Holistic Context-Sensitivity for Run-Time Optimization of Flexible Manufacturing Systems
2. Research Question
- Monitoring of changes during run-time within a FMS (e.g., changing process parameters, environment in which the system is operating etc.), which can be used for further processing.
- Extraction of a current context based on monitored data to be used for knowledge creation, which can be used for (self-) optimization of manufacturing processes.
3. State of the Art
3.1. Context Sensitivity and Context Modelling
3.2. Cyber-Physical Systems
3.3. Service Oriented Architectures
4. Concept for Context Sensitivity
- Adaptation Learner and Context Learner: These services allow the system to learn. Key factor for the learning are the results of the Validator Services (operator’s feedback). These results are analyzed using data mining techniques and are used to improve the operation of the Context Extractor and the Context Sensitive Optimizer during run time (see also Section 5.4).
- Validator (for Context and Adaptation): These services are measuring the performance of optimization and context extraction. The measurement is either based on the manual feedback of the operator (e.g., acceptance of optimization proposals) or on statistical analysis in case the system operates in automatic mode. The results of the validator services are the key input for the learning services.
5.1. Context Model
- the generic device context model
- the domain specific and/or
- application-specific context model(s).
5.2. Context System Monitor
- Monitoring system/sensor module, which contains all services to monitor legacy systems and devices in enterprises vie the Data Access Layer. The distributed monitoring services also call back to this module with their gathered information. The monitoring services can be extended and configured for different data sources.
- Parser module, which contains content parser for the different possible data captured by the monitoring services. This module is parsing the content provided by the monitoring services so that it can be analyzed by the analyzer module. The parser can be extended and configured for different content provided by the monitoring services.
- Analyzer builder module, which correlates the monitored content and constructs the “Monitoring Data” to be stored and handed over to the Context Extractor or any other service that needs this information. The analyzer can be extended and configured for different content provided by the parser module.
5.3. Context Extractor
- Context Model—see Section 5.1 above. All features in the Context Extractor are based on this model.
- Context Monitoring—see Section 5.2 above. The Context Monitoring acts as a proxy between System Monitor and Context Identification.
- Context Identification module, which analyses the Monitoring Data handed over by the Context System Monitor and extracts knowledge context such as what products or components are involved, what resources are used, and what items, parts or units are referenced or manipulated in the current on-going context (see the text to follow).
- Context reasoning module, a rule based system which reasons on the context provided by the Context Identification module, and refines current identified contexts. This module also compares the similarity between the current on-going contexts and historical contexts in the model repository.
- System optimizer interface, which provides the results of the context extraction modules to other up-stream modules/services.
5.3.1. Context Identification
5.3.2. Context Reasoning
- Ontological Reasoning: based on the semantics of the ontology language and the definitions in the Context Model ontology the deductive reasoning is carried out, such as transitive reasoning and subsumption.
- Rule-based Reasoning: uses the deductive techniques as in the Ontological Context Reasoning, but with application-specific rules provided by users. Such application- or domain-specific rules could be provided by a domain expert or constructed based on a statistical analysis of historical data.
- Statistical Reasoning: does not rely on strict logical rules but instead tries to correlate information into possible relations, as suggested by the empirical data, to determine the most possible current context.
- sensori TRUE has value 1 or 0 depending is the value of the current signal at sensor i (e.g., temperature) satisfying the sub-rules associated to the sensori or not,
- n is the number of sensors relevant for the definition of concept j
- wi is the weighing of the sensor value in identification of the context concept j,
- mj is the margin to claim that the context concept j is true or not
- IF sensor1 true (a processing device has a valve attached to it), +
- sensor2 true (the valve is observed by pressure sensor which provides a resource identified as pressure in Bar) >2 THEN
- “The processing device is of type Mixing-Head” (w is 1 for both sensors in this case).
5.3.3. Context Similarity Measurement
- Current Context (CC): The Context (current situation) for which similarity with the context situations (cases) already stored in the database will be computed.
- Stored Context (SC): any of the previously stored context cases which are stored in the database, used for computing the similarity with CC.
- Raw Similarity (RS): the value of the absolute similarity between two entities before being weighted.
- Weighted Similarity (WS): the relative, i.e., weighted value of the similarity. The following equality stands: WS = RS * weight.
5.4. Optimizer and Self-Learning
6. Experimental Results
6.1. Energy Consumption Optimization
6.2. Availability and Efficiency Optimization at CPS Based FMS
- The time/efforts spent for building the both above described applications is estimated to be more than 60% less than time/efforts needed to build individual solution for each optimization.
- The biggest advantages are seen in maintenance and extensibility of the solution: if the processes and conditions change (which is often in FMS processes) the solution can be easily maintained/updated by extending the context model and perhaps adding/modifying certain monitoring services and rules for better context extraction and adaptation, but the overall structure of the optimization solution needs not to be changed. It is estimated that the costs for maintenance of such solution is more than 80% lower than for maintenance of classical solutions.
- The benefit is that the proposed solution can be applied for a number (all) of optimization processes within a factory, i.e., the company does not need to apply a high number of various solutions, which in turn may radically reduce development and maintenance costs of such solutions.
Conflicts of Interest
- Shah, N.B.; Viscito, L.; Wilds, J.; Ross, A.M.; Hastings, D.E. Quantifying Flexibility for Architecting Changeble Systems. In Proceedings of the 6th Conference on Systems Engineering Research, Los Angeles, CA, USA, 4–5 April 2008.
- Ross, A.M.; Rhodes, D.H.; Hastings, D.E. Defining changeability: Reconciling flexibility, adaptability, scalability, modifiability, and robustness for maintaining system lifecycle value. Syst Eng. 2008, 11, 246–262. [Google Scholar] [CrossRef]
- Stokic, D.; Scholze, S.; Kotte, O. Generic Self-Learning Context Sensitive Solution for Adaptive Manufacturing and Decision Making Systems. In Proceedings of the ICONS14—The Ninth International Conference on Systems, Nice, France, 23–27 February 2014.
- Scholze, S.; Barata, J. Context Awareness for Flexible Manufacturing Systems Using Cyber Physical Approaches. In Proceedings of the Technological Innovation for Cyber-Physical Systems: 7th IFIP WG 5.5/SOCOLNET Advanced Doctoral Conference on Computing, Electrical and Industrial Systems (DoCEIS 2016), Costa de Caparica, Portugal, 11–13 April 2016.
- Dey, A.K. Understanding and Using Context. Pers. Ubiquitous Comput. J. 2001, 1, 4–7. [Google Scholar] [CrossRef]
- Scholze, S.; Stokic, D.; Kotte, O. Cross-domain methods and tools for decision support services based on context sensitivity approach. In Proceedings of the 12th IEEE International Conference on Industrial Informatics—INDIN, Porto Alegre, Brazil, 27–30 July 2014.
- Feng, L.; Apers, P.; Jonker, W. Towards context-aware data management for ambient intelligence. In Proceedings of the 15th International Conference, DEXA 2004, Zaragoza, Spain, 30 August –3 September 2004.
- Brézillon, P.; Gonzalez, A.J. Context in Computing—A Cross-Disciplinary Approach for Modeling the Real World; Springer Science + Business Media: New York, NY, USA, 2014. [Google Scholar]
- Uddin, M.K.; Puttonen, J.; Scholze, S.; Dvoryanchikova, A.; Lastra, J.L.M. Ontology-based context-sensitive computing for FMS optimization. Assem. Autom. 2012, 32, 163–174. [Google Scholar] [CrossRef]
- Bittencourt, J.L.; Bonefeld, R.; Scholze, S.; Stokic, D.; Uddin, M.K.; Lastra, J. Energy efficiency improvement through context sensitive self-learning of machine availability. In Proceedings of the 9th IEEE International Conference on Industrial Informatics, Lisbon, Portugal, 26–29 July 2011.
- Chungooraa, N.; Younga, R.I.; Gunendranb, G.; Palmera, C.; Usmana, Z.; Anjuma, N.A.; Cutting-Decellec, A.-F.; Hardinga, J.A.; Casea, K. A model-driven ontology approach for manufacturing system interoperability and knowledge sharing. Comput. Ind. 2013, 64, 392–401. [Google Scholar] [CrossRef]
- Evchina, Y.; Dvoryanchikova, A.; Martinez, J. Ontological framework of context-aware and reasoning middleware for smart homes with health and social services, Man, and Cybernetics. In Proceedings of the IEEE International Conference on Systems, Seoul, Korea, 14–17 October 2012.
- Ruta, M.; di Sciascio, E.; Loseto, G. Semantic-Based Enhancement of ISO/IEC 14543–3 EIB/KNX Standard for Building Automation. IEEE Trans. Ind. Inform. 2011, 7, 731–739. [Google Scholar] [CrossRef]
- Gu, T.; Pung, H.; Zhang, D. A service-oriented middleware for building context-aware services. J. Netw. Comput. Appl. 2005, 28, 1–18. [Google Scholar] [CrossRef]
- Kindberg, T.; Barton, J.; Morgan, J.; Becker, G.; Caswell, D.; Debaty, P.; Gopal, G.; Frid, M.; Krishnan, V.; Morris, H.; et al. People, places, things: Web presence for the real world. In Proceedings of the Third IEEE Workshop on Mobile Computing Systems and Applications, Monterey, CA, USA, 7–8 December 2000.
- Henricksen, K.; Indulska, J.; Rakotonirainy, A. Modeling Context Information in Pervasive Computing Systems. In Proceedings of the First International Conference on Pervasive Computing, Zürich, Switzerland, 26–28 August 2002; pp. 167–180.
- Moore, P.; Hu, B.; Zhu, X.; Campbell, W.; Ratcliffe, M. A Survey of Context Modeling for Pervasive Cooperative Learning. In Proceedings of the First IEEE International Symposium on Information Technologies and Applications in Education (ISITAE’07), Kunming, China, 23–25 November 2007.
- Bettini, C.; Brdiczka, O.; Henricksen, K.; Indulska, J.; Nicklas, D.; Ranganathan, A.; Rib, D. A survey of context modelling and reasoning. Pervasive Mob. Comput. 2010, 6, 161–180. [Google Scholar] [CrossRef]
- Sattanathan, S.; Narendra, N.C.; Maamar, Z. Ontologies for Specifying and reconciling Contexts of Web Services. Electron. Notes Theor. Comput. Sci. 2006, 146, 43–57. [Google Scholar] [CrossRef]
- Luther, M.; Mrohs, B.; Wagner, M.; Steglich, S.; Kellerer, W. Situational reasoning—A practical OWL use case. In Proceedings of the IEEE Autonomous Decentralized Systems ISADS 2005, Chengdu, China, 4–8 April 2005.
- Scholze, S.; Stokic, D.; Barata, J.; Decker, C. Context Extraction for Self-Learning Production Systems. In Proceedings of the INDIN 2012, Beijing, China, 25–27 July 2012.
- Scholze, S.; Correia, A.; Stokic, D. Novel Tools for Product-Service System Engineering. In Proceedings of the 8th CIRP IPSS Conference, Bergamo, Italy, 20–21 June 2016.
- Scholze, S.; Correia, A.; Stokic, D.; Nagorny, N.; Spindler, P. Tools for Human-Product Collaborative Development of Intelligent Product Service Systems. In Proceedings of the PRO-VE 2016—17th Working Conference on Virtual Enterprises, Porto, Portugal, 3–5 October 2016.
- Lee, E.A. Cyber Physical Systems: Design Challenges; University of California: Berkeley, CA, USA, 2008. [Google Scholar]
- Geisberger, E.; Broy, M. agendaCPS: Integrierte Forschungsagenda Cyber-Physical Systems; Deutsche Akademie der Technikwissenschaften; Springer: Berlin, Germany, 2012. [Google Scholar]
- Bettenhausen, K.D.; Kowalewski, S. Cyber Physical Systems: Chancen und Nutzen aus Sicht der Automation. In Thesen und Handlungsfelder; VDI/VDE-Gesellschaft Mess- und Automatisierungstechnik: Düsseldorf, Germany, 2013. [Google Scholar]
- Khaitan, S.; McCalley, J. Design Techniques and Applications of Cyberphysical Systems: A Survey. Syst. J. 2015, 9, 350–365. [Google Scholar] [CrossRef]
- Park, K.-J.; Zheng, R.; Liu, X. Cyber-physical systems: Milestones and research challenges. J. Comput. Commun. 2012, 36, 1–7. [Google Scholar] [CrossRef]
- Gao, S.; Luo, H.; Chen, D.; Li, S.; Gallinari, P.; Ma, Z.; Guo, J. A Cross-Domain Recommendation Model for Cyber-Physical Systems. Trans. Emerg. Top. Comput. 2014, 1, 384–393. [Google Scholar] [CrossRef]
- Lee, J.; Kao, H.A.; Yang, S. Service innovation and smart analytics for industry 4.0 and big data environment. Proc. CIRP 2014, 16, 3–8. [Google Scholar] [CrossRef]
- Herzum, P. Web Services and Service-Oriented Architectures; Cutter Distributed Enterprise Architecture Advisory Service, Executive Report; Cutter Consortium: Arlington, MA, USA, 2002; Volume 4. [Google Scholar]
- Girbea, A.; Suciu, C.; Nechifor, S.; Sisak, F. Design and Implementation of a Service-Oriented Architecture for the Optimization of Industrial Applications. IEEE Trans. Ind. Inform. 2014, 1, 185–196. [Google Scholar] [CrossRef]
- Han, S.; Myoung, L.G.; Crespi, N. Semantic Context-Aware Service Composition for Building Automation System. IEEE Trans. Ind. Inform. 2013, 10, 752–761. [Google Scholar] [CrossRef]
- Ribeiro, L.; Barata, J.; Ferreira, J. The Meaningfulness of Consensus and Context in Diagnosing Evolvable Production Systems; Springer: Berlin/Heidelberg, Germany, 2010; Volume 314, pp. 143–150. [Google Scholar]
- Yu, J.; Xi, L.; Zhou, X. Intelligent monitoring and diagnosis of manufacturing processes using an integrated approach of KBANN and GA. Comput. Ind. 2008, 59, 489–501. [Google Scholar] [CrossRef]
- Lee, A.; Lastra, J.M. Enhancement of industrial monitoring systems by utilizing context awareness. In Proceedings of the IEEE Conference on Cognitive Methods in Situation Awareness and Decision Support, San Diego, CA, USA, 25–28 February 2013.
- Stokic, D.; Scholze, S.; Barata, J. Self-learning embedded services for integration of complex, flexible production systems. In Proceedings of the IECON 2011—37th Annual Conference on IEEE Industrial Electronics Society, Melbourne, Australia, 7–10 November 2011.
- di Orio, G.; Cândido, G.; Barata, J.; Scholze, S.; Kotte, O.; Stokic, D. Self-Learning approach to support lifecycle optimization of Manufacturing processes. In Proceedings of the IECON 2013—39th Annual Conference of the Industrial Electronics Society, Vienna, Austria, 10–13 November 2013.
- Candido, G.; Colombo, A.; Barata, J.; Jammes, F. Service-Oriented Infrastructure to Support the Deployment of Evolvable Production Systems. IEEE Trans. Ind. Inform. 2011, 7, 759–767. [Google Scholar] [CrossRef]
- Scholze, S.; Stokic, D.; Kotte, O.; Barata, J.; di Orio, G.; Candido, G. Reliable Self-Learning Production Systems Based on Context Aware Services. In Proceedings of the 2013 IEEE International Conference on Systems, Man, and Cybernetics, Manchester, UK, 13–16 October 2013.
- RapidMiner. Available online: http://rapid-i.com/ (accessed on 15 December 2016).
- Giovanni, D.O.; Candido, G.; Jose, B.; Luiz, B.J.; Ralf, B. Energy Efficiency in Machine Tools—A Self-Learning Approach. In Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, Manchester, UK, 13–16 October 2013.
- Zentralverband Elektrotechnik- und Elektronikindustrie e.V. Das Referenzarchitekturmodell RAMI 4.0 und die Industrie 4.0-Komponente; Zentralverband Elektrotechnik- und Elektronikindustrie e.V.: Frankfurt, Germany, 2016. [Google Scholar]
© 2017 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ( http://creativecommons.org/licenses/by/4.0/).
Scholze, S.; Barata, J.; Stokic, D. Holistic Context-Sensitivity for Run-Time Optimization of Flexible Manufacturing Systems. Sensors 2017, 17, 455. https://doi.org/10.3390/s17030455
Scholze S, Barata J, Stokic D. Holistic Context-Sensitivity for Run-Time Optimization of Flexible Manufacturing Systems. Sensors. 2017; 17(3):455. https://doi.org/10.3390/s17030455Chicago/Turabian Style
Scholze, Sebastian, Jose Barata, and Dragan Stokic. 2017. "Holistic Context-Sensitivity for Run-Time Optimization of Flexible Manufacturing Systems" Sensors 17, no. 3: 455. https://doi.org/10.3390/s17030455