Minor class-based status detection for pipeline network using enhanced generative adversarial networks

Abstract For the operational status detection of a pipeline network, it is essential to obtain enough samples of each class during the network operation. However, the phenomenon of few actual leak samples give rise to the imbalanced dataset problem. To address this issue, this paper proposes a minor class-based status detection method using enhanced generative adversarial networks (enhanced-GANs). First, a generative model with a U-net structure is established to generate the required samples with the modified normal samples, and the L1 loss and L2 loss functions are utilized to update the network parameters. Then, output results and extracted features regarding different layers of discriminative network are added in the generative network loss function to improve the quality of the generated samples. Furthermore, based on the hidden features extracted by the trained discriminative network, an enhanced dual judgment scheme is proposed to improve the status detection performance. Finally, extensive experiments are carried out to evaluate the proposed method with the dataset collected from a practical pipeline network. The experiment results show that the proposed method can not only provide enough leak samples but also effectively improves the status detection accuracy for a pipeline network.

[1]  Dazhong Ma,et al.  Status detection from spatial-temporal data in pipeline network using data transformation convolutional neural network , 2019, Neurocomputing.

[2]  Huaguang Zhang,et al.  Near-Optimal Control for Nonzero-Sum Differential Games of Continuous-Time Nonlinear Systems Using Single-Network ADP , 2013, IEEE Transactions on Cybernetics.

[3]  Xiaobo Qiu,et al.  Pipeline Leak Detection by Using Time-Domain Statistical Features , 2017, IEEE Sensors Journal.

[4]  Shantanu Datta,et al.  A review on different pipeline fault detection methods , 2016 .

[5]  Liang Lin,et al.  Adaptively Connected Neural Networks , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Yan Li,et al.  Leak Detection and Location of Pipelines Based on LMD and Least Squares Twin Support Vector Machine , 2017, IEEE Access.

[7]  Jun Wang,et al.  An intelligent diagnosis scheme based on generative adversarial learning deep neural networks and its application to planetary gearbox fault pattern recognition , 2018, Neurocomputing.

[8]  Ioan Silea,et al.  A survey on gas leak detection and localization techniques , 2012 .

[9]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[10]  Jinhai Liu,et al.  A leak detection method for oil pipeline based on markov feature and two-stage decision scheme , 2019, Measurement.

[11]  Yi Shen,et al.  Application of improved least-square generative adversarial networks for rail crack detection by AE technique , 2019, Neurocomputing.

[12]  Dazhong Ma,et al.  Data-Core-Based Fuzzy Min–Max Neural Network for Pattern Classification , 2011, IEEE Transactions on Neural Networks.

[13]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[14]  Huaguang Zhang,et al.  A Small-Sample Wind Turbine Fault Detection Method With Synthetic Fault Data Using Generative Adversarial Nets , 2019, IEEE Transactions on Industrial Informatics.

[15]  Qiuye Sun,et al.  The Small-Signal Stability Analysis of the Droop-Controlled Converter in Electromagnetic Timescale , 2019, IEEE Transactions on Sustainable Energy.

[16]  Peng Xu,et al.  Predicting pipeline leakage in petrochemical system through GAN and LSTM , 2019, Knowl. Based Syst..

[17]  Haibo He,et al.  Learning from Imbalanced Data , 2009, IEEE Transactions on Knowledge and Data Engineering.

[18]  Faizal Mustapha,et al.  A pressure-based method for monitoring leaks in a pipe distribution system: A Review , 2017 .

[19]  Huaguang Zhang,et al.  Neural-Network-Based Near-Optimal Control for a Class of Discrete-Time Affine Nonlinear Systems With Control Constraints , 2009, IEEE Transactions on Neural Networks.

[20]  Uthman Baroudi,et al.  Pipeline Leak Detection Systems and Data Fusion: A Survey , 2019, IEEE Access.

[21]  Liang Sun,et al.  Integrated-signal-based leak location method for liquid pipelines , 2014 .

[22]  Ole Morten Aamo,et al.  Leak Detection, Size Estimation and Localization in Pipe Flows , 2016, IEEE Transactions on Automatic Control.

[23]  Diego Cabrera,et al.  Generative Adversarial Networks Selection Approach for Extremely Imbalanced Fault Diagnosis of Reciprocating Machinery , 2019, IEEE Access.

[24]  Nathalie Japkowicz,et al.  The class imbalance problem: A systematic study , 2002, Intell. Data Anal..

[25]  Yi Zheng,et al.  Distributed state estimation for leak detection in water supply networks , 2017 .

[26]  Atsuto Maki,et al.  A systematic study of the class imbalance problem in convolutional neural networks , 2017, Neural Networks.

[27]  Yijun Cai,et al.  Leak Detection and Location Based on ISLMD and CNN in a Pipeline , 2019, IEEE Access.

[28]  Dongfeng Zhao,et al.  Fault diagnosis for distillation process based on CNN–DAE , 2019, Chinese Journal of Chemical Engineering.

[29]  Yong Zhang,et al.  An SAE-based resampling SVM ensemble learning paradigm for pipeline leakage detection , 2020, Neurocomputing.

[30]  Huaguang Zhang,et al.  An iterative adaptive dynamic programming method for solving a class of nonlinear zero-sum differential games , 2011, Autom..

[31]  Fei-Yue Wang,et al.  Traffic Flow Imputation Using Parallel Data and Generative Adversarial Networks , 2020, IEEE Transactions on Intelligent Transportation Systems.

[32]  Manoj Kumar Tiwari,et al.  A review of leakage detection strategies for pressurised pipeline in steady-state , 2020 .