Hybrid modelling by machine learning corrections of analytical model predictions towards high-fidelity simulation solutions

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Authors

Within the fields of materials mechanics, the consideration of physical laws in machine learning predictions besides the use of data can enable low prediction errors and robustness as opposed to predictions only based on data. On the one hand, exclusive utilization of fundamental physical relationships might show significant deviations in their predictions compared to reality, due to simplifications and assumptions. On the other hand, using only data and neglecting wellestablished physical laws can create the need for unreasonably large data sets that are required to exhibit low bias and are usually expensive to collect. However, fundamental but simplified physics in combination with a corrective model that compensates for possible deviations, e.g., to experimental data, can lead to physics-based predictions with low prediction errors, also despite scarce data. In this article, it is demonstrated that a hybrid model approach consisting of a physics-based model that is corrected via an artificial neural network represents an efficient prediction tool as opposed to a purely data-driven model. In particular, a semi-analytical model serves as an efficient low-fidelity model with noticeable prediction errors outside its calibration domain. An artificial neural network is used to correct the semi-analytical solution towards a desired reference solution provided by highfidelity finite element simulations, while the efficiency of the semi-analytical model is maintained and the applicability range enhanced. We utilize residual stresses that are induced by laser shock peening as a use-case example. In addition, it is shown that non-unique relationships between model inputs and outputs lead to high prediction errors and the identification of salient input features via dimensionality analysis is highly beneficial to achieve low prediction errors. In a generalization task, predictions are also outside the process parameter space of the training region while remaining in the trained range of corrections. The corrective model predictions show substantially smaller errors than purely data-driven model predictions, which illustrates one of the benefits of the hybrid modelling approach. Ultimately, when the amount of samples in the data set is reduced, the generalization of the physics-related corrective model outperforms the purely data-driven model, which also demonstrates efficient applicability of the proposed hybrid modelling approach to problems where data is scarce.

OriginalspracheEnglisch
Aufsatznummer1883
ZeitschriftMaterials
Jahrgang14
Ausgabenummer8
Anzahl der Seiten19
ISSN1996-1944
DOIs
PublikationsstatusErschienen - 10.04.2021

Dokumente

DOI

Zuletzt angesehen

Aktivitäten

  1. Identification and characterization of coherent behavior in flows
  2. Intra-firm Wage Dispersion and Cost Coverage of Training: Evidence from German Linked Employer-Employee Data
  3. Liquidity, Flows, Circulation: The Cultural Logic of. Environmentalization - 2020
  4. Towards a New Aesthetic Paradigm
  5. Curator-artist Interactions: Forms of Exchange under the Pressure of the Logic of the Market
  6. PRIORITIZATION OF VETERINARY ANTIBIOTICS FOR ENVIRONMENTAL ANALYSIS USING A SIMPLE SCREENING APPROACH
  7. Of mice, polemics and toxins (dis)placed on stage of public consultation. Situational analysis of the GMO-discourse in Poland
  8. Are Hybrid Work Models Here to Stay?
  9. The Effects of Outcome Uncertainty on Negotiators Facing Externalities
  10. Exploring Urban Music Studies (Roundtable)
  11. Von Foerster‘s chap does brainy job. Die Prototypen des Biological Computer Laboratory (Hyperkult 18)
  12. MULTISCALE APPROACH TO LASER SHOCK PEENING INCLUDING PLASMA SHOCK WAVE SIMULATION
  13. Academy of Management Conference
  14. Cutting Across Lines: Lil Picard and the Reorienting Effects of Collage
  15. Problem Pressure, DRGs, and the Role of and Ideas in Healthcare System Change
  16. Workshop Grey Zones of Simulation - 2015
  17. 6th Austrian Early Scholars Workshop in Management - 2018
  18. Not terminated: In a Plessnerian perspective ‘cyborgized’ men still remain ‘human’ beings
  19. Methoden transformativer Forschung
  20. Professional School (Organisation)
  21. Lessons for conservation biology under global change conditions: a case study on two burnet moth species in the high altitudes of the Pyrenees
  22. Ecopharmacology.
  23. Summer School in the context of Biodiversity-Ecosystem Functioning 2012
  24. International Class Actions Conference - 2019
  25. Bsc-Thesis: Vertical stratification of ant community composition along a forest succession gradient in subtropical China.

Publikationen

  1. Support vector machines with example dependent costs
  2. Water quantity and quality dynamics of the THC - Tuyamuyun hydroengineering complex - and implications for reservoir operation
  3. Automating SPARQL Query Translations between DBpedia and Wikidata
  4. Detection of significant tracer gases by means of polymer gas sensors
  5. Toward a lifespan metric of reading fluency
  6. Biodiversity in space and time - towards a grid mapping for Mongolia
  7. Exploring Management Control Systems for Biodiversity
  8. Model Predictive Control for Energy Optimization in Generators/Motors as Well as Converters and Inverters for Futuristic Integrated Power Networks
  9. The end of certainties
  10. Mit Pixel und Korn
  11. Temperature changes using excimer laser irradiation in a cochlear model
  12. Interplay of formative assessment and instructional quality—interactive effects on students’ mathematics achievement
  13. Auditors' Perceptions of Client Firms
  14. How to Explain Major Policy Change Towards Sustainability? Bringing Together the Multiple Streams Framework and the Multilevel Perspective on Socio-Technical Transitions to Explore the German “Energiewende”
  15. Global Governance and the Interplay of Coordination and Contestation
  16. Inequality in the Transition from Primary to Secondary School
  17. Effect of Bleaching on the Elution of Monomers from Modern Dental Composite Materials
  18. Question Answering Mediated by Visual Clues and Knowledge Graphs
  19. Ähnlichkeit mit unähnlichen Mitteln
  20. Customer Orientation of Service Employees—Toward a Conceptual Framework of a Key Relationship Marketing Construct
  21. States and traits