Using Artificial Neural Network to Predict Low Voltage Anode Effect PFCS at the Duct End of an Electrolysis Cell

Dion, Lukas; Lagacé, Charles-Luc; Kiss, László I.; Poncsák, Sándor

doi:10.1007/978-3-319-48251-4_91

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In early studies, much work related to AE was based on principal component analysis (PCA) [21][22][23] or multivariate statistical methods [1,24]. In recent years, neural networks [5,25,26], extreme gradient boosting (XGBoost) [2] and hybrid algorithms (for example, a hybrid algorithm based on support vector machine (SVM) and k nearest neighbor [27]) have been applied to AE prediction. Without considering of fault mechanism, these methods have higher accuracy and a longer time in advance for prediction.…”

Section: Introductionmentioning

confidence: 99%

A modified neighborhood mutual information and light gradient boosting machine-based long-term prediction approach for anode effect

Pan

Kong

Chen

et al. 2019

Meas. Sci. Technol.

View full text Add to dashboard Cite

The anode effect (AE) often occurs in the aluminum electrolysis process, which seriously affects production efficiency and causes large energy consumption. Therefore, predicting AE in advance has become very important. However, traditional cell resistance-based methods have the disadvantages of low accuracy and short predicting time, and the data-driven methods have not fully considered the relevance between other features and AE, causing the low accuracy for long-term prediction. In this paper, a long-term prediction approach for AE based on a modified neighborhood mutual information and light gradient boosting machine (MNMI-LGBM) is proposed. The MNMI is used to measure the relevance between features and AE for feature selection, and a derivative feature of the cell resistance is fed into the LGBM as a key feature to predict AE. The predicting time in the range of 0–50 min is considered. The results show that the proposed approach has an accuracy above 89% over the entire 0–50 min predicting time range. Specifically, the accuracy achieves 93.6% when predicting time is 50 min. The proposed approach only requires six features as the input of LGBM and can be applied for real-time AE prediction.

show abstract

Section: Introductionmentioning

confidence: 99%

A modified neighborhood mutual information and light gradient boosting machine-based long-term prediction approach for anode effect

Pan

Kong

Chen

et al. 2019

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…It is capable of inferring, from electrical readings, whenever the alumina concentration in a cell approaches the level at which the anode effect will occur. Lukas et al presented an artificial neural network (ANN) method to predict low voltage anode effect perfluorocarbons (PFCs) [22]. The advantage of the method is that it can facilitate understanding of the root cause of the low voltage anode effect.…”

Section: Introductionmentioning

confidence: 99%

Anode effect prediction based on a singular value thresholding and extreme gradient boosting approach

Zhang

Liu

et al. 2018

Meas. Sci. Technol.

View full text Add to dashboard Cite

An anode effect often occurs during the process of aluminum electrolysis that will cause large energy consumption and low efficiency in aluminum production, thus how to identify the anode effect in advance has become an important issue. However, traditional approaches ignore the common incomplete information problem existing in the acquired data, and only consider a single predicting time, resulting in an unreliable result in anode effect prediction. In this paper, a hybrid prediction approach based on a singular value thresholding and extreme gradient boosting (SVT-XGBoost) approach is proposed to identify the anode effect in the aluminum electrolysis process. The SVT is used for data filling by the whole-features transformation, and the XGBoost is utilized for classification of the anode effect. The predicting time is set to 10 min by the comparison. The experimental results show that the proposed approach has an effective ability for anode effect classification using the SVT-XGBoost compared to the previous approaches. Here, the effect of the training sample number is also investigated. The proposed approach could be applied in real-time anode effect prediction in the future.

show abstract

“…Apesar de desconsiderar a emissão de PFC das indústrias de TR, por causa da discrepância entre os dados apresentados pelas indústrias e os apresentados pelos observatórios atmosféricos, WONG et al, 2015 propõem a existência de uma quantidade não detectada ou medida de PFC gerado por efeito anódico de baixa tensão. Novas técnicas de medidas e modelos estão sendo desenvolvidos para a medição e estimativa do CF4 emitido pelas indústrias (DION et al, 2016(DION et al, , 2017MÜHLE et al, 2010, DION et al, 2017.…”

Section: Geração De Pfcs Pela Indústriaunclassified

Estudo da adsorção do perfluorcarbono tetrafluormetano e ácido fluorídrico em leito de óxido de neodímio.

Yamazaki¹

View full text Add to dashboard Cite

The consumption of light rare earths, especially neodymium, has grown significantly in recent years and is expected to grow even more in the coming years. The main process for its industrial production is the electrolytic reduction of its oxide in molten fluorides. This is a similar process to aluminum production and brings the same threats to health and to the environment as this one: generation of HF and tetrafluoromethane (CF4). The present work focuses on the adsorption of HF in a bed of neodymium oxide, as a similar process used for the retention of this gas by alumina in the production of aluminum. In the studied flow range, complete retention of HF was observed by the neodymium oxide bed. CF4 retention by the bed was also evaluated, this time without success. Negative results regarding CF4 retention by alumina beds is also reported in the literature in the case of aluminum production.

show abstract

Using Artificial Neural Network to Predict Low Voltage Anode Effect PFCS at the Duct End of an Electrolysis Cell

Cited by 3 publications

References 0 publications

A modified neighborhood mutual information and light gradient boosting machine-based long-term prediction approach for anode effect

A modified neighborhood mutual information and light gradient boosting machine-based long-term prediction approach for anode effect

Anode effect prediction based on a singular value thresholding and extreme gradient boosting approach

Estudo da adsorção do perfluorcarbono tetrafluormetano e ácido fluorídrico em leito de óxido de neodímio.

Contact Info

Product

Resources

About