Title :
Application of Immune Genetic Neural Network in Pump-jack Fault Diagnosis
Author :
Ren, Weijian ; Liu, Dan
Author_Institution :
Post Doctorial Res. Center of Control Sci. & Eng., Univ. of Sci. & Technol., Beijing, China
Abstract :
A new RBF neural network is presented to overcome the shortcoming that the training process of RBF neural network is slow in the paper. The immune genetic algorithm is combined with the RBF neural network to optimize the center of the RBF network, improve the definition method of affinity degree, and introduce adjusting factor based on density. Thus the learning efficiency and approximation precision are improved, and the number of constructing the centers of hide layer of the network is dispensable. The algorithm was successful in fault diagnosis of pump-jack.
Keywords :
approximation theory; artificial immune systems; fault diagnosis; genetic algorithms; learning (artificial intelligence); lifting equipment; mining equipment; oil drilling; pumps; radial basis function networks; RBF neural network; approximation precision; immune genetic neural network; learning efficiency; oil mining mechanical device; optimization; pump-jack fault diagnosis; Artificial intelligence; Artificial neural networks; Fault diagnosis; Feedforward neural networks; Genetic algorithms; Intelligent systems; Neural networks; Petroleum; Pumps; Radial basis function networks; RBF neural network; fault diagnosis; immune genetic algorithm; pump-jack;
Conference_Titel :
Intelligent Systems, 2009. GCIS '09. WRI Global Congress on
Conference_Location :
Xiamen
Print_ISBN :
978-0-7695-3571-5
DOI :
10.1109/GCIS.2009.48
