Expulsion is an undesired event during resistance spot welding because the weld quality deteriorates. It is the ejection of molten metal from the weld nugget which usually occurs due to applying a high current for a s...Expulsion is an undesired event during resistance spot welding because the weld quality deteriorates. It is the ejection of molten metal from the weld nugget which usually occurs due to applying a high current for a short welding time. Expulsion has a significant impact on the final yield strength of the weld, thus the detection and characterization of expulsion events is significant for the quality assurance of resistance spot welds. In this study, hardness mapping, using a scanning hardness machine, was used as a quality assurance technique for re- sistance spot welding. Hardness tests were conducted on a resistance spot welded sample to prepare a hardness map. The test results showed good correlation between the hardness map and metallographic cross sections. The technique also provided further fundamental understand- ing of the resistance spot welding process, especially regarding the occurrence of expulsion in the nugget.展开更多
This paper presents an experimental study on physical and mechanical properties of high strength steel plates（AISI 4130） joined by resistance spot welding by means of hardness mapping technique. Welding current and ...This paper presents an experimental study on physical and mechanical properties of high strength steel plates（AISI 4130） joined by resistance spot welding by means of hardness mapping technique. Welding current and electrode force were selected as experimental parameters. The welded joints were exposed to tensile-shearing tests in order to determine the strength of the welded zones. Hardness and microstructural examinations were carried out in order to examine the influence of welding parameters on the welded joints. Hardness mapping test was conducted on the large area of weld zone, including the heat afected zone and base plate. Hardness map was used to investigate the efects of current on hardness and microstructure in diferent regions of weld. Low electrode force and high welding current, used during the welding, increased the expulsion. An optimum weld quality was obtained by using 6.5 kA weld current. It was found that mechanical performance of resistance spot welded samples is controlled by nugget diameter and expulsion. Results revealed that hardness mapping technique provides one of the best methods for the physical and mechanical understanding of heterogeneous microstructures using hardness criterion.展开更多
Due to intensive genetic selection for rapid growth rates and high broiler yields in recent years,the global poultry industry has faced a challenging problem in the form of woody breast(WB)conditions.This condition ha...Due to intensive genetic selection for rapid growth rates and high broiler yields in recent years,the global poultry industry has faced a challenging problem in the form of woody breast(WB)conditions.This condition has caused significant economic losses as high as s200 million annually,and the root cause of WB has yet to be identified.Human palpation is the most common method of distinguishing a WB from others.However,this method is time-consuming and subjective.Hyperspectral imaging(HSI)combined with machine learning algorithms can evaluate the WB conditions of fllets in a non-invasive,objective,and high-throughput manner.In this study,250 raw chicken breast fllet samples(normal,mild,severe)were taken,and spatially heterogeneous hardness distribution was first considered when designing HSI processing models.The study not only classified the WB levels from HSI but also built a regression model to correlate the spectral information with sample hardness data.To achieve a satisfactory classification and regression model,a neural network architecture search(NAS)enabled a wide-deep neural network model named NAS-WD,which was developed.In NAS-WD,NAS was first used to automatically optimize the network architecture and hyperparameters.The classification results show that NAS-WD can classify the three WB levels with an overall accuracy of 95%,outperforming the traditional machine learning model,and the regression correlation between the spectral data and hardness was 0.75,which performs significantly better than traditional regression models.展开更多
文摘Expulsion is an undesired event during resistance spot welding because the weld quality deteriorates. It is the ejection of molten metal from the weld nugget which usually occurs due to applying a high current for a short welding time. Expulsion has a significant impact on the final yield strength of the weld, thus the detection and characterization of expulsion events is significant for the quality assurance of resistance spot welds. In this study, hardness mapping, using a scanning hardness machine, was used as a quality assurance technique for re- sistance spot welding. Hardness tests were conducted on a resistance spot welded sample to prepare a hardness map. The test results showed good correlation between the hardness map and metallographic cross sections. The technique also provided further fundamental understand- ing of the resistance spot welding process, especially regarding the occurrence of expulsion in the nugget.
文摘This paper presents an experimental study on physical and mechanical properties of high strength steel plates（AISI 4130） joined by resistance spot welding by means of hardness mapping technique. Welding current and electrode force were selected as experimental parameters. The welded joints were exposed to tensile-shearing tests in order to determine the strength of the welded zones. Hardness and microstructural examinations were carried out in order to examine the influence of welding parameters on the welded joints. Hardness mapping test was conducted on the large area of weld zone, including the heat afected zone and base plate. Hardness map was used to investigate the efects of current on hardness and microstructure in diferent regions of weld. Low electrode force and high welding current, used during the welding, increased the expulsion. An optimum weld quality was obtained by using 6.5 kA weld current. It was found that mechanical performance of resistance spot welded samples is controlled by nugget diameter and expulsion. Results revealed that hardness mapping technique provides one of the best methods for the physical and mechanical understanding of heterogeneous microstructures using hardness criterion.
基金support by the University of Arkansas Experimental Station and the University of Arkansas College of Engineering,USDA National Institute of Food and Agriculture (No:2023-70442-39232,2024-67022-42882).
文摘Due to intensive genetic selection for rapid growth rates and high broiler yields in recent years,the global poultry industry has faced a challenging problem in the form of woody breast(WB)conditions.This condition has caused significant economic losses as high as s200 million annually,and the root cause of WB has yet to be identified.Human palpation is the most common method of distinguishing a WB from others.However,this method is time-consuming and subjective.Hyperspectral imaging(HSI)combined with machine learning algorithms can evaluate the WB conditions of fllets in a non-invasive,objective,and high-throughput manner.In this study,250 raw chicken breast fllet samples(normal,mild,severe)were taken,and spatially heterogeneous hardness distribution was first considered when designing HSI processing models.The study not only classified the WB levels from HSI but also built a regression model to correlate the spectral information with sample hardness data.To achieve a satisfactory classification and regression model,a neural network architecture search(NAS)enabled a wide-deep neural network model named NAS-WD,which was developed.In NAS-WD,NAS was first used to automatically optimize the network architecture and hyperparameters.The classification results show that NAS-WD can classify the three WB levels with an overall accuracy of 95%,outperforming the traditional machine learning model,and the regression correlation between the spectral data and hardness was 0.75,which performs significantly better than traditional regression models.
