Neuro based classification of gas leakage sounds in pipeline

In industry, such as oil refinery industry, there may occur various kinds of safety problems for pipelines aged after its constructions. To realize preventive maintenance of pipelines, there are large needs for the diagnosis technology of gas leakage. In this study, gas leakage sounds generated from the crack of pipe is analized and tried to be used for detection of the gas leakage. Sound data for analysis are generated and collected in the plant where background noise is not negligible. To diagnose the crack, sound data for analysis are sampled applying Fast Fourier Transform. Classification and discrimination of cracks are carried out using Neural Network. As the result of the acoustic experiments, it is proved that acoustic diagnosis can classify a leakage sound of a pipeline. To check the applicability of the proposed algorithm, the identified Neural Network classifier is applied in various cases.