Learning material flow models for manufacturing plants from data traces

Models describing the material flow of discrete manufacturing systems are important documentation artefacts and the basis for a comprehensive understanding of the underlying processes. The analysis of such models allows deriving important key performance indicators enabling the assessment of the current system implementation. However, manual modeling as well as up-to-date model maintenance is an error-prone and costly task. In an effort to allow for the automatic derivation of material flow models, this paper introduces the concept of Material Flow Petri Nets (MFPNs) and presents a learning algorithm for their automatic generation based on recorded PLC I/O data. The proposed algorithm has been evaluated on a case study of a laboratory plant with successful results.

[1]  Birgit Vogel-Heuser,et al.  Researching Evolution in Industrial Plant Automation: Scenarios and Documentation of the Pick and Place Unit , 2014 .

[2]  Kristina Säfsten,et al.  Production Development: Design and Operation of Production Systems , 2009 .

[3]  Simon Peck,et al.  Practice of Petri Nets in Manufacturing , 1993 .

[4]  Winfried Lamersdorf,et al.  Operationalized definitions of non-functional requirements on automated production facilities to measure evolution effects with an automation system , 2013, 2013 IEEE 18th Conference on Emerging Technologies & Factory Automation (ETFA).

[5]  Surendra M. Gupta,et al.  Petri net models of flexible and automated manufacturing systems : a survey , 1996 .

[6]  Dimitri Lefebvre,et al.  Stochastic Petri Net Identification for the Fault Detection and Isolation of Discrete Event Systems , 2011, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[7]  Chris Aldrich,et al.  Unsupervised Process Monitoring and Fault Diagnosis with Machine Learning Methods , 2013, Advances in Computer Vision and Pattern Recognition.

[8]  J. M. A Tanchoco.  Material Flow Systems in Manufacturing , 2012 .

[9]  Birgit Vogel-Heuser,et al.  Challenges for Software Engineering in Automation , 2014 .

[10]  Andreas Grimmer,et al.  Behavioral model synthesis of PLC programs from execution traces , 2014, Proceedings of the 2014 IEEE Emerging Technology and Factory Automation (ETFA).

[11]  Wolfgang Mahnke,et al.  OPC Unified Architecture , 2009, Autom..

[12]  Winfried Lamersdorf,et al.  Evolution Management of Production Facilities by Semi-Automated Requirement Verification , 2014, Autom..

[13]  Wil M. P. van der Aalst.  Process mining , 2012, CACM.

[14]  Yves Dallery,et al.  Manufacturing flow line systems: a review of models and analytical results , 1992, Queueing Syst. Theory Appl..

[15]  Benno Stein,et al.  Learning Behavior Models for Hybrid Timed Systems , 2012, AAAI.

[16]  Lothar Litz,et al.  Formal methods in PLC programming , 2000, Smc 2000 conference proceedings. 2000 ieee international conference on systems, man and cybernetics. 'cybernetics evolving to systems, humans, organizations, and their complex interactions' (cat. no.0.

[17]  Dawn M. Tilbury,et al.  Anomaly Detection Using Model Generation for Event-Based Systems Without a Preexisting Formal Model , 2012, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[18]  Alexander Fay,et al.  Integrating plant and process information as a basis for automated plant diagnosis tasks , 2014, Proceedings of the 2014 IEEE Emerging Technology and Factory Automation (ETFA).

[19]  Jean-Jacques Lesage,et al.  Black-box identification of discrete event systems with optimal partitioning of concurrent subsystems , 2010, Proceedings of the 2010 American Control Conference.

[20]  Matthias Damm,et al.  OPC Unified Architecture , 2009, Autom..