1037/h0042519
- Bishop , C. Pattern Recognition and Machine Learning Springer Science 2006 205 210 0-387-31073-8
- Pedregosa , F. , Varoquaux , G. , Gramfort , A. , Michel , V. et al. Scikit-Learn: Machine Learning in Python JMLR 12 2011 2825 2830 https://www.jmlr.org/papers/v12/pedregosa11a.html