Artificial neural network-based prediction model of residual stress and hardness of nickel-based alloys for UNSM parameters optimization

Sembiring, Jan; Amanov, Auezhan; Pyun, Young Sik

doi:10.1016/j.mtcomm.2020.101391

Cited by 17 publications

(8 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A certain depth of near-surface severe plastic deformation (SPD) layer is observed after the treatment of ultrasonic impact, normally. By means of TEM detection, it has been verified that nanocrystals can be obtained in this SPD layer [ 13 , 14 , 15 ]. The optical micrograph results of the microstructures are shown in Figure 2 .…”

Section: Resultsmentioning

confidence: 99%

“…By means of mechanical methods, some of the SSN techniques have been hotly researched, such as surface mechanical attrition treatment [ 9 ], ultrasonic surface rolling processing [ 10 ], ultrasonic shot peening [ 11 ], laser shock peening [ 12 ], ultrasonic nanocrystalline surface modification [ 13 ], etc. The mechanical properties are generally improved by these treatments, including the hardness, tensile strength, residual stress, and so on [ 9 , 10 , 11 , 12 , 13 ]. The mechanism of grain refinement involves dislocation, twinning, and the new grain boundaries under high angle misorientation.…”

Section: Introductionmentioning

confidence: 99%

“…The grain boundary serves as the importance of the plastic deformation of polycrystalline materials, especially in the fine grains with a size of micro- or nanometers [ 16 ]. It is recognized that the fatigue strength can be enhanced when the materials are subjected to these surface treatments [ 13 , 17 ]. The effects of stress ratio on the fatigue behavior of TC4 shows that the S–N curve presents a fatigue limit at the stress ratio of −1 and −0.5 [ 18 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Influence of Fine Grains on the Bending Fatigue Behavior of Two Implant Titanium Alloys

Cao

Zhu

Gao³

et al. 2020

Materials

View full text Add to dashboard Cite

By means of the ultrasonic surface impact (amplitude of 30 μm, strike number of 48,000 times/mm2), nanograins have been achieved in the surfaces of both Ti6Al4V(TC4) and Ti3Zr2Sn3Mo25Nb(TLM) titanium alloys, mainly because of the dislocation motion. Many mechanical properties are improved, such as hardness, residual stress, and roughness. The rotating–bending fatigue limits of TC4 and TLM subjected to ultrasonic impact are improved by 13.1% and 23.7%, separately. Because of the bending fatigue behavior, which is sensitive to the surface condition, cracks usually initiate from the surface defects under high stress amplitude. By means of an ultrasonic impact tip with the size of 8 mm, most of the inner cracks present at the zone with a depth range of 100~250 μm in the high life region. The inner crack core to TC4 usually appears as a deformed long and narrow α-phase, while the cracks in TLM specimens prefer to initiate at the triple grain boundary junctions. This zone crosses the grain refined layer and the deformed coarse grain layer. With the gradient change of elastic parameters, the model shows an increase of normal stress at this zone. Combined with the loss of plasticity and toughness, it is easy to understand these fatigue behaviors.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Influence of Fine Grains on the Bending Fatigue Behavior of Two Implant Titanium Alloys

Cao

Zhu

Gao³

et al. 2020

Materials

View full text Add to dashboard Cite

show abstract

“…Other researchers used the ANN to predict the mechanical and metallurgical properties such as surface roughness, hardness, and residual stress of steel 316L [20]. In [21], the authors used an ANN prediction model of residual stress and hardness for ultrasonic nanocrystal surface modification (UNSM) parameter optimization on nickel alloys. The surface hardness parameters of Shot Peening on AISI 1017, 1045, 1050, 1060, and 1070 were studied experimentally.…”

Section: Introductionmentioning

confidence: 99%

Prediction of micro-hardness in thread rolling of St37 by convolutional neural networks and transfer learning

Soleymani

Khoshnevisan

Davoodi

2022

Int J Adv Manuf Technol

View full text Add to dashboard Cite

This study introduces a non-destructive method by applying convolutional neural networks (CNN) to predict the microhardness of the thread-rolled steel. Material microstructure images were collected for our research, and micro-hardness tests were conducted to label the extracted microstructure images. In recent years, researchers have used machine learning (ML) and deep learning (DL) models to predict material properties for forming, machining, additive manufacturing, and other processes. However, they encountered industrial limitations primarily because of the absence of historical information on new and unknown materials, which are necessary to predict material properties by DL models. These problems can be solved by employing CNN models. In our work, we used a CNN model with two convolutional layers and visual geometry group (VGG19) as transfer learning (TL). We predicted four classes of micro-hardness of the St37 rolled threads. The prediction results of the micro-hardness test images by our proposed CNN model and pre-trained VGG19 model are comparable. Our proposed model has produced the same precision and recall scores as VGG19 for class B and class C hardness. VGG19 performed slightly better than our model for precision in class A and recall in class D. We observed that the training time of our proposed model using the CPU (central processing unit) was approximately nine times faster than the VGG19 model. Our proposed CNN and VGG19 have direct applications in advanced manufacturing (AM). They can automatically predict the micro-hardness in the thread rolling of St37. Our proposed model requires less memory and computational power and can be deployed more efficiently than the VGG19 model.

show abstract

“…Xie et al [26] developed a finite-element model to predict residual-stress relaxation behavior. Sembiring et al [27] provided intelligent models for describing the residual-stress relaxation behavior of superalloys. Jagtap and Chason [28] developed a stress relaxation kinetic model to depict the stress recovery and relaxation behaviors in polycrystalline thin films.…”

Section: Introductionmentioning

confidence: 99%

Residual-stress relaxation mechanism and model description of 5052H32 Al alloy spun ellipsoidal heads during annealing treatment

et al. 2021

View full text Add to dashboard Cite

Marginal-restraint mandrel-free spinning is an advanced technology for manufacturing ellipsoidal heads with large diameter-thickness ratios. Nevertheless, the spinning-induced residual stress, which greatly influences the in-service performance of spun heads, should be removed. In this study, the effects of annealing on the residual-stress relaxation behavior of 5052H32 aluminum alloy spun heads were investigated. It is found that the residual stress first rapidly decreases and then remains steady with the increase in annealing time at the tested annealing temperatures. The relaxation of the residual stress becomes increasingly obvious with the increase in annealing temperature. When the annealing temperature is less than 220 °C, there are no obvious changes in grain size. Moreover, the spinning-induced dislocations are consumed by the static recovery behavior, which decreases the residual stress during annealing. When the annealing temperature is approximately 300 °C, the broken grains transform into equiaxed grains. In addition, static recrystallization and recovery behaviors occur simultaneously to promote the relaxation of the residual stress. Considering the different stress relaxation mechanisms, a model based on the Zener-Wert-Avrami equation was established to predict the residual-stress relaxation behavior. Finally, the optimized annealing temperature and time were approximately 300 °C and 30 min, respectively.

show abstract

Artificial neural network-based prediction model of residual stress and hardness of nickel-based alloys for UNSM parameters optimization

Cited by 17 publications

References 45 publications

Influence of Fine Grains on the Bending Fatigue Behavior of Two Implant Titanium Alloys

Influence of Fine Grains on the Bending Fatigue Behavior of Two Implant Titanium Alloys

Prediction of micro-hardness in thread rolling of St37 by convolutional neural networks and transfer learning

Residual-stress relaxation mechanism and model description of 5052H32 Al alloy spun ellipsoidal heads during annealing treatment

Contact Info

Product

Resources

About