Scholarlink

<p>In this study, a high horsepower series hybrid tractor is taken as the research object, addressing the issue of poor adaptability of the single rule-based control strategy across diverse working conditions, and the inability to achieve optimal control solely reliant on expert-designed control parameters, an optimized fuzzy control energy management strategy considering working conditions adaptation is proposed. By constructing an online working condition recognition model based on particle swarm optimization support vector machine (PSO-SVM) algorithm, the working condition type is determined in real time. The corresponding fuzzy control strategies are developed, and the genetic algorithm (GA) is introduced to optimize the control parameters offline for optimal power allocation. Simulation results indicate that the proposed EMS exhibits a working condition recognition error of merely 1.19 %, and compared with the power following strategy and the working conditions-adaptive fuzzy control strategy, the comprehensive fuel consumption is reduced by 6.96 % and 3.38 %, respectively, which effectively enhancing the fuel efficiency of the tractor.</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

Optimized fuzzy control energy management strategy for hybrid tractors considering working conditions adaptation

  • 期刊论文

  • 发表日期：

    2025年5月30日

查看全文
  • Bifeng Yin,
  • Long Yun,
  • Xuan Xie,
  • Jian Wang,
  • Youlin Huang

摘要

In this study, a high horsepower series hybrid tractor is taken as the research object, addressing the issue of poor adaptability of the single rule-based control strategy across diverse working conditions, and the inability to achieve optimal control solely reliant on expert-designed control parameters, an optimized fuzzy control energy management strategy considering working conditions adaptation is proposed. By constructing an online working condition recognition model based on particle swarm optimization support vector machine (PSO-SVM) algorithm, the working condition type is determined in real time. The corresponding fuzzy control strategies are developed, and the genetic algorithm (GA) is introduced to optimize the control parameters offline for optimal power allocation. Simulation results indicate that the proposed EMS exhibits a working condition recognition error of merely 1.19 %, and compared with the power following strategy and the working conditions-adaptive fuzzy control strategy, the comprehensive fuel consumption is reduced by 6.96 % and 3.38 %, respectively, which effectively enhancing the fuel efficiency of the tractor.