DEFECT DIAGNOSTICS OF POWER PLANT GAS TURBINE USING HYBRID SVM-ANN METHOD

被引：0

作者：

Lee, Sangmyeong ^{[1
]}

Lee, Sanghun ^{[1
]}

Lim, Juchang ^{[1
]}

Lee, Sangbin ^{[1
]}

机构：

[1] POSCO ENERGY, Inchon, South Korea

来源：

PROCEEDINGS OF THE ASME GAS TURBINE INDIA CONFERENCE 2012 | 2012年

关键词：

ARTIFICIAL NEURAL-NETWORKS; SUPPORT VECTOR MACHINES; FAULT-DIAGNOSIS; ALGORITHM;

D O I：

暂无

中图分类号：

TH [机械、仪表工业];

学科分类号：

0802 ;

摘要：

A hybrid method of an artificial neural network (ANN) combined with a support vector machine (SVM) has been developed for the defect diagnostic system applied to the power plant gas turbine. This method has been suggested to overcome the demerits of the general ANN with the local minima problem and low classification accuracy in case of many nonlinear data. This hybrid approach takes advantage of the reduction of learning data and converging time without any loss of estimation accuracy therefore it has been applied for the power plant monitoring system in order to detect fails and status of compressors and turbines in detail. The results have shown the suggested defect diagnostic algorithm has reliable and suitable efficiency estimation accuracy.

引用

页码：725 / 732

页数：8

共 50 条

[31] Anomaly Detection in Gas Turbine Fuel Systems Using a Sequential Symbolic Method [J].

Li, Fei ;

Wang, Hongzhi ;

Zhou, Guowen ;

Yu, Daren ;

Li, Jiangzhong ;

Gao, Hong .

ENERGIES, 2017, 10 (05)

[32] Exergy and exergoeconomic analysis and multi-objective optimisation of gas turbine power plant by evolutionary algorithms. Case study: Aliabad Katoul power plant [J].

Shamoushaki, Moein ;

Ghanatir, Farrokh ;

Ehyaei, M. A. ;

Ahmadi, Abolfazl .

INTERNATIONAL JOURNAL OF EXERGY, 2017, 22 (03) :279-307

[33] A hybrid method for increasing the speed of SVM training using belief function theory and boundary region [J].

Moslemnejad, Somaye ;

Hamidzadeh, Javad .

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2019, 10 (12) :3557-3574

[34] A Hybrid Method to Predict Postoperative Survival of Lung Cancer Using Improved SMOTE and Adaptive SVM [J].

Shen, Jiang ;

Wu, Jiachao ;

Xu, Man ;

Gan, Dan ;

An, Bang ;

Liu, Fusheng .

COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE, 2021, 2021

[35] Deterministic and Probabilistic Wind Power Forecasting Using a Hybrid Method [J].

Huang, Chao-Ming ;

Huang, Yann-Chang ;

Haung, Kun-Yang ;

Chen, Shin-Ju ;

Yang, Seng-Pei .

2017 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL TECHNOLOGY (ICIT), 2017, :400-405

[36] A Hybrid Multimodel-Based Condition Monitoring and Sensor Fault Detection Method for Aero Gas Turbine [J].

Chen, Xiaonan ;

Tong, Zhiwei ;

Liu, Yuan ;

Wang, Yishou ;

Qing, Xinlin .

IEEE SENSORS JOURNAL, 2024, 24 (20) :32729-32739

[37] Power quality disturbance analysis using data-driven EMD-SVM hybrid approach [J].

Malik, Hasmat ;

Almutairi, Abdulaziz ;

Alotaibi, Majed A. .

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2022, 42 (02) :669-678

[38] Target identification in foliage environment using UWB radar with hybrid wavelet-ICA and SVM method [J].

He, Xiangbo ;

Jiang, Ting .

PHYSICAL COMMUNICATION, 2014, 13 :197-204

[39] Research on fault diagnosis method and interpretability of nuclear power plant based on hybrid transformer model [J].

Zhou, Gui ;

Peng, Min-jun ;

Wang, Hang ;

Sun, Da-bin ;

Li, Zi-kang .

ANNALS OF NUCLEAR ENERGY, 2025, 213

[40] Optimal maintenance scheduling of a gas engine power plant using generalized disjunctive programming [J].

Castro, Pedro M. ;

Grossmann, Ignacio E. ;

Veldhuizen, Patrick ;

Esplin, Douglas .

AICHE JOURNAL, 2014, 60 (06) :2083-2097

← 1 2 3 4 5 →