A hybrid model of LSTM neural networks with a thermodynamic model for condition-based maintenance of compressor fouling

Compressor fouling is one of the critical gas path faults of gas turbines, and the fouling process is significantly influenced by the quality of the inlet air coming from the air intake system with filters. The maintenance strategies for compressor fouling mainly consist of online/offline washing and replacement of filters, where optimizing the washing cycles and the replacement of filters is essential for the economy and safety of gas turbine operation as of the trade-off between the performance improvement and the corresponding costs. By considering the filtration effects of the air intake system, the gas path analysis of the gas turbine is carried out to tackle the coupled fouling process, and a hybrid framework is presented to predict the washing cycle (remaining useful life prediction for washing) and detect filter leakage (diagnosis for filter) via integrating the thermodynamic model and long short-term memory (LSTM) neural networks. The proposed scheme is applied in a field dataset and the results show that: (i) a deterioration index based on the thermodynamic model can be used to evaluate the compressor fouling degree, which is independent of ambient conditions and control factors. (ii) A prediction model based on the LSTM-Hankel method demonstrates good performance in long-time washing cycle prediction. (iii) Air filter leakage will significantly increase the degradation rate of compressor efficiency, which can be identified by the diagnosis model to predict the new washing cycle.

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

[2]  Kenneth M. Bryden,et al.  Using Machine Learning Tools to Predict Compressor Stall , 2020 .

[3]  M.J. Roemer,et al.  Prognostic enhancements to gas turbine diagnostic systems , 2003, 2003 IEEE Aerospace Conference Proceedings (Cat. No.03TH8652).

[4]  Chao Liu,et al.  Deep Transfer Network with Joint Distribution Adaptation: A New Intelligent Fault Diagnosis Framework for Industry Application , 2018, ISA transactions.

[5]  Michael Pecht,et al.  Application of a state space modeling technique to system prognostics based on a health index for condition-based maintenance , 2012 .

[6]  J. Bons.  A Review of Surface Roughness Effects in Gas Turbines , 2010 .

[7]  A. Suman,et al.  Gas Turbine Fouling Tests: Review, Critical Analysis, and Particle Impact Behavior Map , 2018, Journal of Engineering for Gas Turbines and Power.

[8]  Ricardo Chacartegui,et al.  Determining compressor wash programmes for fouled gas turbines , 2009 .

[9]  Adel Alblawi,et al.  Fault diagnosis of an industrial gas turbine based on the thermodynamic model coupled with a multi feedforward artificial neural networks , 2020 .

[10]  Ying Chen,et al.  Enhancement of prognostic models for short-term degradation of gas turbines , 2017, 2017 IEEE International Conference on Prognostics and Health Management (ICPHM).

[11]  Haidong Shao,et al.  Ensemble transfer CNNs driven by multi-channel signals for fault diagnosis of rotating machinery cross working conditions , 2020, Knowl. Based Syst..

[12]  Fatih Camci,et al.  Physics-based prognostic modelling of filter clogging phenomena , 2016 .

[13]  Uyioghosa Igie,et al.  Impact of Inlet Filter Pressure Loss on Single and Two-Spool Gas Turbine Engines for Different Control Modes , 2014 .

[14]  Chao Liu,et al.  An adaptive spatiotemporal feature learning approach for fault diagnosis in complex systems , 2019, Mechanical Systems and Signal Processing.

[15]  Olav Bolland,et al.  Measured Data Correction for Improved Fouling and Degradation Analysis of Offshore Gas Turbines , 2004 .

[16]  Te Han,et al.  Deep transfer learning with limited data for machinery fault diagnosis , 2021, Appl. Soft Comput..

[17]  Cyrus B. Meher-Homji,et al.  The Fouling of Axial Flow Compressors: Causes, Effects, Susceptibility and Sensitivity , 2009 .

[18]  Ihor S. Diakunchak.  Performance Deterioration in Industrial Gas Turbines , 1992 .

[19]  Pericles Pilidis,et al.  Industrial Gas Turbine Performance: Compressor Fouling and On-Line Washing , 2014 .

[20]  Jing Lin,et al.  Transfer fault diagnosis of bearing installed in different machines using enhanced deep auto-encoder , 2020 .

[21]  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..

[22]  Shuying Li,et al.  Improved Method for Gas-Turbine Off-Design Performance Adaptation Based on Field Data , 2020 .

[23]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[24]  Onoufrios Haralampous,et al.  Approximate pressure drop and filtration efficiency expressions for semi-open wall-flow channels , 2014 .

[25]  Friederike C. Mund,et al.  Gas Turbine Compressor Washing: Historical Developments, Trends and Main Design Parameters for Online Systems , 2006 .

[26]  K. Yetilmezsoy,et al.  Modelling the clogging of gas turbine filter houses in heavy-duty power generation systems , 2020 .

[27]  Jingchao Li,et al.  Gas Turbine Gas Path Fault Diagnosis based on Adaptive Nonlinear Steady-State Thermodynamic Model , 2018 .

[28]  Lars E. Bakken,et al.  Filtration of Gas Turbine Intake Air in Offshore Installations: The Gap Between Test Standards and Actual Operating Conditions , 2009 .

[29]  Michele Pinelli,et al.  Artificial Intelligence for the Diagnostics of Gas Turbines—Part I: Neural Network Approach , 2007 .

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

[31]  Klaus Brun,et al.  Gas Turbine Tutorial - Maintenance And Operating Practices Effects On Degradation And Life. , 2007 .

[32]  Klaus Brun,et al.  Technology Review of Modern Gas Turbine Inlet Filtration Systems , 2012 .

[33]  Nina F. Thornhill,et al.  Adaptive detection and prediction of performance degradation in off-shore turbomachinery , 2020, Applied Energy.

[34]  Khashayar Khorasani,et al.  Dynamic neural network-based fault diagnosis of gas turbine engines , 2014, Neurocomputing.

[35]  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..

[36]  Min Chen,et al.  An Approach for Optimal Measurements Selection on Gas Turbine Engine Fault Diagnosis , 2015 .

[37]  Robert X. Gao,et al.  Markov Nonlinear System Estimation for Engine Performance Tracking , 2016 .

[38]  Michele Cagna,et al.  Economical Benefits of Highly Efficient Three-Stage Intake Air Filtration for Gas Turbines , 2008 .

[39]  Mohammad Hassan Saidi,et al.  Simulation of startup operation of an industrial twin-shaft gas turbine based on geometry and control logic , 2019, Energy.

[40]  A. P. Tarabrin,et al.  An Analysis of Axial Compressors Fouling and a Cleaning Method of Their Blading , 1996 .

[41]  Xu Li,et al.  A component map adaptation method for compressor modeling and diagnosis , 2018 .

[42]  Georgios Michailidis,et al.  Performance of Inlet Filtration System in Relation to the Uncaptured Particles Causing Fouling in the Gas Turbine Compressor , 2016 .

[43]  Jinfu Liu,et al.  Anomaly detection of gas turbines based on normal pattern extraction , 2020 .