Based on a 10-year simulation of six Regional Climate Models(RCMs) in phase II of the Regional Climate Model Inter-Comparison Project(RMIP) for Asia,the multivariate statistical method of common principal components(C...Based on a 10-year simulation of six Regional Climate Models(RCMs) in phase II of the Regional Climate Model Inter-Comparison Project(RMIP) for Asia,the multivariate statistical method of common principal components(CPCs) is used to analyze and compare the spatiotemporal characteristics of temperature and precipitation simulated by multi-RCMs over China,including the mean climate states and their seasonal transition,the spatial distribution of interannual variability,and the interannual variation.CPC is an effective statistical tool for analyzing the results of different models.Compared with traditional statistical methods,CPC analyses provide a more complete statistical picture for observation and simulation results.The results of CPC analyses show that the climatological means and the characteristics of seasonal transition over China can be accurately simulated by RCMs.However,large biases exist in the interannual variation in certain years or for individual models.展开更多
针对三相串联故障电弧的研究大多只是提供一种能够识别出故障电弧的方法,没有考虑用于工业实时检测的可能性,提出了一种基于深度置信网络的故障电弧检测方法。首先,通过搭建三相异步电机故障电弧实验平台获取不同故障情况下的电流数据,...针对三相串联故障电弧的研究大多只是提供一种能够识别出故障电弧的方法,没有考虑用于工业实时检测的可能性,提出了一种基于深度置信网络的故障电弧检测方法。首先,通过搭建三相异步电机故障电弧实验平台获取不同故障情况下的电流数据,并利用提升小波变换对其进行去噪;其次,通过核主成分分析法KPCA(kernel principal component analysis)提取去噪之后的数据的主成分,减少需要分析的变量;最后,通过PSO优化的DBN网络进行故障识别,与BP神经网络和极限学习机相比,其检测速度更快且准确率达到了98.8%,为应用于实时检测提供了可能性。展开更多
基金supported by the National Natural Science Foundation of China (General Program,Grant No.40975048)the Strategic Priority Research Program-Climate Change:Carbon Budget and Relevant Issues of the Chinese Academy of Sciences (Grant No. XDA05090207)the Knowledge Innovation Program of the Chinese Academy of Sciences (Grant No.KZCX2-EW-202)
文摘Based on a 10-year simulation of six Regional Climate Models(RCMs) in phase II of the Regional Climate Model Inter-Comparison Project(RMIP) for Asia,the multivariate statistical method of common principal components(CPCs) is used to analyze and compare the spatiotemporal characteristics of temperature and precipitation simulated by multi-RCMs over China,including the mean climate states and their seasonal transition,the spatial distribution of interannual variability,and the interannual variation.CPC is an effective statistical tool for analyzing the results of different models.Compared with traditional statistical methods,CPC analyses provide a more complete statistical picture for observation and simulation results.The results of CPC analyses show that the climatological means and the characteristics of seasonal transition over China can be accurately simulated by RCMs.However,large biases exist in the interannual variation in certain years or for individual models.
文摘针对三相串联故障电弧的研究大多只是提供一种能够识别出故障电弧的方法,没有考虑用于工业实时检测的可能性,提出了一种基于深度置信网络的故障电弧检测方法。首先,通过搭建三相异步电机故障电弧实验平台获取不同故障情况下的电流数据,并利用提升小波变换对其进行去噪;其次,通过核主成分分析法KPCA(kernel principal component analysis)提取去噪之后的数据的主成分,减少需要分析的变量;最后,通过PSO优化的DBN网络进行故障识别,与BP神经网络和极限学习机相比,其检测速度更快且准确率达到了98.8%,为应用于实时检测提供了可能性。