Heats and input variables selection for designing a water detection framework applicable to industrial electric arc furnaces

Alshawarghi, Hamzah; Elkamel, Ali; Moshiri, Behzad; Hourfar, Farzad

doi:10.1002/cjce.23767

Cited by 3 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So, by applying statistical analysis or machine‐learning techniques, (e.g., fingerprinting method, multiway principal component analysis [MPCA], or multiway projection to latent structure [MPLS]), it will be possible to categorize the off‐gas water vapour for various similar heats . More details about the statistical analysis applicable to EAFs are available in the studies by Zuliani et al [ 14,16 ] and Alshawarghi et al [ 6 ]…”

Section: Methodsmentioning

confidence: 99%

“…Hence, there is an industrial need for an effective water leak detection methodology. [5,6] The first step to design an efficient leak detection system for an EAF is to model and identify the dynamics of the process. [7,8] Hence, this paper focuses on analytically performing a mass balance to determine the boundary for the expected water leaving the EAF, which helps the operators to monitor the process.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Water detection framework for industrial electric arc furnaces: Boundary modelling and formulation

et al. 2023

Self Cite

View full text Add to dashboard Cite

This paper describes the development of a boundary model for the off‐gas water vapour in an industrial steelmaking electric arc furnace (EAF). The solution addresses the mechanistic components of a complete EAF water detection framework. The boundary model has been implemented on an industrial alternating current (AC) EAF. The model specifies upper and lower limits in real‐time of the expected EAF off‐gas water vapour leaving the furnace, and it provides a valuable on‐line monitoring tool to the operator on what boundary to expect for the off‐gas water vapour in different circumstances. An essential data required for the framework is the EAF off‐gas composition. So, in this work, an off‐gas analyzer with a human machine interface (HMI) and a supervisory control and data acquisition (SCADA) system was installed in the first step. Then, in order to evaluate the developed water leak detection framework and verify the obtained results, industrial trials were designed in which a certain amount of water was intentionally added into the furnace by increasing the electrode spray water flow rate. Moreover, we have shown how the presented framework can be used to appropriately adjust the alarm setting values in control/emergency shutdown systems of industrial EAF to enhance the safety and availability of the plant.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Water detection framework for industrial electric arc furnaces: Boundary modelling and formulation

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…[ 7 ] To construct a variables selection model, a multiway PCA method is proposed, and the selected variables have a higher correlation with the off‐gas water vapour. [ 8 ] A novel feature extraction method based on PCA and independent component analysis (ICA) is proposed so that the proposed method makes up for the deficiency of PCA, which requires the valuables to follow a Gaussian distribution. [ 9 ] A PCA random discretization ensemble method is investigated so that the proposed strategy outperforms both the PCA algorithm and the random forest method in terms of prediction performance.…”

Section: Introductionmentioning

confidence: 99%

Dynamic global feature extraction and importance‐correlation selection for the prediction of concentrate copper grade and recovery rate

Wang

Zhang

2023

Can J Chem Eng

View full text Add to dashboard Cite

Large-scale industrial data have brought great challenges to data calculation and analysis. Feature extraction and selection have become one of the research emphases in data mining. To mine the dynamic characteristics of large-scale industrial data, a dynamic global feature extraction (DGFE) method integrating principal component analysis (PCA) and kernel principal component analysis (KPCA) is proposed such that the achieved feature set is not only dynamic but also contains linear and non-linear features. To ensure that the obtained feature set is optimal with the minimum redundancy, a new importancecorrelation-based feature selection (ICFS) method is proposed. To verify the validity and feasibility of the proposed methods, the partial least square (PLS) and least square support vector machine (LSSVM) prediction models for the concentrate copper grade and the recovery rate are established. The effectiveness of the proposed methods is verified through data experiments on a copper flotation industrial process.

show abstract

“…The selected heats and input variables are used by empirical predictive models, applicable in fault detection techniques. [ 3 ]…”

mentioning

confidence: 99%

Issue Highlights

2020

Can J Chem Eng

View full text Add to dashboard Cite

Heats and input variables selection for designing a water detection framework applicable to industrial electric arc furnaces

Cited by 3 publications

References 22 publications

Water detection framework for industrial electric arc furnaces: Boundary modelling and formulation

Water detection framework for industrial electric arc furnaces: Boundary modelling and formulation

Dynamic global feature extraction and importance‐correlation selection for the prediction of concentrate copper grade and recovery rate

Issue Highlights

Contact Info

Product

Resources

About