The early-warning model of equipment chain in gas pipeline based on DNN-HMM

Abstract Since the operating state of the compressor unit could be influenced by several factors including connected pipeline, auxiliary system and other related equipment, it is necessary to treat the compressor unit as a sub-chain of the whole pipeline equipment chain. To deal with the indistinguishable phenomena in the compressor unit, including pipeline leakage, ice jam and auxiliary system failure, an innovative early-warning model based on analyses of characteristics of early-warning system and equipment chain is proposed in this thesis, which fully takes advantage of feature extraction of deep belief network (DNN) and hidden state analysis of hidden Markov model (HMM) to estimate the operating status of the compressor unit. Validated by field data, the model is demonstrated to be of preferable accuracy and generalization for early-warning of the equipment chain by results of experiments. Moreover, it is advantageous in terms of processing speed.

[1]  Diego J. Pedregal,et al.  Forecasting turbine problems by means of the state space framework , 2011 .

[2]  Oendrila Samanta,et al.  Smoothing of HMM parameters for efficient recognition of online handwriting , 2014, Pattern Recognit..

[3]  Alan F. Murray,et al.  Continuous restricted Boltzmann machine with an implementable training algorithm , 2003 .

[4]  Dong Yu,et al.  Investigation of full-sequence training of deep belief networks for speech recognition , 2010, INTERSPEECH.

[5]  Camille Couprie,et al.  Learning Hierarchical Features for Scene Labeling , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Amir F. Atiya,et al.  A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition , 2011, Expert Syst. Appl..

[7]  Kunikazu Kobayashi,et al.  Time series forecasting using a deep belief network with restricted Boltzmann machines , 2014, Neurocomputing.

[8]  Wei Liang,et al.  Fault diagnosis of pipeline and pump unit systems using status coupling analysis , 2015 .

[9]  M. Al Yahyai,et al.  Rotor dynamic response of a centrifugal compressor due to liquid carry over: A case study , 2014 .

[10]  P. Baruah,et al.  HMMs for diagnostics and prognostics in machining processes , 2005 .

[11]  L. Baum,et al.  Statistical Inference for Probabilistic Functions of Finite State Markov Chains , 1966 .

[12]  Dong Yu,et al.  Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition , 2012, IEEE Transactions on Audio, Speech, and Language Processing.

[13]  Stephen Ogaji,et al.  Evolution strategy for gas-turbine fault-diagnoses , 2005 .

[14]  Silvio Simani,et al.  Fault diagnosis of an industrial gas turbine prototype using a system identification approach , 2008 .

[15]  María Lourdes Borrajo Diz,et al.  An HMM-based over-sampling technique to improve text classification , 2013, Expert Syst. Appl..

[16]  Dexian Huang,et al.  Data-driven soft sensor development based on deep learning technique , 2014 .

[17]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[18]  Levent Burak Kara,et al.  Neural network-based symbol recognition using a few labeled samples , 2011, Comput. Graph..

[19]  Yan Liu,et al.  Discriminative deep belief networks for visual data classification , 2011, Pattern Recognit..

[20]  Andrew D. Ball,et al.  An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks , 2014, Expert Syst. Appl..

[21]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[22]  Noel Lopes,et al.  Towards adaptive learning with improved convergence of deep belief networks on graphics processing units , 2014, Pattern Recognit..

[23]  Ioannis M. Dokas,et al.  EWaSAP: An early warning sign identification approach based on a systemic hazard analysis , 2013 .

[24]  Pingfeng Wang,et al.  Failure diagnosis using deep belief learning based health state classification , 2013, Reliab. Eng. Syst. Saf..

[25]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[26]  Yongyong He,et al.  Hidden Markov model-based fault diagnostics method in speed-up and speed-down process for rotating machinery , 2005 .

[27]  Wei Liang,et al.  Coupling relations and early-warning for “equipment chain” in long-distance pipeline , 2013 .

[28]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[29]  Yoshua Bengio,et al.  Greedy Layer-Wise Training of Deep Networks , 2006, NIPS.