Support vector machine–based driving cycle recognition for dynamic equivalent fuel consumption minimization strategy with hybrid electric vehicle

Shi, Qin; Qiu, Duoyang; He, Lei; Bing, Wu; Li, Yiming

doi:10.1177/1687814018811020

Cited by 9 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is a supervised learning model in machine learning used in this research to optimize the HEVs' energy management. The support-vector machine is used to analyze data for classification and regression analysis [13,14,15]. It is used to train the data provided and then to predict the operation mode after constructing the model in Matlab-Simulink.…”

Section: Machine Learning-based Energy Management Strategymentioning

confidence: 99%

Optimisation of Hybrid Electric Vehicle Energy Management Using Machine Learning

Asus,

Jian Xiang,

Che Daud

2023

JTSE

View full text Add to dashboard Cite

The focus of the research is on the optimization of the hybrid electric vehicle energy management using machine learning. The objective of this research is to develop the algorithm by using Support Vector Machine (SVM) and to identify the optimal operation mode for SHEV based on the power demand use by using the algorithm. First of all, this research focus on the series hybrid electric vehicle and the vehicle used is an all-terrain vehicle (ATV). Suitable formula will be used to complete the modeling of the vehicle in Energetic Macroscopic Representation (EMR) form and the model constructed by using Matlab Simulink. Then, Support Vector Machine is used to optimize the energy management in the vehicle. The training data from New European Driving Cycle (NEDC) and Worldwide harmonized Light vehicles Test Cycles (WLTC) with 3 classes will put be inside the SVM to undergo training and then the optimal operation modes for each driving cycle will be obtained by using Linear SVM. Then, the obtained results which are the predicted operation mode using the driving cycles and are plotted in the graph. The pattern of the graph is analyzed and then the best predicted operation mode with the highest accuracy among all the driving cycles is chosen. The trained model of the driving cycle with the highest accuracy is used to predict the optimal operation mode for ATV so that to have higher efficiency in energy management by using the Classification Learner inside the Matlab.

show abstract

Section: Machine Learning-based Energy Management Strategymentioning

confidence: 99%

Optimisation of Hybrid Electric Vehicle Energy Management Using Machine Learning

Asus,

Jian Xiang,

Che Daud

2023

JTSE

View full text Add to dashboard Cite

show abstract

“…They analyzed the accelerator pedal opening and its change rate under different driving cycles and established a fuzzy logic recognizer to identify the driving cycle. Shi et al [27] developed a method to identify driving cycle types in realtime with higher accuracy and apply a driving cycle identification model based on a support vector machine optimized by a particle swarm algorithm to ECMS.…”

Section: Introductionmentioning

confidence: 99%

Driving Cycle Recognition Based Adaptive Equivalent Consumption Minimization Strategy for Hybrid Electric Vehicles

et al. 2022

View full text Add to dashboard Cite

Hybrid electric vehicles (HEVs) are considered the most practical option for reducing emissions and fuel consumption of conventionally powered vehicles. Energy management strategies (EMSs) are the core technology of HEVs because of decreasing the cost of the system and limiting its negative effects. Equivalent consumption minimization strategy (ECMS) can achieve instantaneous optimal control and has attracted attention in recent years. In this study, an adaptive equivalent consumption minimization strategy (A-ECMS) based on driving cycle recognition is constructed for a parallel HEV. First, select the standard driving cycle and analyze its characteristic parameters. And then training learning vector quantization (LVQ) neural network-based driving cycle recognizer to achieve an average of 98% accuracy. At last, the optimal equivalent factor (EF) is selected for ECMS by recognizing the current driving cycle. It is jointly simulated and analyzed by AVL CRUISE and Matlab/Simulink software under NEDC and CHTL-LT driving cycle. The results show that compared with the logic-based EMS in the NEDC driving cycle the 100 km fuel consumption of A-ECMS decreases by 3.8% and the battery state of charge (SOC) increases by 1.1% in the CHTC-LT driving cycle, so, fuel economy improves by 3.6%, proving the superiority of the A-ECMS.INDEX TERMS Hybrid electric vehicle (HEV), energy management strategy (EMS), equivalent consumption minimization strategy (ECMS), driving cycle recognition, learning vector quantization (LVQ)

show abstract

“…We analysed how this intelligence can effectively use for the optimum power utilization. Energy management in dual-source fuel cell hybrid electric vehicles (FCHEVs) is a critical aspect of optimizing performance and efficiency [19,20]. In this study, we propose a novel SVM classifier-based energy management strategy (EMS) for FCHEVs to address this challenge.…”

mentioning

confidence: 99%

SVM classifier based energy management strategy for dual‐source fuel cell hybrid electric vehicles

Chatterjee,

Biswas,

Sain

et al. 2024

The Journal of Engineering

View full text Add to dashboard Cite

This study proposes an optimal energy management strategy for dual‐source fuel cell hybrid electric vehicles (FCHEV) utilizing the support vector machine (SVM) classifier. The goal is to optimize power distribution between fuel cells and batteries to enhance vehicle's performance and efficiency. The SVM classifier is trained using a dataset of driving conditions and corresponding optimal power distribution (OPD) values obtained through simulation. The trained classifier predicts real‐time OPD based on driving conditions. In comparison to existing literature, this study conducts a comparative analysis of energy management control strategies like model predictive control (MPC), fuzzy, equivalent consumption minimization strategy (ECMS), proportional‐integral (PI) control, and state machine control (SMC) strategy for FCHEVs using the MATLAB/SIMULINK platform and real‐world driving dataset. The proposed strategy is then tested in a real‐time EV simulator to verify its efficacy. Additionally, this study introduces the SVM classifier technique for selecting the optimal energy management strategy for FCHEVs. Performance analysis using SVM reveals that the MPC control strategy offers the highest efficiency compared to other techniques based on selected features, achieving an average performance of 95% through cross‐validation. This analysis demonstrates the most cost‐effective and fuel‐efficient utilization of electricity flow in a modern energy‐efficient environment.

show abstract

Support vector machine–based driving cycle recognition for dynamic equivalent fuel consumption minimization strategy with hybrid electric vehicle

Cited by 9 publications

References 17 publications

Optimisation of Hybrid Electric Vehicle Energy Management Using Machine Learning

Optimisation of Hybrid Electric Vehicle Energy Management Using Machine Learning

Driving Cycle Recognition Based Adaptive Equivalent Consumption Minimization Strategy for Hybrid Electric Vehicles

SVM classifier based energy management strategy for dual‐source fuel cell hybrid electric vehicles

Contact Info

Product

Resources

About