Modelling IF Steels Using Artificial Neural Networks and Automated Machine Learning

Sgrott, Douglas Macedo; Cerqueira, Fabricio Moreira; Miranda, Fabiano J. F.; Filho, José F. S.; Parpinelli, Rafael Stubs

doi:10.1007/978-3-030-73050-5_64

Cited by 2 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 8 shows only the top 20 most influential features out of a total of 29 features. When comparing these findings with those presented in [21], a noteworthy reduction in the significance of carbon is XVI Brazilian Conference on Computational Intelligence (CBIC 2023), Salvador, October 8th to 11th observed in both models. This decline can be attributed to the inclusion of additional steel types, such as DP, BH, TRIP, and HSLA, alongside IF.…”

Section: Importance Of Input Parameterssupporting

confidence: 54%

See 1 more Smart Citation

Ensemble of Artificial Neural Networks and AutoML for Predicting Steel Properties

Silva,

Serpa,

Sgrott

et al. 2023

Anais Do XVI Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

The design of new steel grades is a continuous pursuit in the metallurgical industry, aiming to develop lighter and stronger materials for diverse industries. This study explores the use of an ensemble of artificial neural networks, named EANN, to model the relationships between chemical composition, process parameters, and mechanical properties of five types of steels. Auto-Keras, an automated machine learning framework, is employed to identify the best configurations for the ANNs and create the ensemble model. The best ANN, named B-ANN, obtained through the same AutoML process, and the one model ANN generated by Auto-Keras, named ANN, are used as a benchmark to evaluate the E-ANN performance. The results obtained show that the E-ANN model is competitive in terms of predictive capability. Sensitivity analysis provides insights into the influence of input parameters on mechanical properties, while Shapley Value analysis highlights the relative importance of these parameters. The findings contribute to the understanding of steel behavior and provide guidance for steel design processes. This study demonstrates the effectiveness of E-ANN in predicting mechanical properties and emphasizes the value of data-driven techniques and automated machine learning in steel design.

show abstract

Section: Importance Of Input Parameterssupporting

confidence: 54%

“…In a recent study, [21] proposed the modeling of IF steels using ANNs. Different activation functions were used, and the hyperparameters were optimized using the Auto-Keras library as NAS.…”

Section: Introductionmentioning

confidence: 99%

Ensemble of Artificial Neural Networks and AutoML for Predicting Steel Properties

Silva,

Serpa,

Sgrott

et al. 2023

Anais Do XVI Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

show abstract

On Least Squares Support Vector Regression for Predicting Mechanical Properties of Steel Rebars

Bessa,

Barreto,

Coelho

et al. 2024

Metals

View full text Add to dashboard Cite

Aiming at ensuring the quality of the product and reducing the cost of steel manufacturing, an increasing number of studies have been developing nonlinear regression models for the prediction of the mechanical properties of steel rebars using machine learning techniques. Bearing this in mind, we revisit this problem by developing a design methodology that amalgamates two powerful concepts in parsimonious model building: (i) sparsity, in the sense that few support vectors are required for building the predictive model, and (ii) locality, in the sense that simpler models can be fitted to smaller data partitions. In this regard, two regression models based on the Least Squares Support Vector Regression (LSSVR) model are developed. The first one is an improved sparse version of the one introduced in a previous work. The second one is a novel local LSSVR-based regression model. The task of interest is the prediction of four output variables (the mechanical properties YS, UTS, UTS/YS, and PE) based on information about its chemical composition (12 variables) and the parameters of the heat treatment rolling (6 variables). The proposed LSSVR-based regression models are evaluated using real-world data collected from steel rebar manufacturing and compared with the global LSSVR model. The local sparse LSSVR approach was able to consistently outperform the standard single regression model approach in the task of interest, achieving improvements in the average R2 from previous studies: 5.04% for UTS, 5.19% for YS, 1.96% for UTS/YS, and 3.41% for PE. Furthermore, the sparsification of the dataset and the local modeling approach significantly reduce the number of SV operations on average, utilizing 34.0% of the total SVs available for UTS estimation, 44.0% for YS, 31.3% for UTS/YS, and 32.8% for PE.

show abstract

Modelling IF Steels Using Artificial Neural Networks and Automated Machine Learning

Cited by 2 publications

References 14 publications

Ensemble of Artificial Neural Networks and AutoML for Predicting Steel Properties

Ensemble of Artificial Neural Networks and AutoML for Predicting Steel Properties

On Least Squares Support Vector Regression for Predicting Mechanical Properties of Steel Rebars

Contact Info

Product

Resources

About