Ballistic impact response of resistance-spot-welded(RSW)double-layered(2×1.6 mm)plates(190 mm×150 mm)for Q&P980 steel impacted by a round-nosed steel bullet(12 mm diameter and 30 mm length)was investigat...Ballistic impact response of resistance-spot-welded(RSW)double-layered(2×1.6 mm)plates(190 mm×150 mm)for Q&P980 steel impacted by a round-nosed steel bullet(12 mm diameter and 30 mm length)was investigated by using gas gun and high-speed camera system.The RSW specimens were spot welded using a 6 mm diameter electrode face producing a 7.2 mm diameter fusion zone of the spot weld.The ballistic curve and energy balance for the tests of the spot weld of the RSW specimens at different velocity were analyzed to characterize the ballistic behavior of the RSW specimens under bullet impact.The fracture mechanisms of the RSW specimens under bullet impact were presented.For the tests below the ballistic limit,the cracks initiated from the notch-tip and propagated along the faying surface or obliquely through the thickness depending on the impact velocity.For the tests above the ballistic limit,the plug fracture in the front plate of the RSW specimen could be caused by the thinning-induced necking in the BM near the HAZ,while the plug fracture in the rear plate of the RSW specimens may be consist of the circumferential cracking from the rear surface and the bending fracture of the hinged part of material.The effects of the electrode indentation and the weld interfaces on deformation and fracture of the RSW specimens under bullet impact were revealed.For the tests above the ballistic limit,the circumferential fracture from the rear surface of the RSW specimens was always initiated along the interior periphery of the electrode indentation and the crack paths were along the FZ/CGHAZ or CGHAZ/FGHAZ interface.When the circumferential crack also formed outside the electrode indentation,the fracture on the BM/HAZ interface could be found.On the front plate of the RSW specimens,the shear/bending induced cracking from the notch-tip were observed and the crack paths were along the FZ/CGHAZ or CGHAZ/FGHAZ interface.展开更多
This research presents an innovative approach to accurately predict the nugget diameter in resistance spot welding(RSW)by leveraging machine learning and transfer learning methods.Initially,low-fidelity(LF)data were o...This research presents an innovative approach to accurately predict the nugget diameter in resistance spot welding(RSW)by leveraging machine learning and transfer learning methods.Initially,low-fidelity(LF)data were obtained through finite element numerical simulation and design of experiments(DOEs)to train the LF machine learning model.Subsequently,high-fidelity(HF)data were collected from RSW process experiments and used to fine-tune the LF model by transfer learning techniques.The accuracy and generalization performance of the models were thoroughly validated.The results demonstrated that combining different fidelity datasets and employing transfer learning could significantly improve the prediction accuracy while minimize the costs associated with experimental trials,and provide an effective and valuable method for predicting critical process parameters in RSW.展开更多
基金supported by the National Natural Science Foundation of China,China under the grant No.11372149K.C.Wong Magna Fund in Ningbo University。
文摘Ballistic impact response of resistance-spot-welded(RSW)double-layered(2×1.6 mm)plates(190 mm×150 mm)for Q&P980 steel impacted by a round-nosed steel bullet(12 mm diameter and 30 mm length)was investigated by using gas gun and high-speed camera system.The RSW specimens were spot welded using a 6 mm diameter electrode face producing a 7.2 mm diameter fusion zone of the spot weld.The ballistic curve and energy balance for the tests of the spot weld of the RSW specimens at different velocity were analyzed to characterize the ballistic behavior of the RSW specimens under bullet impact.The fracture mechanisms of the RSW specimens under bullet impact were presented.For the tests below the ballistic limit,the cracks initiated from the notch-tip and propagated along the faying surface or obliquely through the thickness depending on the impact velocity.For the tests above the ballistic limit,the plug fracture in the front plate of the RSW specimen could be caused by the thinning-induced necking in the BM near the HAZ,while the plug fracture in the rear plate of the RSW specimens may be consist of the circumferential cracking from the rear surface and the bending fracture of the hinged part of material.The effects of the electrode indentation and the weld interfaces on deformation and fracture of the RSW specimens under bullet impact were revealed.For the tests above the ballistic limit,the circumferential fracture from the rear surface of the RSW specimens was always initiated along the interior periphery of the electrode indentation and the crack paths were along the FZ/CGHAZ or CGHAZ/FGHAZ interface.When the circumferential crack also formed outside the electrode indentation,the fracture on the BM/HAZ interface could be found.On the front plate of the RSW specimens,the shear/bending induced cracking from the notch-tip were observed and the crack paths were along the FZ/CGHAZ or CGHAZ/FGHAZ interface.
基金founded by the Construction Project of the National Natural Science Foundation(Grant No.52205377)the National Key Research and Development Program(Grant No.2022YFB4601804)the Key Basic Research Project of Suzhou(Grant Nos.SJC2022029,SJC2022031).
文摘This research presents an innovative approach to accurately predict the nugget diameter in resistance spot welding(RSW)by leveraging machine learning and transfer learning methods.Initially,low-fidelity(LF)data were obtained through finite element numerical simulation and design of experiments(DOEs)to train the LF machine learning model.Subsequently,high-fidelity(HF)data were collected from RSW process experiments and used to fine-tune the LF model by transfer learning techniques.The accuracy and generalization performance of the models were thoroughly validated.The results demonstrated that combining different fidelity datasets and employing transfer learning could significantly improve the prediction accuracy while minimize the costs associated with experimental trials,and provide an effective and valuable method for predicting critical process parameters in RSW.
