Application of General Regression Neural Network in Effectiveness Detection of Temperature Sensors on Transmission Line

Abstract:

The temperature of transmission line is an important parameter in the condition monitoring system on transmission line and its measured value is affected by the state of sensors. General regression neural network (GRNN) was used to construct an auto-detection network for temperature sensors of transmission line. Optimizing design of network, error controlling and effect testing were studied, and also a method of threshold for sensor detection was advanced. The network is verified by practical data from a 220kv transmission line in Sichuan Province and is proved to be with good value of engineering application for sensor state detection of unit.

• Periodical: Applied Mechanics and Materials (Volumes 687-691)
• Pages: 3315-3319
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.687-691.3315
• Online since: November 2014
• Authors: Song Hai Fan, Shu Hong Yang
• Keywords: Condition Monitoring System, General Regression Neural Network, Sensor, Temperature of Transmission, Threshold

References

[1] Huang Xinbo, Chen Ronggui, Wang Xiaojing. Online monitoring and fault diagnosis of transmission line. Beijing: China Power Press, 2010, 10.

[2] Xu Tao, Wang Qi. Application of multiscale principal component analysis based on wavelet packet in sensor fault diagnosis．Proceedings of the CSEE，2011，27(9)：28-32.

[3] Zhang Ji, Wang Bingshu, Di Jian, et al．Research on information fusion for sensors multiple fault diagnosis．Proceedings of the CSEE, 2009, 27(16): 104-108.

[4] Qiu Fengxiang, Si Fengqi, Xu Zhigao．Association rules mining based on principal component analysis at sensor fault detection of power plant．Proceedings of the CSEE, 2012, 29(5): 97-102.

[5] Ferentinos K P, Albright L, Selman B. Neural network-based detection of mechanical, sensor and biological faults in deep-trough hydroponics. Computers and Electronics in Agriculture, 2013(40): 65-85.

DOI: 10.1016/s0168-1699(03)00012-7

[6] Wang Jun, Lv Zhenzhong, Cao Quan. Neural network based method for transducer fault diagnostics and its application. Process Automation Instrumentation, 2008, 24(10): 21-24.

[7] Qiu Tao, Zhang Qingfeng, Ding Yanjun, et al. Nonlinear sensor fault detection and data rebuilding based on principle component analysis. Journal of Tshinghua University, 2006, 46(5): 708-711.

[8] Specht, D.F., A general regression neural network. Neural Netw. IEEE Trans. 1991, 2(6), 568-576.

DOI: 10.1109/72.97934

[9] Zhang Hailin，Yang Ping．A research on fault detection diagnosis technology for sensor．Mechatronics，2001(5)：73-78.