Engine cylinder pressure reconstruction using crank kinematics and recurrently-trained neural networks

A recurrent non-linear autoregressive with exogenous input (NARX) neural network is proposed, and a suitable fully-recurrent training methodology is adapted and tuned, for reconstructing cylinder pressure in multi-cylinder IC engines using measured crank kinematics. This type of indirect sensing is important for cost effective closed-loop combustion control and for On-Board Diagnostics. The challenge addressed is to accurately predict cylinder pressure traces within the cycle under generalisation conditions: i.e. using data not previously seen by the network during training. This involves direct construction and calibration of a suitable inverse crank dynamic model, which owing to singular behaviour at top-dead-centre (TDC), has proved difficult via physical model construction, calibration, and inversion. The NARX architecture is specialised and adapted to cylinder pressure reconstruction, using a fully-recurrent training methodology which is needed because the alternatives are too slow and unreliable for practical network training on production engines. The fully-recurrent Robust Adaptive Gradient Descent (RAGD) algorithm, is tuned initially using synthesised crank kinematics, and then tested on real engine data to assess the reconstruction capability. Real data is obtained from a 1.125 litre, 3-cylinder, in-line, direct injection spark ignition (DISI) engine involving synchronised measurements of crank kinematics and cylinder pressure across a range of steady-state speed and load conditions. The paper shows that a RAGD-trained NARX network using both crank velocity and crank acceleration as input information, provides fast and robust training. By using the optimum epoch identified during RAGD training, acceptably accurate cylinder pressures, and especially accurate location-of-peak-pressure, can be reconstructed robustly under generalisation conditions, making it the most practical NARX configuration and recurrent training methodology for use on production engines.

[1]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[2]  Feilong Liu,et al.  An Experimental Study on Engine Dynamics Model Based In-Cylinder Pressure Estimation , 2012 .

[3]  Andrew Ball,et al.  Non-parametric models in the monitoring of engine performance and condition: Part 2: Non-intrusive estimation of diesel engine cylinder pressure and its use in fault detection , 1999 .

[4]  Yeng Chai Soh,et al.  Robust Adaptive Gradient-Descent Training Algorithm for Recurrent Neural Networks in Discrete Time Domain , 2008, IEEE Transactions on Neural Networks.

[5]  S. Haykin.  Kalman Filtering and Neural Networks , 2001 .

[6]  Roger Johnsson,et al.  Cylinder pressure reconstruction based on complex radial basis function networks from vibration and speed signals , 2006 .

[7]  Zhang Wu,et al.  Reconstruction of Cylinder Pressure of I.C. Engine Based on Neural Networks , 2010, 2010 First International Conference on Pervasive Computing, Signal Processing and Applications.

[8]  H Du,et al.  Reconstructing cylinder pressure from vibration signals based on radial basis function networks , 2001 .

[9]  Robert B. Randall,et al.  RECONSTRUCTION OF DIESEL ENGINE CYLINDER PRESSURE USING A TIME DOMAIN SMOOTHING TECHNIQUE , 1999 .

[10]  Riaz A. Mufti,et al.  Effect of cylinder pressure on engine valve-train friction under motored and fired conditions , 2012 .

[11]  Myoungho Sunwoo,et al.  A study on pegging methods for noisy cylinder pressure signal , 2008 .

[12]  Katarzyna Bizon,et al.  Reconstruction of In-Cylinder Pressure in a Diesel Engine from Vibration Signal Using a RBF Neural Network Model , 2011 .

[13]  Satish Chand,et al.  Reconstruction of cylinder pressure for SI engine using recurrent neural network , 2010, Neural Computing and Applications.

[14]  Stephen Yurkovich,et al.  A Model-based estimator of engine cylinder pressure imbalance for combustion feedback control applications , 2011, Proceedings of the 2011 American Control Conference.

[15]  Robert B. Randall,et al.  EFFECTIVE VIBRATION ANALYSIS OF IC ENGINES USING CYCLOSTATIONARITY. PART II—NEW RESULTS ON THE RECONSTRUCTION OF THE CYLINDER PRESSURES , 2002 .

[16]  John Alexander Steel,et al.  Indirect measurement of cylinder pressure from diesel engines using acoustic emission , 2005 .

[17]  Ibrahim Haskara,et al.  Real-time cylinder pressure and indicated torque estimation via second order sliding modes , 2001, Proceedings of the 2001 American Control Conference. (Cat. No.01CH37148).

[18]  Colin Bennett,et al.  Reconstruction of gasoline engine in-cylinder pressuresusing recurrent neural networks , 2014 .

[19]  Yann Guezennec,et al.  Estimation of cycle-resolved in-cylinder pressure and air-fuel ratio using spark plug ionization current sensing , 2001 .

[20]  Fengshou Gu,et al.  Non-parametric models in the monitoring of engine performance and condition: Part 1: Modelling of non-linear engine processes , 1999 .

[21]  F. Taglialatela,et al.  Determination of combustion parameters using engine crankshaft speed , 2013 .

[22]  Giorgio Rizzoni,et al.  Estimate of indicated torque from crankshaft speed fluctuations: a model for the dynamics of the IC engine , 1989 .

[23]  Paul King,et al.  Multicylinder engine pressure reconstruction using NARX neural networks and crank kinematics , 2007 .

[24]  Johann F. Böhme,et al.  Fast in-cylinder pressure reconstruction from structure-borne sound using the EM algorithm , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[25]  Myoungho Sunwoo,et al.  Torque estimation of spark ignition engines via cylinder pressure measurement , 2003 .

[26]  Julian F Dunne,et al.  A model for simulating the instantaneous crank kinematics and total mechanical losses in a multicylinder in-line engine , 2007 .