Optimization of Plasma Spray Process VIA Orthogonal Test Design Method, SVM, and Improved PSO

Xue, Jing; Huang, Min

doi:10.18178/ijmmm.2017.5.3.308

Cited by 4 publications

(3 citation statements)

References 17 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SVM theory introduced by Vapnik (Ref 18) has faced dramatic attention in statistical learning theory and has been increasingly applied by researchers in various fields, where the TS forms no exception (Ref 19,20). SVM is a supervised-learning algorithm that uses structural risk minimization and a symmetrical loss function, which equally penalizes high and low errors.…”

Section: Support Vector Machine (Svm)mentioning

confidence: 99%

Prediction of Particle Properties in Plasma Spraying Based on Machine Learning

et al. 2021

View full text Add to dashboard Cite

Thermal spraying processes include complex nonlinear interdependencies among process parameters, in-flight particle properties and coating structure. Therefore, employing computer-aided methods is essential to quantify these complex relationships and subsequently enhance the process reproducibility. Typically, classic modeling approaches are pursued to understand these interactions. While these approaches are able to capture very complex systems, the increasingly sophisticated models have the drawback of requiring considerable calculation time. In this study, two different Machine Learning (ML) methods, Residual Neural Network (ResNet) and Support Vector Machine (SVM), were used to estimate the in-flight particle properties in plasma spraying in a much faster manner. To this end, data sets comprising the process parameters such as electrical current and gas flow as well as the in-flight particle velocities, temperatures and positions have been extracted from a CFD simulation of the plasma jet. Furthermore, two Design of Experiments (DOE) methods, Central Composite Design (CCD) and Latin Hypercube Sampling (LHS), have been employed to cover a set of representative process parameters for training the ML models. The results show that the developed ML models are able to estimate the trends of particle properties precisely and dramatically faster than the computation-intensive CFD simulations.

show abstract

Section: Support Vector Machine (Svm)mentioning

confidence: 99%

Prediction of Particle Properties in Plasma Spraying Based on Machine Learning

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Under the effect of compression, the spray coating is peeled off the substrate surface. Skid stress (τ) is determined by the formula [10][11][12][13].…”

Section: Conducting Experimentsmentioning

confidence: 99%

Studying Adhesion between a 67Ni18Cr5Si4B Alloy Powder Coating Produced with the High Velocity Oxygen Fuel Thermal Spray Method HVOF and a Substrate Surface of a Worn C45 Steel Shaft

Dinh

Nguyen

Xuan

2020

KEM

View full text Add to dashboard Cite

Nowadays, thermal spray coatings are used to enhance mechanical properties of the material. One of the technologies used to produce thermal spray coating is HVOF spray technology. This is the most advanced and modern technology which has been widely used in the industry due to its flexibility and ability to create coatings with better adhesion in comparison with other thermal spray methods. This article presents some empirical findings from applying the 67Ni18Cr5Si4B alloy powder coating onto C 45 steel shaft by HVOF spray technology. It also analyzes the influence of some technological parameters on the adhesion of the coating. As a result, the parameters of HVOF spray technology are obtained suitable for recovering worn axis-sized workpieces.

show abstract

“…Taguchi method and ANOVA technique [5][6][7] are proposed and used in this study to solve the problem posed. Compared with a number of optimization methods such as Surface Optimization (RSM) [8], Artificial Neural Network (ANN) [9], Particle Optimization (PSO) [10] and others, the Taguchi method is simple, easy to implement and responds faster to the user while the other methods are complex calculations and some methods require a larger number of experiments. In Vietnam, the study of HVOF spraying method is still very new and there have been no published studies on WC-12Co coating.…”

Section: Introductionmentioning

confidence: 99%

Application of Taguchi Method and Anova Techniques to Maximize HVOF Spraying to WC-12Co

Dinh

Nguyen

Xuan

2020

KEM

View full text Add to dashboard Cite

The purpose of this study was to achieve a low-porosity HVOF (High velocity Oxygen Fuel) spray cover and to determine the effect of spray parameters on the porosity of the coating. The spray parameters studied include: Powder feed rate (A); Spray distance (B); Oxygen/Propane ratio to porosity of WC-12Co coating on 16Mn steel. Taguchi method and ANOVA (Analysis of variance) technique were used to optimize and analyze the effect of spray parameters. The results showed that the optimum spray parameters with A = 26 g/min, B = 0.2m, C = 5 for porosity smallest. Factor A has the greatest influence on porosity, followed by B and C. The experimental result is then compared to optimal results and the error is only 4.2 %. Hence, one can say that the optimal results are reliable and Taguchi method - ANOVA technique proved to be an effective solution to the optimization problem. Parameters for a WC-12Co coating with improved porosity on 16Mn steel substrate have been identified.

show abstract

Optimization of Plasma Spray Process VIA Orthogonal Test Design Method, SVM, and Improved PSO

Cited by 4 publications

References 17 publications

Prediction of Particle Properties in Plasma Spraying Based on Machine Learning

Prediction of Particle Properties in Plasma Spraying Based on Machine Learning

Studying Adhesion between a 67Ni18Cr5Si4B Alloy Powder Coating Produced with the High Velocity Oxygen Fuel Thermal Spray Method HVOF and a Substrate Surface of a Worn C45 Steel Shaft

Application of Taguchi Method and Anova Techniques to Maximize HVOF Spraying to WC-12Co

Contact Info

Product

Resources

About