基于支持向量机的多载量小车实时调度

发布时间：2018-05-28 11:36

本文选题：人工智能 + 多载量小车　；参考：《吉林大学学报(工学版)》2016年06期

【摘要】：为了有效地解决车辆装配系统中多载量小车的实时调度问题,提出了基于支持向量机的实时调度方法。首先对多载量小车的实时调度问题进行描述,同时建立以车辆装配线产量和物料搬运距离作为评价指标的目标函数。然后通过车辆装配线的物料搬运系统仿真生成样本离线训练支持向量机模型,在实时阶段利用支持向量机模型实现多载量小车"等待"或"搬运"的调度决策。试验结果表明,本文提出的方法明显优于最小批量法,其运行速度快、实时调度效果好,且对动态环境变化具有一定的自适应性,能够有效提升多载量小车的实时调度水平。
[Abstract]:In order to effectively solve the real-time scheduling problem of multi-load vehicles in vehicle assembly system, a real-time scheduling method based on support vector machine (SVM) is proposed. Firstly, the real-time scheduling problem of multi-load vehicles is described, and the objective function of vehicle assembly line production and material handling distance is established. Then the sample off-line training support vector machine model is generated by the material handling system simulation of the vehicle assembly line. The support vector machine model is used to realize the scheduling decision of the multi-load vehicle "waiting" or "moving" in the real time stage. The experimental results show that the proposed method is obviously superior to the minimum batch method, its running speed is fast, the real-time scheduling effect is good, and it has certain adaptability to the dynamic environment change, and it can effectively improve the real-time scheduling level of multi-load vehicles.
【作者单位】：同济大学机械与能源工程学院;
【基金】：国家自然科学基金项目(71471135;61273035)
【分类号】：U468.2;TP181

【相似文献】