PREDICTION OF PCCP FAILURE BASED ON HYDROPHNE DETECTING

摘要

Prestressed Concrete Cylinder Pipe (PCCP) is a widely used water pipe all over the world.A major cause of PCCP failure is the internal wire break, which will emit acoustic signal. In thispaper, a hydrophone-based PCCP real-time monitoring and failure-prediction system was proposed.By applying wavelet energy normalization analysis to signal feature extraction and Support VectorMachine (SVM) to signal recognition, a high prediction accuracy of 98.33% was achieved. Theresult showed that the hydrophone-based PCCP failure prediction system is much more effectiveand economic in real application compared with electromagnetic method and acoustic fiber optical.