Defect detection is vital in the nonwoven material industry,ensuring surface quality before producing finished products.Recently,deep learning and computer vision advancements have revolutionized defect detection,maki...Defect detection is vital in the nonwoven material industry,ensuring surface quality before producing finished products.Recently,deep learning and computer vision advancements have revolutionized defect detection,making it a widely adopted approach in various industrial fields.This paper mainly studied the defect detection method for nonwoven materials based on the improved Nano Det-Plus model.Using the constructed samples of defects in nonwoven materials as the research objects,transfer learning experiments were conducted based on the Nano DetPlus object detection framework.Within this framework,the Backbone,path aggregation feature pyramid network(PAFPN)and Head network models were compared and trained through a process of freezing,with the ultimate aim of bolstering the model's feature extraction abilities and elevating detection accuracy.The half-precision quantization method was used to optimize the model after transfer learning experiments,reducing model weights and computational complexity to improve the detection speed.Performance comparisons were conducted between the improved model and the original Nano Det-Plus model,YOLO,SSD and other common industrial defect detection algorithms,validating that the improved methods based on transfer learning and semi-precision quantization enabled the model to meet the practical requirements of industrial production.展开更多
Accurate displacement prediction is critical for the early warning of landslides.The complexity of the coupling relationship between multiple influencing factors and displacement makes the accurate prediction of displ...Accurate displacement prediction is critical for the early warning of landslides.The complexity of the coupling relationship between multiple influencing factors and displacement makes the accurate prediction of displacement difficult.Moreover,in engineering practice,insufficient monitoring data limit the performance of prediction models.To alleviate this problem,a displacement prediction method based on multisource domain transfer learning,which helps accurately predict data in the target domain through the knowledge of one or more source domains,is proposed.First,an optimized variational mode decomposition model based on the minimum sample entropy is used to decompose the cumulative displacement into the trend,periodic,and stochastic components.The trend component is predicted by an autoregressive model,and the periodic component is predicted by the long short-term memory.For the stochastic component,because it is affected by uncertainties,it is predicted by a combination of a Wasserstein generative adversarial network and multisource domain transfer learning for improved prediction accuracy.Considering a real mine slope as a case study,the proposed prediction method was validated.Therefore,this study provides new insights that can be applied to scenarios lacking sample data.展开更多
By using field trials, the migration and transformation of coated controlled release nitrogen （YZS80） in soil under the co-situs application mode were studied. The results indicated that YZS80 nitrogen dissolved out...By using field trials, the migration and transformation of coated controlled release nitrogen （YZS80） in soil under the co-situs application mode were studied. The results indicated that YZS80 nitrogen dissolved out in average speed of about 0.4%/d and 32% totally in 80 d compared with common compound fertUizer. For YZS80, in the vertical downward direction of application points, urea nitrogen content increased significantly （P 〈0.05） in the 45 -80 d and the 30 -60 cm soil layers; nitrate nitrogen content was little change range and in moderate （10 -100 mg/kg） in 0 -80 d and 10 -60 cm soil layers, but increased significantly （ P 〈0.05） 45 -80 d compared to 0 -45 d; ammonium nitrogen content was significant lower （P〈0.05） before 45 d in 10 -30 cm soil layers, but significant higher（P〈0.05） after 45 d in 10 -60 cm soil layers; NO3^- -N/NH4^＋ -N meets gradually the needs of the crop with the extension of time. Under the co-situs application mode, the possibility of burning root and salt injury and loss dsk of nitrate leaching is a significant reduction.展开更多
Effect of direct current electric field （DCEF） on corrosion behaviour of copper printed circuit board （PCB-Cu）, Cl-ion migration behaviour, dendrites growth under thin electrolyte layer was investigated using pote...Effect of direct current electric field （DCEF） on corrosion behaviour of copper printed circuit board （PCB-Cu）, Cl-ion migration behaviour, dendrites growth under thin electrolyte layer was investigated using potentiodynamic polarization and scanning electron microscopy （SEM） with energy dispersive spectrometer （EDS）. Results indicate that DCEF decreases the corrosion of PCB-Cu;Cl-ions directionally migrate from the negative pole to the positive pole, and enrich on the surface of the positive pole, which causes serious localized corrosion; dendrites grow on the surface of the negative pole, and the rate and scale of dendrite growth become faster and greater with the increase of external voltage and exposure time, respectively.展开更多
Study was carried out to analyze the distribution and migration patterns,soil-to-plant transfer and potential health risks of chromium in soil-vegetable system in areas near a ferro-alloy manufactory in Hunan province...Study was carried out to analyze the distribution and migration patterns,soil-to-plant transfer and potential health risks of chromium in soil-vegetable system in areas near a ferro-alloy manufactory in Hunan province.The results show that soils near sewer outlet,sewer channel and in control area are averaged 2 239.5,995.33 and 104.9 mg/kg,respectively.The total Cr has a relative accumulation in soil depth of 200-400 mm near the sewer outlet,mainly enriches in the surface layer（0-200 mm） near the sewer channel and decreases gradually in unpolluted soils.The differential concentration level of enrichment between layers is little.The results also indicate that the three vegetables of celery,lettuce and Chinese cabbage are able to convert the potentially toxic Cr（Ⅵ） species into the non-toxic Cr（Ⅲ） species,and the chromium contents in the edible parts of the vegetables are averaged 11.95 mg/kg.The transfer factors of the three vegetables follow the order：Chinese cabbage lettuce celery.The estimated total daily intake of chromium substantially exceeds the dietary allowable value,which may pose health risks to local population.展开更多
The development of an AIGaN/GaN HEMT power MMIC on SI-SiC designed in microstrip technology is pres- ented. A recessed-gate and a field-plate are used in the device processing to improve the performance of the AIGaN/G...The development of an AIGaN/GaN HEMT power MMIC on SI-SiC designed in microstrip technology is pres- ented. A recessed-gate and a field-plate are used in the device processing to improve the performance of the AIGaN/GaN HEMTs. S-parameter measurements show that the frequency performance of the AIGaN/GaN HEMTs depends significantly on the operating voltage. Higher operating voltage is a key to higher power gain for the AIGaN/GaN HEMTs. The developed 2-stage power MMIC delivers an output power of more than 10W with over 12dB power gain across the band of 9-11GHz at a drain bias of 30V. Peak output power inside the band reaches 14.7W with a power gain of 13.7dB and a PAE of 23%. The MMIC chip size is only 2.0mm × 1. 1mm. This work shows superiority over previously reported X-band AIGaN/GaN HEMT power MMICs in output power per millimeter gate width and output power per unit chip size.展开更多
In electrolyte melts containing K at low temperature, the penetrative and migratory path of alkali metals （K and Na） in pitch, furan, phenolic aldehyde and epoxy based TiB2-C composite cathodes during the electrolys...In electrolyte melts containing K at low temperature, the penetrative and migratory path of alkali metals （K and Na） in pitch, furan, phenolic aldehyde and epoxy based TiB2-C composite cathodes during the electrolysis process were studied by EDS and self-made modified Rapoport apparatus. The electrolysis expansion rates, the diffusion coefficients of the alkali metals and the corrosion rates of the composite cathode were also calculated and discussed. The results show that no matter what kind of binder is used, alkali metals have the same penetrative path in composite cathodes：firstly in pore, then in binder and finally in carbonaceous aggregates. K and Na penetrate into both binder and carbonaceous aggregates, which leads to the expansion of composite cathodes, and K has stronger penetration ability than Na. Electrolysis expansion rate of resin based composite cathode is smaller than that of pitch based composite cathodes, and so do the diffusion coefficient and corrosion rate. Resin based composite cathode has better resistance ability to the penetration of alkali metals than pith based composite cathode, and phenolic aldehyde based composite cathode exhibits the strongest resistance ability. The penetration rate, the diffusion coefficient of alkali metals in phenolic aldehyde based TiB2-C composite cathode and the corresponding corrosion rate are 4.72 mm/h, 2.24×10^-5 cm^2/s and 2.31 mm/a, respectively.展开更多
基金National Key Research and Development Program of China(Nos.2022YFB4700600 and 2022YFB4700605)National Natural Science Foundation of China(Nos.61771123 and 62171116)+1 种基金Fundamental Research Funds for the Central UniversitiesGraduate Student Innovation Fund of Donghua University,China(No.CUSF-DH-D-2022044)。
文摘Defect detection is vital in the nonwoven material industry,ensuring surface quality before producing finished products.Recently,deep learning and computer vision advancements have revolutionized defect detection,making it a widely adopted approach in various industrial fields.This paper mainly studied the defect detection method for nonwoven materials based on the improved Nano Det-Plus model.Using the constructed samples of defects in nonwoven materials as the research objects,transfer learning experiments were conducted based on the Nano DetPlus object detection framework.Within this framework,the Backbone,path aggregation feature pyramid network(PAFPN)and Head network models were compared and trained through a process of freezing,with the ultimate aim of bolstering the model's feature extraction abilities and elevating detection accuracy.The half-precision quantization method was used to optimize the model after transfer learning experiments,reducing model weights and computational complexity to improve the detection speed.Performance comparisons were conducted between the improved model and the original Nano Det-Plus model,YOLO,SSD and other common industrial defect detection algorithms,validating that the improved methods based on transfer learning and semi-precision quantization enabled the model to meet the practical requirements of industrial production.
基金supported by the National Natural Science Foundation of China(Grant No.51674169)Department of Education of Hebei Province of China(Grant No.ZD2019140)+1 种基金Natural Science Foundation of Hebei Province of China(Grant No.F2019210243)S&T Program of Hebei(Grant No.22375413D)School of Electrical and Electronics Engineering。
文摘Accurate displacement prediction is critical for the early warning of landslides.The complexity of the coupling relationship between multiple influencing factors and displacement makes the accurate prediction of displacement difficult.Moreover,in engineering practice,insufficient monitoring data limit the performance of prediction models.To alleviate this problem,a displacement prediction method based on multisource domain transfer learning,which helps accurately predict data in the target domain through the knowledge of one or more source domains,is proposed.First,an optimized variational mode decomposition model based on the minimum sample entropy is used to decompose the cumulative displacement into the trend,periodic,and stochastic components.The trend component is predicted by an autoregressive model,and the periodic component is predicted by the long short-term memory.For the stochastic component,because it is affected by uncertainties,it is predicted by a combination of a Wasserstein generative adversarial network and multisource domain transfer learning for improved prediction accuracy.Considering a real mine slope as a case study,the proposed prediction method was validated.Therefore,this study provides new insights that can be applied to scenarios lacking sample data.
基金Supported by Beijing Science Committee Project"Science & TechnologyNew Star"(2008B38)"The Research and Establishmentof Agrochemical Service System for New Type of Fertilizer"(d0706004040431)The Foundation for Youth Scholars of BeijingAcademy of Agriculture and Forestry Sciences"The Developmentand Evaluation of Micro Water-soluble Cementation Coated Slow-releaseFertilizers Suitable for Semiand Areas"~~
文摘By using field trials, the migration and transformation of coated controlled release nitrogen （YZS80） in soil under the co-situs application mode were studied. The results indicated that YZS80 nitrogen dissolved out in average speed of about 0.4%/d and 32% totally in 80 d compared with common compound fertUizer. For YZS80, in the vertical downward direction of application points, urea nitrogen content increased significantly （P 〈0.05） in the 45 -80 d and the 30 -60 cm soil layers; nitrate nitrogen content was little change range and in moderate （10 -100 mg/kg） in 0 -80 d and 10 -60 cm soil layers, but increased significantly （ P 〈0.05） 45 -80 d compared to 0 -45 d; ammonium nitrogen content was significant lower （P〈0.05） before 45 d in 10 -30 cm soil layers, but significant higher（P〈0.05） after 45 d in 10 -60 cm soil layers; NO3^- -N/NH4^＋ -N meets gradually the needs of the crop with the extension of time. Under the co-situs application mode, the possibility of burning root and salt injury and loss dsk of nitrate leaching is a significant reduction.
基金Project(50871044)supported by the National Natural Science Foundation of ChinaProject(2012M511207)supported by the Postdoctoral Science Foundation of ChinaProject(10122011)supported by the Science Research Foundation of Wuhan Institute Technology,China
文摘Effect of direct current electric field （DCEF） on corrosion behaviour of copper printed circuit board （PCB-Cu）, Cl-ion migration behaviour, dendrites growth under thin electrolyte layer was investigated using potentiodynamic polarization and scanning electron microscopy （SEM） with energy dispersive spectrometer （EDS）. Results indicate that DCEF decreases the corrosion of PCB-Cu;Cl-ions directionally migrate from the negative pole to the positive pole, and enrich on the surface of the positive pole, which causes serious localized corrosion; dendrites grow on the surface of the negative pole, and the rate and scale of dendrite growth become faster and greater with the increase of external voltage and exposure time, respectively.
基金Project (2009ZX07212-001-01) supported by the Key Project of National Natural Science Foundation for Water Pollution Control and RemediationProject (50925417) supported by the National Funds for Distinguished Young Scientists+1 种基金Project (50830301) supported by the National Natural Science Foundation of ChinaProject (51074191) supported by the National Natural Science Foundation of China
文摘Study was carried out to analyze the distribution and migration patterns,soil-to-plant transfer and potential health risks of chromium in soil-vegetable system in areas near a ferro-alloy manufactory in Hunan province.The results show that soils near sewer outlet,sewer channel and in control area are averaged 2 239.5,995.33 and 104.9 mg/kg,respectively.The total Cr has a relative accumulation in soil depth of 200-400 mm near the sewer outlet,mainly enriches in the surface layer（0-200 mm） near the sewer channel and decreases gradually in unpolluted soils.The differential concentration level of enrichment between layers is little.The results also indicate that the three vegetables of celery,lettuce and Chinese cabbage are able to convert the potentially toxic Cr（Ⅵ） species into the non-toxic Cr（Ⅲ） species,and the chromium contents in the edible parts of the vegetables are averaged 11.95 mg/kg.The transfer factors of the three vegetables follow the order：Chinese cabbage lettuce celery.The estimated total daily intake of chromium substantially exceeds the dietary allowable value,which may pose health risks to local population.
文摘The development of an AIGaN/GaN HEMT power MMIC on SI-SiC designed in microstrip technology is pres- ented. A recessed-gate and a field-plate are used in the device processing to improve the performance of the AIGaN/GaN HEMTs. S-parameter measurements show that the frequency performance of the AIGaN/GaN HEMTs depends significantly on the operating voltage. Higher operating voltage is a key to higher power gain for the AIGaN/GaN HEMTs. The developed 2-stage power MMIC delivers an output power of more than 10W with over 12dB power gain across the band of 9-11GHz at a drain bias of 30V. Peak output power inside the band reaches 14.7W with a power gain of 13.7dB and a PAE of 23%. The MMIC chip size is only 2.0mm × 1. 1mm. This work shows superiority over previously reported X-band AIGaN/GaN HEMT power MMICs in output power per millimeter gate width and output power per unit chip size.
基金Project (51304152) supported by the National Natural Science Foundation of ChinaProject (2013JQ7016) supported by the Natural Science Foundation of Shanxi Province,ChinaProject (2013JK0904) supported by Shanxi Provincial Education Department,China
文摘In electrolyte melts containing K at low temperature, the penetrative and migratory path of alkali metals （K and Na） in pitch, furan, phenolic aldehyde and epoxy based TiB2-C composite cathodes during the electrolysis process were studied by EDS and self-made modified Rapoport apparatus. The electrolysis expansion rates, the diffusion coefficients of the alkali metals and the corrosion rates of the composite cathode were also calculated and discussed. The results show that no matter what kind of binder is used, alkali metals have the same penetrative path in composite cathodes：firstly in pore, then in binder and finally in carbonaceous aggregates. K and Na penetrate into both binder and carbonaceous aggregates, which leads to the expansion of composite cathodes, and K has stronger penetration ability than Na. Electrolysis expansion rate of resin based composite cathode is smaller than that of pitch based composite cathodes, and so do the diffusion coefficient and corrosion rate. Resin based composite cathode has better resistance ability to the penetration of alkali metals than pith based composite cathode, and phenolic aldehyde based composite cathode exhibits the strongest resistance ability. The penetration rate, the diffusion coefficient of alkali metals in phenolic aldehyde based TiB2-C composite cathode and the corresponding corrosion rate are 4.72 mm/h, 2.24×10^-5 cm^2/s and 2.31 mm/a, respectively.
