基于IABC-ANFIS的燃气轮机气路故障诊断
|
摘要
为了提高燃气轮机故障诊断的效果,提出了一种基于自适应模糊神经网络(Adaptive Network-based Fuzzy Inference System,ANFIS)和改进的人工蜂群算法(Improved artificial bee colony algorithm,IABC)的故障诊断方法:基于自适应模糊神经网络构建燃气轮机故障诊断模型。针对自适应模糊神经网络受聚类参数影响较大的问题,采用手榴弹爆炸原理改进的人工蜂群算法对这些参数进行优化。仿真结果表明,与未优化的ANFIS模型和ABC-ANFIS模型相比,IABC-ANFIS可以更稳定、准确地识别故障,为燃气轮机故障诊断提供实际参考。
In order to improve the gas turbine fault diagnosis,a fault diagnosis method based on adaptive fuzzy neural network( ANFIS) and improved artificial bee colony algorithm( IABC) is proposed. Firstly,a fault diagnosis model for gas turbine is constructed based on adaptive fuzzy neural network. Secondly,for the problem that the ANFIS model is greatly affected by the clustering parameters,the artificial bee colony algorithm improved by the grenade explosion principle is used to optimize these parameters. The simulation results show that compared with the traditional ANFIS model and ABC-ANFIS model,IABC-ANFIS can identify faults more stably and accurately,and provide practical reference for gas turbine fault diagnosis.
In order to improve the gas turbine fault diagnosis,a fault diagnosis method based on adaptive fuzzy neural network( ANFIS) and improved artificial bee colony algorithm( IABC) is proposed. Firstly,a fault diagnosis model for gas turbine is constructed based on adaptive fuzzy neural network. Secondly,for the problem that the ANFIS model is greatly affected by the clustering parameters,the artificial bee colony algorithm improved by the grenade explosion principle is used to optimize these parameters. The simulation results show that compared with the traditional ANFIS model and ABC-ANFIS model,IABC-ANFIS can identify faults more stably and accurately,and provide practical reference for gas turbine fault diagnosis.
引文
[1]高南兴.中国燃气轮机电站的发展[J].发电设备,2014,28(2):75-80.GAO Nan-xing.The development of Chinese gas turbine power station[J].Power Equipment,2014,28(2):75-80.
[2]王凤月.燃气轮机故障诊断技术综述展望[J].内燃机与配件,2017(19):63.WANG Feng-yue.Overview of gas turbine fault diagnosis technology[J].Internal Combustion Engines&Parts,2017(19):63.
[3]蒋东翔,刘超,杨文广,等.关于重型燃气轮机预测诊断与健康管理的研究综述[J].热能动力工程,2015,30(2):173-179.JIANG Dong-xiang,LIU Chao,YANG Wen-guang,et al.A review of research on predictive diagnosis and health management of heavy duty gas turbines[J].Journal of Engineering for Thermal Energy and Power,2015,30(2):173-179.
[4]MESKIN N,NADERI E,KHORASANI K.Nonlinear fault diagnosis of jet engines by using a multiple model-based approach[J].Journal of Engineering for Gas Turbines and Power,2011,13(1):63-75.
[5]JIANG R,ZHU W.APNN fault diagnosis method for gas turbine[J].World Automation Congress,2012:1-4.
[6]冉翀,屈卫东.基于模糊聚类的燃气轮机故障诊断[J].微型电脑应用,2009,25(6):38-40.RAN Chong,QU Wei-dong.Gas turbine fault diagnosis based on fuzzy clustering[J].Technology Exchange,2009,25(6):38-40.
[7]马继昌,司景萍,牛嘉骅,等.基于自适应模糊神经网络的发动机故障诊断[J].噪声与振动控制,2015,35(2):165-169.MA Ji-chang,SI Jing-ping,NIU Jia-hua,et al.Engine fault diagnosis based on adaptive fuzzy neural network[J].Noise and Vibration Control,2015,35(2):165-169.
[8]张海霞,徐娟.基于自适应模糊神经网络推理系统的齿轮箱故障诊断方法[J].机械与电子,2015(2):51-55.ZHANG Hai-xia,XU Juan.A gearbox fault diagnosis method based on adaptive fuzzy neural network inference system[J].Machinery&Electronics,2015(2):51-55.
[9]JANG J S R.ANFIS:adaptive-network-based fuzzy inference system[J].IEEE Trans on Smc,1993,23(3):665-685.
[10]KARABOGA D.An idea based on honey bee swarm for numerical optimization[R].Erciyes University,Engineering Faculty:Computer Engineering Department,2005.
[11]王雷.基于自适应神经模糊推理系统的三电平逆变器故障诊断研究[D].徐州:中国矿业大学,2015.WANG Lei.Research on fault diagnosis of three-level inverter based on adaptive neuro-fuzzy inference system[D].Xuzhou:China University of Mining and Technology,2015.
[12]韩宝如,邢益良,刘瑶利.基于Takagi-Sugeno型自适应模糊神经网络的模拟电路故障诊断[J].电子质量,2013(3):31-35.HAN Bao-ru,XING Yi-liang,LIU Yao-li.Analysis of analog circuit fault diagnosis based on takagi-sugeno adaptive fuzzy neural network[J].Electronics Quality,2013(3):31-35.
[13]陈安辉.基于GA-ANFIS的股指预测研究[D].哈尔滨:哈尔滨工业大学,2015.CHEN An-hui.Research on stock index forecast based on GA-ANFIS[D].Harbin:Harbin Institute of Technology,2015.
[14]邱正,钱玉良,张云,等.基于人工蜂群算法优化支持向量机的燃气轮机故障诊断[J].热能动力工程,2018(9):39-43.QIU Zheng,QIAN Yu-liang,ZHANG Yun,et al.Gas turbine fault diagnosis based on artificial bee colony algorithm optimized support vector machine[J].Journal of Engineering for Thermal Energy and Power,2018(9):39-43.
[15]魏锋涛,岳明娟,郑建明.基于改进邻域搜索策略的人工蜂群算法[J].控制与决策,2019,34(5):965-972.WEI Feng-tao,YUE Ming-juan,ZHENG Jian-ming.Artificial bee colony algorithm based on improved neighborhood search strategy[J].Control and Decision,2019,34(5):965-972.
[16]AHRARI A,SHARIAT-PANAHI M,ATAI A A.GEM:A novel evolutionary optimization method with improved neighborhood search[J].Applied Mathematics and Computation,2009,210(2):376-386.
[17]赵雄飞,刘永葆,贺星,等.基于小偏差方法的燃气轮机气路故障判据的建立[J].机械工程与自动化,2011(4):115-117.ZHAO Xiong-fei,LIU Yong-bao,HE Xing,et al.The establishment of gas turbine gas path fault criterion based on small deviation method[J].Mechanical Engineering&Automation,2011(4):115-117.
[2]王凤月.燃气轮机故障诊断技术综述展望[J].内燃机与配件,2017(19):63.WANG Feng-yue.Overview of gas turbine fault diagnosis technology[J].Internal Combustion Engines&Parts,2017(19):63.
[3]蒋东翔,刘超,杨文广,等.关于重型燃气轮机预测诊断与健康管理的研究综述[J].热能动力工程,2015,30(2):173-179.JIANG Dong-xiang,LIU Chao,YANG Wen-guang,et al.A review of research on predictive diagnosis and health management of heavy duty gas turbines[J].Journal of Engineering for Thermal Energy and Power,2015,30(2):173-179.
[4]MESKIN N,NADERI E,KHORASANI K.Nonlinear fault diagnosis of jet engines by using a multiple model-based approach[J].Journal of Engineering for Gas Turbines and Power,2011,13(1):63-75.
[5]JIANG R,ZHU W.APNN fault diagnosis method for gas turbine[J].World Automation Congress,2012:1-4.
[6]冉翀,屈卫东.基于模糊聚类的燃气轮机故障诊断[J].微型电脑应用,2009,25(6):38-40.RAN Chong,QU Wei-dong.Gas turbine fault diagnosis based on fuzzy clustering[J].Technology Exchange,2009,25(6):38-40.
[7]马继昌,司景萍,牛嘉骅,等.基于自适应模糊神经网络的发动机故障诊断[J].噪声与振动控制,2015,35(2):165-169.MA Ji-chang,SI Jing-ping,NIU Jia-hua,et al.Engine fault diagnosis based on adaptive fuzzy neural network[J].Noise and Vibration Control,2015,35(2):165-169.
[8]张海霞,徐娟.基于自适应模糊神经网络推理系统的齿轮箱故障诊断方法[J].机械与电子,2015(2):51-55.ZHANG Hai-xia,XU Juan.A gearbox fault diagnosis method based on adaptive fuzzy neural network inference system[J].Machinery&Electronics,2015(2):51-55.
[9]JANG J S R.ANFIS:adaptive-network-based fuzzy inference system[J].IEEE Trans on Smc,1993,23(3):665-685.
[10]KARABOGA D.An idea based on honey bee swarm for numerical optimization[R].Erciyes University,Engineering Faculty:Computer Engineering Department,2005.
[11]王雷.基于自适应神经模糊推理系统的三电平逆变器故障诊断研究[D].徐州:中国矿业大学,2015.WANG Lei.Research on fault diagnosis of three-level inverter based on adaptive neuro-fuzzy inference system[D].Xuzhou:China University of Mining and Technology,2015.
[12]韩宝如,邢益良,刘瑶利.基于Takagi-Sugeno型自适应模糊神经网络的模拟电路故障诊断[J].电子质量,2013(3):31-35.HAN Bao-ru,XING Yi-liang,LIU Yao-li.Analysis of analog circuit fault diagnosis based on takagi-sugeno adaptive fuzzy neural network[J].Electronics Quality,2013(3):31-35.
[13]陈安辉.基于GA-ANFIS的股指预测研究[D].哈尔滨:哈尔滨工业大学,2015.CHEN An-hui.Research on stock index forecast based on GA-ANFIS[D].Harbin:Harbin Institute of Technology,2015.
[14]邱正,钱玉良,张云,等.基于人工蜂群算法优化支持向量机的燃气轮机故障诊断[J].热能动力工程,2018(9):39-43.QIU Zheng,QIAN Yu-liang,ZHANG Yun,et al.Gas turbine fault diagnosis based on artificial bee colony algorithm optimized support vector machine[J].Journal of Engineering for Thermal Energy and Power,2018(9):39-43.
[15]魏锋涛,岳明娟,郑建明.基于改进邻域搜索策略的人工蜂群算法[J].控制与决策,2019,34(5):965-972.WEI Feng-tao,YUE Ming-juan,ZHENG Jian-ming.Artificial bee colony algorithm based on improved neighborhood search strategy[J].Control and Decision,2019,34(5):965-972.
[16]AHRARI A,SHARIAT-PANAHI M,ATAI A A.GEM:A novel evolutionary optimization method with improved neighborhood search[J].Applied Mathematics and Computation,2009,210(2):376-386.
[17]赵雄飞,刘永葆,贺星,等.基于小偏差方法的燃气轮机气路故障判据的建立[J].机械工程与自动化,2011(4):115-117.ZHAO Xiong-fei,LIU Yong-bao,HE Xing,et al.The establishment of gas turbine gas path fault criterion based on small deviation method[J].Mechanical Engineering&Automation,2011(4):115-117.