Gradient-based Reconfiguration of Cyber-Physical Production Systems

Cyber-physical production systems (CPPS) are susceptible to various faults like failing components or leaking connections. Even though CPPS have many possibilities to adapt to faults like using an alternative path or redundant hardware, the full potential is not exploited: Nowadays, the control software of CPPS is static and not able to adapt to unforeseen situations like an unknown fault. Hence, CPPS are not able to adapt to faults but a machine operator needs to reconfigure the system manually. Reconfiguration is the task of recovering valid system behavior after a fault has occurred. To enable CPPS to adapt autonomously to faults, automated reconfiguration is necessary. But since CPPS usually are dynamic systems consisting of interconnections of various components, identifying the necessary changes for reconfiguration is challenging: The effects of changes may only manifest after some time and lead to deviations in components far away from their root. This paper presents an approach on automated reconfiguration for CPPS, i.e. the automated recovery from faults. The approach is based on the usage of a logical calculus that reasons about the consequences of a fault and the possible adaptions. Therefore, the system is modeled in terms of logic. Gradient information is integrated to capture the system dynamics. The applicability of the algorithm is shown using a benchmark system from process engineering. Thus, CPPS are enabled to adapt to faults autonomously.

[1]  Pieter J. Mosterman,et al.  Derivative Estimation for Diagnosis , 1999 .

[2]  Lin Wang,et al.  Process configuration based on generative constraint satisfaction problem , 2017, J. Intell. Manuf..

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

[4]  S. Gentil,et al.  Combining FDI and AI approaches within causal-model-based diagnosis , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[5]  Jian Chen,et al.  Model-Based Fault Tolerant Control for the Thermal Management of PEMFC Systems , 2020, IEEE Transactions on Industrial Electronics.

[6]  László Monostori,et al.  ScienceDirect Variety Management in Manufacturing . Proceedings of the 47 th CIRP Conference on Manufacturing Systems Cyber-physical production systems : Roots , expectations and R & D challenges , 2014 .

[7]  Mykel J. Kochenderfer,et al.  Cooperative Multi-agent Control Using Deep Reinforcement Learning , 2017, AAMAS Workshops.

[8]  Tetsuo Tomiyama,et al.  Resilient architecture for cyber-physical production systems , 2018 .

[9]  Yoram Koren,et al.  Design of reconfigurable manufacturing systems , 2010 .

[10]  Krishna R. Pattipati,et al.  Probabilistic Graphical Models for Fault Diagnosis in Complex Systems , 2016 .

[11]  Daniele Theseider Dupré,et al.  A Spectrum of Definitions for Temporal Model-Based Diagnosis , 1998, Artificial Intelligence.

[12]  Kerstin Vännman,et al.  Process capability indices for one-sided specification intervals and skewed distributions , 2007, Qual. Reliab. Eng. Int..

[13]  Qing-Long Han,et al.  An Overview of Recent Advances in Fixed-Time Cooperative Control of Multiagent Systems , 2018, IEEE Transactions on Industrial Informatics.

[14]  Steven X. Ding,et al.  Fault-Tolerant Control for Systems With Model Uncertainty and Multiplicative Faults , 2020, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[15]  Amedeo Cesta,et al.  A Planning-Based Architecture for a Reconfigurable Manufacturing System , 2016, ICAPS.

[16]  Johan de Kleer,et al.  Hybrid modeling: Applications in real-time diagnosis , 2020, ArXiv.

[17]  Benjamin Kuipers,et al.  The Limits of Qualitative Simulation , 1985, IJCAI.

[18]  P. Gawthrop,et al.  Bond-graph modeling , 2007, IEEE Control Systems.

[19]  Brendan Juba,et al.  Safe Partial Diagnosis from Normal Observations , 2019, AAAI.

[20]  Bernhard Nebel,et al.  A Planning Based Framework for Controlling Hybrid Systems , 2012, ICAPS.

[21]  Antonio Celesti,et al.  An Ontology-Based Resource Reconfiguration Method for Manufacturing Cyber-Physical Systems , 2018, IEEE/ASME Transactions on Mechatronics.

[22]  Oliver Niggemann,et al.  A Concept for the Automated Reconfiguration of Quadcopters , 2020, LWDA.

[23]  Hongjing Liang,et al.  Observer-Based Adaptive Fuzzy Fault-Tolerant Control for Stochastic Nonstrict-Feedback Nonlinear Systems With Input Quantization , 2019, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[24]  Carlos Alonso González,et al.  Possible conflicts: a compilation technique for consistency-based diagnosis , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[25]  Matthias Schneider,et al.  A Cyber-Physical Failure Management System for Smart Factories , 2019 .

[26]  Nikolaj Bjørner,et al.  Satisfiability Modulo Theories: An Appetizer , 2009, SBMF.

[27]  Johan de Kleer,et al.  A Qualitative Physics Based on Confluences , 1984, Artif. Intell..

[28]  Nikolaj Bjørner,et al.  Z3: An Efficient SMT Solver , 2008, TACAS.

[29]  Oliver Niggemann,et al.  Data-driven Identification of Causal Dependencies in Cyber-Physical Production Systems , 2019, ICAART.

[30]  C. A. van Luttervelt,et al.  Toward a resilient manufacturing system , 2011 .

[31]  Martin Buss,et al.  Nonlinear Hybrid Dynamical Systems: Modeling, Optimal Control, and Applications , 2002 .

[32]  G. Ferrari-Trecate,et al.  Reconfiguration strategies for hybrid systems , 2001, Proceedings of the 2001 American Control Conference. (Cat. No.01CH37148).

[33]  Leonid I. Perlovsky,et al.  Conundrum of Combinatorial Complexity , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[34]  Benjamin J. Kaipers,et al.  Qualitative Simulation , 1989, Artif. Intell..