Scholarlink

<p>In response to the issues of low convergence efficiency and the tendency to fall into local optima that traditional algorithm face when solving inspection task allocation in the large-scale and complex environment of oil and gas stations, this article proposes an inspection robot task allocation method based on an improved genetic algorithm (GA). First, an oil and gas station inspection robot task allocation model is constructed, adopting the principle of minimum path cost allocation. Subsequently, the GA is utilized to solve for the optimal solution to the inspection robot task allocation problem. Then, an improved GA combining greedy strategy and heuristic crossover operator is proposed to solve the optimal inspection distance. Finally, adaptive parameters are introduced to ensure a good genetic model. Simulation and experimental results show that in the complex inspection environment of oil and gas stations, the improved GA reduces the shortest inspection distance from 20.3 to 17.5&#xa0;m, a reduction of approximately 13.8%. The minimum number of iterations decreased from 65.4 to 46.8, a reduction of about 28.4%, shortening the shortest inspection distance and enhancing the efficiency of inspection task allocation. The ability to find the optimal solution and the optimal inspection distance in a shorter time validates the superiority of the improved algorithm.</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

Research on inspection task allocation method of inspection robot based on improved genetic algorithm

  • 期刊论文

  • 发表日期：

    2025年9月19日

查看全文
  • Zhengzhi Luo,
  • Yike Han,
  • Yubo Zou,
  • Xin Zhang,
  • Jianing Zhang

摘要

In response to the issues of low convergence efficiency and the tendency to fall into local optima that traditional algorithm face when solving inspection task allocation in the large-scale and complex environment of oil and gas stations, this article proposes an inspection robot task allocation method based on an improved genetic algorithm (GA). First, an oil and gas station inspection robot task allocation model is constructed, adopting the principle of minimum path cost allocation. Subsequently, the GA is utilized to solve for the optimal solution to the inspection robot task allocation problem. Then, an improved GA combining greedy strategy and heuristic crossover operator is proposed to solve the optimal inspection distance. Finally, adaptive parameters are introduced to ensure a good genetic model. Simulation and experimental results show that in the complex inspection environment of oil and gas stations, the improved GA reduces the shortest inspection distance from 20.3 to 17.5 m, a reduction of approximately 13.8%. The minimum number of iterations decreased from 65.4 to 46.8, a reduction of about 28.4%, shortening the shortest inspection distance and enhancing the efficiency of inspection task allocation. The ability to find the optimal solution and the optimal inspection distance in a shorter time validates the superiority of the improved algorithm.