基于改进ILS⁃RVND算法的工业园区智能巡检机器人路径规划方法

Improved ILS⁃RVND algorithm based path planning method of intelligent inspection robot in industrial park

由于工业园区巡回面广泛、巡回点繁多,需消耗大量时间和精力;人工巡检在及时性、可靠性、针对性、效率性等方面存在弊端;易燃易爆高温高湿区域,还存在一定的安全风险。因此,用巡检机器人来代替其安保人员工作便成为必然趋势。基于园区巡检的实际需求,以机器人能源、巡检点时效及巡检完整性为约束,建立园区巡检路径优化的数学模型,优化机器人巡检路径;为提高求解的质量,在随机变邻域迭代搜索算法(ILS⁃RVND)的基础上添加扰动和模拟退火机制,设计适合该问题求解的搜索算法。实验研究表明,该方法可有效降低园区巡检的路程,使量化成本下降约24%,巡检时间下降约36%,且大幅减少巡检点的超时巡检现象,在成本、巡检路径及超时巡检均有明显优势。

Due to extensive inspection areas and many inspection points in the industrial park,which needs to take a lot of time and efforts,manual inspection has shortcomings in timeliness,reliability,pertinence,efficiency,etc.,and there are certain safety risks in the flammable,explosible,high⁃temperature and high⁃humidity areas.Therefore,it has become an inevitable trend to replace the security personnel with inspection robots.On the basis of actual needs of the industrial park inspection,a mathematical model for the optimization of the park inspection path is established to optimize the robot inspection path by taking robot energy,inspection point ageing and inspection integrity as the constraints.In order to improve the quality of the solution,a disturbance and simulated annealing mechanism is added to design a search algorithm suitable for the solution on the basis of the iterative local search of random variable neighborhood descent(ILS⁃RVND)algorithm.Experimental research result shows that this method can effectively shorten the distance of the park inspection,reduce the quantitative cost by about 24%and the inspection time by about 36%,and greatly reduce the phenomenon of overtime inspection at an inspection point.Anyway,it has obvious advantages in cost,inspection path and overtime inspection.