MODELING OF PLASMA SPRAY COATING PROCESS USING ROBUST SOLUTIONS BASED ON NEW INTELLIGENCE METHODS

This study adopts two computational intelligence techniques namely least-squares support vector machine (LS-SVM) and group method of data handling (GMDH) type polynomial neural network to model the plasma spray coating process. The coating qualities were evaluated by determining its thickness, porosity and micro-hardness. Four parameters including primary gas flow rate, stand-off distance, powder flow rate and arc current that affecting the coating properties were chosen as input variables in model development. The performances of the developed models were evaluated by calculating the deviations between the predicted and the actual values based on the performance indices of mean absolute error (MAE), root mean square error (RMSE) and coefﬁcient of determination (R2). The results demonstrate thehigh capability of the LS-SVM and GMDH-type polynomial neural network for prediction of thickness and micro-hardness values with lowest MAE, RMSE and highest R2. Due to the high non-linearity behavior of porosity in coating process, the results obtained by these models for porosity are not very well.

Download Full-text

Transient Heating and Melting of Particles in Plasma Spray Coating Process

Journal of Heat Transfer ◽

10.1115/1.2825868 ◽

1996 ◽

Vol 118 (2) ◽

pp. 471-477 ◽

Cited By ~ 10

Author(s):

M. A. Jog ◽

L. Huang

Keyword(s):

Heat Transfer ◽

Temperature Distribution ◽

Heat Transport ◽

Plasma Spray ◽

Spray Coating ◽

Solid Particles ◽

Coating Process ◽

Transient Heating ◽

Plasma Spray Coating ◽

Gas Ionization

In the plasma spray coating process, solid particles are injected into a plasma jet. The heat transfer from the plasma to the particles results in heating and melting of the particles. The molten particles impact on a surface forming a thin coat. In this paper, we investigate the heating and melting of a spherical particle injected into a thermal plasma. The transient temperature distribution in the particle interior is obtained simultaneously with the temperature and number density variations of the ions, electrons, and the neutrals as well as the electric potential variation in the plasma. Our analysis incorporates a model for the production and recombination of electrons and ions. The transport in the plasma is modeled by considering the main body of the plasma as charge neutral and a charge sheath in the vicinity of the particle surface. The heat flux to the particle is evaluated by taking into account all modes of heat transfer to the surface. The temporal variations of the particle temperature distribution are calculated. Results are compared with the available predictions made without taking into account the gas ionization to assess the importance of ionization and particle charging on the heat transport to the particle. For argon, for the particle materials considered in this study, the effect of gas ionization on the heat transport was found to be negligible for plasma temperatures below 6500 K.

Download Full-text