A Dynamic Time Sequence Recognition and Knowledge Mining Method Based on the Hidden Markov Models (HMMs) for Pipeline Safety Monitoring With Φ-OTDR

• Published in: Journal of lightwave technology Vol. 37; no. 19; pp. 4991 - 5000
• Main Authors: Wu, Huijuan, Liu, Xiangrong, Xiao, Yao, Rao, Yunjiang
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.10.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Buried pipes; Distributed optical fiber sensor; Feature extraction; Field tests; Hidden Markov models; HMMs; knowledge mining; Machine learning; Markov analysis; Markov chains; Monitoring; Optical fiber cables; Optical fiber communication; Optical fiber sensors; Performance measurement; pipeline monitoring; Pipeline safety; Pipelines; Recognition; Reflectometry; Φ-OTDR
• ISSN: 0733-8724; 1558-2213
• DOI: 10.1109/JLT.2019.2926745

With the rapid development and extensive applications of phase-sensitive optical time-domain reflectometry to long distance pipeline safety monitoring, it is still challenging to find a very efficient way to achieve highly correct recognition and really deep understanding of physical events sensed in a wide dynamic environment, as the vibration signals usually exhibit non-linear and non-stationary characteristics caused by the complicated environments. In this paper, a dynamic time sequence recognition and knowledge mining method based on the hidden Markov models (HMMs) is proposed to solve this problem. First, local structure feature of the signal is extracted in multiple analysis domains in the time sequence order; and then the HMMs are trained, built, and used to mine the temporal evolution information and identify the sequential state process of typical events. The experimental results with real field test data show that the average recognition accuracy of this paper is as high as 98.2% for frequently encountered five typical events along buried pipelines. All the related performance metrics such as precision, recall, and F-score are better than those traditional machine learning methods such, RF, XGB, DT, and BN.