Intelligent Energy Management Based on the Driving Cycle Sensitivity Identification Using SVM
Published 1 January 2009
Liang Zhang, Xin Zhang, Yi Tian, Zhang Xinn
Citations10
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A driving cycle sensitivity parameter is defined, which is used to create different driving cycles to substitute a kind of the on-road driving conditions, and the parameters of control strategy are optimized by genetic agency on these different cycles.
Abstract
Hybrid Electric Vehicles (HEV) offer the ability to significantly reduce fuel consumptions and emission. Management of energy is one of essential elements in the implementation of hybrid electric vehicles. Engine and motor should satisfy the driver's demand in different driving environment. This paper defines a driving cycle sensitivity parameter, which is used to create different driving cycles to substitute a kind of the on-road driving conditions. The parameters of control strategy are optimized by genetic agency on these different cycles. In this paper support vector machines (SVM) is used to identify the driving cycle sensitivity parameter. And an intelligent energy management is crated, which could change the parameters in control strategy to the genetic optimized results. Simulation work is carried out for the validation of proposed intelligent management, and the results show it's great in improving fuel economy and reducing emissions.
Keywords
EngineeringChemical Engineering
Machine LearningSupport-vector networks
40,463 Citations1995Corinna Cortes, Vladimir Vapnik
High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated and the performance of the support- vector network is compared to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
The Nature of Statistical Learning Theory
39,279 Citations1995Vladimir Vapnik
Machine LearningSupport-Vector Networks
33,035 Citations1995Corinna Cortes, Vladimir Vapnik
High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated and the performance of the support- vector network is compared to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
TechnometricsStatistical Learning Theory
26,913 Citations1999Yuhai Wu, Vladimir Vapnik
Presenting a method for determining the necessary and sufficient conditions for consistency of learning process, the author covers function estimates from small data pools, applying these estimations to real-life problems, and much more.
Neural ComputationBounds on Error Expectation for Support Vector Machines
627 Citations2000Vladimir Vapnik, Olivier Chapelle
It is proved that the value of the span is always smaller (and can be much smaller) than the diameter of the smallest sphere containing the support vectors, used in previous bounds.
Transportation Research Part D Transport and EnvironmentIndependent driving pattern factors and their influence on fuel-use and exhaust emission factors
581 Citations2001Eva Ericsson
PerceptionAction Categories and the Perception of Biological Motion
431 Citations1993Winand H. Dittrich
It is argued that the perceptual analysis of actions and movements starts primarily on an intermediate level of action coding and comprises more than just the similarity of movement patterns or simple structures.
Computer Vision and Image UnderstandingParameterized Modeling and Recognition of Activities
313 Citations1999Yaser Yacoob, Michael J. Black
IEEE Transactions on Vehicular TechnologyIntelligent Energy Management Agent for a Parallel Hybrid Vehicle—Part I: System Architecture and Design of the Driving Situation Identification Process
298 Citations2005Reza Langari, Jong‐Seob Won
It is specifically shown that a learning vector quantization (LVQ) network can effectively determine the driving condition using a limited duration of driving data.
Journal of Dynamic Systems Measurement and ControlMulti-Mode Driving Control of a Parallel Hybrid Electric Vehicle Using Driving Pattern Recognition
219 Citations2000Soonil Jeon, Sung-Tae Jo +2 more
A multi-mode driving control algorithm using driving pattern recognition and applied to a parallel hybrid electric vehicle (parallel HEV) to optimize the vehicle performances on a temporary driving pattern.
Understanding human motion patterns
128 Citations2002Yong‐Xin Guo, Gang Xu +1 more
The human motion can be recorded as a sequence of the stick figure parameters, which can be used as input of a motion pattern analyzer, when recognition of human motion patterns is addressed.
Optimisation of energy flow management in hybrid electric vehicles via genetic algorithms
108 Citations2002Antonio Piccolo, Lucio Ippolito +2 more
The proposed methodology identifies, using the genetic algorithm, the value of the energy flow management parameters that minimize the cost function in terms of fuel consumption and emissions to contribute to a substantial reduction of the pollutant emissions from hybrid electric vehicles.
SAE technical papers on CD-ROM/SAE technical paper seriesImproved Driving Cycle for Testing Automotive Exhaust Emissions
104 Citations1978M. Kuhler, D Karstens
SAE technical papers on CD-ROM/SAE technical paper seriesIntelligent Control of Hybrid Vehicles Using Neural Networks and Fuzzy Logic
65 Citations1998Bernd Baumann, Giorgio Rizzoni +1 more
Munich Personal RePEc Archive (Ludwig Maximilian University of Munich)The Perception of Articulated Motion: Recognizing Moving Light Displays
61 Citations1992Nigel Goddard
It is shown that recognition of gait can be achieved directly from motion features, without complex shape information, and that the motion information need not be finely quantized, which indicates the value of the structured connectionist paradigm in modeling perceptual processes.
SAE technical papers on CD-ROM/SAE technical paper seriesImpact of Drive Cycle Aggressiveness and Speed on HEVs Fuel Consumption Sensitivity
60 Citations2007P. Sharer, R. Leydier +1 more
SAE technical papers on CD-ROM/SAE technical paper seriesHeavy Duty Testing Cycles: Survey and Comparison
58 Citations1994Reda M. Bata, Yasser Yacoub +4 more
Web Intelligence and Agent Systems An International JournalA study on rough set-aided feature selection for automatic web-page classification
33 Citations2006Toshiko Wakaki, Hiroyuki Itakura +3 more
The experimental results show that the combination of the rough set-aided feature selection method and the Support Vector Machine with the linear kernel is quite useful in practice to classify Web-pages into multiple categories because not only the experiments give acceptable accuracy but also the high dimensionality reduction is achieved without the need to search for a threshold for feature selection.
SAE technical papers on CD-ROM/SAE technical paper seriesRepresentative Kinematic Sequences for the Road Traffic in France
27 Citations1989J P Crauser, Michel Maurin +1 more