This content is not included in your SAE MOBILUS subscription, or you are not logged in.
Advanced Statistical System Identification in ECU-Development and Optimization
ISSN: 0148-7191, e-ISSN: 2688-3627
Published September 29, 2015 by SAE International in United States
Annotation ability available
The use of design of experiment (DoE) and data-driven simulation has become state-of-the-art in engine development and base calibration to cope with the drastically increased complexity of today's engine ECUs (electronic control units). Based on the representation of the engine behavior with a virtual plant model, offline optimizers can be used to find the optimal calibration settings for the engine controller, e.g. with respect to fuel consumption and exhaust gas emissions. This increases the efficiency of the calibration process and reduces the need for expensive test stand runs. The present paper describes the application of Gaussian process regression, a statistical modeling approach with practical benefits in terms of achievable model accuracy and usability. The implementation of the algorithm in a commercial tool framework enables a broad use in series engine calibration. Recent developments have extended the approach towards dynamic systems identification and simulation of transient behavior. Due to the data-driven nature, the generated plant models can further be used to replace time-consuming 1-D simulations (meta-modeling) without loss in model quality while meeting real-time requirements, e.g. for utilization in hardware-in-the-loop (HiL) environments. The application and benefits of the statistical modeling approach are shown on several examples.
CitationGutjahr, T., Kleinegraeber, H., Huber, T., and Kruse, T., "Advanced Statistical System Identification in ECU-Development and Optimization," SAE Technical Paper 2015-01-2796, 2015, https://doi.org/10.4271/2015-01-2796.
- Ulmer, H., Kruse, T. and Lang, T., “New Simulation and Automation Solutions for the Optimized Calibration of Complex Electronic Systems.” ETAS GmbH, Stuttgart, 2011.
- Röpke, K. et al., 5th Conference on “Design of Experiments (DoE) in Engine Development,” Berlin, 2009.
- Berger, B. and Rauscher, F., “Evaluation of Gaussian Processes for Black-Box Engine Modelling.” 6th Conference on “Design of Experiments (DoE) in Engine Development,” Berlin, 2011.
- Rasmussen, C. E. and Williams, C. K. I., “Gaussian Processes for Machine Learning.” MIT Press, 2006.
- Nelles, O., “Nonlinear System Identification: From Classical Approaches to Neural Networks and Fuzzy Models.” Springer, 2001.
- Quiñnonero-Candela, J., Rasmussen, C. E. and Williams, C. K. I., “Approximation Methods for Gaussian Process Regression.” Technical report, Microsoft Research, 2007.
- Röpke, K. et al., 6th Conference on “Design of Experiments (DoE) in Engine Development”, Berlin, 2011.
- Girard, A., Rasmussen, C. E. and Murray-Smith, R., “Gaussian Process Priors with Uncertain Inputs: Multiple-Step-Ahead Prediction.” Technical Report TR-2002-119, University of Glasgow, 2002.
- Groot, P., Lucas, P. and van den Bosch, P., “Multiple-step Time Series Forecasting with Sparse Gaussian Processes.” 23rd Benelux Conference on Artificial Intelligence, 2011.
- Kalman, R. E. and Bertram, J. E., “General Synthesis Procedure for Computer Control of Single and Multi-Loop Linear Systems.” Transactions of the American Institute of Electrical Engineers, volume 77, 1958.
- Isermann, R., “Digital Control Systems.” Springer, 1981.
- ECOpoint Inc. Emission Test Cycles: Worldwide Engine and Vehicle Test Cycles. March 2015. URL: http://www.dieselnet.com/standards/cycles/nrtc.php
- Griffiths, P. G., “Embedded Software Control Design for an Electronic Throttle Body.” Master's Thesis, Berkeley, CA, 2002.
- Lumpp, B., Tanimou, M., Trapel, E., Muenzenmay, M., McMackin, M., Bouillon, E., and Zimmermann, K., “Desktop Simulation and Calibration of Diesel Engine ECU Software using Software-In-The-Loop Methodology.” GT-SUITE European Conference, 2013.