The use of numerical modeling in the development and optimization of thermal spray processes has been hampered by the complexities of the process, with up to 50 interdependent variables involved, and the need to identify and explicitly define each relationship. This work demonstrates an alternative modeling approach that employs neural network learning algorithms. Plasma spraying was selected as the test case because it presents the greatest challenge in terms of processing parameters and the magnitude of their effect on layer quality. This paper provides an introduction to neural networks and its use in thermal spraying. A companion paper in these same proceedings presents an example in which the method is used to link processing parameters with in-flight particle characteristics in a dc plasma jet. Paper includes a German-language abstract.

This paper shows how in-flight particle diagnostics can be used to optimize parameter sets for new layer materials and to detect drift in the control of thermal spraying lines. It describes the equipment and methods used to measure the temperature, velocity, and diameter of spray particles in a plasma jet and explains how torch current, plasma gas composition, carrier and total gas flow, and stand-off distance are varied according to a statistical design plan to determine their effect. The results are presented in the form of process maps and data plots, from which several conclusions are drawn. Paper includes a German-language abstract.

This study examines the melting characteristics of wire feedstock used in arc and flame spray processes and how they relate to coating quality. A high-speed CCD camera reveals important details in how different types of wire melt away during spraying. Solid and tube cored wires, for example, melt off in a much more continuous manner than grooved wires during high-velocity combustion spraying. During arc spraying, however, no significant differences are observed. The paper also analyzes various coating microstructures and explains how they correlate with the melt off behavior of different wire designs. Paper includes a German-language abstract.

Arc spraying is an economical method for applying metallic layers due to its high spray rates and uniform melting of spray particles. The main disadvantage is the difficulty in achieving sufficient particle velocity to ensure good layer adhesion. This study investigates the influence of nozzle geometry, arc power, and gas pressure on the size and velocity of particles in an arc spray jet. The experiments were conducted using particle image velocimetry (PIV) to measure the spatial and velocity distribution of particles in flight. For X45Cr13 steel, particle velocities were found to be between 85 and 95 m/s at a gas volume flow of around 1 m 3 /min. Velocities of up to 150 m/s were ultimately achieved, but at the expense of higher atomizer gas consumption. Paper text in German.

In this study, a neural network is used to model the complex relationships associated with dc plasma spraying. The paper describes how training and test data were experimentally obtained for alumina-titania particles processed under different conditions in order to assess various learning approaches and the predictive ability of the model. As reported, 80% of the test database was successfully recognized and the misclassifications are the result of not having enough data sets to adequately cover the wide range of values obtained during the experiments. This work considers in-flight particle characteristics as a first step of a more global approach that includes coating microstructure and mechanical properties as well. Paper includes a German-language abstract.

This paper investigates the effect of chamber pressure on plasma jet expansion characteristics. It presents images of the plasma jet corresponding to different chamber pressures and torch parameters and correlates them with enthalpy probe and pressure measurements recorded in different areas of the torch nozzle. A transition from an over-expanded to an under-expanded flow regime, as evidenced by a change in jet topology, is shown to be a function of chamber pressure. This transition pressure strongly depends on torch parameters and is characterized by an estimation of a rarefaction parameter based on nozzle exit and chamber pressure. At low chamber pressures, a progressive change from a continuum to a transition flow regime is shown by the thickening of the shock structures. Paper includes a German-language abstract.