Neural Network Monitoring Model for Industrial Gas Turbine
Keywords:Artificial neural network, Fault diagnosis system, Fault monitoring system, Gas turbine, Graphical user interface
Monitoring and diagnostic faults of industrial gas turbine are not an easy way by using conventional methods due to the nature and complexity of faults. Artificial neural network is considered an efficient tool to monitor and diagnose faults. In this paper, we proposed an efficient neural network model to monitor the gas turbine engine for on-line processing with aÂ twofold advantage. First, the model is able to diagnose the fault in case of uncertainty or corrupted data. Second, it can predict the extent of the deterioration of the performance efficiency of the turbine engine through a simple graphical user interface. The experiment has been done on five faulty conditions and the proposed neural network model tested with new dataset. The results have proven that, the proposed model produced satisfactory results with10-10 mean square error that considered optimal results when compared with training data sets.
Kumar, A., Marzia, Z., Nita, G., & Vineet, S, â€œRenewable Energy System Design by Artificial Neural Network Simulation Approachâ€. In Proceedings of IEEE Electrical Power and Energy(EPEC '14):142-147,2014.
Olausson, P, â€œOn the Selection of Methods and Tools for Analysis of Heat and Power Plantsâ€ , Division of Thermal Power engineering, Lund Institute of Technology, LUND, Sweden.P.O. Box 118, SE-221 00 ,2003.
Arriagada, J, â€œOn the Analysis and Fault-Diagnosis Tools for Small-Scale Heat and Power Plantsâ€ ,Thesis, Department of Heat and Power Engineering, Lund University, 2003.
Arriagada, J., Olausson, P., & Selimovic, A, â€œArtificial Neural Network Simulator for SOFC Performance Predictionâ€, Journal of Power Sources,112:54-60, 2002.
Shasha, W., Weimin, W., Yongqiang, S.,&Ya, Z, â€œGas Turbine Condition Monitoring and Prognosis: A Reviewâ€, Advanced Engineering Forum, 2-3 :694-699,2012 .
Young, K., Dimitri, N.,Vitali, V., Ming, Y., & Ted, F, â€œA Fault Diagnosis Method for Industrial Gas Turbines Using Bayesian Data Analysisâ€,Journal of Engineering for Gas Turbines and Power, Transactions of The ASME, 132(4),2010.
Hamid, A., XiaoQi, C., &Raazesh, S, â€œAnalysis of ANN-Based Modelling Approach for Industrial Systems â€, International Journal of Innovation, Management and Technology.4(1),2013.
Inseok, H., Sungwan, K., Youdan, K., &Chze, E, â€œA Survey of Fault Detection, Isolation, and Reconfiguration Methodsâ€, IEEE Trans. Contr. Sys. Tech, 18(3):636-653,2010.
Sobhani-Tehrani, E., &Khorasani, K, â€œFault diagnosis of nonlinear systems using a hybrid approach .Springerâ€, Berlin,chapter 2 Germany. Lecture Notes in Control and Information Sciences, no. 383,2009.
Assadi, M., Mesbahi, E., Torisson, T., Lindquist, T., Arriagada, J. ,&Olausson, P, â€œA Novel Correction Technique for Simple Gas Turbine Parametersâ€. In Proceedings of ASME Turbo Expo, USA ,GT-0009, 2001.
Nesma, A., Walaa, H., &Ghada, T, â€œPerformance Deterioration of Gas Turbine: Survey and Challenges Aheadâ€, International Journal of Engineering Research-Online 4(1),2016.
Mesbahi, E., Assadi, M., Torisson, T.,& Lindquist, T, â€œA Unique Correction Technique for Evaporative Gas Turbine (EvGT) Parametersâ€. Proceedings of the ASME Turbo Expo, USA.GT-0008,2001.
Arriagada, J., Genrup, M., Assadi, M.,&Loberg, A, â€œ Fault Diagnosis System for an Industrial Gas Turbine by Means of Neural Networksâ€, Proceedings of International Gas Turbine, Tokyo, Japan. TS-001:2-7, 2003.
Bourquin, J., Schmidli, H., van, H.,&Leuenberger, H, â€œ Advantages of Artificial Neural Networks (ANNs) as alternative modeling technique for data sets showing non-linear relationships using data from a galenical study on a solid dosage formâ€, European Journal of Pharmaceutical Sciences, 7(1):5â€“16, 1998.
Hamid, A., XiaoQi, C., Mohammad, B. M., &Raazesh, S, â€œANN-based system identification for industrial systems.Gas Turbines Modeling Simulation and Controlâ€. Advanced Materials Research, 622-623:611-617,2013.
Fast, M., Assadi, M.,& De, S. , â€œCondition based maintenance of gas turbines using simulation data and artificial neural network: A demonstration of feasibilityâ€, In Proceedings of The ASME Turbo Expo, USA 2: 153â€“161,2008.
Fast, M., PalmeÂ´, .T, &Genrup, M. â€œA novel approach for gas turbines monitoring combining CUSUM technique and artificial neural networkâ€. Proceedings of the ASME Turbo Expo, USA, 1: 567â€“574, 2009.
Arriagada, J., Constantini, M., Olausson, P., Assadi, M., &Torisson, T. â€œArtificial Neural Network Model for a Biomass-Fueled Boilerâ€ ,ASME. Turbo Expo 2:681-688,2003.
Simani, S., & Ron, J, â€œFault diagnosis of an industrial gas turbine prototype using a system identification approach, Control Engineering Practiceâ€,16(7):769â€“786,2008.
Guez, A., &Selinsky, J, â€œA neuromorphic controller with a human teacherâ€, IEEEInternational Conference on Neural Networks, 2:595-602,1988.
Tu, J. â€œAdvantages and Disadvantages of Using Artificial Neural Networks versus Logistic Regression for Predicting Medical Outcomesâ€, Journal of Clinical Epidemiology, 49(11): 1225-1231.1996.
Hamid, A. â€œModelling, Simulation and Control of Gas Turbines Using Artificial Neural Networksâ€. Ph.D. Thesis of Philosophy in Mechanical Engineering . University of Canterbury Christchurch, New Zealand, 2014.
Olausson, P., Haggstahl, D., Arriagada, J., Dahlquist ., Assadi, M, â€œ Hybrid model of an evaporative gas turbine power plant utilizing physical models and artificial neural networksâ€. Proceedings of the ASME Turbo Expo, USA.GT2003-38116,2003.
KrÃ¶se, B.,&Smagt, P, â€œAn introduction to neural networksâ€ .Eighth edition.The University of Amsterdam,1996.
Fast, M , â€œArtificial Neural Networks for Gas Turbine Monitoring â€, Ph.D. thesis. Sweden Lund,2010.
Fast, M., & Palme, T, â€œApplication of artiï¬cial neural networks to the condition monitoring and diagnosis of a combined heat and power plantâ€, Journal of Energy,35:1114-1120,2010.
Fast, M., Assadi, M., & De, S, â€œDevelopment and multi-utility of an ANN model for an industrial gas turbineâ€, Applied Energy, 86:9â€“17, 2009.
How to Cite
- Papers must be submitted on the understanding that they have not been published elsewhere (except in the form of an abstract or as part of a published lecture, review, or thesis) and are not currently under consideration by another journal published by any other publisher.
- It is also the authors responsibility to ensure that the articles emanating from a particular source are submitted with the necessary approval.
- The authors warrant that the paper is original and that he/she is the author of the paper, except for material that is clearly identified as to its original source, with permission notices from the copyright owners where required.
- The authors ensure that all the references carefully and they are accurate in the text as well as in the list of references (and vice versa).
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Attribution-NonCommercial 4.0 International that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
- The journal/publisher is not responsible for subsequent uses of the work. It is the author's responsibility to bring an infringement action if so desired by the author.