Health state diagnosis of aluminum electrolytic cells based on Adaboost-PSO-SVM

被引：0

作者：

Yin G. ^{[1
]}

Qian Z. ^{[1
]}

Cao W. ^{[2
]}

Quan P. ^{[2
]}

Xu H. ^{[2
]}

Yan F. ^{[3
]}

Wang M. ^{[4
]}

Xiang Y. ^{[5
]}

Xiang D. ^{[6
]}

Lu J. ^{[3
]}

Zuo Y. ^{[7
]}

He W. ^{[8
]}

Lu R. ^{[3
]}

机构：

[1] State Key Laboratory of Coal Mine Disaster Dynamics and Control, College of Resource and Safety Engineering, Chongqing University, Chongqing

[2] Aba Aluminium Factory, Aba, Sichuan

[3] Guiyang Aluminium Magnesium Design & Research Institute Co., Ltd., Guizhou, Guiyang

[4] Chongqing Qineng Electric Aluminum Co., Ltd., Chongqing

[5] Communication NCO Academy, Army Engineering University of PLA, Chongqing

[6] China Automobile Research Institute New Energy Technology Co., Ltd., Chongqing

[7] Qinghai Haiyuan Green Wheel Manufacturing Co., Ltd., Qinghai, Xining

[8] Bomei Qimingxing Aluminium Co., Ltd., Sichuan, Meishan

来源：

Huagong Xuebao/CIESC Journal | 2024年 / 75卷 / 01期

关键词：

algorithm; electrolysis; experimental validation; health state; prediction;

D O I：

10.11949/0438-1157.20231066

中图分类号：

学科分类号：

摘要：

In order to solve the problem of frequent failures of aluminum electrolytic cells in the aluminum electrolytic production process, a health state diagnosis model of aluminum electrolytic cells based on support vector machine (SVM) was proposed. The thickness of the wall, current efficiency and electrolytic temperature were taken as the comprehensive evaluation indexes of the health state of aluminum electrolytic cells, and the health state of aluminum electrolytic cells was divided into four grades: excellent, good, medium and poor. Considering that traditional support vector machine (SVM) can only be applied to binary classification problem, Adaboost algorithm is used to transform SVM binary classification problem into multi-classification problem to solve aluminum electrolytic cell health diagnosis problem, which fully considers the weight of submodels and strengthens the applicability of the model. The hyperparameters of the model were optimized by using PSO algorithm. The classification accuracy of the model was 94.70% and the Macro-F1 score was 0.9453 in the aluminum electrolytic cells. Compared with the Adaboost-SVM model without optimization algorithm and the PSO-SVM model without integrated algorithm, Adaboost-PSO-SVM improves classification accuracy by 8.34% and 4.93%, and Macro-F1 scores by 8.84% and 5.20%, respectively. Compared with the current mainstream machine learning algorithms DT and KNN, the classification accuracy is improved by 13.64% and 11.11%, respectively, and Macro-F1 scores are improved by 13.47% and 11.04%, respectively. The model provides a comprehensive assessment of the optimal maintenance period for aluminum electrolytic cells. This not only reduces the frequency of failures in aluminum electrolytic cells but also enhances the economic benefits of aluminum plants. © 2024 Materials China. All rights reserved.

引用

页码：354 / 365

页数：11

共 41 条

[1] Fu C H., Comprehensive analysis and evaluation means of electrolytic cell condition, World Nonferrous Metals, 11, pp. 36-39, (2012)
[2] Pass J M, Zheng Y, Wead W B, Et al., Classification of cell states for aluminum electrolysis based on data, Computer Engineering & Applications, 180, 3, pp. H946-H955, (2015)
[3] Deng S S., The abnormal diagnosis of aluminum reduction cell based on anode current, (2017)
[4] Zhang Y R, Yang C H, Zhu H Q., Classification of cell states for aluminum electrolysis based on data, Computer Engineering and Applications, 51, 11, pp. 233-237, (2015)
[5] Hou J, Tian X F, Kong S Q., Prediction of aluminum pot conditions based on LSTM, Light Metals, 1, pp. 33-37, (2021)
[6] Cao D Y, Kong S Q, Gao L., Research on state clustering of aluminum electrolytic cell based on Gaussian mixture model, Light Metals, 2, pp. 26-30, (2020)
[7] Wei Y H., Research on status diagnosis and superheat degree identification of aluminum reduction cell based on fire eye image, (2022)
[8] Chen Z G, Li Y G, Lu M, Et al., Aluminum electrolysis cell condition knowledge representation model and reduction method based on Bayesian probability semantic network, Control and Decision, 35, 7, pp. 1569-1583, (2020)
[9] Li J J, Gao T H, Ji X Y., Aluminum electrolysis abnormal state diagnosis method based on cuckoo support vector machine and deep learning, Light Metals, 10, pp. 32-40, (2019)
[10] Cui G M, Xue F Y, Liu P L., Prediction modelof the current efficiency for aluminum electrolysis process based on status classification, Computer Simulation, 34, 1, pp. 288-291, (2017)

← 1 2 3 4 5 →