Adaptive Naive Bayes Classifier Based Filter Using Kernel Density Estimation for Pipeline Leakage Detection

Pipelines are among the principal means of transporting hydrocarbon fluids and gases, so leakage detection is critical to avoid the loss of these energy resources. In this article, based on studies in field data, we model pipeline leakage as an increase in the mean value of the flow rate difference between the inlet and the outlet sensors, where the increased value is unknown and subject to change. Then, an adaptive filter is proposed based on the naive Bayes classification and the estimated cumulative distribution function (CDF) of the data in steady-state conditions using kernel density estimation. The proposed filter has a better performance in small leaks in comparison with different benchmarks.