Learning-based control strategies for hybrid electric vehicles

Geulen, Sascha; Joševski, Martina; Nellen, Johanna; Fuchs, Janosch; Netz, Lukas; Wolters, Benedikt; Abel, Dirk; Ábrahám, Erika; Unger, Walter

doi:10.1109/cca.2015.7320858

Cited by 3 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, machine learning (ML) techniques have gained popularity for their ability to control complex tasks by deriving patterns or rules from a data-set or through experience [29,30]. These techniques have also been extended to automotive applications, for example, drive cycle prediction [31], drive cycle recognition [32], training the torque split controller from DP using supervised machine learning (SML) [33], reinforcement learning (RL) for power distribution between the battery and the capacitor [34], etc. In certain tasks, controllers trained using ML have outperformed the controllers based on classical control theory [35].…”

Section: Torque Split Controlmentioning

confidence: 99%

See 1 more Smart Citation

Powertrain Control for Hybrid-Electric Vehicles Using Supervised Machine Learning

Harold¹,

Prakash²,

Hofman³

2020

Vehicles

View full text Add to dashboard Cite

This paper presents a novel framework to enable automatic re-training of the supervisory powertrain control strategy for hybrid electric vehicles using supervised machine learning. The aim of re-training is to customize the control strategy to a user-specific driving behavior without human intervention. The framework is designed to update the control strategy at the end of a driving task. A combination of dynamic programming and supervised machine learning is used to train the control strategy. The trained control strategy denoted as SML is compared to an online-implementable strategy based on the combination of the optimal operation line and Pontryagin’s minimum principle denoted as OOL-PMP, on the basis of fuel consumption. SML consistently performed better than OOL-PMP, evaluated over five standard drive cycles. The EUDC performance was almost identical while on FTP75 the OOL-PMP consumed 14.7% more fuel than SML. Moreover, the deviation from the global benchmark obtained from dynamic programming was between 1.8% and 5.4% for SML and between 5.8% and 16.8% for OOL-PMP. Furthermore, a test-case was conducted to emulate a real-world driving scenario wherein a trained controller is exposed to a new drive cycle. It is found that the performance on the new drive cycle deviates significantly from the optimal policy; however, this performance gap is bridged with a single re-training episode for the respective test-case.

show abstract

Section: Torque Split Controlmentioning

confidence: 99%

“…In the case of supervisory control strategies for an HEV, certain learning based strategies are shown to be comparable to the commonly used control strategies [31]. For continuous-spaces, the actor-critic method was used for the power management in a PHEV [36].…”

Section: Torque Split Controlmentioning

confidence: 99%

Powertrain Control for Hybrid-Electric Vehicles Using Supervised Machine Learning

Harold¹,

Prakash²,

Hofman³

2020

Vehicles

View full text Add to dashboard Cite

show abstract

“…The control strategies RDP and ADP [4] are based on receding dynamic programming [1], where the fuel consumption is minimized using an objective function that calculates the weighted sum of the fuel mass flow and the deviation of the battery state of charge from SoC ref for a prediction horizon. Additionally, ADP uses a cost-to-go approximation in the objective function to estimate the costs that are needed for the rest of the driving cycle.…”

Section: Resultsmentioning

confidence: 99%

A Genetic Algorithm based Control Strategy for the Energy Management Problem in PHEVs

Nellen

Wolters

Netz

et al.

EPiC Series in Computing

Self Cite

View full text Add to dashboard Cite

Genetic algorithms have been applied to various optimization problems in the past. Our library GeneiAL implements a framework for genetic algorithms specially targeted to the area of hybrid electric vehicles. In a parallel hybrid electric vehicle (PHEV), an internal combustion engine and an electrical motor are coupled on the same axis in parallel. In the area of PHEVs, genetic algorithms have been extensively used for the optimization of parameter tuning of control strategies. We use GeneiAL to control the torque distribution between the engines directly. The objective function of this control strategy minimizes the weighted sum of functions that evaluate the fuel consumption, the battery state of charge, and drivability aspects over a prediction horizon of fixed finite length. We analyze the influence of these weights and different configurations for the genetic algorithm on the computation time, the convergence, and the quality of the optimization result. For promising configurations, we compare the results of our control strategy with common control strategies.

show abstract

Extended driving range control strategy for hybrid electric vehicle

Balan

Avirajamanjula

2023

INSTRUMENTATION ENGINEERING, ELECTRONICS AND TELECOMMUNICATIONS – 2021 (IEET-2021): Proceedings of the VII International Forum

View full text Add to dashboard Cite

Learning-based control strategies for hybrid electric vehicles

Cited by 3 publications

References 6 publications

Powertrain Control for Hybrid-Electric Vehicles Using Supervised Machine Learning

Powertrain Control for Hybrid-Electric Vehicles Using Supervised Machine Learning

A Genetic Algorithm based Control Strategy for the Energy Management Problem in PHEVs

Extended driving range control strategy for hybrid electric vehicle

Contact Info

Product

Resources

About