On the consideration of electrodes ageing for the prediction of in-flight particle characteristics of atmospheric plasma spray using decision tree model

The in-flight powder particle characteristics, such as the particle velocity and temperature, have significant influence on the coating formation in an atmospheric plasma spray (APS) process. The relationship between the input process parameters and the in-flight particle characteristics is understandably of paramount importance for coating properties design and quality control. It is also well known that the ageing of electrodes affects this relationship. In recent years, machine learning algorithms have proven to be able to take into account such complex nonlinear interactions. This work explores for the first time the application of a decision tree model to measure and to predict in-flight particle characteristics of an APS process considering electrodes ageing. Experiments were performed to record simultaneously the input process parameters, the in-flight powder particle characteristics and the electrodes usage time. Various spray durations are considered to emulate the actual coating spray production setting. Sensor data is firstly cleaned and transformed. Several decision tree algorithms are compared and the implication of using such model for an APS process as the electrodes age are discussed.