Fault diagnosis of gas turbines with thermodynamic analysis restraining the interference of boundary conditions based on STN

Abstract Gas turbines are widely used in natural gas-fired power generation and long-distance natural gas pipelines. The complexity and diversity of boundary conditions usually have a great influence on the measurement parameters, which makes them difficult to reflect the actual health status of gas turbines and leads to lower diagnostic accuracy. In the gas path analysis of gas turbines, traditional mechanism and data-driven methods are difficult to consider the interference of boundary conditions. A novel fault diagnostic method deriving from the spatial transformer network (STN) is proposed to restrain the influences of boundary conditions on fault diagnostic results. It can realize fault detection with higher accuracy by converting different boundary conditions to a designed one. The established STN is then combined with the typical small deviation (SD) theory and a classification network to complete the gas path analyses. The proposed two methods are verified and compared with traditional methods through simulation experiments and field data. Compared with the traditional SD method, the fault detection accuracy is increased by 2.92% in the STN-SD method, and the STN-MLP method improves the diagnostic accuracy by 5.24%. The proposed two methods also have good performance in the field data analysis and realize fast fault detection and early warning. This work provides a reliable way to detect faults subjecting to the influence of complex boundary conditions and provides reference and support for the fault diagnosis of other thermodynamic systems.

[1]  Kun Yu,et al.  A Combined Polynomial Chirplet Transform and Synchroextracting Technique for Analyzing Nonstationary Signals of Rotating Machinery , 2020, IEEE Transactions on Instrumentation and Measurement.

[2]  Mohammadreza Tahan,et al.  Performance-based health monitoring, diagnostics and prognostics for condition-based maintenance of gas turbines: A review , 2017 .

[3]  Anindya Ghoshal,et al.  Compressible flows on moving domains: Stabilized methods, weakly enforced essential boundary conditions, sliding interfaces, and application to gas-turbine modeling , 2017 .

[4]  Yi-Guang Li,et al.  Gas Turbine Performance and Health Status Estimation Using Adaptive Gas Path Analysis , 2010 .

[5]  William Y. Svrcek,et al.  The effect of major parameters on simulation results of gas pipelines , 2007 .

[6]  Andrew Zisserman,et al.  Spatial Transformer Networks , 2015, NIPS.

[7]  Babak Nadjar Araabi,et al.  Data driven sensor and actuator fault detection and isolation in wind turbine using classifier fusion , 2018 .

[8]  Huisheng Zhang,et al.  A Dynamic Reliability-Centered Maintenance Analysis Method for Natural Gas Compressor Station Based on Diagnostic and Prognostic Technology , 2016 .

[9]  Mustafa Demetgul,et al.  Thermal analysis MLP neural network based fault diagnosis on worm gears , 2016 .

[10]  Dengji Zhou,et al.  A Damage Evaluation Model of Turbine Blade for Gas Turbine , 2016 .

[11]  Riti Singh,et al.  An Integrated Fault Diagnostics Model Using Genetic Algorithm and Neural Networks , 2006 .

[12]  Ricardo Martinez-Botas,et al.  Performance prediction of a nozzled and nozzleless mixed-flow turbine in steady conditions , 2011 .

[13]  Roger Z. Ríos-Mercado,et al.  Optimization problems in natural gas transportation systems. A state-of-the-art review , 2015 .

[14]  Hanqing Lu,et al.  Pixelwise Deep Sequence Learning for Moving Object Detection , 2019, IEEE Transactions on Circuits and Systems for Video Technology.

[15]  Mohamed Talaat,et al.  A hybrid model of an artificial neural network with thermodynamic model for system diagnosis of electrical power plant gas turbine , 2018, Eng. Appl. Artif. Intell..

[16]  Huisheng Zhang,et al.  Fault diagnosis of gas turbine based on partly interpretable convolutional neural networks , 2020, Energy.

[17]  Huisheng Zhang,et al.  A gas path fault diagnostic model of gas turbines based on changes of blade profiles , 2020 .

[18]  Stephan Staudacher,et al.  Assessment of Gas Turbine and Combined Cycle Power Plant Performance Degradation , 2011 .

[19]  Pedram Ghamisi,et al.  LiDAR Data Classification Using Spatial Transformation and CNN , 2019, IEEE Geoscience and Remote Sensing Letters.

[20]  Madjid Soltani,et al.  Performance improvement of gas turbines of Fars (Iran) combined cycle power plant by intake air cooling using a media evaporative cooler , 2007 .

[21]  Dimitri N. Mavris,et al.  A Fault Diagnosis Method for Industrial Gas Turbines Using Bayesian Data Analysis , 2010 .

[22]  Lin Lin,et al.  A novel gas turbine fault diagnosis method based on transfer learning with CNN , 2019, Measurement.

[23]  Yi-Guang Li,et al.  Rough Set Diagnostic Frameworks for Gas Turbine Fault Classification , 2013 .

[24]  Weng Shi-lie.  A New Algorithm Method of Gas Turbine Gas Path Diagnosis , 2008 .

[25]  L. A. Urban.  Parameter Selection for Multiple Fault Diagnostics of Gas Turbine Engines , 1975 .

[26]  Riti Singh,et al.  Aero-engine turbine blade life assessment using the Neu/Sehitoglu damage model , 2014 .

[27]  Hyung Hee Cho,et al.  Thermo-structural analysis of cracks on gas turbine vane segment having multiple airfoils , 2017 .

[28]  G. Krishnaiah,et al.  Neural network approach for a combined performance and mechanical health monitoring of a gas turbine engine , 2012 .

[29]  Riti Singh,et al.  Gas Turbine Engine and Sensor Fault Diagnosis Using Optimization Techniques , 2002 .

[30]  Juan Antonio Álvarez,et al.  Deep neural network for traffic sign recognition systems: An analysis of spatial transformers and stochastic optimisation methods , 2018, Neural Networks.

[31]  Min Chen,et al.  Transfer-learning based gas path analysis method for gas turbines , 2019, Applied Thermal Engineering.

[32]  K. Mathioudakis,et al.  Enhanced Fault Localization Using Probabilistic Fusion With Gas Path Analysis Algorithms , 2008 .

[33]  Dries Verstraete,et al.  Impact of heat transfer on the performance of micro gas turbines , 2015 .

[34]  A. G. Stamatis,et al.  Evaluation of gas path analysis methods for gas turbine diagnosis , 2011 .

[35]  Huisheng Zhang,et al.  A New Gas Path Fault Diagnostic Method of Gas Turbine Based on Support Vector Machine , 2015 .

[36]  Xu Li,et al.  Deep learning-based adversarial multi-classifier optimization for cross-domain machinery fault diagnostics , 2020 .

[37]  Tomaž Katrašnik.  Improved model to determine turbine and compressor boundary conditions with the method of characteristics , 2006 .

[38]  K. Khorasani,et al.  Fault detection and isolation of gas turbine engines using a bank of neural networks , 2015 .

[39]  Feng Lu,et al.  Gas Path On-line Fault Diagnostics Using a Nonlinear Integrated Model for Gas Turbine Engines , 2014 .

[40]  Daniele Cocco,et al.  Performance evaluation of chemically recuperated gas turbine (CRGT) power plants fuelled by di-methyl-ether (DME) , 2006 .

[41]  Praveen Linga,et al.  Review of natural gas hydrates as an energy resource: Prospects and challenges ☆ , 2016 .

[42]  Daren Yu,et al.  Mechanism and influencing factors analysis of flowing instability of supercritical endothermic hydrocarbon fuel within a small-scale channel , 2014 .

[43]  Guo Yan Feng,et al.  The Time-Frequency Analysis Method Based on EMD White Noise Energy Density Distribution Characteristics of the Internal Combustion Engine Vibration , 2013 .

[44]  Md. Mustafizur Rahman,et al.  Development of renewable energy sector in Bangladesh: Current status and future potentials , 2017 .

[45]  Coriolano Salvini,et al.  Neural management for heat and power cogeneration plants , 2006, Eng. Appl. Artif. Intell..

[46]  Nan Zhou,et al.  China's energy and emissions outlook to 2050: Perspectives from bottom-up energy end-use model , 2013 .

[47]  S. I. Gilani,et al.  Gas turbine gas-path fault identification using nested artificial neural networks , 2018, Aircraft Engineering and Aerospace Technology.

[48]  O. J. Venturini,et al.  A new methodology of thermodynamic diagnosis, using the thermoeconomic method together with an artificial neural network (ANN): A case study of an externally fired gas turbine (EFGT) , 2017 .

[49]  Riti Singh,et al.  Improved Multiple Point Nonlinear Genetic Algorithm Based Performance Adaptation Using Least Square Method , 2012 .

[50]  Peter J. Fleming,et al.  Gas turbine engine prognostics using Bayesian hierarchical models: A variational approach , 2016 .

[51]  Dong Wang,et al.  Adaptive deep feature learning network with Nesterov momentum and its application to rotating machinery fault diagnosis , 2018, Neurocomputing.

[52]  K. Mathioudakis,et al.  Optimal measurement and health index selection for gas turbine performance status and fault diagnosis , 1992 .

[53]  Xu Li,et al.  Deep representation clustering-based fault diagnosis method with unsupervised data applied to rotating machinery , 2020 .

[54]  Subham Dawn,et al.  Novel prediction‐reliability based graphical DGA technique using multi‐layer perceptron network & gas ratio combination algorithm , 2019, IET Science, Measurement & Technology.

[55]  Chad M. Holcomb,et al.  Estimating Recoverable Performance Degradation Rates and Optimizing Maintenance Scheduling , 2018, Journal of Engineering for Gas Turbines and Power.

[56]  Bruno Facchini,et al.  Influence of Ambient Conditions on an Aeroderivative Gas Turbine Based Cogeneration Plant — A Comparison of Numerical Simulation With Field Performance Data , 2000 .

[57]  A. Ziaei-Asl,et al.  Thermo-mechanical behavior of gas turbine blade equipped with cooling ducts and protective coating with different thicknesses , 2019, International Journal of Mechanical Sciences.