Published Papers
     Search Papers (Springer,
   After 2008)
     Search Papers (Dbpia,
   Until 2007)
     Search Papers (JMST
   own data base)
       - Classification By Year   
       - Classification By Topic
     Special Issues
   
           
   
 
 
Subject Keyword Abstract Author
 
 
Diagnosis of mechanical pumping system using neural networks and system parameters analysis

Tai-Ming Tsai
The Journal of Mechanical Science and Technology, vol. 23, no. 1, pp.124-135, 2009

Abstract : Normally, a mechanical pumping system is equipped to monitor some of the important input and output signals which are set to the prescribed values. This paper addressed dealing with these signals to establish the database of input- output relation by using a number of neural network models through learning algorithms. These signals encompass normal and abnormal running conditions. The abnormal running conditions were artificially generated. Meanwhile, for the purpose of setting up an on-line diagnosis network, the learning speed and accuracy of three kinds of networks, viz., the backpropagation (BPN), radial basis function (RBF) and adaptive linear (ADALINE) neural networks have been compared and assessed. The assessment criteria of the networks are compared with the correlation result matrix in terms of the neuron vectors. Both BPN and RBF are judged by the maximum vector based on the post-regression analysis, and the ADALINE is judged by the minimum vector based on the least mean square error analysis. By ignoring the neural network training time, it has been shown that if the mechanical diagnosis system is tackled off-line, the RBF method is suggested. However, for on-line diagnosis, the BPN method is recommended.

Keyword : Neural network; System diagnosis; Correlation analysis; Sensitivity analysis; Radial basis function method; Backpropagation

 
 
 
 
 
JMST Editorial Office: #702 KSTC New Bldg, 22 7-gil, Teheran-ro, Gangnam-gu, Seoul 06130, Korea
TEL: +82-2-501-3605, E-mail: editorial@j-mst.org
JMST Production Office: #702 KSTC New Bldg, 22 7-gil, Teheran-ro, Gangnam-gu, Seoul 06130, Korea
TEL: +82-2-501-6056, FAX: +82-2-501-3649, E-mail: editorial@j-mst.org