Scholarlink

<p>The energy management strategy (EMS) in a hybrid electric vehicle (HEV) is crucial for enhancing fuel economy and reducing pollutant emissions. Deep-CNN is a powerful tool for tasks like image recognition and classification. A Deep-convolutional neural network (CNN) is proposed to predict fuel consumption based on various driving conditions, such as acceleration, road gradient, and speed. To enhance the prediction performance of Deep-CNN, the weights are tuned optimally using a beta scented Dwarf Mongoose optimization (BS-DMO) Strategy leads to better performance including accurate fuel consumption prediction in Hybrid electric vehicles (HEVs). This optimization strategy focuses on improving performance by efficiently searching for the best parameters across different solutions. Accordingly, the proposed BS-DMO + CNN model demonstrated superior performance, achieving significantly lower error metrics, including mean absolute error (MAE), mean squared error (MSE), and root mean squared error (RMSE) compared to conventional methods. Sensitivity analysis confirms that an optimal parameter of 1.5 yields the best results, while convergence analysis shows that the BS-DMO + CNN consistently achieves minimal cost values, enhancing its effectiveness in energy management.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep-Convolutional Neural Networks-Based Model for Energy Management in Power Split Hybrid Electric Vehicle

  • 期刊论文

  • 发表日期：

    2025年4月18日

查看全文
  • R. Vijayakumar,
  • K. Malarvizhi

摘要

The energy management strategy (EMS) in a hybrid electric vehicle (HEV) is crucial for enhancing fuel economy and reducing pollutant emissions. Deep-CNN is a powerful tool for tasks like image recognition and classification. A Deep-convolutional neural network (CNN) is proposed to predict fuel consumption based on various driving conditions, such as acceleration, road gradient, and speed. To enhance the prediction performance of Deep-CNN, the weights are tuned optimally using a beta scented Dwarf Mongoose optimization (BS-DMO) Strategy leads to better performance including accurate fuel consumption prediction in Hybrid electric vehicles (HEVs). This optimization strategy focuses on improving performance by efficiently searching for the best parameters across different solutions. Accordingly, the proposed BS-DMO + CNN model demonstrated superior performance, achieving significantly lower error metrics, including mean absolute error (MAE), mean squared error (MSE), and root mean squared error (RMSE) compared to conventional methods. Sensitivity analysis confirms that an optimal parameter of 1.5 yields the best results, while convergence analysis shows that the BS-DMO + CNN consistently achieves minimal cost values, enhancing its effectiveness in energy management.