Optimal calibration of variable biofuel blend dual-injection engines using sparse Bayesian extreme learning machine and metaheuristic optimization

Abstract Although many combinations of biofuel blends are available in the market, it is more beneficial to vary the ratio of biofuel blends at different engine operating conditions for optimal engine performance. Dual-injection engines have the potential to implement such function. However, while optimal engine calibration is critical for achieving high performance, the use of two injection systems, together with other modern engine technologies, leads the calibration of the dual-injection engines to a very complicated task. Traditional trial-and-error-based calibration approach can no longer be adopted as it would be time-, fuel- and labor-consuming. Therefore, a new and fast calibration method based on sparse Bayesian extreme learning machine (SBELM) and metaheuristic optimization is proposed to optimize the dual-injection engines operating with biofuels. A dual-injection spark-ignition engine fueled with ethanol and gasoline is employed for demonstration purpose. The engine response for various parameters is firstly acquired, and an engine model is then constructed using SBELM. With the engine model, the optimal engine settings are determined based on recently proposed metaheuristic optimization methods. Experimental results validate the optimal settings obtained with the proposed methodology, indicating that the use of machine learning and metaheuristic optimization for dual-injection engine calibration is effective and promising.

[1]  Zoran Filipi,et al.  Simulation-based optimal calibration of spark ignition engines with multiple objectives: fuel economy and combustion variability , 2011 .

[2]  Xin-She Yang,et al.  Flower pollination algorithm: A novel approach for multiobjective optimization , 2014, ArXiv.

[3]  G. Hong,et al.  Investigation to Leveraging Effect of Ethanol Direct Injection (EDI) in a Gasoline Port Injection (GPI) Engine , 2013 .

[4]  Mohammad. Rasul,et al.  Role of biofuel and their binary (diesel–biodiesel) and ternary (ethanol–biodiesel–diesel) blends on internal combustion engines emission reduction , 2016 .

[5]  Li Ke,et al.  Automotive engine power performance tuning under numerical and nominal data , 2012 .

[6]  Willard W. Pulkrabek,et al.  Engineering Fundamentals of the Internal Combustion Engine , 1997 .

[7]  Pak Kin Wong,et al.  Modeling and optimization of biodiesel engine performance using kernel-based extreme learning machine and cuckoo search , 2015 .

[8]  A. Graham Bell.  Four-Stroke Performance Tuning , 1999 .

[9]  Dimitrios C. Rakopoulos,et al.  Impact of properties of vegetable oil, bio-diesel, ethanol and n-butanol on the combustion and emissions of turbocharged HDDI diesel engine operating under steady and transient conditions , 2015 .

[10]  Luigi del Re,et al.  Identification for Automotive Systems , 2012 .

[11]  Dheeraj B Gosala,et al.  Experimental studies on simultaneous injection of ethanol–gasoline and n-butanol–gasoline in the intake port of a four stroke SI engine , 2016 .

[12]  Chi-Man Vong,et al.  Efficient point-by-point engine calibration using machine learning and sequential design of experiment strategies , 2017, J. Frankl. Inst..

[13]  Gholamhassan Najafi,et al.  Optimization of performance and exhaust emission parameters of a SI (spark ignition) engine with gasoline–ethanol blended fuels using response surface methodology , 2015 .

[14]  Obed M. Ali,et al.  Analysis of blended fuel properties and engine performance with palm biodiesel–diesel blended fuel , 2016 .

[15]  Ritchie Daniel,et al.  Combustion performance of 2,5-dimethylfuran blends using dual-injection compared to direct-injection in a SI engine , 2012 .

[16]  Bang-quan He,et al.  Combustion characteristics of a gasoline engine with independent intake port injection and direct injection systems for n-butanol and gasoline , 2016 .

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

[18]  Stanislav V. Bohac,et al.  Real-time, adaptive machine learning for non-stationary, near chaotic gasoline engine combustion time series , 2015, Neural Networks.

[19]  Nam-Ho Kim,et al.  A study on the combustion and emission characteristics of an SI engine under full load conditions with ethanol port injection and gasoline direct injection , 2015 .

[20]  Xin-She Yang,et al.  Cuckoo search: recent advances and applications , 2013, Neural Computing and Applications.

[21]  Haji Hassan Masjuki,et al.  Higher alcohol–biodiesel–diesel blends: An approach for improving the performance, emission, and combustion of a light-duty diesel engine , 2016 .

[22]  Murray J. Thomson,et al.  A review of the combustion and emissions properties of advanced transportation biofuels and their impact on existing and future engines , 2015 .

[23]  Hedi Jedli,et al.  Modeling of a bioethanol combustion engine under different operating conditions , 2014 .

[24]  Xin-She Yang,et al.  Cuckoo Search via Lévy flights , 2009, 2009 World Congress on Nature & Biologically Inspired Computing (NaBIC).

[25]  Ritchie Daniel,et al.  Gaseous and particulate matter emissions of biofuel blends in dual-injection compared to direct-injection and port injection , 2013 .

[26]  Dalia Yousri,et al.  Flower Pollination Algorithm based solar PV parameter estimation , 2015 .

[27]  Chi-Man Vong,et al.  Sparse Bayesian extreme learning machine and its application to biofuel engine performance prediction , 2015, Neurocomputing.

[28]  Guang Hong,et al.  Investigation of the effect of heated ethanol fuel on combustion and emissions of an ethanol direct injection plus gasoline port injection (EDI + GPI) engine , 2016 .

[29]  Rizalman Mamat,et al.  Application of response surface methodology in optimization of performance and exhaust emissions of secondary butyl alcohol-gasoline blends in SI engine , 2017 .

[30]  Xin-She Yang,et al.  Flower Pollination Algorithm for Global Optimization , 2012, UCNC.

[31]  Investigations of Port Dual Injection (PDI) Strategies in Single Cylinder SI Engine Fueled with Ethanol/Gasoline Blends , 2016 .

[32]  Zhi Wang,et al.  Dual-Fuel Spark Ignition (DFSI) combustion fuelled with different alcohols and gasoline for fuel efficiency , 2015 .

[33]  Kyoungdoug Min,et al.  The Effect of Ethanol Injection Strategy on Knock Suppression of the Gasoline/Ethanol Dual Fuel Combustion in a Spark-Ignited Engine , 2015 .

[34]  Zhijin Zhang,et al.  Combustion and particle number emissions of a direct injection spark ignition engine operating on ethanol/gasoline and n-butanol/gasoline blends with exhaust gas recirculation , 2014 .