主办：陕西省汽车工程学会
ISSN 1671-7988  CN 61-1394/TH
创刊：1976年
汽车实用技术

汽车实用技术 ›› 2022, Vol. 47 ›› Issue (16): 18-24.DOI: 10.16638/j.cnki.1671-7988.2022.016.004

• 智能网联汽车 • 上一篇    

卡方变异的 SSA 的 FSC 赛车转向 梯形优化方法

王家欣 1,2，李 强*1   

  1. 1.浙江科技学院 机械与能源工程学院,2.浙江工业大学 机械工程学院
  • 发布日期:2022-09-30
  • 通讯作者: 李强
  • 作者简介:王家欣（1998—），男，硕士研究生，研究方向为赛车转向系统，E-mail:7790920395@qq.com。
  • 基金资助:
    浙江省大学生科技创新活动计划项目（2020R415002）。

An Optimization Method of FSC Racing Car Steering Trapezoid Based on Chi-square Mutation SSA

WANG Jiaxin1,2 , LI Qiang*1   

  1. 1.School of Mechanical and Energy Engineering, Zhejiang University of Science and Technology,2.College of Mechanical Engineering, Zhejiang University of Technology,
  • Published:2022-09-30
  • Contact: LI Qiang

PDF

摘要： 针对群智能优化算法在空间转向梯形优化在迭代后期，全局搜索能力减弱，算法易陷 入局部最优解的问题，提出基于卡方变异的麻雀搜索算法的转向梯形优化方法。首先，利用 卡方分布改进发现者执行广泛搜索策略时的更新公式；其次，对小于种群平均适应度的个体 进行卡方变异操作，进而在保留麻雀搜索算法部分局部搜索能力的同时，增加种群的多样性， 提高算法跳出局部最优解的能力。实验结果表明，文章的优化方法相对基本麻雀搜索算法和 利用高斯分布和高斯变异改进的麻雀搜索算法，寻优精度分别提高 5.44%和 4.35%，稳健性分 别提高 57.78%和 65.99%，但平均耗时分别增加 83.47%和减少 3.99%。因此，文章算法优化 方法相对基本麻雀搜索算法寻优精度更高、稳健性更强，全局寻优能力提升。

关键词: 空间转向梯形；卡方变异；方程式赛车；麻雀搜索算法

Abstract: Aiming at the problem that the swarm intelligence optimization algorithm turns to trapezoidal optimization in space at the later stage of the iteration, the global search ability is weakened and the algorithm is easy to fall into the local optimal solution, a turning trapezoidal optimization method based on chi-square mutation sparrow search algorithm is proposed. First, use the chi-square distribution to improve the update formula when the discoverer executes a broad search strategy. Secondly, perform chi-square mutation operations on individuals whose fitness is less than the average fitness of the population to increase the diversity of the population while retaining the partial search capabilities of the sparrow search algorithm, Improve the ability of the algorithm to jump out of the local optimal solution. The experimental results show that, compared with the basic sparrow search algorithm and the improved sparrow search algorithm using Gaussian distribution and Gaussian mutation, the optimization method in this paper improves the optimization accuracy by 5.44% and 4.35%, and the robustness by 57.78% and 65.99%, but the average time consumption increases by 83.47% respectively and a reduction of 3.99%. According to this, the algorithm optimization method in this paper has higher precision and stronger robustness than the basic sparrow search algorithm optimization method, and the global optimization ability is improved.

Key words: Spatial steering trapezoid; Chi-square mutation; Formula racing; Sparrow search algorithm