Camber Prediction Based on Fusion Method with Mechanism Model and Machine Learning in Plate Rolling

Ding, Jing Guo; He, Yang; Kong, Ling Pu; Peng, Wen

doi:10.2355/isijinternational.isijint-2020-357

Cited by 16 publications

(7 citation statements)

References 14 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The concept of modeling refers to the search for and selection of an ML algorithm suitable for specified research objectives by considering the characteristics of the preprocessed dataset. It also includes the entire process of training and evaluating the model using training and test datasets and selecting the best-performing model [58]. Considering that the background dataset used in this study was time-series data, it was mostly based on daily numeric information.…”

Section: Modeling Overviewmentioning

confidence: 99%

A Prediction Model for Spot LNG Prices Based on Machine Learning Algorithms to Reduce Fluctuation Risks in Purchasing Prices

Yang

Choi

2023

Energies

View full text Add to dashboard Cite

The ongoing Russia–Ukraine conflict has exacerbated the global crisis of natural gas supply, particularly in Europe. During the winter season, major importers of liquefied natural gas (LNG), such as South Korea and Japan, were directly affected by fluctuating spot LNG prices. This study aimed to use machine learning (ML) to predict the Japan Korea Marker (JKM), a spot LNG price index, to reduce price fluctuation risks for LNG importers such as the Korean Gas Corporation (KOGAS). Hence, price prediction models were developed based on long short-term memory (LSTM), artificial neural network (ANN), and support vector machine (SVM) algorithms, which were used for time series data prediction. Eighty-seven variables were collected for JKM prediction, of which eight were selected for modeling. Four scenarios (scenarios A, B, C, and D) were devised and tested to analyze the effect of each variable on the performance of the models. Among the eight variables, JKM, national balancing point (NBP), and Brent price indexes demonstrated the largest effects on the performance of the ML models. In contrast, the variable of LNG import volume in China had the least effect. The LSTM model showed a mean absolute error (MAE) of 0.195, making it the best-performing algorithm. However, the LSTM model demonstrated a decreased in performance of at least 57% during the COVID-19 period, which raises concerns regarding the reliability of the test results obtained during that time. The study compared the ML models’ prediction performances with those of the traditional statistical model, autoregressive integrated moving averages (ARIMA), to verify their effectiveness. The comparison results showed that the LSTM model’s performance deviated by an MAE of 15–22%, which can be attributed to the constraints of the small dataset size and conceptual structural differences between the ML and ARIMA models. However, if a sufficiently large dataset can be secured for training, the ML model is expected to perform better than the ARIMA. Additionally, separate tests were conducted to predict the trends of JKM fluctuations and comprehensively validate the practicality of the ML models. Based on the test results, LSTM model, identified as the optimal ML algorithm, achieved a performance of 53% during the regular period and 57% d during the abnormal period (i.e., COVID-19). Subject matter experts agreed that the performance of the ML models could be improved through additional studies, ultimately reducing the risk of price fluctuations when purchasing spot LNG.

show abstract

Section: Modeling Overviewmentioning

confidence: 99%

A Prediction Model for Spot LNG Prices Based on Machine Learning Algorithms to Reduce Fluctuation Risks in Purchasing Prices

Yang

Choi

2023

Energies

View full text Add to dashboard Cite

show abstract

“…Modeling is the process of generalizing data patterns by applying specific algorithms after preprocessing and analyzing a prepared dataset [39]. An ML algorithm appropriate for the prepared dataset and the deduced values was selected, and an optimal model was created through training, fine-tuning, and relevance evaluation.…”

Section: Modeling For Flue Gas Predictionmentioning

confidence: 99%

Prediction Modeling of Flue Gas Control for Combustion Efficiency Optimization for Steel Mill Power Plant Boilers Based on Partial Least Squares Regression (PLSR)

Lee,

Choi,

Lee

2023

Energies

View full text Add to dashboard Cite

The energy-intensive steel industry, which consumes substantial amounts of electricity, meets its power demands through external electricity purchases and self-generation through the operation of its own generators. This study aimed to optimize boiler combustion efficiency and increase power generation output by deriving optimal operational values for O2 and CO within the boiler flue gas using machine learning (ML) with the aim of achieving maximum boiler efficiency. This study focuses on the power-generation boilers at steel mill P in Korea. First, 361 types of operation data from power generation equipment were collected and preprocessed. Subsequently, a partial least squares regression (PLSR) algorithm was used to develop a prediction model for O2 and CO values, known as the Boiler Flue Gas Prediction Model (BFG-PM). The prediction accuracy for O2 was notably high (83.2%), whereas that for CO was lower (53.4%). Nonetheless, the model’s reliability was high because more than 90% of the predicted values were within a 10% error range. Finally, the correlation of the BFG-PM model was applied to the performance test code (PTC) 4.0 for the boiler efficiency calculations formula, deriving the optimal O2 and CO control points. Through a simulation, it was verified that the boiler efficiency was improved by controlling the combustion air. In addition, an average increase in boiler efficiency of 0.29% was confirmed by applying it directly to the generator operating on-site. The results of this study are expected to contribute to annual cost savings, with a reduction of USD 217,000 in electricity purchasing costs and USD 19,700 in greenhouse gas emissions trading expenses.

show abstract

“…The prediction ability and generalization performance of the model are evaluated by calculating the root mean square error (RMSE), mean square correlation coefficient (R 2 ), and mean absolute error (MAE). The specific calculation formulas are expressed in Equation ( 22)- (24).…”

Section: Model Performance Evaluation Criteriamentioning

confidence: 99%

“…It meets the requirement of schedule‐free rolling in the production of wide nonoriented electrical steel and has been successfully applied in production. Jing et al [ 24 ] proposed a prediction model of a steel‐plate rolling camber based on a mechanism model and ML. The error range of the model was controlled within ±6%, and accurate control of the camber was realized.…”

Section: Introductionmentioning

confidence: 99%

Strip Thickness and Profile–Flatness Prediction in Tandem Hot Rolling Process Using Mechanism Model‐Guided Machine Learning

Liu

Wang

Sun

et al. 2022

steel research int.

View full text Add to dashboard Cite

This study is focused on the multivariable, nonlinear, strong‐coupling, and time‐varying characteristics of the quality control process of hot strip rolling. Using the rolling process data from a continuously variable crown (CVC) mill of a 1580 mm hot tandem rolling line, a new prediction model of the strip thickness, profile, and flatness in hot rolling based on rolling mechanism model‐guided machine learning (ML) is developed. The weighted processing (WP) method is used to fuse the rolling mechanism and process data, to improve the relationship between the strong correlation features and the model. Combined with nondominated sorting genetic algorithm III (NSGA‐III), multiple parameters of multioutput support vector regression (M‐SVR) are optimized. The results show that the root mean square error (RMSE), mean square correlation coefficient (R 2), and mean absolute error (MAE) of the strip thickness, crown, and flatness are 2.0159, 1.3191, and 0.9355; 0.9854, 0.9895, and 0.9873; and 16.601, 1.126, and 0.604, respectively. Moreover, the established method of data fusion rolling mechanism shows strong capability to improve the model prediction accuracy, increasing it by 60%. Thus, it can offer theoretical guidance for realizing accurate control of the quality of strips and improving the quality of hot‐rolled products.

show abstract

Camber Prediction Based on Fusion Method with Mechanism Model and Machine Learning in Plate Rolling

Cited by 16 publications

References 14 publications

A Prediction Model for Spot LNG Prices Based on Machine Learning Algorithms to Reduce Fluctuation Risks in Purchasing Prices

A Prediction Model for Spot LNG Prices Based on Machine Learning Algorithms to Reduce Fluctuation Risks in Purchasing Prices

Prediction Modeling of Flue Gas Control for Combustion Efficiency Optimization for Steel Mill Power Plant Boilers Based on Partial Least Squares Regression (PLSR)

Strip Thickness and Profile–Flatness Prediction in Tandem Hot Rolling Process Using Mechanism Model‐Guided Machine Learning

Contact Info

Product

Resources

About