15405

13801

كارشناسي ارشد

كنترل

اصفهان : دانشگاه صنعتي اصفهان

1398

ده، 95ص. : مصور، جدول، نمودار

ايمان ايزدي

جعفر قيصري، جواد عسگري

1398/10/30

كتابنامه

برق

مهندسي برق و كامپيوتر

1398/11/01

2594271

Online Fault Identification Using Process Mining Techniques Ali Norouzifar ali noroozi@ec iut ac ir January 8 2020 Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language Farsi Supervisors Assist Prof Iman Izadi iman izadi@cc iut ac ir Abstract Development of industrial networks and computational power of automation systems in recent years have eliminatedmany previous limitations in collection and transferring of high volumes of data These data are stored for a long time Thisimmense volume of data in industrial automation systems is an abundant source of information With recent developments indata sciences and understanding importance of processing raw data tendency to use these concepts for processing industrialdata has increased Fault diagnosis and identification of fault propagation path are among the most important applicationsof analyzing industrial data Development of these solutions has important role in reducing accidents and failures andalso preventing financial life and environmental consequences For this purpose many different approaches have beenrecommended most of which make use of process variables Process variables data has some limitations for practicalapplications For instance industries compress this data source over time which cause loss of information Also theseapproaches usually have high computational load and should be in execution consistently In this research alarm data sourcefrom history of alarm management system has been used for introduction of new approach to fault diagnosis Proposedalgorithm makes use of process mining approaches for the final goal Process mining is still a young field related to datascience and mostly is used for analysis of event based databases First a framework for using process mining is introduced inwhich models are discovered for activated alarms due to known fault scenarios based on historical alarm data After choosingappropriate model according to evaluation metrics these models are used for online fault diagnosis Online conformancechecking using incremental prefix alignments is used to check conformance of activated alarms and discovered modelsfor fault scenarios Tennessee Eastman chemical process is used as a simulation of real chemical process to illustrateperformance of the algorithm An alarm management system for this process is designed in Matlab which produces alarmsfor known fault scenarios and stores them Online fault diagnosis algorithm is deployed with Python programing language Key Words Fault Identification Causalities Alarm Management System Process Mining ProcessModeling

ايمان ايزدي

جعفر قيصري، جواد عسگري