Unsupervised learning method for events identification in φ-OTDR

作者：Zhang, Jie; Zhao, Xiaoting; Zhao, Yiming; Zhong, Xiang; Wang, Yidan; Meng, Fanchao; Ding, Jinmin; Niu, Yingli; Zhang, Xinghua; Dong, Liang; Liang, Sheng^*

来源：Optical and Quantum Electronics, 2022, 54(7): 457.

DOI：10.1007/s11082-022-03748-y

• Fiber-optic distributed vibration sensor
• Phase-sensitive optical time domain reflectometry (phi-OTDR)
• Unsupervised learning
• Clustering
• Event identification

In this paper, an unsupervised-learning method for events-identification in phi-OTDR fiber-optic distributed vibration sensor is proposed. The different vibration-events including blowing, raining, direct and indirect hitting, and noise-induced false vibration are clustered by the k-means algorithm. The equivalent classification accuracy of 99.4% has been obtained, compared with the actual classes of vibration-events in the experiment. With the cluster-number of 3, the maximal Calinski-Harabaz index and Silhouette coefficient are obtained as 2653 and 0.7206, respectively. It is found that our clustering method is effective for the events-identification of phi-OTDR without any prior labels, which provides an interesting application of unsupervised-learning in self-classification of vibration-events for phi-OTDR.

• 单位
  北京交通大学