Abstract:Dynamic programming (DP) provides the optimal global solution to the energy management problem for hybrid electric vehicles (HEVs), but needs complete a-priori knowledge of the driving cycle and has high computational requirements. This article presents a possible methodology to extract rules from the dynamic programming solution to design an implementable rule-based strategy. The case study considered is a series/parallel HEV, in which a clutch allows to switch from one configuration to another. The strategy … Show more
“…These reference strategies can be used to validate heuristic strategies or to improve existing strategies based on observations made from the references as it is done in [2]. In [3] are utilized to derive rule-based strategies for driving mode and torque-split by analyzing common patterns therein. Support Vector Machines (SVMs) are learning algorithms already used in applications on HEVs.…”
In this paper a data driven operational strategy for a hybrid electric vehicle (HEV) is developed. There are two big benefits of the proposed approach: The possibility of real-time implementation within embedded control units and the high potential for automated calibration. Starting point is a user defined set of fuel-optimized driving cycles for a hybrid vehicle, which is generated applying e.g. state of the art dynamic programming techniques. From this data the introduced methodology extracts a control strategy that determines the torque-split factor for a given driving situation.The approach is based on a combination of optimization and classification, as well as regression strategies. The data created by a dynamic programming algorithm (DP) is used to train support vector machines (SVMs) in order to get rid of the necessity of a-priori knowledge of the whole driving cycle. From the resulting functions a control law is derived that is able to identify a suitable torque-split factor, independent of the further driving course. Since reducing the information input into the control law will per definition reduce performance, validation of the methodology is based on comparison with optimized driving cycles generated by dynamic programming that use the whole driving cycle information.
“…These reference strategies can be used to validate heuristic strategies or to improve existing strategies based on observations made from the references as it is done in [2]. In [3] are utilized to derive rule-based strategies for driving mode and torque-split by analyzing common patterns therein. Support Vector Machines (SVMs) are learning algorithms already used in applications on HEVs.…”
In this paper a data driven operational strategy for a hybrid electric vehicle (HEV) is developed. There are two big benefits of the proposed approach: The possibility of real-time implementation within embedded control units and the high potential for automated calibration. Starting point is a user defined set of fuel-optimized driving cycles for a hybrid vehicle, which is generated applying e.g. state of the art dynamic programming techniques. From this data the introduced methodology extracts a control strategy that determines the torque-split factor for a given driving situation.The approach is based on a combination of optimization and classification, as well as regression strategies. The data created by a dynamic programming algorithm (DP) is used to train support vector machines (SVMs) in order to get rid of the necessity of a-priori knowledge of the whole driving cycle. From the resulting functions a control law is derived that is able to identify a suitable torque-split factor, independent of the further driving course. Since reducing the information input into the control law will per definition reduce performance, validation of the methodology is based on comparison with optimized driving cycles generated by dynamic programming that use the whole driving cycle information.
“…It is based on Bellman's principle of optimality [11] and is able to manage dynamic models of the system; since DP is commonly used to solve time-continuous control problems, the model has to be discretized in a sequence of time steps for which DP is capable of determining the optimal control laws. Even though the need for a backward procedure means that the solution can be obtained only offline, for a driving cycle known a priori, and therefore it is not implementable on a real vehicle, the optimal control law can be used to gather information for the development of simpler and implementable strategies and to benchmark their performance [16,17].…”
Plug-in hybrid electric vehicles (pHEVs) could represent the stepping stone to move towards a more sustainable mobility and combine the benefits of electric powertrains with the high range capability of conventional vehicles. Nevertheless, despite the huge potential in terms of CO 2 emissions reduction, the performance of such vehicles has to be deeply investigated in real world driving conditions considering also the CO 2 production related to battery recharge which, on the contrary, is currently only partially considered by the European regulation to foster the diffusion of pHEVs. Therefore, this paper aims to assess, through numerical simulation, the real performance of a test case pHEV, the energy management system (EMS) of which is targeted to the minimization of its overall CO 2 emissions. The paper highlights, at the same time, the relevance of the CO 2 production related to the battery recharge from the power grid. Different technologies mixes used to produce the electricity required for the battery recharge are also taken into account in order to assess the influence of this parameter on the vehicle CO 2 emissions. Finally, since the operating cost still represents the main driver in orienting the customer's choice, an alternative approach for the EMS, targeted to the minimization of this variable, is also analyzed.
“…Nonetheless, the behavior obtained by the DP solution could in principle be mimicked and reproduced by means of a set of rules which are of easier implementation. Thus, inspired by Lin et al (2003), Bianchi et al (2010Bianchi et al ( , 2011 and Biasini et al (2012) we went through a re-thinking of a 1 500 2 000 2 500 3 000 3 500…”
Section: Rule-based Approaches Based On Optimization Methodsmentioning
-The aim of this paper is to document 15 years of hybrid electric vehicle energy management research at The Ohio State University Center for Automotive Research (OSU-CAR). Hybrid Electric Vehicle (HEV) technology encompasses many diverse aspects. In this paper, we focus exclusively on the evolution of supervisory control strategies for on-board energy management in HEV. We present a series of control algorithms that have been developed in simulation and implemented in prototype vehicles for charge-sustaining HEV at OSU-CAR. These solutions span from fuzzy-logic control algorithms to more sophisticated model-based optimal control methods. Finally, methods developed for plug-in HEV energy management are also discussed.Re´sume´-Gestion e´nerge´tique des ve´hicules hybrides e´lectriques : 15 ans de de´veloppement a`l'universite´d'É tat de l'Ohio -Le but de cet article est de documenter 15 ans de recherche sur la gestion e´nerge´tique des ve´hicules hybrides e´lectriques, effectue´e au centre de recherche automobile de l'Ohio State University (OSU-CAR). La technologie VHE (Ve´hicules Hybrides É lectriques) englobe divers aspects. Dans cet article, nous nous concentrons exclusivement sur l'e´volution des strate´gies de controˆle de surveillance pour la gestion e´nerge´tique embarque´e dans les VHE. Nous pre´sentons une se´rie d'algorithmes de controˆle qui, a`l'OSU-CAR, ont e´ted e´veloppe´s en simulation et mis en oeuvre dans des ve´hicules prototypes pour les VHE avec maintien de la charge. Ces solutions couvrent tant les algorithmes de controˆle par logique floue que les me´thodes sophistique´es de controˆle optimal base´sur un mode`le. Enfin, les me´thodes de´veloppe´es pour la gestion e´nerge´tique des VHR (Ve´hicules Hybrides Rechargeables) sont e´galement aborde´es.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.