期刊文献+

基于聚类神经网络算法的故障诊断系统研究 被引量:5

Study on Fault Diagnosis System Based on FCM-ANN Algorithm
下载PDF
导出
摘要 以化工行业生产设备的故障诊断为研究背景,探讨了故障诊断的研究现状和研究方法。为了提高故障诊断的准确度,将模糊C均值算法与神经网络相结合,提出了基于聚类神经网络(FCM-ANN)算法的故障诊断方法。该故障诊断方法能显著降低数据集的复杂度,在一定程度上减轻了神经网络学习的压力。与传统的神经网络方法相比,该故障诊断方法的诊断率有了较大提高,误报率和漏报率也较低,诊断效果较为显著。对该故障诊断方法的有效性和实用性进行了验证,即在某化工企业故障诊断系统平台上进行了测试和使用。将该故障诊断方法运用到该企业的故障诊断系统中,从数据采集、数据处理出发,对如何在系统中使用FCM-ANN算法进行了阐述。运行结果表明,该系统提高了系统的准确率,增强了系统的实用性。 The current research status and methods of fault diagnosis are discussed based on the research background of fault diagnosis of production equipment in chemical industry. In order to improve the accuracy of fault diagnosis,by combining the Fuzzy C-means algorithm with artificial neural network( FCM-ANN) the fault diagnosis method based on FCM-ANN algorithm is proposed. The fault diagnosis method can significantly reduce the complexity of the data set and relieve the pressure of neural network learning to some extent. Compared with the traditional neural network methods,this fault diagnosis method has a higher diagnosis rate,and lower false alarm rate and missing alarm,and the diagnosis effect is more significant. The validity and practicability of the proposed fault diagnosis method is conducted,which is implemented on the fault diagnosis system platform of a certain chemical enterprise. The algorithm is applied to the fault diagnosis system of the enterprise platform,from data acquisition,data processing,how to use FCM-ANN algorithm in the system are expounded. The results of system operation show that this research improves the system accuracy and enhances the system practicality.
作者 陶雯 朱月 李荣雨 TAO Wen;ZHU Yue;LI Rongyu(College of Mathematics and Information Technology,Jiangsu Second Normal University,Nanjing 210013,China;College of Computer Science and Technology,Nanjing Tech University,Nanjing 211816,China)
出处 《自动化仪表》 CAS 2018年第7期24-28,33,共6页 Process Automation Instrumentation
基金 江苏省教育厅自然科学基金资助项目(12KJB510007)
关键词 模糊C均值 神经网络 三层架构模型 化工设备 模糊聚类 故障诊断 Fuzzy C-means (FCM) Neural network Three layer architecture model Chemical equipment Fuzzy clustering Fault diagnosis
  • 相关文献

参考文献4

二级参考文献137

  • 1闵睿,许黎明,魏臣隽,胡德金.机械加工系统运行状态异常检测方法的研究[J].仪器仪表学报,2006,27(z3):1777-1778. 被引量:9
  • 2杨善林,李永森,胡笑旋,潘若愚.K-MEANS算法中的K值优化问题研究[J].系统工程理论与实践,2006,26(2):97-101. 被引量:191
  • 3Solice P., Krogh A.. Learning with ensembles: How over-Fiting can be useful. In: Touretzky D., Mozer M., Hasselmo M. eds.. Advances in Neural Information Processing Systems, 1995, 7: 231~238.
  • 4Schapire R.E.. The strength of weak learnability. Machine Learning, 1990, 5(2): 197~227.
  • 5Friedman L.. Bagging predictors. Machine Learning, 1996, 24(2): 123~140.
  • 6Jang M., Cho S.. Observational learning algorithm for an ensemble of neural networks. Pattern Analysis & Applications, 2002, 5: 154~167.
  • 7Zhou Z.-H., Wu J.-X., Tang W.. Ensemble neural networks: Many could be better than all. Artificial Intelligence, 2002, 137(1~2): 239~263.
  • 8Zhou Z.-H., Wu J.-X., Tang W., Chen Z.-Q.. Combining regression estimator: GA-based selective neural network Ensemble. International Journal of Computational Intelligence and Applications, 2001, 1(4): 341~356.
  • 9Perrone M.P., Cooper L.N.. When networks disagree: Ensemble method for neural networks. In: Mammone R.J. eds.. Artificial Neural Networks for Speed and Vision, New York: Chapman & Hall, 1993, 126~142.
  • 10Opitz D., Shavlik J.. Actively searching for an efficient neural network ensemble. Connection Science, 1996, 8(3~4): 337~353.

共引文献156

同被引文献56

引证文献5

二级引证文献12

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部