MPFDT: A Fault and Anomaly Diagnosis Tool for PLC Controlled Manufacturing Systems

DC Field Value Language
dc.contributor.advisorGi-Nam Wang-
dc.contributor.authorARUP GHOSH-
dc.date.accessioned2022-11-29T02:31:59Z-
dc.date.available2022-11-29T02:31:59Z-
dc.date.issued2018-08-
dc.identifier.other27756-
dc.identifier.urihttps://dspace.ajou.ac.kr/handle/2018.oak/19470-
dc.description학위논문(박사)--아주대학교 일반대학원 :산업공학과,2018. 8-
dc.description.tableofcontentsCONTENTS CHAPTER 1. INTRODUCTION CHAPTER 2. BACKGROUND STUDY AND LITERATURE REVIEW Section 2.1. Decentralized Fault Diagnosis Approaches Section 2.2. Centralized Fault Diagnosis Approaches CHAPTER 3. MPFDT: SYSTEM OVERVIEW AND WORKING PRINCIPLE CHAPTER 4. MDSVTF MODEL FORMULATION AND FADI PROCEDURE Section 4.1. Theoretical MDSVTF automaton model and its practical applications Section 4.2. Integrating the trend information of the continuously varying analog I/O signals into the MDSVTF model Section 4.3. The fault and anomaly detection and isolation procedure of MPFDT (based on the MDSVTF automaton model) CHAPTER 5. THE POWER CONSUMPTION AND THE ANALOG I/O SIGNAL SEGMENTATION PROCEDURE, AND THE NEURAL NETWORK BASED SIGNAL DEVIATION DETECTION PROCEDURE Section 5.1. Brief Review of Related Works on Health Condition Monitoring of Industrial Machines Section 5.2. The Analog PLC I/O Signal Segmentation Procedure Section 5.3. The Power Consumption Signal Segmentation Procedure Section 5.4. The Autoassociative Neural Network (AANN) Based Time Series Signal Deviation Detectors CHAPTER 6. CONCLUSION AND FUTURE WORK REFERENCES Appendix I: Transition Time Clustering Algorithm Appendix II: Experimental Study, Results, and Discussion-
dc.language.isoeng-
dc.publisherThe Graduate School, Ajou University-
dc.rights아주대학교 논문은 저작권에 의해 보호받습니다.-
dc.titleMPFDT: A Fault and Anomaly Diagnosis Tool for PLC Controlled Manufacturing Systems-
dc.typeThesis-
dc.contributor.affiliation아주대학교 일반대학원-
dc.contributor.department일반대학원 산업공학과-
dc.date.awarded2018. 8-
dc.description.degreeDoctoral-
dc.identifier.localId887786-
dc.identifier.uciI804:41038-000000027756-
dc.identifier.urlhttp://dcoll.ajou.ac.kr:9080/dcollection/common/orgView/000000027756-
dc.subject.keywordArtificial neural network (ANN)-
dc.subject.keywordelectrical energy usage monitoring-
dc.subject.keywordfault detection and isolation-
dc.subject.keywordindustrial process monitoring-
dc.subject.keywordprogrammable logic controller (PLC)-
dc.description.alternativeAbstractThe Fault and Anomaly Detection and Isolation (FADI) in Programmable Logic Controller (PLC) controlled systems is an important and challenging problem. In this thesis, we present an automated tool, called the Manufacturing Process Failure Diagnosis Tool (MPFDT) that can detect and isolate the faults and anomalies in the PLC controlled manufacturing systems effectively. MPFDT utilizes two independent knowledge-based process behaviour models of the manufacturing system to satisfy the FADI purpose. The fundamental idea is to detect the inconsistencies between the modelled and the observed manufacturing process behaviour. The first model is a Deterministic Finite-state Automaton (DFA) based control process model of the manufacturing system that is used to determine whether the observed state transition behaviour of the PLC control process is consistent with the modelled state transition behaviour or not. The second model is basically a set of Artificial Neural Network (ANN) based one-class classifiers that are used to identify whether any significant difference exist between the observed and the reference electrical power consumption profile of the manufacturing system or not. The experimental results show that the FADI accuracy rate of the proposed tool is very high (more than 98%).-
Appears in Collections:
Special Graduate Schools > Graduate School of Science and Technology > Department of Industrial Engineering > 4. Theses(Ph.D)
Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse