Artificial Intelligence for the Diagnostics of Gas Turbines—Part II: Neuro-Fuzzy ApproachSource: Journal of Engineering for Gas Turbines and Power:;2007:;volume( 129 ):;issue: 003::page 720DOI: 10.1115/1.2431392Publisher: The American Society of Mechanical Engineers (ASME)
Abstract: In the paper, neuro-fuzzy systems (NFSs) for gas turbine diagnostics are studied and developed. The same procedure used previously for the setup of neural network (NN) models (, , , and , 2007, ASME J. Eng. Gas Turbines Power, 129(3), pp. 711–719) was used. In particular, the same database of patterns was used for both training and testing the NFSs. This database was obtained by running a cycle program, calibrated on a 255MW single-shaft gas turbine working in the ENEL combined cycle power plant of La Spezia (Italy). The database contains the variations of the Health Indices (which are the characteristic parameters that are indices of gas turbine health state, such as efficiencies and characteristic flow passage areas of compressor and turbine) and the corresponding variations of the measured quantities with respect to the values in new and clean conditions. The analyses carried out are aimed at the selection of the most appropriate NFS structure for gas turbine diagnostics, in terms of computational time of the NFS training phase, accuracy, and robustness towards measurement uncertainty during simulations. In particular, adaptive neuro-fuzzy inference system (ANFIS) architectures were considered and tested, and their performance was compared to that obtainable by using the NN models. An analysis was also performed in order to identify the most significant ANFIS inputs. The results obtained show that ANFISs are robust with respect to measurement uncertainty, and, in all the cases analyzed, the performance (in terms of accuracy during simulations and time spent for the training phase) proved to be better than that obtainable by multi-input/multioutput (MIMO) and multi-input/single-output (MISO) neural networks trained and tested on the same data.
keyword(s): Flow (Dynamics) , Algorithms , Gas turbines , Testing , Errors , Measurement uncertainty , Interior walls , Compressors , Artificial neural networks , Turbines , Engineering simulation , Cycles , Fuzzy neural nets , Artificial intelligence AND Robustness ,
|
Show full item record
contributor author | R. Bettocchi | |
contributor author | M. Pinelli | |
contributor author | P. R. Spina | |
contributor author | M. Venturini | |
date accessioned | 2017-05-09T00:23:38Z | |
date available | 2017-05-09T00:23:38Z | |
date copyright | July, 2007 | |
date issued | 2007 | |
identifier issn | 1528-8919 | |
identifier other | JETPEZ-26960#720_1.pdf | |
identifier uri | http://yetl.yabesh.ir/yetl/handle/yetl/135698 | |
description abstract | In the paper, neuro-fuzzy systems (NFSs) for gas turbine diagnostics are studied and developed. The same procedure used previously for the setup of neural network (NN) models (, , , and , 2007, ASME J. Eng. Gas Turbines Power, 129(3), pp. 711–719) was used. In particular, the same database of patterns was used for both training and testing the NFSs. This database was obtained by running a cycle program, calibrated on a 255MW single-shaft gas turbine working in the ENEL combined cycle power plant of La Spezia (Italy). The database contains the variations of the Health Indices (which are the characteristic parameters that are indices of gas turbine health state, such as efficiencies and characteristic flow passage areas of compressor and turbine) and the corresponding variations of the measured quantities with respect to the values in new and clean conditions. The analyses carried out are aimed at the selection of the most appropriate NFS structure for gas turbine diagnostics, in terms of computational time of the NFS training phase, accuracy, and robustness towards measurement uncertainty during simulations. In particular, adaptive neuro-fuzzy inference system (ANFIS) architectures were considered and tested, and their performance was compared to that obtainable by using the NN models. An analysis was also performed in order to identify the most significant ANFIS inputs. The results obtained show that ANFISs are robust with respect to measurement uncertainty, and, in all the cases analyzed, the performance (in terms of accuracy during simulations and time spent for the training phase) proved to be better than that obtainable by multi-input/multioutput (MIMO) and multi-input/single-output (MISO) neural networks trained and tested on the same data. | |
publisher | The American Society of Mechanical Engineers (ASME) | |
title | Artificial Intelligence for the Diagnostics of Gas Turbines—Part II: Neuro-Fuzzy Approach | |
type | Journal Paper | |
journal volume | 129 | |
journal issue | 3 | |
journal title | Journal of Engineering for Gas Turbines and Power | |
identifier doi | 10.1115/1.2431392 | |
journal fristpage | 720 | |
journal lastpage | 729 | |
identifier eissn | 0742-4795 | |
keywords | Flow (Dynamics) | |
keywords | Algorithms | |
keywords | Gas turbines | |
keywords | Testing | |
keywords | Errors | |
keywords | Measurement uncertainty | |
keywords | Interior walls | |
keywords | Compressors | |
keywords | Artificial neural networks | |
keywords | Turbines | |
keywords | Engineering simulation | |
keywords | Cycles | |
keywords | Fuzzy neural nets | |
keywords | Artificial intelligence AND Robustness | |
tree | Journal of Engineering for Gas Turbines and Power:;2007:;volume( 129 ):;issue: 003 | |
contenttype | Fulltext |