Studies on Parameters Affecting Temperature of Liquid Steel and Prediction Using Modified AdaBoost.RT Algorithm Ensemble Extreme Learning Machine

Wang, Senhui; Li, Haifeng; Zhang, Yongjie; Wang, Cheng; He, Xin; Chen, Denghong; Yang, Ke

doi:10.3390/met12122028

Cited by 6 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some notable examples are the use of a wavelet transform-based weighting algorithm for the support vector machine (SVM) framework [21] and the use of an outlier detection component to either replace or remove outliers in the dataset [23]. The published ML models predicting the end-point temperature of the VTD process are more sparse but follow the same regimen as the corresponding research on the LRF process [28][29][30].…”

Section: Previous Workmentioning

confidence: 99%

A Proposed Methodology to Evaluate Machine Learning Models at Near-Upper-Bound Predictive Performance—Some Practical Cases from the Steel Industry

Carlsson,

Samuelsson

2023

Processes

View full text Add to dashboard Cite

The present work aims to answer three essential research questions (RQs) that have previously not been explicitly dealt with in the field of applied machine learning (ML) in steel process engineering. RQ1: How many training data points are needed to create a model with near-upper-bound predictive performance on test data? RQ2: What is the near-upper-bound predictive performance on test data? RQ3: For how long can a model be used before its predictive performance starts to decrease? A methodology to answer these RQs is proposed. The methodology uses a developed sampling algorithm that samples numerous unique training and test datasets. Each sample was used to create one ML model. The predictive performance of the resulting ML models was analyzed using common statistical tools. The proposed methodology was applied to four disparate datasets from the steel industry in order to externally validate the experimental results. It was shown that the proposed methodology can be used to answer each of the three RQs. Furthermore, a few findings that contradict established ML knowledge were also found during the application of the proposed methodology.

show abstract

Section: Previous Workmentioning

confidence: 99%

A Proposed Methodology to Evaluate Machine Learning Models at Near-Upper-Bound Predictive Performance—Some Practical Cases from the Steel Industry

Carlsson,

Samuelsson

2023

Processes

View full text Add to dashboard Cite

show abstract

Multimodel Predictions on Converter Raw Material Addition Under GRNN Optimization: A Comparative Study

Wang,

Fang,

Zhu

et al. 2024

Metall Mater Trans B

View full text Add to dashboard Cite

Calculation of production balances and costs in ladle furnace refining process with addition of scrap steel

Wang,

Fang,

Zhu

et al. 2024

Ironmaking & Steelmaking: Processes, Products and Applicati

View full text Add to dashboard Cite

As increasing the scrap steel ratio has become an important approach for energy conservation and emission reduction in the steel industry, the technology of multi-point scrap addition has emerged. Ladle furnace (LF) refining is a feasible step for scrap steel utilisation, which is often overlooked and relied solely on empirical adjustment, resulting in difficulty of precise control. It is necessary to conduct in-depth research on this process using scientific methods and explore the impact of scrap steel addition on other materials. A comprehensive calculation model was established by scientifically investigating material and thermal balances in the LF process in this article, and the impact of initial steel and scrap compositions, temperature, mass and price of scrap on production costs were analysed and compared based on the model. The results showed that as the carbon and silicon content in the initial steel increase by every 0.01% could on average reduce the production cost per ton of steel by 4.013 CNY and 0.8473 CNY, respectively, and increases by 0.123 CNY as the sulphur content increase every 0.001%. The impact of scrap composition on costs is similar to that of the initial molten steel. Increasing the carbon and sulphur content in scrap by every 0.01% will on average increase costs by 0.0765 CNY and 0.01 CNY, respectively. When the price difference between scrap and the crude steel price is within 450–500 CNY/t, increasing scrap addition will create more profit. The relative reduction in smelting time is 7.97 s as the scrap temperature increases every 50°C. The present study holds academic and industrial significance in improving LF efficiency and promoting the LF process towards a more sustainable direction.

show abstract

Studies on Parameters Affecting Temperature of Liquid Steel and Prediction Using Modified AdaBoost.RT Algorithm Ensemble Extreme Learning Machine

Cited by 6 publications

References 27 publications

A Proposed Methodology to Evaluate Machine Learning Models at Near-Upper-Bound Predictive Performance—Some Practical Cases from the Steel Industry

A Proposed Methodology to Evaluate Machine Learning Models at Near-Upper-Bound Predictive Performance—Some Practical Cases from the Steel Industry

Multimodel Predictions on Converter Raw Material Addition Under GRNN Optimization: A Comparative Study

Calculation of production balances and costs in ladle furnace refining process with addition of scrap steel

Contact Info

Product

Resources

About