Title :
Fault diagnostics of blast furnace based on NN-DPSO-SVM
Author :
Liu, Limei ; Wang, Anna ; Sha, Mo ; Wang, Zhe
Author_Institution :
Coll. of Inf. Sci. & Eng., Northeastern Univ., Shenyang, China
Abstract :
Since fault diagnosis of blast furnace is very important in manufacturing, in this paper, a new strategy based on NN-DPSO-SVM is proposed to solve it. Using the nearest neighbor principle deletes the useless samples so that the training set is pruned. A modified discrete particle swarm optimization is applied to optimize the feature selection and the SVM parameters so that the algorithm can improve the performance of the SVM classifier and increase the recognition accuracy. Binary tree classification model is constructed rationally to solve the multi-class fault diagnosis. The new method in this paper can select the best fault features in much shorter time and have fewer errors and better generalization performance in the application of fault diagnosis of the blast furnace.
Keywords :
blast furnaces; fault diagnosis; fault trees; feature extraction; particle swarm optimisation; support vector machines; NN-DPSO-SVM; binary tree classification model; blast furnace; discrete particle swarm optimization; fault diagnosis; feature selection; nearest neighbor principle; support vector machines; Artificial neural networks; Blast furnaces; Classification algorithms; Fault diagnosis; Particle swarm optimization; Support vector machines; Training; NN-DPSO-SVM; blast furnace; fault diagnosis;
Conference_Titel :
Intelligent Control and Automation (WCICA), 2010 8th World Congress on
Conference_Location :
Jinan
Print_ISBN :
978-1-4244-6712-9
DOI :
10.1109/WCICA.2010.5554626
