Fault diagnosis expert system of semiconductor manufacturing equipment using a Bayesian network

It is well known that fault diagnosis is very important to improve the availability of semiconductor manufacturing equipment. But how to acquire, represent and reason the diagnosis and maintenance knowledge is the key of a fault diagnosis expert system. According to the features of the knowledge source, production rule was chosen as the knowledge representing method. And Bayesian network (BN) with improved causal relationship questionnaire and probability scale methods was proposed as inference machine to diagnose the possible root causes, corresponding probabilities and suggested solutions. Based on above methods, a fault diagnosis expert system was proposed, whose overall structure and key technologies, including knowledge acquisition, representation and inference methods were presented in detail. Furthermore, this expert system was designed by using Unified Modelling Language (UML) method and developed with MS VS.NET and SQL Server 2000. Two cases in a chipset assembly and test factory showed the inferring process by BN and validated the inferring result of the expert system, which proves it accurate and believable.

[1]  Silja Renooij,et al.  Talking probabilities: communicating probabilistic information with words and numbers , 1999, Int. J. Approx. Reason..

[2]  Yang Yu,et al.  Fault Diagnosis of Metro Shield Machine Based on Rough Set and Neural Network , 2010, 2010 Third International Conference on Intelligent Networks and Intelligent Systems.

[3]  Adel Alaeddini,et al.  Using Bayesian networks for root cause analysis in statistical process control , 2011, Expert Syst. Appl..

[4]  Mohamed A. A. Wahab,et al.  Bayesian Networks for Fault Diagnosis of a Large Power Station and its Transmission Lines , 2012 .

[5]  Sun Jin,et al.  A Bayesian network approach for fixture fault diagnosis in launch of the assembly process , 2012 .

[6]  Cheng-Lung Huang,et al.  Attribute Selection Based on Rough Set Theory for Electromagnetic Interference (EMI) Fault Diagnosis , 2006 .

[7]  Jianzhong Fu,et al.  Intelligent fault diagnosis using rough set method and evidence theory for NC machine tools , 2009, Int. J. Comput. Integr. Manuf..

[8]  J.-W. Li,et al.  Modelling a quality assurance information system for product development projects with the UML approach , 2007, Int. J. Comput. Integr. Manuf..

[9]  Wang Shuo,et al.  Using Expert's Knowledge to Build Bayesian Networks , 2007, 2007 International Conference on Computational Intelligence and Security Workshops (CISW 2007).

[10]  Michel Kinnaert,et al.  Fuzzy model-based fault detection and diagnosis for a pilot heat exchanger , 2011, Int. J. Syst. Sci..

[11]  James A. Stori,et al.  A Bayesian network approach to root cause diagnosis of process variations , 2005 .

[12]  Atthapol Ngaopitakkul,et al.  An application of a discrete wavelet transform and a back-propagation neural network algorithm for fault diagnosis on single-circuit transmission line , 2013, Int. J. Syst. Sci..

[13]  Béchir el Ayeb,et al.  IMIOL: A SYSTEM FOR INDEXING IMAGES BY THEIR SEMANTIC CONTENT BASED ON POSSIBILISTIC FUZZY CLUSTERING AND ADAPTIVE RESONANCE THEORY NEURAL NETWORKS LEARNING , 2010, Appl. Artif. Intell..

[14]  Silja Renooij,et al.  Evaluation of a verbal-numerical probability scale , 2003, Int. J. Approx. Reason..

[15]  Yinhua Liu,et al.  Application of Bayesian networks for diagnostics in the assembly process by considering small measurement data sets , 2013 .

[16]  R. Ganesh Narayanan,et al.  An expert system based on artificial neural network for predicting the tensile behavior of tailor welded blanks , 2009, Expert Syst. Appl..

[17]  Zhu Chang-an,et al.  Inference Method for Fault Diagnosis of Complex Systems Based on Bayesian Network , 2008, 2008 Second International Symposium on Intelligent Information Technology Application.

[18]  Sergio Mussati,et al.  Fault diagnosis for an MSF desalination plant by using Bayesian networks , 2010 .

[19]  Wen-Yau Liang,et al.  Rough Sets as a Knowledge Discovery and Classification Tool for the Diagnosis of Students with Learning Disabilities , 2011, Int. J. Comput. Intell. Syst..

[20]  Yao-Jung Shiao,et al.  An expert system for fault diagnosis in internal combustion engines using probability neural network , 2008, Expert Syst. Appl..

[21]  Lian-yun He.  Application of Bayesian Network in Power Grid Fault Diagnosis , 2008, 2008 Fourth International Conference on Natural Computation.