The Model of Pump Head Data Mining Based on SVM

Abstract:

The curve of flow-head is one of the most important indicators to assess water pump performance. While it is difficult to get measured data in real condition and the data is very limited. The method of pump data mining based on support vector machine (SVM) is built due to its superiority in dealing with small sample event. The method is aimed at finding out the unknown data between measured data and drawing more accurate flow-head curve. It was found that the model of pump data mining based on SVM is much better than neural network when their curves are compared.

• Periodical: Applied Mechanics and Materials (Volumes 405-408)
• Pages: 3263-3268
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.405-408.3263
• Online since: September 2013
• Authors: Kai Ding*, Jin Hui Zhang, Xiao Xun Zhu
• Keywords: Curve of Flow-Head, Data Mining (DM), Neural Network (NN), Support Vector Machine (SVM)

References

[1] Alexander Y，Ronald L，Recognition of Bearing Failures using Wavelets and Neural Networks，TFTS97，Coventry(UK), August 27-29，(1997).

[2] GA Adepoju，SOA Ogunjuyigbe，KO Alawode．Application of Neural Network to Load Forecasting in Nigerian Electrical Power System [J]．The Pacific Journal of Science and Technology．2007，8(1)：68-72.

[3] U.B. Filik，M. Kurban．A new approach for the short-term load forecasting with autoregressive and artificial neural network models [J]. International Journal of Computational Intelligence Research．2007，3(1)：66-71.

DOI: 10.5019/j.ijcir.2007.88

[4] M. Daneshdoost，M. Lotfalian，G. Bumroonggit，et al．Neural network with fuzzy set-based classification for short-term load forecasting [J] ．Power Systems, IEEE Transactions on．1998，13 (4)：1386-1391.

DOI: 10.1109/59.736281

[5] PK Dash，AC Liew，S. Rahman．Fuzzy neural network and fuzzy expert system for load forecasting [J]．Generation, Transmission and Distribution, IEE Proceedings-，1996，IET: 106-114.

DOI: 10.1049/ip-gtd:19960314

[6] T. Joachims．Making large scale SVM learning practical [J] ．(1999).

[7] J.C. Platt．12 Fast Training of Support Vector Machines using Sequential Minimal Optimization [J] ．(1999).

[8] S.S. Keerthi S.K. Shevade，C. Bhattacharyya，et al．Improvements to Platt's SMO algorithm for SVM classifier design [J] ．Neural Computation．2001，13 (3)：637-649.

DOI: 10.1162/089976601300014493

[9] P.W. Chen J.Y. Wang H.M. Lee．Model selection of SVMs using GA approach [C] ．Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on，2004，IEEE: 2035-(2040).

DOI: 10.1109/ijcnn.2004.1380929

[10] Z. Chunhong，J. Licheng．Automatic parameters selection for SVM based on GA [J] ．Intelligent Control and Automation, 2004. WCICA 2004. Fifth World Congress on, 2004，IEEE：1869-1872.

DOI: 10.1109/wcica.2004.1341000