MétaCan
Menu
Back to cohort
Record W4389540760 · doi:10.17118/11143/21167

An efficient energy management strategy based on adaptive nonlinearparticle swarm optimization for light electric vehicles

2023· article· en· W4389540760 on OpenAlexaff
Abdelhakim Khaldi, Raynald Guilbault

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldEngineering
TopicElectric and Hybrid Vehicle Technologies
Canadian institutionsÉcole de Technologie Supérieure
Fundersnot available
KeywordsParticle swarm optimizationComputer scienceNonlinear systemSwarm behaviourMathematical optimizationPhysicsArtificial intelligenceMathematicsAlgorithm

Abstract

fetched live from OpenAlex

In terms of improving the energy consumption of electric vehicles (EVs), the dual motor with planetary differential (DMPD) powertrain stands out as the best potential replacement for the single motor powertrain. A planetary differential introduces a redundant kinematic degree of freedom, providing three operation modes: two single motor modes and one dual motor mode. Hence, there is an infinite number of operation points for the motors. Among them there is one where the motors operate in their best efficiency zone, and that increases the efficiency of the system as a whole. For an optimal running, such an architecture requires a control method to identify the optimal power split between the motors. This paper proposes an efficient energy management strategy (EMS) based on the adaptive nonlinear particle swarm optimization (ANLPSO) algorithm, a variant of the original PSO algorithm. Compared to classical optimization techniques, PSO offers reliable evaluations and simple implementations, while ANLPSO introduces additional control on the inertia weight, on the memory term and on the social knowledge. ANLPSO also favors a high exploration/exploitation ratio at the search beginning and gradually reduces it approaching the end. Moreover, the considered version integrates additional control on the initial particle distribution via a landscape subdivision. The goal of this study is to enhance the instantaneous efficiency of DMPD and improve the overall efficiency of EVs during standard driving cycles. The adopted ANLPSO algorithm is compared with the discrete parametric optimization method proposed in a recent publication for urban EV. The comparison uses the parameters and conditions imposed by the urban cycle New European Driving Cycle (NEDC). The simulation results prove the capacity of the proposed model of efficiently identifying the optimal operation points. Compared to the reference, the determined points lead to an overall efficiency improvement of 2.93% for the traction flow and of 4.58% for the regeneration flow. In addition, the study compares the efficiency of the DMPD configuration with that of the single motor powertrain (SMP). This analysis uses the proposed EMS to establish the optimal energy consumption over both the urban and highway scenarios of NEDC. The simulation results reveal that the DMPD outperforms the SMP for both the traction and the regeneration flows, namely, the efficiency gains associated with the DMPD configuration are 9.4% for the traction and 9.8% for the regeneration over the urban cycle, and 2.5% for the traction and 3.2% for the regeneration over the highway cycle.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.004
Threshold uncertainty score0.008

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0010.000
Open science0.0010.001
Research integrity0.0010.000
Insufficient payload (model declined to judge)0.0010.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.012
GPT teacher head0.223
Teacher spread0.211 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2023
Admission routes1
Has abstractyes

Explore more

Same topicElectric and Hybrid Vehicle TechnologiesFrench-language works237,207