The Application of Neural Network in Dam Safety Monitoring

Abstract:

Dam safety monitoring is an important means for remaining the dam safe, while stress-strain monitoring has been an extremely important part in the dam monitoring. Sometimes the traditional forecasting methods are not high accuracy, so, in order to improve the accuracy of prediction. This paper presents a dam strain prediction model based on Least Squares Support Vector Machines(LS-SVM). Applied in one dam, LS-SVM shows the advantages of good robustness and high prediction accuracy. The strain prediction accuracy improves a lot than using the traditional stepwise regression method, so it provides reliable and effective ways and means in dam strain analysis.

• Periodical: Advanced Materials Research (Volume 304)
• Pages: 84-89
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.304.84
• Online since: July 2011
• Authors: Wei Zhang, Dong Jian Zheng, Cong Cong Wang
• Keywords: Dam Safety Monitoring, Forecast, Neural Network (NN), Step Regression, Strain

References

[1] Peng Hong. Several issues on data analysis of dam and engineering monitoring[J]. Dam and Safety, 2010(1): 31-35.

[2] Cong Peijiang. Time-Varying Model for Dam Stress-Strain Monitoring Data Based on Multiple Factors[J]. Geomatics and Information Science of Wuhan University, 2008，33（9）：914-917.

[3] Deng Naiyang, Tian Yingjie. Support Vector Machines: Theory, Algorithms and Development[M]. Beijing: Science Press, (2009).

[4] Luo Wei, Xi Huayong. Rainfall forecast based on least squares support vector machines[J]. Yangtze River, 2008, 39(19): 29-31.

[5] Gu Chongshi, Wu Zhongru. Safety Monitoring of Dams and Dam Foundations—Theories& Methods and Their Applications[M]. HoHai University Press, (2006).