Sound Recognition Algorithm for Power Devices Based on Substation Inspection Robots

Abstract:

Transformer and high reactance are two important devices in power substations, and the running sound has the information of their running state. But inspection robots don’t have the function of sound recognition. A new sound recognition algorithm based on harmonics feature and vector quantization for power substation devices was proposed. Inspection robots is adopted to record and sample the running sound of the devices, the 27 harmonics in [0Hz,1300Hz] is adopted as the feature vector, the LBG algorithm is adopted to train the optimal codebook for VQ, and the running state of the transformer and high reactance was recognized with the high recognition ratio 99%.

• Periodical: Applied Mechanics and Materials (Volumes 599-601)
• Pages: 1139-1144
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.599-601.1139
• Online since: August 2014
• Authors: Dong Song Li*, Zhi Qian Zhou, Chao Zhang, Peng Du, Yu Rong Hu
• Keywords: Harmonics Feature, LBG Algorithm, Power Substation Inspection Robot, Vector Quantization

References

[1] Hu Qiming, Hu Runzi, Zhou Ping. Application of Inspection Robot Technology in Substation. Central China Electric Power， 2011. 5, (24)，36-39.

[2] Lu Shouyin, Su Jianjun. Application of robot in substation Device Inspection. Robot Technique and Application, 2007, 5(1): 33-36.

[3] Yao Yong, Abnormal Sound Analysis And Discrimination of Power devices. Popular Utilization of Electricity, 2003(1)，41.

[4] Zhao Li. Speech Signal Processing. Beijing, China Machine Press, (2003).

[5] Luan Shaowen. Feature Extraction of Abnormal Sound in Public Places. Computer Engineering, 2010, 36(7): 208-210.

[6] Xie Guodong, Yi Quan, Han Zhaofu, Yang Jianchang, Research on Battlefield Target Sound Recognition Technology. . Fire Control and Command Control, 2006, 28(3): 9-11.

[7] Zhang Minghan, Shi Weiren, Ding Ning. Research on Abnormal Sound Recognition Based on Learning, Chinese Journal of science of Instrument，2009. 6, 30(6), 37-40.

[8] C. Clavel, T. Ehrette, G. Richard. Events detection for an audio-based surveillance system, IEEE International Conference on Multimedia and Expo, (2005).

DOI: 10.1109/icme.2005.1521669

[9] Lv XiaoYun. Abnormal audio recognition algorithm based on MFCC and short-term energy. 2010, 3: 796-798.

DOI: 10.3724/sp.j.1087.2010.00796

[10] Liu Hui, Yang Juanan, Xu Xuezhong. A New Low Altitude Passive Acoustic Target Identifying Approach Research Based on MFCC and HMM. Journal of Projectiles; Rockets; Missiles and Guidance, 2007, (5): 217-222.

[11] Lv XiaoYun, Wang Hongxia. Abnormal audio recognition algorithm based on MFCC and short-term energy . Journal of Computer Applications, 2010. 30(3), 796-798.

DOI: 10.3724/sp.j.1087.2010.00796

[12] Chen Jie, Zhang Linghua, Wu Xihong. Feature Extraction Based on Wavelet Package-LPCC in speaker recognition[. Journal of Nanjin University of Post and Telecommunication (natural science) 2007. 12, 27(6), 54-56.

[13] Ai Changsheng, He Guangwei, Dong Quancheng, tool-wear on line monitoring cutting sound linear predictive cepstrum coefficient （LPCC） correlation analysis. China Mechanical Engineering, 20(17), 2009. 9, 2045-(2048).