Digital image correlation study on tensile properties of high strength quenched and tempered steel weld joints prepared by K-TIG and GMAW

Su, Lihong; Fei, Zhenyu; Davis, Bradley; Li, Huijun; Bornstein, Huon

doi:10.1016/j.msea.2021.142033

Cited by 15 publications

(5 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A CNN model consisting of three convolutional layers and two pooling layers was adopted, and classification training was performed on the input variables. (5) The CNN model achieved a prediction accuracy of 97.7% in predicting the occurrence of penetration conditions in weld joints. For precision, it was 100% for class 0 and class 2, and 96.2% for class 1.…”

Section: Discussionmentioning

confidence: 95%

“…The weld quality directly impacts the integrity, durability, and safety of the fabricated components. Traditional methods to assess the quality of weld joints involve destructive testing, such as confirming weld shape [1][2][3][4] and evaluating mechanical properties through tensile testing [4][5][6] and fatigue testing [7][8][9][10]. However, these methods only facilitate a partial inspection of the weld joints and indirectly represent the welding quality of the overall structure [11,12].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of Convolutional Neural Networks for Classifying Penetration Conditions in GMAW Processes Using STFT of Welding Data

Kim,

Lee,

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

For manufacturing components with thick plates, such as in the heavy equipment and shipbuilding industries, the gas metal arc welding (GMAW) process is applied. Among the components that apply the thick plate GMAW process, there are groove butt joints, which are fabricated through multi-pass welding. Various welding qualities are managed in multi-pass welding, and the root-pass weld is controlled to ensure complete joint penetration (CJP). Currently, the state of complete joint penetration during root-pass welding is managed visually, making it difficult to confirm the penetration condition in real time. Therefore, there is a need to predict the penetration condition in real time. In this study, we propose a convolutional neural network (CNN)-based prediction model that can classify penetration conditions using welding current and voltage data from the root pass of V-groove butt joints. The root gap of the joints was varied between 1.0 and 2.0 mm, and the wire feed rate was adjusted. During welding, the current and voltage were measured. The welding current and voltage are transformed into a short-time Fourier transform (STFT) representation depicting the arc and wire extension lengths. The transformed dynamic resistance STFT information serves as the input variable for the CNN model. Preprocessing steps, including thresholding, are applied to optimize the input variables. The CNN architecture comprises three convolutional layers and two pooling layers. The model classifies penetration conditions as partial joint penetration (PJP), CJP, and burn-through, achieving a high accuracy of 97.8%. The proposed method facilitates the non-destructive evaluation of the root-pass welding quality without expensive monitoring equipment, such as vision cameras. It is expected to be immediately applied to the thick plate welding process using readily available welding data.

show abstract

Section: Discussionmentioning

confidence: 95%

Section: Introductionmentioning

confidence: 99%

Application of Convolutional Neural Networks for Classifying Penetration Conditions in GMAW Processes Using STFT of Welding Data

Kim,

Lee,

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Te idea of using a fller metal in keyhole-TIG has overcome the problem of poor properties. As suggested by Fei et al [25] and Su et al [26], the use of the fller material has remarkably enhanced the capability of the keyhole-TIG process.…”

Section: Discussionmentioning

confidence: 97%

A Comparative Analysis among Quenched, Tempered, and Stepped Cooled TIG Welded SS-304 Plates Based on Tensile Strength, Hardness, and Microstructural Appearance

Dewangan

Saksham

Paul

et al. 2023

Advances in Materials Science and Engineering

View full text Add to dashboard Cite

The present experimental work critically analyses the changes in microstructural orientation and mechanical properties of TIG (tungsten inert gas) welded AISI-304 (SS) plates which have undergone through various heat treatments. The characteristics of heat-treated samples have been compared with those of untreated samples which is denoted by the original sample in this study. Five SS-304 plates were welded by the TIG method. Out of five, four plates were heat treated and one plate was put in the original condition. Four heat treatment includes quenching, stepped heat treating (sand + water), tempering-1 (quick quench then sand cooling), and tempering-2 (quick quench then air cooling). In all the five plates, the tensile test and microhardness test have been performed. In addition, microscopic observation of cross-sectional surfaces has also been carried out. The base metal (BM) zone of all five plates mainly consists of equiaxed γ-grains, although twin can be observed only in the original sample. The heat-affected zone (HAZ) imparts both lathy and dendritic type δ-ferrite at the transition of the BM and welded zone (WZ). At the welded zone, the γ-matrix has become coarse with numerous spots and dendrites of δ-ferrite could be seen. Sample 3, tempered by means by water sprinkling for a very short time and then cooling in sand, has shown satisfactory results among all. The sample has achieved the 23% higher extension value and 10% higher hardness at WZ than these of the original sample, although a negligible loss (0.2%) of ultimate tensile strength (UTS) is also reported in sample 3.

show abstract

“…Keyhole TIG (K-TIG) welding increases the carrying current and reduces the area of the arc cathode area by adding a water cooling system to the tungsten electrode torch, so as to improve the arc energy density and arc pressure [20][21][22][23]. When the welding current is large enough, the arc pressure is greater than the surface tension of the liquid molten pool, and small holes are formed inside the molten pool [24][25][26][27].…”

Section: Introductionmentioning

confidence: 99%

Arc Characteristics and Welding Process of Laser K-TIG Hybrid Welding

Zhang

et al. 2022

Metals

View full text Add to dashboard Cite

The Q235 steel plate butt joint was successfully welded by the laser K-TIG hybrid welding method. The effects of hybrid welding process parameters such as welding current, the distance between heat sources, laser power, laser defocusing amount, and welding speed on the coupled arc profile and welding process stability were studied. The results indicated that the laser deflects the K-TIG arc, and the deflection angle becomes smaller as the arc current increases. After K-TIG generates small holes, if the laser beam acts on the bottom of the keyhole, the welded depth can be further increased; however, the laser power has little effect on the welded depth. The distance between heat sources is the main factor affecting the state of laser-arc coupling. Optical microstructures of welded joints showed that the grains in the arc zone were coarser than those in the laser zone, and there are more columnar crystals in the fusion zone. The microhardness of the weld center is significantly higher than that of the base metal, up to 220 HV. At the same time, the change of tensile strength of the weld under the influence of a single parameter was analyzed, and it was found that tensile properties of the weld first increased and then decreased with the increase of K-TIG arc current I, heat source distance D, and welding speed V, respectively. With the increase of laser power P, it first decreased and then increased, and with the increase of laser defocusing amount δf, it showed a downward trend.

show abstract

Digital image correlation study on tensile properties of high strength quenched and tempered steel weld joints prepared by K-TIG and GMAW

Cited by 15 publications

References 48 publications

Application of Convolutional Neural Networks for Classifying Penetration Conditions in GMAW Processes Using STFT of Welding Data

Application of Convolutional Neural Networks for Classifying Penetration Conditions in GMAW Processes Using STFT of Welding Data

A Comparative Analysis among Quenched, Tempered, and Stepped Cooled TIG Welded SS-304 Plates Based on Tensile Strength, Hardness, and Microstructural Appearance

Arc Characteristics and Welding Process of Laser K-TIG Hybrid Welding

Contact Info

Product

Resources

About