Measurement of the molecular ratio of Aluminum electrolytes using laser-induced breakdown spectroscopy

被引:5
作者
Lu, Hui [1 ,2 ]
Hu, Xiaojun [1 ]
Ma, Liang [2 ]
Li, Meng [2 ]
Cao, Bin [2 ]
机构
[1] Univ Sci & Technol Beijing, State Key Lab Adv Met, Beijing 10083, Peoples R China
[2] Guiyang Aluminum Magnesium Design & Res Inst Co L, Guiyang 550081, Peoples R China
基金
中国国家自然科学基金;
关键词
Electrolytic aluminum industry; Electrolyte; Molecular ratio; Laser-induced breakdown spectroscopy (LIBS); Algorithm; SUPPORT VECTOR MACHINE; PARTIAL LEAST-SQUARES; QUANTITATIVE-ANALYSIS; IRON-ORE; LIBS; REGRESSION; OPTIMIZATION; EMPHASIS; SAMPLES; MN;
D O I
10.1016/j.sab.2019.105753
中图分类号
O433 [光谱学];
学科分类号
0703 ; 070302 ;
摘要
Electrolytes cause the electrolytic reaction of alumina, producing aluminum. Their main component is cryolite. The molecular ratio of electrolytes is an important index to judge the acidity and alkalinity of industrial electrolytes, which are also critical for aluminum electrolysis. The molecular ratio is numerically equal to the molar ratio of NaF to AlF3. The goal of this study was to measure the molecular ratio of electrolytes via laser-induced breakdown spectroscopy (LIBS). First, the micro-morphology, element distribution, and phase structure of industrial electrolytes were analyzed. Second, an artificial neural network (ANN), a support vector machine (SVM), random forest regression (RFR), and gradient-boosting regression (GBR) algorithms were used to establish calibration models for original spectral data and normalized spectral data respectively, and the performances of different models were compared. Calibration models were used to predict independent samples. Finally, partial least squares (PLS) and principal component analysis (PCA) were used to reduce the dimension of the spectral data and screen the variables. Multiple linear regression (MLR), PLS, ANN, and SVM were used to build prediction models based on the new variables screened out, and the generalization abilities of different models were investigated using the leave-one-out cross-validation (LOOCV) method. For the PLS-ANN and PCA-SVM models, the root mean square errors (RMSEs) were 0.100 and 0.136, while the mean relative error (MRE) was 1.204% and 3.142%, respectively. The calibration models were used to test the independent samples, and the measurement results were compared and analyzed. In conclusion, this work provides a temporary new method of testing the electrolyte molecular ratio.
引用
收藏
页数:13
相关论文
共 51 条
[1]  
[Anonymous], 2010, 7392010 YST MIN IND
[2]  
Baggio S., 1980, ALUMINIUM, V56, P276
[3]   Laser-induced breakdown spectroscopy applications in the steel industry: Rapid analysis of segregation and decarburization [J].
Boue-Bigne, Fabienne .
SPECTROCHIMICA ACTA PART B-ATOMIC SPECTROSCOPY, 2008, 63 (10) :1122-1129
[4]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[5]   Pigment identification in paintings employing laser induced breakdown spectroscopy and Raman microscopy [J].
Burgio, L ;
Melessanaki, K ;
Doulgeridis, M ;
Clark, RJH ;
Anglos, D .
SPECTROCHIMICA ACTA PART B-ATOMIC SPECTROSCOPY, 2001, 56 (06) :905-913
[6]   Application of laser-induced breakdown spectroscopy (LIBS) coupled with PCA for rapid classification of soil samples in geothermal areas [J].
Chatterjee, Sitangshu ;
Singh, Manjeet ;
Biswal, Bishnu Prasad ;
Sinha, Uday Kumar ;
Patbhaje, Suraj ;
Sarkar, Arnab .
ANALYTICAL AND BIOANALYTICAL CHEMISTRY, 2019, 411 (13) :2855-2866
[7]  
Chu G., 2003, ACTA METALLURGICA SI, V16, P489
[8]   Support vector machines (SVM) in near infrared (NIR) spectroscopy: Focus on parameters optimization and model interpretation [J].
Devos, Olivier ;
Ruckebusch, Cyril ;
Durand, Alexandra ;
Duponchel, Ludovic ;
Huvenne, Jean-Pierre .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2009, 96 (01) :27-33
[9]  
DEWING EW, 1991, CAN METALL QUART, V30, P153
[10]   Evaluation of Laser-Induced Breakdown Spectroscopy (LIBS) as a Measurement Technique for Evaluation of Total Elemental Concentration in Soils [J].
Diaz, Daniel ;
Hahn, David W. ;
Molinat, Alejandro .
APPLIED SPECTROSCOPY, 2012, 66 (01) :99-106