A Comparison Study of Constitutive Equation, Neural Networks, and Support Vector Regression for Modeling Hot Deformation of 316L Stainless Steel

Song, Shin-Hyung

doi:10.3390/ma13173766

Cited by 15 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning involves the use of AI theory combined with big data to guide computers for training and learning; eventually, a simple AI model with input and output relationships will be developed to help researchers make design decisions [ 21 , 22 , 23 , 24 ]. Machine learning [ 25 , 26 , 27 , 28 ] can be applied for regression or classification models using either supervised or unsupervised learning. In this review, because the input datasets are labeled, the learning algorithm for predicting the reliability life is considered supervised.…”

Section: Introductionmentioning

confidence: 99%

An Overview of AI-Assisted Design-on-Simulation Technology for Reliability Life Prediction of Advanced Packaging

et al. 2021

View full text Add to dashboard Cite

Several design parameters affect the reliability of wafer-level type advanced packaging, such as upper and lower pad sizes, solder volume, buffer layer thickness, and chip thickness, etc. Conventionally, the accelerated thermal cycling test (ATCT) is used to evaluate the reliability life of electronic packaging; however, optimizing the design parameters through ATCT is time-consuming and expensive, reducing the number of experiments becomes a critical issue. In recent years, many researchers have adopted the finite-element-based design-on-simulation (DoS) technology for the reliability assessment of electronic packaging. DoS technology can effectively shorten the design cycle, reduce costs, and effectively optimize the packaging structure. However, the simulation analysis results are highly dependent on the individual researcher and are usually inconsistent between them. Artificial intelligence (AI) can help researchers avoid the shortcomings of the human factor. This study demonstrates AI-assisted DoS technology by combining artificial intelligence and simulation technologies to predict wafer level package (WLP) reliability. In order to ensure reliability prediction accuracy, the simulation procedure was validated by several experiments prior to creating a large AI training database. This research studies several machine learning models, including artificial neural network (ANN), recurrent neural network (RNN), support vector regression (SVR), kernel ridge regression (KRR), K-nearest neighbor (KNN), and random forest (RF). These models are evaluated in this study based on prediction accuracy and CPU time consumption.

show abstract

Section: Introductionmentioning

confidence: 99%

An Overview of AI-Assisted Design-on-Simulation Technology for Reliability Life Prediction of Advanced Packaging

et al. 2021

View full text Add to dashboard Cite

show abstract

“…According to the previous research from Sellars and McTegart [17,18], the Arrhenius flow stress constitutive equation, which can unambiguously and effectively reveal the thermal deformation phenomenon, is formulated and analyzed. The flow stress, temperature, and strain rate can be characterized by Eq.…”

Section: Establishment and Verification Of Constitutive Equationmentioning

confidence: 99%

“…The contour line describes the power dissipation rate and divides the plastic instability region. The thermal process maps theory originates from the dynamic material model (DMM) proposed by Prasad et al [16][17][18][19]. The power dissipation maps describe the power dissipation under a certain strain.…”

Section: Processing Mapsmentioning

confidence: 99%

Analysis of thermal deformation behavior and workability of 37CrS4 special steel

Yang¹,

Wang²,

Xue³

2023

View full text Add to dashboard Cite

In order to optimize the thermal forging process of 37CrS4 special steel, single-pass thermal pressing tests are conducted, and a strain compensation Arrhenius constitutive equation is proposed based on the stress-strain curves of 37CrS4 at the temperature of 900-1100 • C and the strain rate of 0.1-10 s −1 . The stress values calculated from the equation are in good agreement with the counterparts in the thermal simulation compression test. The high correlation between the calculated and experimental data verifies the correctness of the strain compensation based on Arrhenius constitutive equation. According to the dynamic material model and instability criterion, the processing maps of 37CrS4 are established. It is concluded that 37CrS4 is more suitable for thermal working at a strain rate of 0.1-0.37 s −1 and temperature of 1000-1100 • C.

show abstract

“…For the purposes of comparison of the acquired data with another steel commonly applied in the nuclear power industry, 08Ch18N10T (AISI 321) steel was tested, too. However, since the behavior of 08Ch18N10T steel has already been well-researched (e.g., [60][61][62][63]), the testing was performed only under selected conditions-see Table 3. The hot compression tests were performed using the above described machined cylindrical samples.…”

Section: Hot Compression Testingmentioning

confidence: 99%

Determining Hot Deformation Behavior and Rheology Laws of Selected Austenitic Stainless Steels

Němec,

Kunčická,

Opěla

et al. 2023

Metals

View full text Add to dashboard Cite

Due to their versatile properties, austenitic stainless steels have a wide application potential, including in specific fields, such as the nuclear power industry. ChN35VT steel is a chromium–nickel–tungsten type of steel stabilized by titanium, and it is suitable for parts subjected to considerable mechanical stress at elevated temperatures. However, the available data on its deformation behavior at elevated/high temperatures is scarce. The core of the presented research was thus the experimental characterization of the deformation behavior of the ChN35VT steel under hot conditions via the determination of flow stress curves, and their correlation with microstructure development. The obtained data was further compared with data acquired for 08Ch18N10T steel, which is also known for its applicability in the nuclear power industry. The experimental results were subsequently used to determine the Hensel-Spittel rheology laws for both the steels. The ChN35VT steel exhibited notably higher flow stress values in comparison with the 08Ch18N10T steel. This difference was more significant the lower the temperature and the higher the strain rate. Considering the peak stress values, the lowest difference was ~8 MPa (1250 °C and 0.01 s−1), and the highest was ~150 MPa (850 °C and 10 s−1). These findings also corresponded to the microstructure developments—the higher the deformation temperature, the more negligible the observed differences as regards the grain size and morphology.

show abstract

A Comparison Study of Constitutive Equation, Neural Networks, and Support Vector Regression for Modeling Hot Deformation of 316L Stainless Steel

Cited by 15 publications

References 13 publications

An Overview of AI-Assisted Design-on-Simulation Technology for Reliability Life Prediction of Advanced Packaging

An Overview of AI-Assisted Design-on-Simulation Technology for Reliability Life Prediction of Advanced Packaging

Analysis of thermal deformation behavior and workability of 37CrS4 special steel

Determining Hot Deformation Behavior and Rheology Laws of Selected Austenitic Stainless Steels

Contact Info

Product

Resources

About