Based on the idea that modules are independent of machines, different combinations of modules and machines result in different configurations and the system performances differ under different configurations, a kind o...Based on the idea that modules are independent of machines, different combinations of modules and machines result in different configurations and the system performances differ under different configurations, a kind of cyclic reconfigurable flow shops are proposed for the new manufacturing paradigm-reconfigurable manufacturing system. The cyclic reconfigurable flow shop is modeled as a timed event graph. The optimal configuration is defined as the one under which the cyclic reconfigurable flow shop functions with the minimum cycle time and the minimum number of pallets. The optimal configuration, the minimum cycle time and the minimum number of pallets can be obtained in two steps.展开更多
短时交通流预测在智能交通系统中扮演重要的角色。针对交通流复杂多变的时空特征、非平稳性及外部因素引发的数据异常,提出考虑异常因素的混合深度神经网络预测模型(hybrid deep neural network forecasting model considering anomalou...短时交通流预测在智能交通系统中扮演重要的角色。针对交通流复杂多变的时空特征、非平稳性及外部因素引发的数据异常,提出考虑异常因素的混合深度神经网络预测模型(hybrid deep neural network forecasting model considering anomalous factors,HDNNF-CAF)。该模型将邻接矩阵、交通流量矩阵及交通流其他参数矩阵结合异常数据处理理论,进行数据预处理和异常数据识别。建立异常数据时空特征提取理论,捕获异常数据时空信息;利用变分模态分解(VMD)降低交通流数据非平稳性,并提出图卷积网络(GCN)优化Informer理论分别对各个子序列进行特征提取,以组合生成交通流时空信息。最终结合异常数据与交通流数据的时空信息生成预测结果。在真实数据集PeMS04上进行验证,实验结果表明,HDNNF-CAF能够有效识别交通流异常数据,提高预测精度,优于一些现有方法。展开更多
基金Supported by National Key Fundamental Research and Development Project of P. R. China (2002CB312200)
文摘Based on the idea that modules are independent of machines, different combinations of modules and machines result in different configurations and the system performances differ under different configurations, a kind of cyclic reconfigurable flow shops are proposed for the new manufacturing paradigm-reconfigurable manufacturing system. The cyclic reconfigurable flow shop is modeled as a timed event graph. The optimal configuration is defined as the one under which the cyclic reconfigurable flow shop functions with the minimum cycle time and the minimum number of pallets. The optimal configuration, the minimum cycle time and the minimum number of pallets can be obtained in two steps.
文摘短时交通流预测在智能交通系统中扮演重要的角色。针对交通流复杂多变的时空特征、非平稳性及外部因素引发的数据异常,提出考虑异常因素的混合深度神经网络预测模型(hybrid deep neural network forecasting model considering anomalous factors,HDNNF-CAF)。该模型将邻接矩阵、交通流量矩阵及交通流其他参数矩阵结合异常数据处理理论,进行数据预处理和异常数据识别。建立异常数据时空特征提取理论,捕获异常数据时空信息;利用变分模态分解(VMD)降低交通流数据非平稳性,并提出图卷积网络(GCN)优化Informer理论分别对各个子序列进行特征提取,以组合生成交通流时空信息。最终结合异常数据与交通流数据的时空信息生成预测结果。在真实数据集PeMS04上进行验证,实验结果表明,HDNNF-CAF能够有效识别交通流异常数据,提高预测精度,优于一些现有方法。
文摘交通流预测是智能交通系统(intelligent transportation system,ITS)中交通管理的重要基础和热门研究方向.传统的交通流预测方法通常需要借助大量高质量历史观测数据进行预测,而针对更为普遍的数据稀缺的交通路网场景预测精度则急剧下降.针对这一问题,提出一种基于时空图卷积网络的迁移学习模型(transfer learning based on spatial-temporal graph convolutional network,TL-STGCN),结合数据充足的源路网的交通流特征,辅助预测数据稀缺的目标路网未来交通流.首先,采用基于时间注意力的时空图卷积网络学习源路网和目标路网交通流数据的时空特征表示;其次,结合迁移学习方法,提取两个路网特征表示的域不变时空特征;最后,利用这些域不变时空特征对目标路网未来交通流做出预测.为了验证模型的有效性,在真实世界数据集上进行实验.结果表明,与现有方法对比,TL-STGCN在平均绝对误差、均方根误差以及平均绝对百分比误差指标中均取得最高精度,证明对于数据稀缺的交通路网预测任务,TL-STGCN具有更好的预测性能.
