Recently,machine learning-based technologies have been developed to automate the classification of wafer map defect patterns during semiconductormanufacturing.The existing approaches used in the wafer map pattern clas...Recently,machine learning-based technologies have been developed to automate the classification of wafer map defect patterns during semiconductormanufacturing.The existing approaches used in the wafer map pattern classification include directly learning the image through a convolution neural network and applying the ensemble method after extracting image features.This study aims to classify wafer map defects more effectively and derive robust algorithms even for datasets with insufficient defect patterns.First,the number of defects during the actual process may be limited.Therefore,insufficient data are generated using convolutional auto-encoder(CAE),and the expanded data are verified using the evaluation technique of structural similarity index measure(SSIM).After extracting handcrafted features,a boosted stacking ensemble model that integrates the four base-level classifiers with the extreme gradient boosting classifier as a meta-level classifier is designed and built for training the model based on the expanded data for final prediction.Since the proposed algorithm shows better performance than those of existing ensemble classifiers even for insufficient defect patterns,the results of this study will contribute to improving the product quality and yield of the actual semiconductor manufacturing process.展开更多
[Objective] This study aimed to analyze the baking cost and benefit under different tobacco loading patterns, and to further explore labor-and cost-saving measures for modern tobacco agriculture. [Method] The cost and...[Objective] This study aimed to analyze the baking cost and benefit under different tobacco loading patterns, and to further explore labor-and cost-saving measures for modern tobacco agriculture. [Method] The cost and benefit of baking under three different tobacco loading patterns in a bulk curing barn were analyzed from the perspectives of baking equipment cost, labor cost, energy consumption and comprehensive income. The upper, middle and lower tobacco leaves were detected. [Result] Compared with conventional loading pattern, loose-leaf stacking and needle- style tobacco clip loading patterns significantly reduced the labor costs and energy costs during tobacco curing. The comprehensive benefits of tobacco clip and looseleaf stacking loading patterns were higher than that of conventional loading pattern, and the benefits of dry tobacco was improved by 0.67 and 1.07 yuan/kg, respec- tively. The benefit of loose-leaf stacking loading pattern was higher than that of to bacco clip loading pattern, [Conclusion] Among the three loading patterns, the loading pattern of loose-leaf stacking is most worthy of popularization and application.展开更多
The aim of this work is to establish volcanic seismic reflection configuration models in the rift basins of Northeast China from a new perspective,the volcanostratigraphic structure.Accordingly,the volcanostratigraphi...The aim of this work is to establish volcanic seismic reflection configuration models in the rift basins of Northeast China from a new perspective,the volcanostratigraphic structure.Accordingly,the volcanostratigraphic structure of an outcrop near the Hailaier Rift Basin was analyzed to understand the characteristics and causal factors of physical boundaries.Further,3D seismic reflection data and analysis of deep boreholes in the Songliao Rift Basin were used to establish the relationship between volcanic seismic reflection configurations and volcanostratigraphic structures.These studies suggested that in volcanic successions,physical boundaries coincide with volcanic boundaries,and their distributions are controlled by the stacking patterns of volcanic units.Therefore,volcanic seismic reflection configurations can be interpreted in terms of the stacking patterns of volcanic units.These are also referred to as general bedding patterns in volcanostratigraphy.Furthermore,four typical seismic reflection configurations were identified,namely,the chaotic,the parallel continuous,the hummocky,the multi-mound superimposed and the composite.The corresponding interpretation models comprised single massive unit,vertical,intersectional,lateral multi-mound,and composite stacking patterns.The hummocky and composite reflection configurations with intersectional and composite stacking patterns are the most favorable for the exploration of volcanic reservoirs in rift basins.展开更多
采用钌钛网(Ti/Ru O2)为阳极、钛网(Ti)为阴极、活性炭颗粒为三维粒子电极的电催化氧化装置深度处理焦化废水,通过分析处理效果和能耗研究了三维粒子电极填充方式的影响。结果显示三维悬挂电极填充方式的处理效果和能耗与传统三维电极...采用钌钛网(Ti/Ru O2)为阳极、钛网(Ti)为阴极、活性炭颗粒为三维粒子电极的电催化氧化装置深度处理焦化废水,通过分析处理效果和能耗研究了三维粒子电极填充方式的影响。结果显示三维悬挂电极填充方式的处理效果和能耗与传统三维电极填充方式相近,但所需材料质量及反应器容积分别为后者的34%与67%。新的填充方式在电流密度2.5 m A/cm2、悬挂电极总质量49.4g、流速100 m L/min的条件下处理120 min后,焦化废水ρ(COD)由99 mg/L降至53 mg/L,COD去除率为46.5%,单位COD处理能耗为68.5 k W·h/kg,吨水能耗为3.15 k W·h/t。展开更多
基金the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.NRF-2021R1A5A8033165)the“Human Resources Program in Energy Technology”of the Korea Institute of Energy Technology Evaluation and Planning(KETEP)and was granted financial resources from the Ministry of Trade,Industry&Energy,Republic of Korea(No.20214000000200).
文摘Recently,machine learning-based technologies have been developed to automate the classification of wafer map defect patterns during semiconductormanufacturing.The existing approaches used in the wafer map pattern classification include directly learning the image through a convolution neural network and applying the ensemble method after extracting image features.This study aims to classify wafer map defects more effectively and derive robust algorithms even for datasets with insufficient defect patterns.First,the number of defects during the actual process may be limited.Therefore,insufficient data are generated using convolutional auto-encoder(CAE),and the expanded data are verified using the evaluation technique of structural similarity index measure(SSIM).After extracting handcrafted features,a boosted stacking ensemble model that integrates the four base-level classifiers with the extreme gradient boosting classifier as a meta-level classifier is designed and built for training the model based on the expanded data for final prediction.Since the proposed algorithm shows better performance than those of existing ensemble classifiers even for insufficient defect patterns,the results of this study will contribute to improving the product quality and yield of the actual semiconductor manufacturing process.
文摘[Objective] This study aimed to analyze the baking cost and benefit under different tobacco loading patterns, and to further explore labor-and cost-saving measures for modern tobacco agriculture. [Method] The cost and benefit of baking under three different tobacco loading patterns in a bulk curing barn were analyzed from the perspectives of baking equipment cost, labor cost, energy consumption and comprehensive income. The upper, middle and lower tobacco leaves were detected. [Result] Compared with conventional loading pattern, loose-leaf stacking and needle- style tobacco clip loading patterns significantly reduced the labor costs and energy costs during tobacco curing. The comprehensive benefits of tobacco clip and looseleaf stacking loading patterns were higher than that of conventional loading pattern, and the benefits of dry tobacco was improved by 0.67 and 1.07 yuan/kg, respec- tively. The benefit of loose-leaf stacking loading pattern was higher than that of to bacco clip loading pattern, [Conclusion] Among the three loading patterns, the loading pattern of loose-leaf stacking is most worthy of popularization and application.
基金Projects(41472304,41430322) supported by the National Natural Science Foundation of ChinaProject(2012CB822002) supported by National Major State Basic Research Program of China
文摘The aim of this work is to establish volcanic seismic reflection configuration models in the rift basins of Northeast China from a new perspective,the volcanostratigraphic structure.Accordingly,the volcanostratigraphic structure of an outcrop near the Hailaier Rift Basin was analyzed to understand the characteristics and causal factors of physical boundaries.Further,3D seismic reflection data and analysis of deep boreholes in the Songliao Rift Basin were used to establish the relationship between volcanic seismic reflection configurations and volcanostratigraphic structures.These studies suggested that in volcanic successions,physical boundaries coincide with volcanic boundaries,and their distributions are controlled by the stacking patterns of volcanic units.Therefore,volcanic seismic reflection configurations can be interpreted in terms of the stacking patterns of volcanic units.These are also referred to as general bedding patterns in volcanostratigraphy.Furthermore,four typical seismic reflection configurations were identified,namely,the chaotic,the parallel continuous,the hummocky,the multi-mound superimposed and the composite.The corresponding interpretation models comprised single massive unit,vertical,intersectional,lateral multi-mound,and composite stacking patterns.The hummocky and composite reflection configurations with intersectional and composite stacking patterns are the most favorable for the exploration of volcanic reservoirs in rift basins.
文摘采用钌钛网(Ti/Ru O2)为阳极、钛网(Ti)为阴极、活性炭颗粒为三维粒子电极的电催化氧化装置深度处理焦化废水,通过分析处理效果和能耗研究了三维粒子电极填充方式的影响。结果显示三维悬挂电极填充方式的处理效果和能耗与传统三维电极填充方式相近,但所需材料质量及反应器容积分别为后者的34%与67%。新的填充方式在电流密度2.5 m A/cm2、悬挂电极总质量49.4g、流速100 m L/min的条件下处理120 min后,焦化废水ρ(COD)由99 mg/L降至53 mg/L,COD去除率为46.5%,单位COD处理能耗为68.5 k W·h/kg,吨水能耗为3.15 k W·h/t。
