ODERU: Optimisation of Semantic Service-Based Processes in Manufacturing
1 like168 views
The document discusses the ORDEDU project, which focuses on optimizing semantic service-based processes in manufacturing. It describes the architecture, workflow, and two main applications: one for machine maintenance and the other for car exhaust production. Results indicate significant improvements in machine availability, maintenance costs, and production scheduling efficiencies.
ODERU: Optimisation of Semantic Service-Based Processes in Manufacturing
- 1. ODERU: Optimisation of Semantic Service-Based Processes in Manufacturing Luca Mazzola, Patrick Kapahnke, and Matthias Klusch German Research Center for Artificial Intelligence (DFKI), Saarbrücken, Germany KESW conference 2017– Stettin (PL) 09/Nov/2017KEWS 2017 , Luca Mazzola
- 2. • Context • Needs • ODERU architecture and overview • Semantics for tasks and Services • Infrastructure and surrounding PEE • Constraint Optimization for QoS • Process service plans • Two Applications • Machine Maintenance • OEE for Automotive Part Production • Validation Agenda 09/Nov/2017KEWS 2017 , Luca Mazzola
- 3. • SOA • BPMN optimization • XaaS • Industry 4.0 • QoS Manufacturing Domain Context 09/Nov/2017KEWS 2017 , Luca Mazzola
- 4. • ICT Integration for BPMN in Manufacturing • Dynamic design and execution of BPMN • Adaptation to changing context • Service and Process Plan Optimization • Functional and non-Functional requirements • Semantic models and KPI representation • QoS consideration and aggregation methods • Effective composition of complete PSP • Support for run-time incremental re-planning Needs for ODERU 09/Nov/2017KEWS 2017 , Luca Mazzola
- 5. Architecture - Semantics 09/Nov/2017KEWS 2017 , Luca Mazzola • Process Task and Services semantically annotated • IOPE (Inputs/Outputs/Preconditions/Effects) • Use of an OWL2 ontology, called CDM-Core • Hydraulic metal press maintenance • Car exhaust production • BPMN extension for semantic annotation at the Task level • OWL-S description of service into a repository
- 6. Architecture - Infrastructure 09/Nov/2017KEWS 2017 , Luca Mazzola
- 7. Architecture – COP for QoS 09/Nov/2017KEWS 2017 , Luca Mazzola • BPMN extension for (COP) Constraint Optimization Problem definition, at the process level • Based on a newly defined COPSE2 grammar • Usage of complex formulas • Adaptable type of constraints • User-definable optimization objective function • Internally the COP is solved by the JaCoP package, but extensible to include any COP solver • Result encoded back into the produced PSP in term of services selection and/or variable assignments
- 8. Architecture – PSP 09/Nov/2017KEWS 2017 , Luca Mazzola 2 steps: Service selection + Optimal Service composition
- 9. Application 1 (UC1) 09/Nov/2017KEWS 2017 , Luca Mazzola • Maintenance of clutch-brake mechanism into metallic presses, operate by geographically distributed TAS team using part(s) provided by SP providers • Objective @ design-time: provide a feasible combination (TAS team + SP provider) for common cases as fallback solution. • Objective @ run-time: find one optimal combination that respects the constraints (guarantee, time to completion, max cost, TAS team schedule, SP availability, etc) minimising cost and time required
- 10. Application 2 (UC2) 09/Nov/2017KEWS 2017 , Luca Mazzola • Optimization of car exhaust production by maximization of some OEE components for the robot cell involved Objective @ design-time: compute the optimal independent parameters setting for the best compatible robot cell in the pool of candidates • Objective @ run-time distinguished in two cases: a. searching for better setting after each batch b. changing the service used due to a robot unavailability and find its optimal parameters
- 11. Validation 09/Nov/2017KEWS 2017 , Luca Mazzola • Application 1: • (up to) 60% reduction of unscheduled machine breakdown • (up to) 15% reduction of the total machine breakdowns (machine availability increased of ~18%) • (up to) 50% reduction in intervention time and • (up to) 25% reduction in costs for maintenance intervention • Application 2: • increase speed to allocate production schedule to the manufacturing assets (from the current 6 hours to 1 hour) • reduce significantly the time for engaging additional manufacturing assets (from 6 months to 2 weeks) • scenario (A): increase aggregated OEE measure • from current 60% to 70% • scenario (B): increase OEE single components: “Quality” from 55% to 75% and “Availability” from 60% to 70% Ongoing activity: expected results
- 12. Resources 09/Nov/2017KEWS 2017 , Luca Mazzola Mazzola, L., Kapahnke, P., Vujic, M., & Klusch, M. (2016). CDM-Core: A Manufacturing Domain Ontology in OWL2 for Production and Maintenance. In KEOD (pp. 136-143). Mazzola, L., Kapahnke, P., Waibel, P., Hochreiner, C., & Klusch, M. (2017). FCE4BPMN: On- demand QoS-based optimised process model execution in the cloud. In Proceedings of the 23rd ICE/IEEE ITMC Conference. IEEE. Mazzola L., Kapahnke P., Klusch M. (2017) ODERU: Optimisation of Semantic Service- Based Processes in Manufacturing. In: Różewski P., Lange C. (eds) Knowledge Engineering and Semantic Web. KESW 2017. Communications in Computer and Information Science, vol 786. Springer, Cham Mazzola L., Kapahnke P., Klusch M. (2017). Pattern-Based Semantic Composition of Optimal Process Service Plans with ODERU. In Proceedings of The 19th Int. Conference on Information Integration and Web-based Applications & Services, Salzburg, Austria, December 4–6, 2017 (iiWAS ’17), 10 pages. DOI: https://doi.org/10.1145/3151759.3151773 Mazzola L., and Kapahnke P. (2017). DLP: a Web-based Facility for Exploration and Basic Modification of Ontologies by Domain Experts. In Proceedings of The 19th Int. Conference on Information Integration and Web-based Applications & Services, Salzburg, Austria, December 4–6, 2017 (iiWAS ’17), 5 pages. DOI: https://doi.org/10.1145/3151759.3151816 Forthcoming
- 13. THANKS FOR THE ATTENTION QUESTIONS? LUCA.MAZZOLA@DFKI.DE MAZZOLA.LUCA@GMAIL.COM http://www.crema-project.eu H2020-RIA agreement 637066 https://www.linkedin.com/in/mazzolaluca/ The ODERU code can be found at: https://oderu.sourceforge.io/ 09/Nov/2017KEWS 2017 , Luca Mazzola