Anode effect prediction based on support vector machine and K nearest neighbor

The prediction of the anode effect has long been a challenging industrial issue in aluminum electrolytic production. For improving the prediction precision of the anode effect, this paper combines support vector machine (SVM) and K nearest neighbor (KNN) algorithm. First of all, samples are extracted from the real-time production data and weighted with Relief algorithm. Afterwards, the classifier is selected from the two methods depending on the distance from the test sample to the optimal hyperplane of SVM. Compared with traditional approaches, the hybrid method can predict the anode effect more accurately. The prediction accuracy can reach about 89% and the predictable time can up to half an hour. Extensive experimental results validate the proposed method's effectiveness.

[1]  Nazatul Aini Abd Majid,et al.  Aluminium process fault detection by Multiway Principal Component Analysis , 2011 .

[2]  Kaibo Zhou,et al.  Anode effect prediction of aluminum electrolysis using GRNN , 2015, 2015 Chinese Automation Congress (CAC).

[3]  Nazatul Aini Abd Majid,et al.  Multivariate statistical monitoring of the aluminium smelting process , 2011, Comput. Chem. Eng..

[4]  Hao Wu,et al.  The application of the equipment fault diagnosis based on modified Elman neural network , 2011, Proceedings of 2011 International Conference on Electronic & Mechanical Engineering and Information Technology.

[5]  Minyong Shi,et al.  Improved Feature Weight Algorithm and Its Application to Text Classification , 2016 .

[6]  Kaibo Zhou,et al.  Cell resistance slope combined with LVQ neural network for prediction of anode effect , 2015, 2015 Sixth International Conference on Intelligent Control and Information Processing (ICICIP).

[7]  Deyong You,et al.  WPD-PCA-Based Laser Welding Process Monitoring and Defects Diagnosis by Using FNN and SVM , 2015, IEEE Transactions on Industrial Electronics.

[8]  Yang Xiao,et al.  Fault Diagnosis Using a Joint Model Based on Sparse Representation and SVM , 2016, IEEE Transactions on Instrumentation and Measurement.

[9]  Haibo He,et al.  Optimized Relative Transformation Matrix Using Bacterial Foraging Algorithm for Process Fault Detection , 2016, IEEE Transactions on Industrial Electronics.

[10]  H. Vogt,et al.  On the mechanism of the anode effect in aluminum electrolysis , 2000 .

[11]  Ke Wang,et al.  Optimal dissolved gas ratios selected by genetic algorithm for power transformer fault diagnosis based on support vector machine , 2016, IEEE Transactions on Dielectrics and Electrical Insulation.

[12]  Liping Qu,et al.  The Multi-class SVM Is Applied in Transformer Fault Diagnosis , 2015, 2015 14th International Symposium on Distributed Computing and Applications for Business Engineering and Science (DCABES).

[13]  Brent R. Young,et al.  Diagnosing faults in aluminium processing by using multivariate statistical approaches , 2012, Journal of Materials Science.

[14]  Ding Lei,et al.  Frequency characteristic and its application of the cell resistance in aluminum electrolysis , 2012, 2012 7th International Conference on Computer Science & Education (ICCSE).

[15]  Feng Qiao,et al.  Neural network fault prediction and its application , 2010, 2010 8th World Congress on Intelligent Control and Automation.

[16]  Byron L. D. Bezerra,et al.  A KNN-SVM hybrid model for cursive handwriting recognition , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[17]  Jules Thibault,et al.  Neural networks for the identification of the aluminium electrolysis process , 1998 .