The prediction of torque in a diesel engine using ion currents and artificial neural networks

Ion currents in engines contain important information on combustion that sensors that are currently used are unable to detect. This study focuses on the analysis of ion current signals in a diesel engine. The various features of the ion current signal are described in the context of the heat release rate and in-cylinder pressure signal to better understand the components of the ion current. A variety of back-propagation artificial neural networks are used to predict expansion work, net indicated mean effective pressure and engine out torque from the ion current signal. The factors affecting the performance of the artificial neural networks that were investigated were the number of hidden layers, number of hidden nodes and the desired training error. It was found that more complex networks were better able to predict engine out torque and took longer to train. A reduction in the desired training error improved performance up to a point when the network was no longer able to converge. The effect of averaging on the signal was also tested. Averaging signals at the input to the network was found to reduce the accuracy of predictions of the network, as a result of the reduction in size of the training set.

[1]  Liisa Pirjola,et al.  Heavy duty diesel engine exhaust aerosol particle and ion measurements. , 2009, Environmental science & technology.

[2]  M. S. Goodman,et al.  Transient Air/Fuel Ratio Control of an S.I. Engine Using Neural Networks , 1996 .

[3]  Lars Eriksson,et al.  An ion-sense engine fine-tuner , 1998 .

[4]  M. Taveniku,et al.  Estimating pressure peak position and air-fuel ratio using the ionization current and artificial neural networks , 1997, Proceedings of Conference on Intelligent Transportation Systems.

[5]  Richard J. Atkinson,et al.  Neural Network-Based Diesel Engine Emissions Prediction Using In-Cylinder Combustion Pressure , 1999 .

[6]  P. Mehresha,et al.  Combustion timing in HCCI engines determined by ion-sensor : experimental and kinetic modeling , 2004 .

[7]  M. Glavmo,et al.  Closed Loop Start of Combustion Control Utilizing Ionization Sensing in a Diesel Engine , 1999 .

[8]  Fabian Mauss,et al.  Local Air-Fuel Ratio Measurements Using the Spark Plug as an Ionization Sensor , 1997 .

[9]  Mitsunobu Kajitani,et al.  Development of New Ion Current Combustion Control System , 1998 .

[10]  Ahmed A. Abdel-Rehim,et al.  Characteristics of ion current signals in compression ignition and spark ignition engines , 2010 .

[11]  Fredrik Haglind,et al.  Validation of a zero-dimensional model for prediction of NOx and engine performance for electronically controlled marine two-stroke diesel engines , 2012 .

[12]  Christopher J. Rutland,et al.  Application of artificial neural networks in engine modelling , 2004 .

[13]  Ming Chia Lai,et al.  In-cylinder air/fuel ratio approximation using spark gap ionization sensing , 1998 .

[14]  Damon Honnery,et al.  Heat release model for the combustion of diesel oil emulsions in DI diesel engines , 2005 .

[15]  Dierk Schröder,et al.  Air-Fuel Ratio Control for Direct Injecting Combustion Engines Using Neural Networks , 1998 .

[16]  Damon Honnery,et al.  Performance, emissions and heat release characteristics of direct injection diesel engine operating on diesel oil emulsion , 2006 .

[17]  Magín Lapuerta,et al.  Modeling diesel particulate emissions with neural networks , 2001 .

[18]  Joseph R. Asik,et al.  Transient A/F Estimation and Control Using a Neural Network , 1997 .

[19]  Pascal Higelin,et al.  Limitations of Ionization Current Sensors and Comparison with Cylinder Pressure Sensors , 2000 .

[20]  P. Gaffuri,et al.  Autoignition Chemistry of the Hexane Isomers : An Experimental nd Kinetic Modeling Sudy , 2007 .

[21]  Steffen Leonhardt,et al.  Real-time supervision for diesel engine injection , 1994 .

[22]  Stephen T. Welstead,et al.  Neural network and fuzzy logic applications in C/C++ , 1994, Wiley professional computing.

[24]  Naeim A. Henein,et al.  Ion Current, Combustion and Emission Characteristics in an Automotive Common Rail Diesel Engine , 2010 .

[25]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[26]  Robert W. Dibble,et al.  Combustion Timing in HCCI Engines Determined by Ion-Sensor: Experimental and Kinetic Modeling , 2005 .

[27]  Rolf Isermann,et al.  Fast neural networks for diesel engine control design , 1999 .

[28]  Steffen Leonhardt,et al.  Real-time supervision for diesel engine injection , 1994 .

[29]  Wen-Hua Chen,et al.  Computationally Inexpensive Methods of Ion Current Signal Manipulation for Predicting the Characteristics of Engine In-Cylinder Pressure , 2006 .

[30]  Nigel N. Clark,et al.  NEURAL NETWORK MODELLING OF THE EMISSIONS AND PERFORMANCE OF A HEAVY-DUTY DIESEL ENGINE , 2000 .

[31]  D. Flowers,et al.  Experimental and numerical investigation of effect of fuel on ion sensor signal to determine combustion timing in homogeneous charge compression ignition engines , 2005 .

[32]  Christian Igel,et al.  Empirical evaluation of the improved Rprop learning algorithms , 2003, Neurocomputing.

[33]  Ulrich Spicher,et al.  Ion current measurement in diesel engines , 2004 .