Dissolved gas analysis(DGA)is an effective online fault diagnosis technique for large oil-immersed transformers.However,due to the limited number of DGA data,most deep learning models will be overfitted and the classi...Dissolved gas analysis(DGA)is an effective online fault diagnosis technique for large oil-immersed transformers.However,due to the limited number of DGA data,most deep learning models will be overfitted and the classification accuracy cannot be guaranteed.Therefore,this paper has introduced the idea of deep neural networks into the multi-grained cascade forest(gcForest),which is a tree-based deep learning model,and proposed an improved gcForest that can be accelerated by GPU.Firstly,in order to extract features more effectively and reduce memory consumption,the multi-grained scanning of gcForest is replaced by convolutional neural networks.Secondly,the cascade forest(CasForest)is replaced by cascade eXtreme gradient boosting(CasXGBoost)to improve the classification ability.Finally,235 DGA samples are used to train and evaluate the proposed model.The average fault diagnosis accuracy of the improved gcForest is 88.08%,while the average recall,precision,and Fl-score are 0.89,0.90,0.89,respectively.Moreover,the proposed method still has high fault diagnosis accuracy for datasets of different sizes.展开更多
Owls have the potential to be keystone species for conservation in fragmented landscapes, as the absence of these predators could profoundly change community structure. Yet few studies have examined how whole communit...Owls have the potential to be keystone species for conservation in fragmented landscapes, as the absence of these predators could profoundly change community structure. Yet few studies have examined how whole communities of owls respond to fragmentation, especially in the tropics. When evaluating the effect of factors related to fragmentation, such as fragment area and distance to the edge, on these birds, it is also important in heterogeneous landscapes to ask how ＇location factors＇ such as the topography, vegetation and soil of the fragment predict their persistence. In Xishuangbanna, southwest China, we established 43 transects （200 mx60 m） within 20 forest fragments to sample nocturnal birds, both visually and aurally. We used a multimodel inference approach to identify the factors that influence owl species richness, and generalized linear mixed models to predict the occurrence probabilities of each species. We found that fragmentation factors dominated location factors, with larger fragments having more species, and four of eight species were significantly more likely to occur in large fragments. Given the potential importance of these birds on regulating small mammal and other animal populations, and thus indirectly affecting seed dispersal, we suggest further protection of large f ragments and programs to increase their connectivity to the remaining smaller fragments.展开更多
针对故障诊断中单一来源信号特征信息表征不充分以及深度神经网络调参复杂、构建难度大等问题,提出了一种基于声振特征融合和改进级联森林的离心泵故障诊断方法。首先,对多个传感器采集的声振信号进行小波包去噪,提取降噪信号的时域特...针对故障诊断中单一来源信号特征信息表征不充分以及深度神经网络调参复杂、构建难度大等问题,提出了一种基于声振特征融合和改进级联森林的离心泵故障诊断方法。首先,对多个传感器采集的声振信号进行小波包去噪,提取降噪信号的时域特征、频域特征和小波包能量特征。利用核主成分分析(kernel principal component analysis,KPCA)对声振信号特征进行特征融合与数据降维,得到特征矩阵。在深度级联森林的基础上引入极端随机森林构建级联层,并添加XGBoost预测器提升模型性能,得到改进级联森林模型。利用改进的级联森林模型进行故障分类,试验结果表明,该方法能够有效识别离心泵的故障类型,并且声振信号特征融合相比于单源信号特征能够有效提升诊断精度。展开更多
Higher requirements for the accuracy of relevant models are put throughout the transformation and upgrade of the iron and steel sector to intelligent production.It has been difficult to meet the needs of the field wit...Higher requirements for the accuracy of relevant models are put throughout the transformation and upgrade of the iron and steel sector to intelligent production.It has been difficult to meet the needs of the field with the usual prediction model of mechanical properties of hotrolled strip.Insufficient data and difficult parameter adjustment limit deep learning models based on multi-layer networks in practical applications;besides,the limited discrete process parameters used make it impossible to effectively depict the actual strip processing process.In order to solve these problems,this research proposed a new sampling approach for mechanical characteristics input data of hot-rolled strip based on the multi-grained cascade forest(gcForest)framework.According to the characteristics of complex process flow and abnormal sensitivity of process path and parameters to product quality in the hot-rolled strip production,a three-dimensional continuous time series process data sampling method based on time-temperature-deformation was designed.The basic information of strip steel(chemical composition and typical process parameters)is fused with the local process information collected by multi-grained scanning,so that the next link’s input has both local and global features.Furthermore,in the multi-grained scanning structure,a sub sampling scheme with a variable window was designed,so that input data with different dimensions can get output characteristics of the same dimension after passing through the multi-grained scanning structure,allowing the cascade forest structure to be trained normally.Finally,actual production data of three steel grades was used to conduct the experimental evaluation.The results revealed that the gcForest-based mechanical property prediction model outperforms the competition in terms of comprehensive performance,ease of parameter adjustment,and ability to sustain high prediction accuracy with fewer samples.展开更多
基金supported in part by the National Natural Science Foundation of China under Grant(52277138)Natural Science Foundation of Guangxi under Grant(2018JJB160064,2018JJA160176)。
文摘Dissolved gas analysis(DGA)is an effective online fault diagnosis technique for large oil-immersed transformers.However,due to the limited number of DGA data,most deep learning models will be overfitted and the classification accuracy cannot be guaranteed.Therefore,this paper has introduced the idea of deep neural networks into the multi-grained cascade forest(gcForest),which is a tree-based deep learning model,and proposed an improved gcForest that can be accelerated by GPU.Firstly,in order to extract features more effectively and reduce memory consumption,the multi-grained scanning of gcForest is replaced by convolutional neural networks.Secondly,the cascade forest(CasForest)is replaced by cascade eXtreme gradient boosting(CasXGBoost)to improve the classification ability.Finally,235 DGA samples are used to train and evaluate the proposed model.The average fault diagnosis accuracy of the improved gcForest is 88.08%,while the average recall,precision,and Fl-score are 0.89,0.90,0.89,respectively.Moreover,the proposed method still has high fault diagnosis accuracy for datasets of different sizes.
基金financially supported by the 1000 Plan Recruitment Program of Global Experts of China to EG
文摘Owls have the potential to be keystone species for conservation in fragmented landscapes, as the absence of these predators could profoundly change community structure. Yet few studies have examined how whole communities of owls respond to fragmentation, especially in the tropics. When evaluating the effect of factors related to fragmentation, such as fragment area and distance to the edge, on these birds, it is also important in heterogeneous landscapes to ask how ＇location factors＇ such as the topography, vegetation and soil of the fragment predict their persistence. In Xishuangbanna, southwest China, we established 43 transects （200 mx60 m） within 20 forest fragments to sample nocturnal birds, both visually and aurally. We used a multimodel inference approach to identify the factors that influence owl species richness, and generalized linear mixed models to predict the occurrence probabilities of each species. We found that fragmentation factors dominated location factors, with larger fragments having more species, and four of eight species were significantly more likely to occur in large fragments. Given the potential importance of these birds on regulating small mammal and other animal populations, and thus indirectly affecting seed dispersal, we suggest further protection of large f ragments and programs to increase their connectivity to the remaining smaller fragments.
文摘针对故障诊断中单一来源信号特征信息表征不充分以及深度神经网络调参复杂、构建难度大等问题,提出了一种基于声振特征融合和改进级联森林的离心泵故障诊断方法。首先,对多个传感器采集的声振信号进行小波包去噪,提取降噪信号的时域特征、频域特征和小波包能量特征。利用核主成分分析(kernel principal component analysis,KPCA)对声振信号特征进行特征融合与数据降维,得到特征矩阵。在深度级联森林的基础上引入极端随机森林构建级联层,并添加XGBoost预测器提升模型性能,得到改进级联森林模型。利用改进的级联森林模型进行故障分类,试验结果表明,该方法能够有效识别离心泵的故障类型,并且声振信号特征融合相比于单源信号特征能够有效提升诊断精度。
基金financially supported by the National Natural Science Foundation of China(No.52004029)the Fundamental Research Funds for the Central Universities,China(No.FRF-TT-20-06).
文摘Higher requirements for the accuracy of relevant models are put throughout the transformation and upgrade of the iron and steel sector to intelligent production.It has been difficult to meet the needs of the field with the usual prediction model of mechanical properties of hotrolled strip.Insufficient data and difficult parameter adjustment limit deep learning models based on multi-layer networks in practical applications;besides,the limited discrete process parameters used make it impossible to effectively depict the actual strip processing process.In order to solve these problems,this research proposed a new sampling approach for mechanical characteristics input data of hot-rolled strip based on the multi-grained cascade forest(gcForest)framework.According to the characteristics of complex process flow and abnormal sensitivity of process path and parameters to product quality in the hot-rolled strip production,a three-dimensional continuous time series process data sampling method based on time-temperature-deformation was designed.The basic information of strip steel(chemical composition and typical process parameters)is fused with the local process information collected by multi-grained scanning,so that the next link’s input has both local and global features.Furthermore,in the multi-grained scanning structure,a sub sampling scheme with a variable window was designed,so that input data with different dimensions can get output characteristics of the same dimension after passing through the multi-grained scanning structure,allowing the cascade forest structure to be trained normally.Finally,actual production data of three steel grades was used to conduct the experimental evaluation.The results revealed that the gcForest-based mechanical property prediction model outperforms the competition in terms of comprehensive performance,ease of parameter adjustment,and ability to sustain high prediction accuracy with fewer samples.
