Modeling Mechanical Properties of 25Cr-20Ni-0.4C Steels over a Wide Range of Temperatures by Neural Networks

Narayana, P.L.; Kim, Jaehwan; Maurya, A.K.; Park, Chan Hee; Hong, Jae‐Keun; Yeom, Jong‐Taek; Reddy, N.S.

doi:10.3390/met10020256

Cited by 9 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Narayana designed an artificial neural network (ANN) model to correlate the complex relations among composition, temperature, and mechanical properties of steels. The ANN predictions are more accurate with experimental results as compared with the calculated properties of the existing model [14,15]. Some studies improve the performance of feature selection by choosing effective measurement indicators [16,17].…”

Section: Introductionmentioning

confidence: 89%

Novel Prediction Model for Steel Mechanical Properties with MSVR Based on MIC and Complex Network Clustering

Yan

2021

Metals

View full text Add to dashboard Cite

Traditional mechanical properties prediction models are mostly based on experience and mechanism, which neglect the linear and nonlinear relationships between process parameters. Aiming at the high-dimensional data collected in the complex industrial process of steel production, a new prediction model is proposed. The multidimensional support vector regression (MSVR)-based model is combined with the feature selection method, which involves maximum information coefficient (MIC) correlation characterization and complex network clustering. Firstly, MIC is used to measure the correlation between process parameters and mechanical properties, based on which a complex network is constructed and hierarchical clustering is performed. Secondly, we evaluate all parameters and select a representative one for each partition as the input of the subsequent model based on the centrality and influence indicators. Finally, an actual steel production case is used to train the MSVR prediction model. The prediction results show that our proposed framework can capture effective features from the full parameters in terms of higher prediction accuracy and is less time-consuming compared with the Pearson-based subset, full-parameter subset, and empirical subset input. The feature selection method based on MIC can dig out some nonlinear relationships which cannot be found by Pearson coefficient.

show abstract

Section: Introductionmentioning

confidence: 89%

Novel Prediction Model for Steel Mechanical Properties with MSVR Based on MIC and Complex Network Clustering

Yan

2021

Metals

View full text Add to dashboard Cite

show abstract

“…Neurons present in the input and output layers equal the number of input and output parameters, respectively [47]. Finding the optimum number of hidden layers and neurons helps design the best architecture [48] The data used to test the models was obtained from an order fulfillment center. The parameters optimization of the proposed MLPNN model was performed using a random search and trial and error approach.…”

Section: Design Of Mlp Neural Networkmentioning

confidence: 99%

Order Demand Forecast Using a Combined Approach of Stepwise Linear Regression Coefficients and Artificial Neural Network

Gündoğdu

2022

Bitlis Eren Üniversitesi Fen Bilimleri Dergisi

View full text Add to dashboard Cite

Abstract Nowadays, businesses' forecasts to meet the demands have become more critical. This study aimed to predict the fifteen-day order demand for an order fulfillment center using a Multilayer Perceptron Neural Network (MLPNN). The dataset used in the study was created from a real database of a large Brazilian logistics company and thirteen variables. Linear Regression Coefficients (LRC) were used as a feature selection method to reduce estimation errors. The study showed that among the variables, order type_A (A5), order type_B (A6), and order type_C (A7) had the most significant impact on total order forecasting. The effect of A6 was found to be greater than the effect of A7 and A5. The performance of the proposed model was evaluated using the mean absolute percent error (MAPE). LRC-MLPNN provided a MAPE of 2.97%. The results showed that better forecasting performance was obtained by selecting the independent variables to be used as input to the forecasting model with LRC. The proposed model can also be applied to different estimation problems.

show abstract

“…Narayana et al [16] investigated the evolution of the microstructure of a chromiumnickel alloy under hot forging and non-isothermal conditions using ANNs. They stated that the essential feature of the model is the lattice code used in the estimation of steady state volume fraction and grain size, which fits well with their predicted results, indicating the exceptional ability of ANNs to predict these parameters.…”

Section: Introductionmentioning

confidence: 99%

Optimization of Thermomechanical Processing under Double-Pass Hot Compression Tests of a High Nb and N-Bearing Austenitic Stainless-Steel Biomaterial Using Artificial Neural Networks

Sulzbach

Rodrigues

et al. 2022

Metals

View full text Add to dashboard Cite

Physical simulation is a useful tool for examining the events that occur during the multiple stages of thermomechanical processing, since it requires no industrial equipment. Instead, it involves hot deformation testing in the laboratory, similar to industrial-scale processes, such as controlled hot rolling and forging, but under different conditions of friction and heat transfer. Our purpose in this work was to develop an artificial neural network (ANN) to optimize the thermomechanical behavior of stainless-steel biomaterial in a double-pass hot compression test, adapted to the Arrhenius–Avrami constitutive model. The method consists of calculating the static softening fraction (Xs) and mean recrystallized grain size (ds), implementing an ANN based on data obtained from hot compression tests, using a vacuum chamber in a DIL 805A/D quenching dilatometer at temperatures of 1000, 1050, 1100 and 1200 °C, in passes (ε1 = ε2) of 0.15 and 0.30, a strain rate of 1.0 s−1 and time between passes (tp) of 1, 10, 100, 400, 800 and 1000 s. The constitutive analysis and the experimental and ANN-simulated results were in good agreement, indicating that ASTM F-1586 austenitic stainless steel used as a biomaterial undergoes up to Xs = 40% of softening due solely to static recovery (SRV) in less than 1.0 s interval between passes (tp), followed by metadynamic recrystallization (MDRX) at strains greater than 0.30. At T > 1050 °C, the behavior of the softening curves Xs vs. tp showed the formation of plateaus for long times between passes (tp), delaying the softening kinetics and modifying the profile of the curves produced by the moderate stacking fault energy, γsfe = 69 mJ/m2 and the strain-induced interaction between recrystallization and precipitation (Z-phase). Thus, the use of this ANN allows one to optimize the ideal thermomechanical parameters for distribution and refinement of grains with better mechanical properties.

show abstract

Modeling Mechanical Properties of 25Cr-20Ni-0.4C Steels over a Wide Range of Temperatures by Neural Networks

Cited by 9 publications

References 20 publications

Novel Prediction Model for Steel Mechanical Properties with MSVR Based on MIC and Complex Network Clustering

Novel Prediction Model for Steel Mechanical Properties with MSVR Based on MIC and Complex Network Clustering

Order Demand Forecast Using a Combined Approach of Stepwise Linear Regression Coefficients and Artificial Neural Network

Optimization of Thermomechanical Processing under Double-Pass Hot Compression Tests of a High Nb and N-Bearing Austenitic Stainless-Steel Biomaterial Using Artificial Neural Networks

Contact Info

Product

Resources

About