h1

TY  - THES
AU  - Dokhanchi, Ali
TI  - Towards digital shadow in plasma spraying
VL  - 74
PB  - RWTH Aachen University
VL  - Dissertation
CY  - Düren
M1  - RWTH-2023-09800
SN  - 978-3-8440-9268-4
T2  - Schriftenreihe Oberflächentechnik
SP  - 1 Online-Ressource : Illustrationen, Diagramme
PY  - 2023
N1  - Druckausgabe: 2023. - Auch veröffentlicht auf dem Publikationsserver der RWTH Aachen University
N1  - Dissertation, RWTH Aachen University, 2023
AB  - Atmospheric Plasma Spraying (APS) is a versatile coating technology, which offers a broad range of functional features. Deposition efficiency (DE) is a major performance measure in APS, which is determined by dozens of intrinsic and extrinsic influencing factors. Because of the nonlinear and complicated interdependencies of the contributing variables, enhancing DE has always been a challenging task in the process development of APS. Hence, employing an ensemble of computer-aided methods is inevitable to understand and control these correlations in such a complex coating technology. The concept of the so-called Digital Shadow combines domain-specific models with data-driven techniques of Artificial Intelligence (AI), inferred by autonomous agents to create a sufficiently accurate image of the production process including all relevant data. This dissertation is devoted to the development of the primary steps towards a Digital Shadow in APS with the ultimate goal of improving the process efficiency. Modern AI methods, namely Support Vector Machine (SVM) and Adaptive Neuro-Fuzzy Inference System (ANFIS), were used in this work to predict DE. For this purpose, both simulation and experimental data from the entire process chain of APS were employed to train the AI models, and combine them in the frame of an expert system. These data include process parameters, in-flight particle properties and DE on the substrate. The developed expert system consists of two subsystems: one for predicting in-flight particle properties from process parameters using SVM technique and another for predicting DE from particle properties using ANFIS. To tackle the problem of insufficient data for training the aforementioned AI models two approaches were pursued: 1) A method was developed for in situ determination of spatially resolved deposition efficiencies on the substrate, namely Local Deposition Efficiency (LDE). By using LDE, sufficient amount of data for learning algorithms could be generated, while providing that much data for ex situ measurements of global DE and their corresponding particle properties would be impractical. 2) Simulation data for the in-flight particle properties were generated by using the simulation models of the plasma jet already developed at IOT. The combination of these two strategies provided the aggregated and purpose driven data sets required for a Digital Shadow in APS. The developed expert system can be used as a tool to adjust the process parameters to produce sustainable and cost-effective coatings, and subsequently improves the integration of coating process into production chain.
LB  - PUB:(DE-HGF)11 ; PUB:(DE-HGF)3
DO  - DOI:10.18154/RWTH-2023-09800
UR  - https://publications.rwth-aachen.de/record/971794
ER  -