Pipeline leakage detection and isolation: An integrated approach of statistical and wavelet feature extraction with multi-layer perceptron neural network (MLPNN) |
| |
Affiliation: | 1. Masdar Institute for Science & Technology, United Arab Emirates;2. Non-linearity and Complexity Research Group, Aston University, UK;1. State Key Laboratory of Precision Measurement Technology and Instrument, Tianjin University, Tianjin 300072, PR China;2. School of Information Science and Engineering, Yanshan University, Qin Huang Dao, Hebei Province 066004, PR China;1. Tongji University, State Key Laboratory of Disaster Reduction in Civil Engineering, Siping 1239, Shanghai 200092, China;2. Tongji University, College of Civil Engineering, Siping 1239, Shanghai 200092, China |
| |
Abstract: | Leakage diagnosis of hydrocarbon pipelines can prevent environmental and financial losses. This work proposes a novel method that not only detects the occurrence of a leakage fault, but also suggests its location and severity. The OLGA software is employed to provide the pipeline inlet pressure and outlet flow rates as the training data for the Fault Detection and Isolation (FDI) system. The FDI system is comprised of a Multi-Layer Perceptron Neural Network (MLPNN) classifier with various feature extraction methods including the statistical techniques, wavelet transform, and a fusion of both methods. Once different leakage scenarios are considered and the preprocessing methods are done, the proposed FDI system is applied to a 20-km pipeline in southern Iran (Goldkari-Binak pipeline) and a promising severity and location detectability (a correct classification rate of 92%) and a low False Alarm Rate (FAR) were achieved. |
| |
Keywords: | Pipeline leakage Fault detection and isolation (FDI) system Multi-layer perceptron neural network (MLPNN) classifier Wavelet transform Statistical features ABC" },{" #name" :" keyword" ," $" :{" id" :" kwrd0040" }," $$" :[{" #name" :" text" ," _" :" artificial bee colony ANN" },{" #name" :" keyword" ," $" :{" id" :" kwrd0050" }," $$" :[{" #name" :" text" ," _" :" artificial neural network CCR" },{" #name" :" keyword" ," $" :{" id" :" kwrd0060" }," $$" :[{" #name" :" text" ," _" :" correct classification rate DWT" },{" #name" :" keyword" ," $" :{" id" :" kwrd0070" }," $$" :[{" #name" :" text" ," _" :" discrete wavelet transform FAR" },{" #name" :" keyword" ," $" :{" id" :" kwrd0080" }," $$" :[{" #name" :" text" ," _" :" false alarm rate FDI" },{" #name" :" keyword" ," $" :{" id" :" kwrd0090" }," $$" :[{" #name" :" text" ," _" :" fault detection and isolation LMSE" },{" #name" :" keyword" ," $" :{" id" :" kwrd0100" }," $$" :[{" #name" :" text" ," _" :" least mean square error LPG" },{" #name" :" keyword" ," $" :{" id" :" kwrd0110" }," $$" :[{" #name" :" text" ," _" :" liquefied petroleum gas MLPNN" },{" #name" :" keyword" ," $" :{" id" :" kwrd0120" }," $$" :[{" #name" :" text" ," _" :" multi-layer perceptron neural network MSE" },{" #name" :" keyword" ," $" :{" id" :" kwrd0130" }," $$" :[{" #name" :" text" ," _" :" mean square error NPW" },{" #name" :" keyword" ," $" :{" id" :" kwrd0140" }," $$" :[{" #name" :" text" ," _" :" negative pressure wave PNN" },{" #name" :" keyword" ," $" :{" id" :" kwrd0150" }," $$" :[{" #name" :" text" ," _" :" probabilistic neural network RTTM" },{" #name" :" keyword" ," $" :{" id" :" kwrd0160" }," $$" :[{" #name" :" text" ," _" :" real time transient modeling SCADA" },{" #name" :" keyword" ," $" :{" id" :" kwrd0170" }," $$" :[{" #name" :" text" ," _" :" supervisory control and data acquisition STFT" },{" #name" :" keyword" ," $" :{" id" :" kwrd0180" }," $$" :[{" #name" :" text" ," _" :" short-time fourier transform SVM" },{" #name" :" keyword" ," $" :{" id" :" kwrd0190" }," $$" :[{" #name" :" text" ," _" :" support vector machine |
本文献已被 ScienceDirect 等数据库收录! |
|