PM_(2.5) forecasting technology can provide a scientific and effective way to assist environmental governance and protect public health.To forecast PM_(2.5),an enhanced hybrid ensemble deep learning model is proposed ...PM_(2.5) forecasting technology can provide a scientific and effective way to assist environmental governance and protect public health.To forecast PM_(2.5),an enhanced hybrid ensemble deep learning model is proposed in this research.The whole framework of the proposed model can be generalized as follows:the original PM_(2.5) series is decomposed into 8 sub-series with different frequency characteristics by variational mode decomposition(VMD);the long short-term memory(LSTM)network,echo state network(ESN),and temporal convolutional network(TCN)are applied for parallel forecasting for 8 different frequency PM_(2.5) sub-series;the gradient boosting decision tree(GBDT)is applied to assemble and reconstruct the forecasting results of LSTM,ESN and TCN.By comparing the forecasting data of the models over 3 PM_(2.5) series collected from Shenyang,Changsha and Shenzhen,the conclusions can be drawn that GBDT is a more effective method to integrate the forecasting result than traditional heuristic algorithms;MAE values of the proposed model on 3 PM_(2.5) series are 1.587,1.718 and 1.327μg/m3,respectively and the proposed model achieves more accurate results for all experiments than sixteen alternative forecasting models which contain three state-of-the-art models.展开更多
Gas–liquid two-phase flow abounds in industrial processes and facilities. Identification of its flow pattern plays an essential role in the field of multiphase flow measurement. A bluff body was introduced in this s...Gas–liquid two-phase flow abounds in industrial processes and facilities. Identification of its flow pattern plays an essential role in the field of multiphase flow measurement. A bluff body was introduced in this study to recognize gas–liquid flow patterns by inducing fluid oscillation that enlarged differences between each flow pattern. Experiments with air–water mixtures were carried out in horizontal pipelines at ambient temperature and atmospheric pressure. Differential pressure signals from the bluff-body wake were obtained in bubble, bubble/plug transitional, plug, slug, and annular flows. Utilizing the adaptive ensemble empirical mode decomposition method and the Hilbert transform, the time–frequency entropy S of the differential pressure signals was obtained. By combining S and other flow parameters, such as the volumetric void fraction β, the dryness x, the ratio of density φ and the modified fluid coefficient ψ, a new flow pattern map was constructed which adopted S（1–x）φ and （1–β）ψ as the vertical and horizontal coordinates, respectively. The overall rate of classification of the map was verified to be 92.9% by the experimental data. It provides an effective and simple solution to the gas–liquid flow pattern identification problems.展开更多
Wafer bin map(WBM)inspection is a critical approach for evaluating the semiconductor manufacturing process.An excellent inspection algorithm can improve the production efficiency and yield.This paper proposes a WBM de...Wafer bin map(WBM)inspection is a critical approach for evaluating the semiconductor manufacturing process.An excellent inspection algorithm can improve the production efficiency and yield.This paper proposes a WBM defect pattern inspection strategy based on the DenseNet deep learning model,the structure and training loss function are improved according to the characteristics of the WBM.In addition,a constrained mean filtering algorithm is proposed to filter the noise grains.In model prediction,an entropy-based Monte Carlo dropout algorithm is employed to quantify the uncertainty of the model decision.The experimental results show that the recognition ability of the improved DenseNet is better than that of traditional algorithms in terms of typical WBM defect patterns.Analyzing the model uncertainty can not only effectively reduce the miss or false detection rate but also help to identify new patterns.展开更多
基金Project(52072412)supported by the National Natural Science Foundation of ChinaProject(2019CX005)supported by the Innovation Driven Project of the Central South University,China。
文摘PM_(2.5) forecasting technology can provide a scientific and effective way to assist environmental governance and protect public health.To forecast PM_(2.5),an enhanced hybrid ensemble deep learning model is proposed in this research.The whole framework of the proposed model can be generalized as follows:the original PM_(2.5) series is decomposed into 8 sub-series with different frequency characteristics by variational mode decomposition(VMD);the long short-term memory(LSTM)network,echo state network(ESN),and temporal convolutional network(TCN)are applied for parallel forecasting for 8 different frequency PM_(2.5) sub-series;the gradient boosting decision tree(GBDT)is applied to assemble and reconstruct the forecasting results of LSTM,ESN and TCN.By comparing the forecasting data of the models over 3 PM_(2.5) series collected from Shenyang,Changsha and Shenzhen,the conclusions can be drawn that GBDT is a more effective method to integrate the forecasting result than traditional heuristic algorithms;MAE values of the proposed model on 3 PM_(2.5) series are 1.587,1.718 and 1.327μg/m3,respectively and the proposed model achieves more accurate results for all experiments than sixteen alternative forecasting models which contain three state-of-the-art models.
基金Project(51576213)supported by the National Natural Science Foundation of ChinaProject(2015RS4015)supported by the Hunan Scientific Program,ChinaProject(2016zzts323)supported by the Innovation Project of Central South University,China
文摘Gas–liquid two-phase flow abounds in industrial processes and facilities. Identification of its flow pattern plays an essential role in the field of multiphase flow measurement. A bluff body was introduced in this study to recognize gas–liquid flow patterns by inducing fluid oscillation that enlarged differences between each flow pattern. Experiments with air–water mixtures were carried out in horizontal pipelines at ambient temperature and atmospheric pressure. Differential pressure signals from the bluff-body wake were obtained in bubble, bubble/plug transitional, plug, slug, and annular flows. Utilizing the adaptive ensemble empirical mode decomposition method and the Hilbert transform, the time–frequency entropy S of the differential pressure signals was obtained. By combining S and other flow parameters, such as the volumetric void fraction β, the dryness x, the ratio of density φ and the modified fluid coefficient ψ, a new flow pattern map was constructed which adopted S（1–x）φ and （1–β）ψ as the vertical and horizontal coordinates, respectively. The overall rate of classification of the map was verified to be 92.9% by the experimental data. It provides an effective and simple solution to the gas–liquid flow pattern identification problems.
基金Project(Z135060009002)supported by the Ministry of Industry and Information Technology of ChinaProject(KZ202010005004)supported by Beijing Municipal Commission of Education and Beijing Municipal Natural Science Foundation of China。
文摘Wafer bin map(WBM)inspection is a critical approach for evaluating the semiconductor manufacturing process.An excellent inspection algorithm can improve the production efficiency and yield.This paper proposes a WBM defect pattern inspection strategy based on the DenseNet deep learning model,the structure and training loss function are improved according to the characteristics of the WBM.In addition,a constrained mean filtering algorithm is proposed to filter the noise grains.In model prediction,an entropy-based Monte Carlo dropout algorithm is employed to quantify the uncertainty of the model decision.The experimental results show that the recognition ability of the improved DenseNet is better than that of traditional algorithms in terms of typical WBM defect patterns.Analyzing the model uncertainty can not only effectively reduce the miss or false detection rate but also help to identify new patterns.
