Research On Underground Cable Intrusion Warning System Based On Optical Fiber Vibration Sensing Technology

With the acceleration of the process of urbanization in China,considering the overall image of the city and the tense situation of urban land,underground cable is replacing the traditional overhead transmission network,and the way of underground cable has been greatly increased.However,the subsequent monitoring of cable safety has also become increasingly prominent.Therefore,designing and developing an underground cable intrusion warning system has important scientific value and practical significance for the safety monitoring of underground cables.The work carried out in this thesis mainly covers the following aspects:First of all,this paper analyzes the existing intrusion warning technology,and propose the research subject of this paper based on the analysis result,namely,the underground cable intrusion warning system based on optical fiber vibration sensing technology.Second,this paper analyzes the basic structure of the optical fiber sensor and the principle of sensing,elaborates the relationship between the optical fiber sensor output signal and the intrusion vibration signal.After comparative analysis of several commonly used phase interferometers,an optical fiber sensor based on the Mach-Zehnder interference structure was selected.On this basis,the selection of hardware and the construction of the hardware platform have been completed.Then,this paper deeply studies the intrusion signal recognition algorithms of the intrusion warning system.After analyzing the intrusion event and its signal characteristics,the corresponding intrusion signals are collected for research.Then the commonly used digital processing technology(preprocessing,denoising)and feature extraction algorithm(timedomain features,wavelet packet energy features,MFCC features)are used to process intrusion signals.Based on this,a feature extraction method based on Intrinsic Time-scale Decomposition(ITD)is proposed innovatively,and an experiment of intrusion signal recognition is designed based on support vector machine and BP neural network.Based on the experiment,the design of intrusion signal recognition algorithm is completed.After completing the design of the intrusion signal recognition algorithm and the analysis of the needs of the intrusion warning system,the paper designs and implements the software platform of the system,and the whole framework and the work flow of the system are described and analyzed in detail.Finally,this paper sets up an experimental environment to conduct field test of the intrusion warning system's intrusion warning,basic system parameters,and functional modules.The field test proved that the solution of underground cable intrusion warning system based on optical fiber vibration sensing technology is reasonable,the recognition algorithm is accurate,and the expected monitoring and recognition performance is achieved.At the same time,the modular design of the software architecture lays a good foundation for the subsequent upgrade and maintenance of intrusion recognition algorithms,and effectively promoting the practical application of intrusion warning systems.