Accurate fault root cause diagnosis is essential for ensuring stable industrial production. Traditional methods, which typically rely on the entire time series and overlook critical local features, can lead to biased ...Accurate fault root cause diagnosis is essential for ensuring stable industrial production. Traditional methods, which typically rely on the entire time series and overlook critical local features, can lead to biased inferences about causal relationships, thus hindering the accurate identification of root cause variables. This study proposed a shapelet-based state evolution graph for fault root cause diagnosis (SEG-RCD), which enables causal inference through the analysis of the important local features. First, the regularized autoencoder and fault contribution plot are used to identify the fault onset time and candidate root cause variables, respectively. Then, the most representative shapelets were extracted to construct a state evolution graph. Finally, the propagation path was extracted based on fault unit shapelets to pinpoint the fault root cause variable. The SEG-RCD can reduce the interference of noncausal information, enhancing the accuracy and interpretability of fault root cause diagnosis. The superiority of the proposed SEG-RCD was verified through experiments on a simulated penicillin fermentation process and an actual one.展开更多
针对基于shapelets转换的时间序列分类方法中候选shapelets存在较大相似性的问题,提出一种基于多样化top-k shapelets转换的分类方法 Div Top KShapelet。该方法采用多样化top-k查询技术,去除相似shapelets,并筛选出最具代表性的k个shap...针对基于shapelets转换的时间序列分类方法中候选shapelets存在较大相似性的问题,提出一种基于多样化top-k shapelets转换的分类方法 Div Top KShapelet。该方法采用多样化top-k查询技术,去除相似shapelets,并筛选出最具代表性的k个shapelets集合,最后以最优shapelets集合为特征对数据集进行转换,达到提高分类准确率及时间效率的目的。实验结果表明,Div Top KShapelet分类方法不仅比传统分类方法具有更高的准确率,而且与使用聚类筛选的方法(Cluster Shapelet)和shapelets覆盖的方法(Shapelet Selection)相比,分类准确率最多提高了48.43%和32.61%;同时在所有15个数据集上均有计算效率的提升,最少加速了1.09倍,最高可达到287.8倍。展开更多
shapelets是描述时间序列局部特征的子序列,它能最大程度对不同类别进行区分。从它的发明至今一直吸引着研究者的关注,但是由于过高的时间复杂度阻碍了它被广泛应用。一种快速查找多个shapelets的方法(NonSimilar Discover of Shapelet,...shapelets是描述时间序列局部特征的子序列,它能最大程度对不同类别进行区分。从它的发明至今一直吸引着研究者的关注,但是由于过高的时间复杂度阻碍了它被广泛应用。一种快速查找多个shapelets的方法(NonSimilar Discover of Shapelet,NSDS)被提出:基于shapelets非相似的特性,根据子序列间距离分布设置一个距离阈值,以此过滤掉候选集中的相似子序列。再使用类可分离性作为过滤后的候选子序列的评价标准,最终选择出性能最好的多个shapelets。通过在单变量时间序列数据集上的实验表明了该方法可以极大缩短查找shapelets时间,而且能保持较高的分类准确性。将该方法扩展到多变量时间序列,对多个变量采用组合分类器的方法来提高整体分类的准确率。展开更多
针对现有shapelets分类方法不能解决不平衡时间序列分类的问题,提出了基于多样化top-k shapelets转换的时间序列分类方法,用不平衡数据分类评价指标曲线下面积(Area Under Curve,AUC)代替传统的信息熵,作为衡量shapelets的标准,并利用...针对现有shapelets分类方法不能解决不平衡时间序列分类的问题,提出了基于多样化top-k shapelets转换的时间序列分类方法,用不平衡数据分类评价指标曲线下面积(Area Under Curve,AUC)代替传统的信息熵,作为衡量shapelets的标准,并利用多样化top-k shapelets对训练集进行转换,最后使用SMOTE方法对转换后的训练集进行过采样。该方法利用AUC值对不平衡数据不敏感的特性,提高shapelets特征评估分类的准确性,不仅可以有效提取时间序列特征,还能在特征的基础上进行数据集的平衡处理。展开更多
基金support from the following foundations:the National Natural Science Foundation of China(62322309,62433004)Shanghai Science and Technology Innovation Action Plan(23S41900500)Shanghai Pilot Program for Basic Research(22TQ1400100-16).
文摘Accurate fault root cause diagnosis is essential for ensuring stable industrial production. Traditional methods, which typically rely on the entire time series and overlook critical local features, can lead to biased inferences about causal relationships, thus hindering the accurate identification of root cause variables. This study proposed a shapelet-based state evolution graph for fault root cause diagnosis (SEG-RCD), which enables causal inference through the analysis of the important local features. First, the regularized autoencoder and fault contribution plot are used to identify the fault onset time and candidate root cause variables, respectively. Then, the most representative shapelets were extracted to construct a state evolution graph. Finally, the propagation path was extracted based on fault unit shapelets to pinpoint the fault root cause variable. The SEG-RCD can reduce the interference of noncausal information, enhancing the accuracy and interpretability of fault root cause diagnosis. The superiority of the proposed SEG-RCD was verified through experiments on a simulated penicillin fermentation process and an actual one.
文摘针对基于shapelets转换的时间序列分类方法中候选shapelets存在较大相似性的问题,提出一种基于多样化top-k shapelets转换的分类方法 Div Top KShapelet。该方法采用多样化top-k查询技术,去除相似shapelets,并筛选出最具代表性的k个shapelets集合,最后以最优shapelets集合为特征对数据集进行转换,达到提高分类准确率及时间效率的目的。实验结果表明,Div Top KShapelet分类方法不仅比传统分类方法具有更高的准确率,而且与使用聚类筛选的方法(Cluster Shapelet)和shapelets覆盖的方法(Shapelet Selection)相比,分类准确率最多提高了48.43%和32.61%;同时在所有15个数据集上均有计算效率的提升,最少加速了1.09倍,最高可达到287.8倍。
文摘shapelets是描述时间序列局部特征的子序列,它能最大程度对不同类别进行区分。从它的发明至今一直吸引着研究者的关注,但是由于过高的时间复杂度阻碍了它被广泛应用。一种快速查找多个shapelets的方法(NonSimilar Discover of Shapelet,NSDS)被提出:基于shapelets非相似的特性,根据子序列间距离分布设置一个距离阈值,以此过滤掉候选集中的相似子序列。再使用类可分离性作为过滤后的候选子序列的评价标准,最终选择出性能最好的多个shapelets。通过在单变量时间序列数据集上的实验表明了该方法可以极大缩短查找shapelets时间,而且能保持较高的分类准确性。将该方法扩展到多变量时间序列,对多个变量采用组合分类器的方法来提高整体分类的准确率。
文摘针对现有shapelets分类方法不能解决不平衡时间序列分类的问题,提出了基于多样化top-k shapelets转换的时间序列分类方法,用不平衡数据分类评价指标曲线下面积(Area Under Curve,AUC)代替传统的信息熵,作为衡量shapelets的标准,并利用多样化top-k shapelets对训练集进行转换,最后使用SMOTE方法对转换后的训练集进行过采样。该方法利用AUC值对不平衡数据不敏感的特性,提高shapelets特征评估分类的准确性,不仅可以有效提取时间序列特征,还能在特征的基础上进行数据集的平衡处理。
