On vehicle surrogate learning with genetic programming ensembles

Learning surrogates for product design and optimization is potential to capitalize on competitive market segments. In this paper we propose an approach to learn surrogates of product performance from historical clusters by using ensembles of Genetic Programming. By using computational experiments involving more than 500 surrogate learning instances and 27,858 observations of vehicle models collected over the last thirty years shows (1) the feasibility to learn function surrogates as symbolic ensembles at different levels of granularity of the hierarchical vehicle clustering, (2) the direct relationship of the predictive ability of the learned surrogates in both seen (training) and unseen (testing) scenarios as a function of the number of cluster instances, and (3) the attractive predictive ability of relatively smaller ensemble of trees in unseen scenarios. We believe our approach introduces the building blocks to further advance on studies regarding data-driven product design and market segmentation.

[1]  John B. Heywood,et al.  Determinants of US passenger car weight , 2014 .

[2]  Jiaqiao Hu,et al.  Simulation optimization via promising region search and surrogate model approximation , 2016, 2016 Winter Simulation Conference (WSC).

[3]  Chris Bingham,et al.  Electric vehicle efficiency mapping , 2012 .

[4]  Lihui Wang,et al.  Multi-objective Evolutionary Optimisation for Product Design and Manufacturing , 2011 .

[5]  Clive Neal-Sturgess,et al.  Optimization of passenger car design for the mitigation of pedestrian head injury using a genetic algorithm , 2005, GECCO '05.

[6]  Riichiro Mizoguchi,et al.  Ontology-based systematization of functional knowledge , 2004 .

[7]  Michel Hecquet,et al.  An Optimization Methodology to Pre Design an Electric Vehicle Powertrain , 2014, 2014 IEEE Vehicle Power and Propulsion Conference (VPPC).

[8]  Maria Pia Fanti,et al.  Optimal fuel consumption for heavy trucks: A review , 2017, 2017 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI).

[9]  Victor Parque,et al.  Reinforced Explorit on Optimizing Vehicle Powertrains , 2013, ICONIP.

[10]  Tomoyuki Miyashita,et al.  Learning the Optimal Product Design Through History , 2015, ICONIP.

[11]  M. Becherif,et al.  Heat management methodology for enhanced global efficiency in hybrid electric vehicles , 2017 .

[12]  Hossein Zare-Behtash,et al.  State-of-the-art in aerodynamic shape optimisation methods , 2018, Appl. Soft Comput..

[13]  Peng Hao,et al.  Integrated-Connected Eco-Driving System for PHEVs With Co-Optimization of Vehicle Dynamics and Powertrain Operations , 2017, IEEE Transactions on Intelligent Vehicles.

[14]  Francis Eng Hock Tay,et al.  A methodology for evolutionary product design , 2003, Engineering with Computers.

[15]  John R. Woodward,et al.  Metaheuristic Design Pattern: Surrogate Fitness Functions , 2015, GECCO.

[16]  Alexandre Chasse,et al.  Fuel consumption prediction for heavy-duty vehicles using digital maps , 2017, 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC).

[17]  Tomoyuki Miyashita,et al.  A method to learn high-performing and novel product layouts and its application to vehicle design , 2017, Neurocomputing.

[18]  Theo Hofman,et al.  Integrated design optimization of the transmission system and vehicle control for electric vehicles , 2017 .

[19]  Steven Skiena,et al.  The Algorithm Design Manual , 2020, Texts in Computer Science.

[20]  Ming Li,et al.  Quantification of road grade to improve the estimation of fuel consumptions using the global positioning system , 2017 .

[21]  B. Grzybowski,et al.  Parallel optimization of synthetic pathways within the network of organic chemistry. , 2012, Angewandte Chemie.

[22]  Victor Parque,et al.  Searching for machine modularity using explorit , 2014, 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[23]  Michael Stolz,et al.  Testing of autonomous vehicles using surrogate models and stochastic optimization , 2017, 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC).

[24]  Jürgen Branke,et al.  On Using Surrogates with Genetic Programming , 2015, Evolutionary Computation.

[25]  William M. Bowen,et al.  Vehicle Fuel Economy and Vehicle Miles Traveled: An Empirical Investigation of Jevon’s Paradox , 2018 .

[26]  Tibor Bercsey,et al.  The Autogenetic Design Theory: An evolutionary view of the design process , 2003 .

[27]  Tomoyuki Miyashita,et al.  On succinct representation of directed graphs , 2017, 2017 IEEE International Conference on Big Data and Smart Computing (BigComp).

[28]  Timothy A. Whitehead,et al.  Optimization of affinity, specificity and function of designed influenza inhibitors using deep sequencing , 2012, Nature Biotechnology.

[29]  Zhenpo Wang,et al.  Optimal Component Sizing of a Four-Wheel Independently-Actuated Electric Vehicle With a Real-Time Torque Distribution Strategy , 2018, IEEE Access.

[30]  Luís C. Neves,et al.  Application of machine learning for fuel consumption modelling of trucks , 2017, 2017 IEEE International Conference on Big Data (Big Data).

[31]  Shigeo Morishima,et al.  Car designing tool using multivariate analysis , 2006, SIGGRAPH '06.

[32]  Tielong Shen,et al.  Fuel consumption estimation of multi-crankshaft engine , 2017, 2017 36th Chinese Control Conference (CCC).

[33]  Peter Gratzfeld,et al.  Gaussian process surrogate model for the design of circular, planar coils used in inductive power transfer for electric vehicles , 2016 .

[34]  Robin Sibson,et al.  SLINK: An Optimally Efficient Algorithm for the Single-Link Cluster Method , 1973, Comput. J..

[35]  Rui Wang,et al.  Dynamic programming technique in hybrid electric vehicle optimization , 2012, 2012 IEEE International Electric Vehicle Conference.

[36]  Victor Parque,et al.  Neural Computing with Concurrent Synchrony , 2014, ICONIP.

[37]  Shingo Mabu,et al.  Genetic network programming with changing structures for a novel stock selection model , 2011, GECCO '11.

[38]  Bernhard Sendhoff,et al.  Evolution by Adapting Surrogates , 2013, Evolutionary Computation.

[39]  David P. Dobkin,et al.  The quickhull algorithm for convex hulls , 1996, TOMS.

[40]  Tomoyuki Miyashita,et al.  On k-subset sum using enumerative encoding , 2016, 2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT).

[41]  Seyed Hossein Iranmanesh,et al.  Application of ANFIS and LLNF models to automobile fuel consumption prediction: A comparative study , 2012, 2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA).