A journal of IEEE and CAA , publishes high-quality papers in English on original theoretical/experimental research and development in all areas of automation
Advanced Search
Volume 10 Issue 4
Apr.  2023

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 11.8, Top 4% (SCI Q1)
    CiteScore: 17.6, Top 3% (Q1)
    Google Scholar h5-index: 77， TOP 5
Turn off MathJax
Article Contents
Article Navigation >  IEEE/CAA Journal of Automatica Sinica  > 2023  >  10(4): 1064-1076
T. Sun, C. Wang, H. L. Dong, Y. N. Zhou, and C. Guan, “A novel parameter-optimized recurrent attention network for pipeline leakage detection,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 4, pp. 1064–1076, Apr. 2023. doi: 10.1109/JAS.2023.123180
Citation: T. Sun, C. Wang, H. L. Dong, Y. N. Zhou, and C. Guan, “A novel parameter-optimized recurrent attention network for pipeline leakage detection,” IEEE/CAA J. Autom. Sinica, vol. 10, no. 4, pp. 1064–1076, Apr. 2023. doi: 10.1109/JAS.2023.123180
shu

A Novel Parameter-Optimized Recurrent Attention Network for Pipeline Leakage Detection

doi: 10.1109/JAS.2023.123180

  • Sanya Offshore Oil & Gas Research Institute, Northeast Petroleum University, Sanya 572024, Artificial Intelligence Energy Research Institute, Northeast Petroleum University, and also with the Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control, Northeast Petroleum University, Daqing 163318, China

Funds:  This work was supported in part by the National Natural Science Foundation of China (U21A2019, 61873058), Hainan Province Science and Technology Special Fund of China (ZDYF2022SHFZ105), and the Alexander von Humboldt Foundation of Germany
More Information
    Abstract
  • Accurate detection of pipeline leakage is essential to maintain the safety of pipeline transportation. Recently, deep learning (DL) has emerged as a promising tool for pipeline leakage detection (PLD). However, most existing DL methods have difficulty in achieving good performance in identifying leakage types due to the complex time dynamics of pipeline data. On the other hand, the initial parameter selection in the detection model is generally random, which may lead to unstable recognition performance. For this reason, a hybrid DL framework referred to as parameter-optimized recurrent attention network (PRAN) is presented in this paper to improve the accuracy of PLD. First, a parameter-optimized long short-term memory (LSTM) network is introduced to extract effective and robust features, which exploits a particle swarm optimization (PSO) algorithm with cross-entropy fitness function to search for globally optimal parameters. With this framework, the learning representation capability of the model is improved and the convergence rate is accelerated. Moreover, an anomaly-attention mechanism (AM) is proposed to discover class discriminative information by weighting the hidden states, which contributes to amplifying the normal-abnormal distinguishable discrepancy, further improving the accuracy of PLD. After that, the proposed PRAN not only implements the adaptive optimization of network parameters, but also enlarges the contribution of normal-abnormal discrepancy, thereby overcoming the drawbacks of instability and poor generalization. Finally, the experimental results demonstrate the effectiveness and superiority of the proposed PRAN for PLD.

     

    • FullText(HTML)
  • loading
    • References(53)
  • [1]
    X. H. Li, G. M. Chen, and H. W. Zhu, “Quantitative risk analysis on leakage failure of submarine oil and gas pipelines using Bayesian network,” Process Safety and Environmental Protection, vol. 103, pp. 163–173, 2016. doi: 10.1016/j.psep.2016.06.006
    [2]
    R. Xiao, Q. F. Hu, and J. Li, “Leak detection of gas pipelines using acoustic signals based on wavelet transform and support vector machine,” Measurement, vol. 146, pp. 479–489, 2019. doi: 10.1016/j.measurement.2019.06.050
    [3]
    F. L. Ning, Z. H. Cheng, D. Meng, S. Duan, and J. Wei, “Enhanced spectrum convolutional neural architecture: An intelligent leak detection method for gas pipeline,” Process Safety and Environmental Protection, vol. 146, pp. 726–735, 2021.
    [4]
    C. Wang, F. Han, Y. Zhang, and J. Y. Lu, “An SAE-based resampling SVM ensemble learning paradigm for pipeline leakage detection,” Neurocomputing, vol. 403, pp. 237–246, 2020. doi: 10.1016/j.neucom.2020.04.105
    [5]
    S. B. Zhu, Z. L. Li, S. M. Zhang, and H. F. Zhang, “Deep belief network-based internal valve leakage rate prediction approach,” Measurement, vol. 133, pp. 182–192, 2019. doi: 10.1016/j.measurement.2018.10.020
    [6]
    C. Lee and D. Yoo, “Development of leakage detection model and its application for water distribution networks using RNN-LSTM,” Sustainability, vol. 13, no. 16, p. 9262, 2021.
    [7]
    B. Wang, Y. B. Guo, D. Wang, Y. Zhang, R. He, and J. Chen, “Prediction model of natural gas pipeline crack evolution based on optimized DCNN-LSTM,” Mechanical Systems and Signal Processing, vol. 181, p. 109557, 2022.
    [8]
    P. Xu, R. Du, and Z. B. Zhang, “Predicting pipeline leakage in petrochemical system through GAN and LSTM,” Knowledge-Based Systems, vol. 175, pp. 50–61, 2019. doi: 10.1016/j.knosys.2019.03.013
    [9]
    W. B. Liu, Z. D. Wang, L. Hu, and X. H. Liu, “A deep learning approach for classifying patient attendance disposal from emergency departments,” in Proc. 15th IEEE Int. Conf. Control and Autom., Edinburgh, UK, 2019, pp. 278–283.
    [10]
    W. B. Liu, Z. D. Wang, Y. Yuan, N. Y. Zeng, K. Hone, and X. H. Liu, “A novel sigmoid-function-based adaptive weighted particle swarm optimizer,” IEEE Trans. Cybernetics, vol. 51, no. 2, pp. 1085–1093, 2019.
    [11]
    C. Wang, Z. D. Wang, Q.-L. Han, F. Han, and H. L. Dong, “Novel leader-follower-based particle swarm optimizer inspired by multiagent systems: Algorithm, experiments, and applications,” IEEE Trans. Systems,Man,and Cybernetics: Systems, vol. 53, no. 3, pp. 1322–1334, 2023. doi: 10.1109/TSMC.2022.3196853
    [12]
    C. Wang, Y. Zhang, J. B. Song, Q. Q. Liu, and H. L. Dong, “A novel optimized SVM algorithm based on PSO with saturation and mixed time-delays for classification of oil pipeline leak detection,” Systems Science and Control Engineering, vol. 7, no. 1, pp. 75–88, 2019.
    [13]
    D. M. Wang, L. J. Zhu, J. K. Yue, J. Y. Lu, D. W. Li, and G. F. Li, “Application of variational mode decomposition based on particle swarm optimization in pipeline leak detection,” Engineering Research Express, vol. 2, no. 4, p. 045036, 2020.
    [14]
    H. Zhang and X. J. Yu, “Research on oil and gas pipeline defect recognition based on IPSO for RBF neural network,” Sustainable Computing: Informatics and Systems, vol. 20, pp. 203–209, 2018. doi: 10.1016/j.suscom.2017.08.002
    [15]
    X. Li, W. Zhang, and Q. Ding, “Understanding and improving deep learning-based rolling bearing fault diagnosis with attention mechanism,” Signal Processing, vol. 161, pp. 136–154, 2019. doi: 10.1016/j.sigpro.2019.03.019
    [16]
    Z. Long, X. F. Zhang, L. Zhang, G. J. Qin, S. D. Huang, D. Y. Song, H. D. Shao, and G. P. Wu, “Motor fault diagnosis using attention mechanism and improved adaboost driven by multi-sensor information,” Measurement, vol. 170, p. 108718, 2021.
    [17]
    L. Xiang, P. H. Wang, X. Yang, A. J. Hu, and H. Su, “Fault detection of wind turbine based on SCADA data analysis using CNN and LSTM with attention mechanism,” Measurement, vol. 175, p. 109094, 2021.
    [18]
    A. H. Khan, S. Li, and X. Luo, “Obstacle avoidance and tracking control of redundant robotic manipulator: An RNN-based metaheuristic approach,” IEEE Trans. Industrial Informatics, vol. 16, no. 7, pp. 4670–4680, 2019.
    [19]
    S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997. doi: 10.1162/neco.1997.9.8.1735
    [20]
    J. Kennedy and R. C. Eberhart, “Particle swarm optimization,” in Proc. ICNN Int. Conf. Neural Networks, Perth, Australia, 1995, pp. 1942–1948.
    [21]
    C. Wang, Z. D. Wang, F. Han, H. L. Dong, and H. J. Liu, “A novel PID-like particle swarm optimizer: On terminal convergence analysis,” Complex and Intelligent Systems, vol. 8, no. 2, pp. 1217–1228, 2022.
    [22]
    N. Y. Zeng, Z. D. Wang, W. B. Liu, H. Zhang, K. Hone, and X. H. Liu, “A dynamic neighborhood-based switching particle swarm optimization algorithm,” IEEE Trans. Cybernetics, vol. 52, no. 9, pp. 9290–9301, 2022. doi: 10.1109/TCYB.2020.3029748
    [23]
    A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention is all you need,” Advances in Neural Information Processing Systems, pp. 5998–6008, 2017.
    [24]
    W. B. Liu, Z. D. Wang, N. Y. Zeng, F. E. Alsaadi, and X. H. Liu, “A PSO-based deep learning approach to classifying patients from emergency departments,” Int. J. Machine Learning and Cybernetics, vol. 12, no. 7, pp. 1939–1948, 2021. doi: 10.1007/s13042-021-01285-w
    [25]
    J. Williams and D. Zipser, “A learning algorithm for continually running fully recurrent neural networks,” Neural Computation, vol. 1, no. 2, pp. 270–280, 1989. doi: 10.1162/neco.1989.1.2.270
    [26]
    K. Cho, B. Van, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, “Learning phrase representations using RNN encoder-decoder for statistical machine translation,” arXiv preprint arXiv: 1406.1078, 2014.
    [27]
    Y. LeCun, B. Boser, J. Denker, D. Henderson, R. Howard, W. Hubbard, and L. Jackel, “Backpropagation applied to handwritten zip code recognition,” Neural Computation, vol. 1, no. 4, pp. 541–551, 1989. doi: 10.1162/neco.1989.1.4.541
    [28]
    X. J. Shi, Z. R, Chen, H. Wang, D. Y. Yeung, W. K. Wong, and W. C. Woo, “Convolutional LSTM network: A machine learning approach for precipitation nowcasting,” in Advances in Neural Information Processing Systems, 2015, pp. 802–810.
    [29]
    Z. H. Huang, W. Xu, and K. Yu, “Bidirectional LSTM-CRF models for sequence tagging,” arXiv preprint arXiv: 1508.01991, 2015.
    [30]
    A. Trischler, Z. Ye, X. D. Yuan, and K. Suleman, “Natural language comprehension with the epireader,” arXiv preprint arXiv: 1606.02270, 2016.
    [31]
    H. W. Chen, Z. D. Wang, J. L. Liang, and M. Z. Li, “State estimation for stochastic time-varying Boolean networks,” IEEE Trans. Autom. Control, vol. 65, no. 12, pp. 5480–5487, 2020. doi: 10.1109/TAC.2020.2973817
    [32]
    H. W. Chen, Z. D. Wang, B. Shen, and J. L. Liang, “Distributed recursive filtering over sensor networks with non-logarithmic sensor resolution,” IEEE Trans. Autom. Control, vol. 67, no. 10, pp. 5408–5415, 2022. doi: 10.1109/TAC.2021.3115473
    [33]
    J. Hu, C. Q. Jia, H. Yu, and H. J. Liu, “Dynamic event-triggered state estimation for nonlinear coupled output complex networks subject to innovation constraints,” IEEE/CAA J. Autom. Sinica, vol. 9, no. 5, pp. 941–944, 2022. doi: 10.1109/JAS.2022.105581
    [34]
    Z. R. Hu, P. Shi, and L. G. Wu, “Preserving state and control privacies in networked systems with tokenized polytopic transforms,” IEEE Trans. Circuits and Systems II: Express Briefs, vol. 69, no. 1, pp. 104–108, 2022. doi: 10.1109/TCSII.2021.3075471
    [35]
    C. Q. Jia, J. Hu, D. Y. Chen, Z. P. Cao, J. P. Huang, and H. L. Tan, “Adaptive event-triggered state estimation for a class of stochastic complex networks subject to coding-decoding schemes and missing measurements,” Neurocomputing, vol. 494, pp. 297–307, 2022. doi: 10.1016/j.neucom.2022.04.096
    [36]
    Y. M. Ju, X. Tian, H. J. Liu, and L. F. Ma, “Fault detection of networked dynamical systems: A survey of trends and techniques,” Int. J. Systems Science, vol. 52, no. 16, pp. 3390–3409, 2021. doi: 10.1080/00207721.2021.1998722
    [37]
    N. Li, Q. Li, and J. H. Suo, “Dynamic event-triggered H∞ state estimation for delayed complex networks with randomly occurring nonlinearities,” Neurocomputing, vol. 421, pp. 97–104, 2021. doi: 10.1016/j.neucom.2020.08.048
    [38]
    W. B. Liu, Z. D. Wang, L. L. Tian, S. Lauria, and X. H. Liu, “Melt pool segmentation for additive manufacturing: A generative adversarial network approach,” Computers and Electrical Engineering, vol. 92, p. 107183, 2021.
    [39]
    Z. T. Liu, W. Y. Lin, X. H. Yu, J. J. Rodríguez-Andina, and H. J. Gao, “Approximation-free robust synchronization control for dual-linear-motors-driven systems with uncertainties and disturbances,” IEEE Trans. Industrial Electronics, vol. 69, no. 10, pp. 10500–10509, 2022. doi: 10.1109/TIE.2021.3137619
    [40]
    X. Luo, Z. G. Liu, S. Li, M. S. Shang, and Z. D. Wang, “A fast non-negative latent factor model based on generalized momentum method,” IEEE Trans. Systems,Man,and Cybernetics: Systems, vol. 51, no. 1, pp. 610–620, 2018.
    [41]
    X. Luo, H. Wu, H. Q. Yuan, and M. C. Zhou, “Temporal pattern-aware QoS prediction via biased non-negative latent factorization of tensors,” IEEE Trans. Cybernetics, vol. 50, no. 5, pp. 1798–1809, 2019.
    [42]
    X. Luo, M. C. Zhou, S. Li, Y. N. Xia, Z. H. You, Q. S. Zhu, and H. Leung, “Incorporation of efficient second-order solvers into latent factor models for accurate prediction of missing QoS data,” IEEE Trans. Cybernetics, vol. 48, no. 4, pp. 1216–1228, 2017.
    [43]
    L. F. Ma, Z. D. Wang, Y. Chen, and X. J. Yi, “Probability-guaranteed distributed filtering for nonlinear systems with innovation constraints over sensor networks,” IEEE Trans. Control of Network Systems, vol. 8, no. 2, pp. 951–963, 2021. doi: 10.1109/TCNS.2021.3049361
    [44]
    J. H. Suo, N. Li, and Q. Li, “Event-triggered H∞ state estimation for discrete-time delayed switched stochastic neural networks with persistent dwell-time switching regularities and sensor saturations,” Neurocomputing, vol. 455, pp. 297–307, 2021. doi: 10.1016/j.neucom.2021.01.131
    [45]
    P. Wen, X. Li, N. Hou, and S. Mu, “Distributed recursive fault estimation with binary encoding schemes over sensor networks,” Systems Science and Control Engineering, vol. 10, no. 1, pp. 417–427, 2022.
    [46]
    J. J. Yang, L. F. Ma, Y. G. Chen, and X. J. Yi, “l2−l∞ state estimation for continuous stochastic delayed neural networks via memory event-triggering strategy,” Int. J. Systems Science, vol. 53, no. 13, pp. 2742–2757, 2022. doi: 10.1080/00207721.2022.2055192
    [47]
    N. Y. Zeng, P. S. Wu, Z. D. Wang, H. Li, W. B. Liu, and X. H. Liu, “A small-sized object detection oriented multi-scale feature fusion approach with application to defect detection,” IEEE Trans. Instrumentation and Measurement, vol. 71, p. 3507014, 2022.
    [48]
    J. Zhang, J. Song, J. Li, F. Han, and H. Zhang, “Observer-based non-fragile H∞-consensus control for multi-agent systems under deception attacks,” Int. J. Systems Science, vol. 52, no. 6, pp. 1223–1236, 2021. doi: 10.1080/00207721.2021.1884917
    [49]
    P. F. Zhao, H. J. Liu, G. He, and D. R. Ding, “Outlier-resistant l2–l∞ state estimation for discrete-time memristive neural networks with time-delays,” Systems Science and Control Engineering, vol. 9, no. 1, pp. 88–97, 2021.
    [50]
    Z. Z. Zhao, W. Qian, and X. Z. Xu, “Stability analysis for delayed neural networks based on a generalized free-weighting matrix integral inequality,” Systems Science and Control Engineering, vol. 9, no. s1, pp. 6–13, 2021.
    [51]
    L. Zou, Z. D. Wang, H. Geng, and X. H. Liu, “Set-membership filtering subject to impulsive measurement outliers: A recursive algorithm,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 2, pp. 377–388, 2021. doi: 10.1109/JAS.2021.1003826
    [52]
    H. W. Chen, Z. D. Wang, B. Shen, and J. L. Liang, “Model evaluation of the stochastic boolean control networks,” IEEE Trans. Autom. Control, vol. 67, no. 8, pp. 4146–4153, 2022. doi: 10.1109/TAC.2021.3106896
    [53]
    X. L. Wang, D. R. Ding, X. H. Ge, and Q.-L. Han, “Supplementary control for quantized discrete-time nonlinear systems under goal representation heuristic dynamic programming, IEEE Trans. Neural Networks and Learning Systems,” 2022. DOI: 10.1109/TNNLS.2022.3201521.
    • Related Articles
    • Supplements(0)

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(22)  / Tables(4)

    Get Citation
    PDF
    XML

    Article Metrics

    Article views (597) PDF downloads(45) Cited by()

    Highlights

    • In this paper, we propose a novel parameter-optimized recurrent attention network (PRAN) for the pipeline leakage detection, which can not only implement the adaptive optimization of network parameters, but also enlarge the contribution of normal-abnormal discrepancy, thereby further improving the detection accuracy
    • We present a novel particle swarm optimization (PSO)-optimized long short-term memory (LSTM) network for the pipeline leakage detection. In particular, the PSO algorithm can be seamlessly incorporated into the detection model by adopting a fitness function that is consistent with the LSTM. In this way, the selection of LSTM parameters is released from the dependency on expert experience, thus improving the performance of detection model
    • We introduce an anomaly-attention mechanism (AM) to excavate class discriminative information by weighting the hidden states, which is conducive to enlarging the normal-abnormal distinguishable discrepancy. The AM enhances the contribution of abnormal time points, which is capable of overcoming the poor generalization and enhancing the representational power of model
    • The proposed PRAN algorithm is successfully applied to the pipeline leakage detection. Experimental results demonstrate that the proposed model outperforms other existing methods in terms of accuracy and convergence

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return