基于改进被囊群算法的露天矿无人驾驶卡车运输调度

Unmanned truck transportation scheduling in open-pit mines based on improved tunicate swarm algorithm

  • 摘要: 针对露天矿无人驾驶卡车运输调度问题,以无人驾驶卡车燃油费用、固定启用费用、故障维修费用及网络基站建设与维护费用之和最小为目标函数,并以采矿场开采量、破碎场破碎量、卡车数量、卡车运输工作量为约束条件,建立了露天矿无人驾驶卡车运输调度优化模型。针对被囊群算法存在全局勘探和局部开采能力不平衡的问题,提出了一种基于Singer映射和参数位置自适应更新机制的改进被囊群算法(ITSA),并将其用于求解露天矿无人驾驶卡车运输调度优化模型。该算法引入Singer映射用于增强初始被囊种群在解空间中的分布性,加快压缩解空间大小,从而提高算法收敛速度;通过参数位置自适应更新机制调节被囊个体与最优被囊个体位置,以增大解空间的搜索范围,从而使算法跳出局部最优。仿真结果表明:与灰狼优化算法(GWO)、鲸鱼优化算法(WOA)、原子搜索优化算法(ASO)及被囊群算法(TSA)4种群智能优化算法相比,ITSA具有更好的收敛精度、收敛速度和稳定性能;在单峰基准函数上,ITSA的各项评价指标远优于其他4种算法,表明ITSA具有更好的局部开采能力;在多峰基准函数上,ITSA的各项评价指标表现出更好的寻优性能,表明ITSA具有更好的全局勘探性能。实际应用场景表明,ITSA用于求解无人驾驶卡车运输调度优化模型时具有更快的收敛速度和更高的收敛精度,且减少了卡车运输费用和运输距离。

     

    Abstract: In order to solve the problem of unmanned truck transportation scheduling in open-pit mines, the minimum sum of fuel cost, fixed start-up cost, breakdown maintenance cost, and network base station construction and maintenance cost are taken as the objective functions. The mining amount of mining station, crushing amount of crushing station, truck number and truck transportation workload are taken as the constraint conditions. The optimization model of unmanned truck transportation scheduling in open-pit mines is established. To solve the problem of imbalance between global exploration and local mining ability in the tunicate swarm algorithm, an improved tunicate swarm algorithm (ITSA) based on Singer mapping and adaptive updating mechanism of parameter position is proposed. And it is applied to solve the optimization model of unmanned truck transportation scheduling in open-pit mines. Singer mapping is introduced to enhance the distribution of the initial tunicate swarm in the solution space and accelerate the compression of the solution space, thus improving the convergence speed of the algorithm. Through the adaptive updating mechanism of parameter position, the positions of the tunicate and the optimal tunicate are adjusted to increase the search range of the solution space. Therefore, the algorithm jumps out of the local optimization. The simulation results show that ITSA has better convergence precision, convergence speed and stability compared with the four population intelligent optimization algorithms of grey wolf optimization algorithm (GWO), whale optimization algorithm (WOA), atom search optimization algorithm (ASO) and tunicate swarm algorithm (TSA). In the unimodal benchmark function, the evaluation indexes of ITSA are far better than those of the other four algorithms, which shows that ITSA has better local mining capacity. In the multi-peak benchmark function, the evaluation indexes of ITSA show better optimization performance, which indicates that ITSA has better global exploration performance. The practical application scenario verification shows that ITSA has faster convergence speed and higher convergence precision when used for solving the unmanned truck transportation scheduling optimization model. And ITSA reduces the truck transportation cost and transportation distance.

     

/

返回文章
返回