Energy management strategy for battery/supercapacitor hybrid electric city bus based on driving pattern recognition

Shi, Junzhe; Xu, Bin; Shen, Yimin; Wu, Jiun-Huei Proty

doi:10.1016/j.energy.2021.122752

Cited by 53 publications

(13 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…20 The Grey Wolf optimizer (GWO) algorithm is known for its simplicity in parameter settings, good robustness, fast convergence, and high accuracy in optimization. [21][22][23][24] Therefore, the GWO algorithm is utilized to optimize the initial weights and bias parameters of the LSTM neural network.…”

Section: Gwo-optimized Lstm Recognition Modelmentioning

confidence: 99%

“…The initial weights and parameters of the LSTM neural network have a significant impact on the model's performance and can easily get trapped in local optima, requiring optimization of its parameters 20 . The Grey Wolf optimizer (GWO) algorithm is known for its simplicity in parameter settings, good robustness, fast convergence, and high accuracy in optimization 21‐24 . Therefore, the GWO algorithm is utilized to optimize the initial weights and bias parameters of the LSTM neural network.…”

Section: Gwo‐lstm Working Condition Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive fuzzy energy management strategy for range‐extended electric vehicles integrated with deep learning

Nie,

Chen,

Wei

et al. 2024

Energy Science & Engineering

View full text Add to dashboard Cite

A novel framework for adaptive energy management, rooted in deep learning principles, is proposed to minimize fuel consumption in extended‐range electric vehicles amidst intricate driving scenarios. This innovative approach integrates a long short‐term memory (LSTM) network for pattern recognition across three driving patterns and an adaptive fuzzy controller. To mitigate the impact of poor hyperparameter selection on recognition accuracy, Gray Wolf Optimization is employed to optimize the hidden layer nodes, training times, and learning rate of the LSTM. Simultaneously, a genetic algorithm is utilized to optimize the vertex coordinates of the fuzzy control membership function, enabling the adaptive adjustment of parameters in the fuzzy energy management strategy. The condition recognition model accurately identifies the vehicle's driving status and seamlessly transitions to an energy management strategy tailored to the present conditions. This ensures optimal operation, enhancing overall fuel efficiency and performance. The simulation results robustly validate the efficacy of this approach: the GWO‐LSTM network achieves an impressive 97.7% accuracy in recognizing working conditions, surpassing the 88.9% accuracy of the traditional LSTM network. Furthermore, the fuel consumption reduction achieved by the adaptive fuzzy energy management strategy amounts to 11.9% compared with the conventional fuzzy energy management approach. This outcome underscores the tangible enhancement in vehicle fuel economy resulting from the seamless integration of deep learning techniques.

show abstract

Section: Gwo-optimized Lstm Recognition Modelmentioning

confidence: 99%

Section: Gwo‐lstm Working Condition Recognitionmentioning

confidence: 99%

Adaptive fuzzy energy management strategy for range‐extended electric vehicles integrated with deep learning

Nie,

Chen,

Wei

et al. 2024

Energy Science & Engineering

View full text Add to dashboard Cite

show abstract

“…To improve the robustness, a slew of learning-based EMSs have been studied recently, such as supervised learning [20], unsupervised learning [21], reinforcement learning (RL) [22], deep reinforcement learning (DRL) [23], and so forth. At each time step, they select a set of control actions and then update control strategies according to the real-time feedback and the accumulated historical information.…”

Section: Introductionmentioning

confidence: 99%

Computationally Efficient Energy Management for a Parallel Hybrid Electric Vehicle Using Adaptive Dynamic Programming

Liu

Tan

Zhu

et al. 2024

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

“…Supercapacitors are the first choice for applications that require high power (>10 kW/kg) in a short burst or fast charge/discharge (<10 s). , Advances in materials development through extensive investigation of the supercapacitor mechanism have made it possible to use them in electric vehicles, portable electronic devices, and even as biocompatible materials in biomedical devices. − Unlike commercially available rechargeable batteries, supercapacitor devices function by storing opposite charges at the electrode–electrolyte interface through a physical adsorption process allowing fast charging while longer discharging time desirable for application in integrated energy devices . Based on their working mechanism, supercapacitors can be classified as electrochemical double-layer (EDL)/pseudo/hybrid capacitors .…”

Section: Introductionmentioning

confidence: 99%

Intrinsic Properties of GO/RGO Bilayer Electrodes Dictate Their Inter-/Intralayer Intractability to Modulate Their Capacitance Performance

Islam

Hasan

Sarker³

et al. 2023

ACS Omega

View full text Add to dashboard Cite

The demand for high-capacity energy storage along with high power output and faster charging has made supercapacitors a key area of energy research. The charge storage capacity of capacitors is largely dependent on the electrode materials utilized. To that end, graphene oxide (GO) and reduced GO (RGO) have been extensively employed for preparing supercapacitors. However, to date, no study has reported utilizing a GO/RGO bilayer electrode material for supercapacitor application. Herein, we report the synthesis of GO/RGO bilayer electrodes on fluorine-doped tin oxide (FTO) conducting substrates with four different combinations, namely, RGO-RGO, RGO-GO, GO-RGO, and GO-GO. Electrochemical capacitance analysis based on a symmetrical electrode configuration revealed that FTO-GO-RGO electrodes had the best areal capacitance performance. However, the highest specific areal capacitance (27.85 mF/cm2) for both symmetric/asymmetric configurations was achieved with FTO-GO-RGO as the anode and FTO-GO-GO as the cathode. The heterogeneous capacitance performance of the GO/RGO bilayer systems was analyzed based on structural characterization and computational simulation methods. Based on our analysis, we identified that inter-/intralayer molecular interaction of the GO/RGO bilayer sheets through the confinement pressure effect might have prompted their unique physicochemical properties. This work highlights the importance of probing multilayer GO/RGO electrode fabrication methods for preparation of high-capacity supercapacitors through fine-tuning their structural and molecular properties.

show abstract

Energy management strategy for battery/supercapacitor hybrid electric city bus based on driving pattern recognition

Cited by 53 publications

References 22 publications

Adaptive fuzzy energy management strategy for range‐extended electric vehicles integrated with deep learning

Adaptive fuzzy energy management strategy for range‐extended electric vehicles integrated with deep learning

Computationally Efficient Energy Management for a Parallel Hybrid Electric Vehicle Using Adaptive Dynamic Programming

Intrinsic Properties of GO/RGO Bilayer Electrodes Dictate Their Inter-/Intralayer Intractability to Modulate Their Capacitance Performance

Contact Info

Product

Resources

About