油浸式变压器微型仿生鱼全局路径规划策略

为有效检测大型变压器内部的故障位置和故障类型,通过利用微型仿生鱼对变压器内部进行视觉观测,可较直观的检查变压器内部故障。微型仿生鱼在检测过程中的路径规划是仿生鱼任务完成的关键。针对变压器内部复杂的三维空间,本文提出了基于人工势场法和蚁群算法的三维全局路径规划策略,并利用LABVIEW对变压器微型仿生鱼的三维全局路径规划结果进行了仿真分析。分析结果表明：当引入了人工势场法的相关机理,蚁群算法将不再盲目进行搜索,而是优先选取人工势场合力方向的临近栅格点,提高了算法搜索速度和全局寻优能力。基于人工势场法和蚁群算法的三维全局路径规划策略对微型仿生鱼进行了有效路径规划,具有较好的实用性,这对后续变压器微型仿生鱼样机的控制提供了重要参考。

The 3D Global Path Planning Strategy of Miniature Robot in The Large Transformer

In order to effectively identify the fault type and locate the fault position in the large transformer, the miniature bionic fish is used for visual observation to inspect the internal transformer faults. The route planning is the key task for the miniature bionic fish in the process of detection. Aiming at the complex three-dimensional (3D) space inside the transformer, a 3D global path planning strategy based on the artificial potential field method and the ant colony algorithm is proposed in this study. The 3D global path planning results are further simulated and analyzed by using the LABVIEW software. The simulation results demonstrate that when the artificial potential field method is introduced, the ant colony algorithm can avoid blind search and firstly select the adjacent grid points of the artificial potential field resultant direction. Therefore, the search speed and global optimization ability of the algorithm are improved. The proposed 3D global path planning strategy based on the artificial potential field method and the ant colony algorithm can achieve an effective path planning, and provides an important reference for the intelligent control of the following miniature robot prototype.