A BiLSTM Based Pipeline Leak Detection and Disturbance Assisted Localization Method

Negative pressure wave (NPW) based fluid pipeline leak detection and localization method detects leaks by capturing the pressure inflecting trends and locates leaks by calculating the time difference of arrival (TDOA) of NPW between the upstream and downstream sensors. However, in practical situations, pressure variations under normal working conditions such as pump, valve operations etc., may be misidentified as leaks due to the similar pressure inflection transients caused. In addition, for leak localization, traditional TDOA method assumes the NPW propagation speed as a constant, which is inconsistent with the reality. In this paper, a deep learning based pipeline leak detection and disturbance assisted localization method is proposed. At first, unlike the traditional methods, which only focus on detecting pressure transients for leaks, a deep learning based pressure sequence classification scheme is proposed to identify not only the leaks but also the typical recurrent non-leak pressure disturbances. Secondly, instead of using an empirical constant as NPW speed to calculate leak locations, a disturbance assisted localization method is proposed to online update the NPW speed by exploiting non-leak disturbances. The proposed approach is data driven, i.e., only pressure signals are needed. For validation, the approach is tested on both simulation data and real-world pipeline leak experimental data. Comparison and case studies are also performed. It is shown that the proposed method achieves high detection accuracy with rare false alarms and significantly reduced leak localization errors.