1. Proceedings
  2. I3M
  3. 2022
  4. EMSS
  5. 10.46354/i3m.2022.emss.006

Data-driven recipe optimisation based on unified digital twins and shared prediction models

  • a René Wöstmann  ,
  • b Thorbjörn Borggräfe ,
  • c Sascha Janßen,
  • d Josef Kimberger,
  • e Solomon Ould,
  • f Nick Bennett,
  • j Nick Bennett,
  • k Victor Hernandez Moreno,
  • l Jochen Deuse 
  • a,b,c,l   RIF Institute of Research and Transfer e.V.,Joseph-von-Fraunhofer-Str. 20,Dortmund,44227,Germany
  • d  Bitburger Braugruppe GmbH, Römermauer 3,Bitburg,54634, Germany
  • e,f,j,k,l Centre for Advanced Manufacturing, University of Technology Sydney, 15 Broadway, 2007 Ultimo,Australia
Cite as
Wöstmann R., Borggräfe T., Janßen S., KimbergerJ., Olud S., Bennett N,, Hernandez Moreno V., and Deuse J. (2022).,Data-driven recipe optimisation based on unified digital twins and shared prediction models. Proceedings of the 34th European Modeling & Simulation Symposium (EMSS 2022). , 006 . DOI: https://doi.org/10.46354/i3m.2022.emss.006

Abstract

The importance of cross-process multivariate data analysis for improving products and processes is continuously increasing. Artificial intelligence and machine learning offer new possibilities to represent complex cause-effect relationships in models and to use the for optimisation. For consistent and scalable usage, unified data structures and representations of products, processes and resources are required in order to be able to use larger data populations as well as deploy these  models in different application contexts. The paper presents an approach of shared prediction models for recipe optimization based on unified digital twins in the beverage industry. For this purpose, a central generic data model was created, which is the basis for unified digital twins and thus the integration of physical and digital entities, as well as the foundation for cross-process data analysis.

References

  1. Ahrend,U.,Aleksy,M., Berning,M., Gebhardt,J.,Mendoza,F., & Schulz,D. (2019). Challengesof the digital transformation: The role ofsensors, sensor networks, IoT-devices, and5G : Invited Paper. In2019 First InternationalConference on Societal Automation (SA)(pp.1–12). IEEE.https://doi.org/10.1109/SA47457.2019.8938077
  2. Al-Fuqaha,A., Guizani,M., Mohammadi,M.,Aledhari,M., & Ayyash,M. (2015). Internet ofThings: A Survey on Enabling Technologies,Protocols, and Applications.IEEECommunications Surveys &Tutorials,17(4),2347–2376.https://doi.org/10.1109/COMST.2015.2444095
  3. Alpaydin,E. (2020).Introduction to Machine Learning(Fourth edition).Adaptive computation andmachine learning. The MIT Press.
  4. Arndt,S. (2018). Protokolle und Standards. In N.Gronau (Ed.),Industrial Internet of Things(pp.39–80). GITO.
  5. Ban,Y., Kearney,K., Sundahl,B., Medina,L.,Bonnecaze,R.T., & Chopra,M.J. (2021,February 22–27). Fast etch recipe creationwith automated model-based processoptimization. In J.Bannister & N. Mohanty(Eds.),Advanced Etch Technology and ProcessIntegration for Nanopatterning X(p.22). SPIE.https://doi.org/10.1117/12.2583868
  6. Barthelmey,A. (2021).Digitaler Zwilling fürdurchgängige Datenbereitstellung und-nutzungim Lebenszyklus wandlungsfähigerProduktionssysteme.Schriftenreihe IndustrialEngineering: Vol. 35. Shaker.
  7. Barthelmey,A. (2021).Digitaler Zwilling fürdurchgängige Datenbereitstellung und-nutzungim Lebenszyklus wandlungsfähigerProduktionssysteme.Schriftenreihe IndustrialEngineering: Vol. 35. Shaker.
  8. Brewer World. (2020).Brauer AI Serves MachineLearning And AI On Tap, Shows Us How ToBrewThe Perfect IPA. https://www.brewer-world.com/brauer-ai-serves-machine-learning-and-ai-on-tap-shows-us-how-to-brew-the-perfect-ipa/
  9. Holland, J. H.(2006)Studying complex adaptivesystems.Jrl Syst Sci & Complexity, 19: 1–8.
  10. Bröckner,S., Benfer,R., Borzt,M., Engell,S.,Knösche,C., & Kröner,A. (2021).ProcessSimulation-Fit for the future? Position paper ofthe ProcessNet working Committe ProcessSImulation, Process Synhesis and KnwoledgeProcessing, 2021.
  11. Derler,P., Lee,E.A., & Sangiovanni Vincentelli,A.(2012). Modeling Cyber-Physical Systems.Proceedings of the IEEE,100(1), 13–28.https://doi.org/10.1109/JPROC.2011.2160929
  12. Fuller,A., Fan,Z., Day,C., & Barlow,C. (2019, October29).Digital Twin: Enabling Technologies,Challenges and Open Research.http://arxiv.org/pdf/1911.01276v5https://doi.org/10.1109/ACCESS.2020.2998358
  13. Garrido-Merchán,E.C., & Albarca-Molina,A. (2018).Suggesting Cooking Recipes ThroughSimulation and Bayesian Optimization,11314(1), 277–284.https://doi.org/10.1007/978-3-030-03493-1_30
  14. Garrido-Merchán,E.C., & Albarca-Molina,A. (2018).Suggesting Cooking Recipes ThroughSimulation and Bayesian Optimization,11314(1), 277–284.https://doi.org/10.1007/978-3-030-03493-1_30
  15. Ge,Z., Song,Z., Ding,S.X., & Huang,B. (2017). DataMining and Analytics in the Process Industry:The Role of Machine Learning.IEEE Access,5,20590–20616.https://doi.org/10.1109/ACCESS.2017.2756872
  16. Grum,M., Sultanow,E., Friedmann,D., Ullrich,A., &Gronau,N. (2020).Tools des MaschinellenLernens. GITO Verlag.https://doi.org/10.30844/grum_2020
  17. Haupt,R.L. (Ed.). (2020).Wireless communicationssystems: An introduction(First edition). Wiley-IEEE Press.https://doi.org/10.1002/9781119419204
  18. Heidrich,M., & Luo,J.J. (2016).Industrial Internet ofThings: Referenzarchitektur für dieKommunikation.https://www.iks.fraunhofer.de/content/dam/esk/dokumente/Whitepaper_IoT_dt_April16.pdf
  19. IEC (63278-1 ED1).Asset administration shell forindustrial applications:Part 1: Administrationshell structure.
  20. IEC (61512-1:1997).Batch control:Part 1: Models andterminology (IEC 61512-1:1997). Berlin. VDEVerlag.
  21. ISO (16400-1:2020).Automation systems andintegration-Equipment behaviour catalogues
  22. Kritzinger,W., Karner,M., Traar,G., Henjes,J., &Sihn,W. (2018). Digital Twin inmanufacturing: A categorical literature reviewand classification.IFAC-PapersOnLine,51(11),1016–1022.https://doi.org/10.1016/j.ifacol.2018.08.474
  23. Longo,F., Padovano,A., Nicoletti,L., Mohaiad,Elbasheer, & Diaz,R. (2021). Digital twins formanufacturing and logistics systems: issimulation practiceready? InProceedings ofthe 33rd European Modeling & SimulationSymposium(435-442.). CAL-TEK srl.https://doi.org/10.46354/i3m.2021.emss.062
  24. Narziß,L., Back,W., Gastl,M., & Zarnkow,M. (2017).Abriss der Bierbrauerei. Wiley.https://doi.org/10.1002/9783527812820
  25. Nasar,M., & Abu Kausar,M. (2019). Suitability OfInfluxdb Database For IoT Applications.
    International Journal of Innovative Technologyand Exploring Engineering,8(10), ArticleJ92250881019, 1850–1857.https://doi.org/10.35940/ijitee.J9225.0881019
  26. Perno,M., Hvam,L., & Haug,A. (2022).Implementation of digital twins in the processindustry: A systematic literature review ofenablers and barriers.Computers in Industry,134, 103558.
  27. Pethig,F., Schriegel,S., Maier,A., Otto,J., &Jasperneite,J. (2017).Industrie-4.0-Kommunikation mit OPC UA. VDMA Verlag.https://www.researchgate.net/publication/316432275_Industrie-40-Kommunikation_mit_OPC_UA
  28. prostep. (2019).Production Lifecycle InformationManagement: Information management fromengineering to the shop floor. White Paper.https://www.prostep.org/fileadmin/downloads/WhitePaper_PLIM_EN.pdf
  29. Renggli,C., Rimanic,L., Gürel,N.M., Karlaš,B.,Wu,W., & Zhang,C. (2021).A Data Quality-Driven Viewof MLOps.http://arxiv.org/pdf/2102.07750v1
  30. Robinson,S., & Dehbi,A. (2021).How sweet it is: UsingCloud AI to whip up new treats with MarsMaltesers.https://cloud.google.com/blog/products/ai-machine-learning/baking-with-maltesers-marmite-and-cloud-ai 
  31. Schmitt,J., Bönig,J., Borggräfe,T., Beitinger,G., &Deuse,J. (2020). Predictive model-basedquality inspection using Machine Learningand Edge Cloud Computing.AdvancedEngineering Informatics,45, 1–10.
  32. Tao,F.,Zhang, M. &Nee,A.Y.C.(2019).Digital TwinDrivenSmartManufacturing. Academic Press.https://www.sciencedirect.com/science/book/9780128176306
  33. Tao,F., Zhang,H., Liu,A., & Nee,A.Y.C.(2019). DigitalTwin in Industry: State-of-the-Art.IEEETransactions on Industrial Informatics,15(4),2405–2415. https://doi.org/10.1109/TII.2018.2873186
  34. Tarallo,E., Akabane,G.K., Shimabukuro,C.I.,Mello,J., & Amancio,D. (2019). MachineLearning in Predicting Demand for Fast-Moving Consumer Goods: An ExploratoryResearch.IFAC-PapersOnLine,52(13), 737–742.https://doi.org/10.1016/j.ifacol.2019.11.203
  35. Werner,R., Takacs,R., Geier,D., Becker,T.,Weißenberg,N., Haße,H., Sollacher,R.,Thalhofer,M., Schumm,B., & Steinke,I.(2021). The Challenge of Implementing DigitalTwins in Operating Value Chains.Advances inBiochemical Engineering/biotechnology,177,127–166.https://doi.org/10.1007/10_2020_153 
  36. West,N., Gries,J., Brockmeier,C., Göbel,J.C., &Deuse,J. (2021). Towards integrated DataAnalysis Quality: Criteria for the application ofIndustrial Data Science. InIEEE 22ndInternational Conference on Information Reuseand Integration for Data Science (IRI). Symposium conducted at the meeting ofInstitute of Electrical and ElectronicsEngineers (IEEE), Virtually.
  37. Wöstmann,R., Schlunder,P., Temme,F.,Klinkenberg,R., Kimberger,J., Spichtinger,A.,Goldhacker,M., & Deuse,J. (2020). Conceptionof a Reference Architecture for MachineLearning in the Process Industry. In IEEEComputer Society (Chair),2020 IEEEInternational Conference onBig Data (Big Data). Symposium conducted at the meeting ofInstitute of Electrical and ElectronicsEngineers (IEEE), Atlanta, GA.https://doi.ieeecomputersociety.org/10.1109/BigData50022.2020.9378290
  38. Xia,K., Sacco,C., Kirkpatrick,M., Saidy,C., Nguyen,L.,Kircaliali,A., & Harik,R. (2021). A digital twinto train deep reinforcement learning agent forsmart manufacturing plants: Environment,interfaces and intelligence.Journal ofManufacturing Systems,58, 210–230.https://doi.org/10.1016/j.jmsy.2020.06.012