Abstract
The objective of this study is to present a neural observer that estimates changing injection behavior due to wear and aging effects within the nozzle of a common rail diesel injector. Using a dynamic identification system in combination with a modified learning rule, the neural observer is applicable to a wide range of problem sets. A multilayer perceptron (MLP) network with three layers and few neurons in the hidden layer ensures fast computing and high efficiency; network learning is based on quasi-Newton optimization and an additional line search algorithm. Modeling the bottom part of the injector introduces a simulation model, which is validated with experimental data from a solenoid common rail diesel injector. Estimation results conform well with the altered plant and therefore demonstrate the significant benefit of using the proposed neural network observer concept.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abdollahi, F., Talebi, H., Patel, R.: A stable neural network-based observer with application to flexible-joint manipulators. IEEE Trans. Neural Netw. 17, 118–129 (2006). https://doi.org/10.1109/TNN.2005.863458
dAmbrosio, S., Ferrari, A.: Diesel injector coking: optical-chemical analysis of deposits and influence on injected flow-rate. Fuel spray and engine performance. J. Eng. Gas Turbines Power 134 (2012). https://doi.org/10.1115/1.4005991
Hintz, C.: Identifikation nichtlinearer mechatronischer Systeme mit strukturierten rekurrenten Netzen. PhD thesis, Technical University of Munich (2003)
Hofmann, O., Strau, P., Schuckert, S., Huber, B. et al.: Identification of aging effects in common rail diesel injectors using geometric classifiers and neural networks. SAE Technical Paper 2016-01-0813, SAE International (2016). https://doi.org/10.4271/2016-01-0813
Hofmann, O., Han, S., and Rixen, D.: Common rail diesel injectors with nozzle wear: modeling and state estimation. SAE Technical Paper 2017-01-0543, SAE International (2017). https://doi.org/10.4271/2017-01-0543
Ikemoto, M., Omae, K., Nakai, K., Ueda, R., Kakehashi, N., Sunami, K.: Injection nozzle coking mechanism in common-rail diesel engine. SAE Int. J. Fuels Lubric. 5(2011-01-1818), 78–87 (2011). https://doi.org/10.4271/2011-01-1818
Krogerus, T.R., Hyvnen M.P., Huhtala K.J.: A survey of analysis, modeling, and diagnostics of diesel fuel injection systems. J. Eng. Gas Turbines Power 138, 081501-1–081501-11 (2016). https://doi.org/10.1115/1.4032417
Nam, K., Yoon, M., Park, S., Sunwoo, M.: Development of a sensorless estimation algorithm of the injection timing and rate for an HSDI common-rail injector. JSME Int. J. Series C 47, 882–888 (2004). https://doi.org/10.1299/jsmec.47.882
Narendra, K., Annaswamy, A.: Stable adaptive systems. Int. J. Adapt. Control Signal Process. 4, 185–186 (1990). https://doi.org/10.1002/acs.4480040212
Nelles, O.: Nonlinear system identification: from classical approaches to neural networks and fuzzy models. Springer, Berlin Heidelberg, Germany (2001). https://doi.org/10.1007/978-3-662-04323-3
Nocedal, J., Wright, S.: Numerical Optimization. Springer Science & Business Media, New York, USA (2006). https://doi.org/10.1007/978-0-387-40065-5
Pfeiffer, F., Borchsenius, F.: New hydraulic system modelling. J. Vib. Control 10, 1493–1515 (2004). https://doi.org/10.1177/1077546304042063
Satkoski, C.A., Ruikar, N.S., Biggs, S.D., Shaver, G.M.: Piezoelectric fuel injection: cycle-to-cycle control of tightly spaced injections. Control Eng. Practice 20, 1175–1182 (2012). https://doi.org/10.1016/j.conengprac.2012.06.002
Talebi, H., Abdollahi, F., Patel, R., Khorasani, K.: Neural network-based state estimation of nonlinear systems. Lect. Notes Control Inf. Sci. 395, 15–35 (2010). https://doi.org/10.1007/978-1-4419-1438-5
Williams, R., Zipser D.: A learning algorithm for continually running fully recurrent neural networks. Neural Comput. 1, 270–280 (1989). https://doi.org/10.1162/neco.1989.1.2.270
Acknowledgements
This research is supported by the German Research Foundation (DFG, grant number RI2451/1). The authors would like to thank Sebastian Schuckert and Georg Wachtmeister of the Chair of Internal Combustion Engines, Technical University of Munich, for providing the experimental data used for validating the injector model.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Hofmann, O., Kiener, M., Rixen, D. (2019). A Neural Network Observer for Injection Rate Estimation in Common Rail Injectors with Nozzle Wear. In: Fleury, A., Rade, D., Kurka, P. (eds) Proceedings of DINAME 2017. DINAME 2017. Lecture Notes in Mechanical Engineering(). Springer, Cham. https://doi.org/10.1007/978-3-319-91217-2_19
Download citation
DOI: https://doi.org/10.1007/978-3-319-91217-2_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-91216-5
Online ISBN: 978-3-319-91217-2
eBook Packages: EngineeringEngineering (R0)