Introduction to statistical pattern recognition (2nd ed.)
Introduction to statistical pattern recognition (2nd ed.)
Hi-index | 0.00 |
A new approach and solution to the continuous leak monitoring problem in underground gas pipelines is presented. This approach places permanent monitoring units along the pipeline. These units detect acoustic signals in the pipeline and discriminate leak sounds from other man made or natural nonleak sounds that can occur. The system uses the kNN classifier as the detector with LPC cepstrums as signal features. To increase system performance pipeline effects on acoustic signals were taken into account during the classifier training faze. Each unit can detect 1/4" diameter leaks from a distance of 300 meters, yielding 600 meters as the maximum distance between units.