Machine Learning for Identification and Optimal Control of Advanced Automotive Engines.

Machine Learning for Identification and Optimal Control of Advanced Automotive Engines by Vijay Manikandan Janakiraman Co-Chairs: Professor Dennis N. Assanis, Professor XuanLong Nguyen and Professor Jeffrey Stein The complexity of automotive engines continues to increase to meet increasing performance requirements such as high fuel economy and low emissions. The increased sensing capabilities associated with such systems generate a large volume of informative data. With advancements in computing technologies, predictive models of complex dynamic systems useful for diagnostics and controls can be developed using data based learning. Such models have a short development time and can serve as alternatives to traditional physics based modeling. In this thesis, the modeling and control problem of an advanced automotive engine, the homogeneous charge compression ignition (HCCI) engine, is addressed using data based learning techniques. Several frameworks including design of experiments for data generation, identification of HCCI combustion variables, modeling the HCCI operating envelope and model predictive control have been developed and analyzed. In addition, stable online learning algorithms for a general class of nonlinear systems have been developed using extreme

[1]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[2]  D. Assanis,et al.  Homogeneous Charge Compression Ignition (HCCI) Engines , 2003 .

[3]  Bengt Johansson,et al.  HCCI Operating Range in a Turbo-charged Multi Cylinder Engine with VVT and Spray-Guided DI , 2009 .

[4]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[5]  Haralambos Sarimveis,et al.  A new algorithm for online structure and parameter adaptation of RBF networks , 2003, Neural Networks.

[6]  Mrdjan Jankovic,et al.  Nonlinear Observer-Based Control of Load Transitions in Homogeneous Charge Compression Ignition Engines , 2007, IEEE Transactions on Control Systems Technology.

[7]  Kevin M. Passino,et al.  Stable Adaptive Control and Estimation for Nonlinear Systems , 2001 .

[8]  Nello Cristianini,et al.  Controlling the Sensitivity of Support Vector Machines , 1999 .

[9]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[10]  Danil V. Prokhorov,et al.  Neural Networks in Automotive Applications , 2008, Computational Intelligence in Automotive Applications.

[11]  P. Olver.  Nonlinear Systems , 2013 .

[12]  G. Abd-Alla,et al.  Using exhaust gas recirculation in internal combustion engines: a review , 2002 .

[13]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[14]  Mrdjan J. Jankovic,et al.  Control Oriented Model and Dynamometer Testing for a Single-Cylinder, Heated-Air HCCI Engine , 2009 .

[15]  Marco Sorrentino,et al.  Development of recurrent neural networks for virtual sensing of NOx emissions in internal combustion engines , 2009 .

[16]  Jatinder N. D. Gupta,et al.  Comparative evaluation of genetic algorithm and backpropagation for training neural networks , 2000, Inf. Sci..

[17]  Taro Aoyama,et al.  An experimental study on premixed-charge compression ignition gasoline engine , 1995 .

[18]  Danil V. Prokhorov,et al.  Toyota Prius HEV neurocontrol and diagnostics , 2008, Neural Networks.

[19]  Bengt Johansson,et al.  HCCI Combustion Phasing in a Multi Cylinder Engine Using Variable Compression Ratio , 2002 .

[20]  Kar-Ann Toh,et al.  Deterministic Neural Classification , 2008, Neural Computation.

[21]  John J. Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities , 1999 .

[22]  C. Chiang,et al.  Constrained control of Homogeneous Charge Compression Ignition (HCCI) engines , 2010, 2010 5th IEEE Conference on Industrial Electronics and Applications.

[23]  R. C. Williamson,et al.  Support vector regression with automatic accuracy control. , 1998 .

[24]  De-Shuang Huang,et al.  Determining the centers of radial basis probabilistic neural networks by recursive orthogonal least square algorithms , 2005, Appl. Math. Comput..

[25]  A. Asuncion,et al.  UCI Machine Learning Repository, University of California, Irvine, School of Information and Computer Sciences , 2007 .

[26]  Gregory M. Shaver.  Stability analysis of residual-affected HCCI using convex optimization , 2009 .

[27]  S. Lyashevskiy,et al.  Nonlinear Systems Identification using the Lyapunov Method , 1994 .

[28]  Bengt Johansson,et al.  Homogeneous Charge Compression Ignition (HCCI) Using Isooctane, Ethanol and Natural Gas - A Comparison with Spark Ignition Operation , 1997 .

[29]  Vera Kurková,et al.  Kolmogorov's theorem and multilayer neural networks , 1992, Neural Networks.

[30]  Yonggwan Won,et al.  Regularized online sequential learning algorithm for single-hidden layer feedforward neural networks , 2011, Pattern Recognit. Lett..

[31]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[32]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[33]  G. Kalghatgi,et al.  Combustion Limits and Efficiency in a Homogeneous Charge Compression Ignition Engine , 2006 .

[34]  Narasimhan Sundararajan,et al.  An efficient sequential learning algorithm for growing and pruning RBF (GAP-RBF) networks , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[35]  Tianping Chen,et al.  Approximation capability to functions of several variables, nonlinear functionals and operators by radial basis function neural networks , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[36]  I. V. Kolmanovsky,et al.  Support vector machine-based determination of gasoline direct injected engine admissible operating envelope , 2002 .

[37]  O. Nelles.  Nonlinear System Identification: From Classical Approaches to Neural Networks and Fuzzy Models , 2000 .

[38]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[39]  Mingfa Yao,et al.  Progress and recent trends in homogeneous charge compression ignition (HCCI) engines , 2009 .

[40]  Keith R. Godfrey,et al.  Perturbation signals for system identification , 1993 .

[41]  Yonghong Tan,et al.  Nonlinear Dynamic Modelling Of Automotive Engines Using Neural Networks , 1997, Proceedings of the 1997 IEEE International Conference on Control Applications.

[42]  George E. Tsekouras,et al.  A novel training algorithm for RBF neural network using a hybrid fuzzy clustering approach , 2012, Fuzzy Sets Syst..

[43]  J. Christian Gerdes,et al.  Model-Based Control of HCCI Engines Using Exhaust Recompression , 2010, IEEE Transactions on Control Systems Technology.

[44]  Wei Chen,et al.  A fundamental study on the control of the HCCI combustion and emissions by fuel design concept combined with controllable EGR. Part 2. Effect of operating conditions and EGR on HCCI combustion , 2005 .

[45]  Erik Hellström,et al.  Fuel governor augmented control of recompression HCCI combustion during large load transients , 2012, 2012 American Control Conference (ACC).

[46]  Robert J. Scaringe,et al.  On the High Load Limit of Boosted Gasoline HCCI Engine Operating in NVO mode , 2010 .

[47]  M. Viberg,et al.  Adaptive neural nets filter using a recursive Levenberg-Marquardt search direction , 1998, Conference Record of Thirty-Second Asilomar Conference on Signals, Systems and Computers (Cat. No.98CH36284).

[48]  XuanLong Nguyen,et al.  A System Identification Framework for Modeling Complex Combustion Dynamics Using Support Vector Machines , 2014, ICINCO 2014.

[49]  M. Shahbakhti,et al.  Characterizing the cyclic variability of ignition timing in a homogeneous charge compression ignition engine fuelled with n-heptane/iso-octane blend fuels , 2008 .

[50]  Witold Pedrycz,et al.  Improving RBF networks performance in regression tasks by means of a supervised fuzzy clustering , 2006, Neurocomputing.

[51]  Bernhard Schölkopf,et al.  New Support Vector Algorithms , 2000, Neural Computation.

[52]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[53]  Margaret S. Wooldridge,et al.  A multi-mode combustion diagram for spark assisted compression ignition , 2010 .

[54]  Junichi Takanashi,et al.  A study of gasoline-fuelled HCCI engine equipped with an electromagnetic valve train , 2004 .

[55]  Robert D. Nowak,et al.  Nonlinear system identification with pseudorandom multilevel excitation sequences , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[56]  Wai K. Cheng,et al.  On HCCI Engine Knock , 2007 .

[57]  Yonggwan Won,et al.  A Robust Online Sequential Extreme Learning Machine , 2007, ISNN.

[58]  Dingli Yu,et al.  Selecting radial basis function network centers with recursive orthogonal least squares training , 2000, IEEE Trans. Neural Networks Learn. Syst..

[59]  Jooyoung Park,et al.  Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.

[60]  George A. Kontarakis.  Homogeneous charge compression ignition in four-stroke internal combustion engines , 2001 .

[61]  John E. Dec,et al.  Isolating the Effects of Fuel Chemistry on Combustion Phasing in an HCCI Engine and the Potential of Fuel Stratification for Ignition Control , 2004 .

[62]  Zhihong Man,et al.  On improving the conditioning of extreme learning machine: A linear case , 2009, 2009 7th International Conference on Information, Communications and Signal Processing (ICICS).

[63]  XuanLong Nguyen,et al.  Nonlinear identification of a gasoline HCCI engine using neural networks coupled with principal component analysis , 2013, Appl. Soft Comput..

[64]  Haibo He,et al.  Learning from Imbalanced Data , 2009, IEEE Transactions on Knowledge and Data Engineering.

[65]  Narasimhan Sundararajan,et al.  A Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks , 2006, IEEE Transactions on Neural Networks.

[66]  Klaus-Robert Müller,et al.  Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.

[67]  Alfred Leipertz,et al.  Simultaneous temperature and exhaust-gas recirculation-measurements in a homogeneous charge-compression ignition engine by use of pure rotational coherent anti-Stokes Raman spectroscopy. , 2006, Applied optics.

[68]  Vincent A. Akpan,et al.  Adaptive predictive control using recurrent neural network identification , 2009, 2009 17th Mediterranean Conference on Control and Automation.

[69]  Liu Biao,et al.  System identification of locomotive diesel engines with autoregressive neural network , 2009, 2009 4th IEEE Conference on Industrial Electronics and Applications.

[70]  Robert W. Dibble,et al.  1.9-Liter Four-Cylinder HCCI Engine Operation with Exhaust Gas Recirculation , 2001 .

[71]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[72]  Jeff Sterniak,et al.  Support Vector Machines for Identification of HCCI Combustion Dynamics , 2012, ICINCO.

[73]  A.G. Stefanopoulou,et al.  Dynamics of Homogeneous Charge Compression Ignition (HCCI) Engines with High Dilution , 2007, 2007 American Control Conference.

[74]  Dingli Yu,et al.  Modelling a variable valve timing spark ignition engine using different neural networks , 2004 .

[75]  Rajit Johri,et al.  Real-Time Transient Soot and NO , 2011 .

[76]  N. M. Barnes,et al.  Rapid, supervised training of a two-layer, opto-electronic neural network using simulated annealing , 1992 .

[77]  Léon Bottou,et al.  Large-Scale Machine Learning with Stochastic Gradient Descent , 2010, COMPSTAT.

[78]  Giorgio Rizzoni,et al.  The Effect of Engine Misfire on Exhaust Emission Levels in Spark Ignition Engines , 1995 .

[79]  Armando Blanco,et al.  A real-coded genetic algorithm for training recurrent neural networks , 2001, Neural Networks.

[80]  J. Gerdes,et al.  Physics-Based Modeling and Control of Residual-Affected HCCI Engines , 2009 .

[81]  Song-Charng Kong,et al.  A study of natural gas/DME combustion in HCCI engines using CFD with detailed chemical kinetics , 2007 .

[82]  Jesús Alcalá-Fdez,et al.  KEEL Data-Mining Software Tool: Data Set Repository, Integration of Algorithms and Experimental Analysis Framework , 2011, J. Multiple Valued Log. Soft Comput..

[83]  Jan M. Maciejowski,et al.  Predictive control : with constraints , 2002 .

[84]  Nathan Srebro,et al.  SVM optimization: inverse dependence on training set size , 2008, ICML '08.

[85]  Mark W. Schmidt,et al.  A Stochastic Gradient Method with an Exponential Convergence Rate for Strongly-Convex Optimization with Finite Training Sets , 2012, ArXiv.

[86]  Luigi del Re,et al.  Automotive model predictive control : models, methods and applications , 2010 .

[87]  J. Dec,et al.  The Potential of HCCI Combustion for High Efficiency and Low Emissions , 2002 .

[88]  Mingfa Yao,et al.  Charge stratification to control HCCI: Experiments and CFD modeling with n-heptane as fuel , 2009 .

[89]  Maciej Lawrynczuk.  Neural Networks in Model Predictive Control , 2009, Intelligent Systems for Knowledge Management.

[90]  Marco Sorrentino,et al.  RECURRENT NEURAL NETWORKS FOR AIR-FUEL RATIO ESTIMATION AND CONTROL IN SPARK-IGNITED ENGINES , 2008 .

[91]  Randall S. Sexton,et al.  Optimization of neural networks: A comparative analysis of the genetic algorithm and simulated annealing , 1999, Eur. J. Oper. Res..

[92]  Fei Han,et al.  An Improved Extreme Learning Machine Based on Particle Swarm Optimization , 2011, ICIC.

[93]  Bengt Johansson,et al.  Supercharging HCCI to Extend the Operating Range in a Multi-Cylinder VCR-HCCI Engine , 2003 .

[94]  James D. Keeler,et al.  Layered Neural Networks with Gaussian Hidden Units as Universal Approximations , 1990, Neural Computation.

[95]  Morgan M. Andreae,et al.  Effect of ambient conditions and fuel properties on homogeneous charge compression ignition engine operation , 2006 .

[96]  Jian Ma,et al.  On the approximation capability of neural networks-dynamic system modeling and control , 2008 .

[97]  Emanuel Marom,et al.  Efficient Training of Recurrent Neural Network with Time Delays , 1997, Neural Networks.

[98]  S. Effati,et al.  A novel recurrent nonlinear neural network for solving quadratic programming problems , 2011 .

[99]  John C. Platt.  A Resource-Allocating Network for Function Interpolation , 1991, Neural Computation.

[100]  Narasimhan Sundararajan,et al.  A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation , 2005, IEEE Transactions on Neural Networks.

[101]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[102]  Zhi Wang,et al.  A computational study of direct injection gasoline HCCI engine with secondary injection , 2006 .

[103]  A. Dobson.  An Introduction to Generalized Linear Models, Second Edition , 2001 .

[104]  R. Johansson,et al.  Model predictive Control of Homogeneous Charge Compression Ignition (HCCI) engine dynamics , 2006, 2006 IEEE Conference on Computer Aided Control System Design, 2006 IEEE International Conference on Control Applications, 2006 IEEE International Symposium on Intelligent Control.