Online calibration of spark advance for combustion phase control of gasoline SI engines

Calibration in combustion phase control is an effective way to get sophisticated engine performance, but is only workable by analyzing offline data or running engine in test mode. When engine is aged or runs at unfamiliar situations, traditional calibration method cannot promise the same performance as before. To improve calibration technique, an online calibration method for combustion phase control is presented, which also works when engine is running in driving operating condition. Based on bilinear interpolation algorithm, online calibration problem is converted to parameters estimation issue, then stochastic gradient descent algorithm is utilized to estimate parameters by iteratively updates. Finally, the proposed strategy is verified on a gasoline spark ignition engine.

[1]  Carlos Guardiola,et al.  Adaptive calibration for reduced fuel consumption and emissions , 2016 .

[2]  Christopher M. Atkinson,et al.  Calibration Optimization of a Heavy-Duty Diesel Engine with GTL Diesel Fuel , 2016 .

[3]  Li Jiang,et al.  Preliminary Results on Optimal Variable Valve Timing and Spark Timing Control via Extremum Seeking , 2010 .

[4]  Jinwu Gao,et al.  Combustion Phase Control of SI Gasoline Engines Using Hypothesis Test , 2015 .

[5]  Yuhu Wu,et al.  A statistical combustion phase control approach of SI engines , 2017 .

[6]  Mitsuji Sampei,et al.  On-Line Feedforward Map Generation for Engine Ignition Timing Control , 2014 .

[7]  Erik Hellström,et al.  On-Board Calibration of Spark Timing by Extremum Seeking for Flex-Fuel Engines , 2013, IEEE Transactions on Control Systems Technology.

[8]  Enrico Corti,et al.  A Statistical Approach to Spark Advance Mapping , 2010 .

[9]  Matthias Schultalbers,et al.  Analytical Calibration of Map-Based Energy Managements of Parallel Hybrid Vehicles , 2014 .

[10]  Pipitone Emiliano,et al.  Spark Ignition Feedback Control by Means of Combustion Phase Indicators on Steady and Transient Operation , 2014 .

[11]  A. Thomas Shenton,et al.  Peak Pressure Position Control of Four Cylinders through the Ion Current Method , 2009 .

[12]  XuanLong Nguyen,et al.  Stochastic gradient based extreme learning machines for stable online learning of advanced combustion engines , 2016, Neurocomputing.

[13]  Pak Kin Wong.  Compensation Map Calibration of Engine Management Systems Using Least-Squares Support Vector Committee Machine and Evolutionary Optimization , 2013 .