After establishing an offline process control based on the optical process diagnostic system PFI (Particle Flux Imaging) the process robustness has been increased through experimental identification of the impact of the noise factors „electrode wear“ and „injector wear“ in the APS process. Neural Networks were used for implementing a control software into a modern GTV APS process center. In combination with the PFI system a tool was installed in the process center that is able to predict the coating quality through the characteristics of the plasma and the particle plume. The neural network can be trained for all applications and all feedstock materials. The offline controller is instructing the operator through a desktop in order to train the network. The training procedure, that means the monitoring of the process through different parameter setups and its reactions, is generated and executed automatically.

Due to the fact that not every aspect of the coating quality can be influenced by controlling the process parameters, the noise factors must be regarded. For the APS process the electrode wear and the injector wear were identified as the most influencing noise factors. Both were analysed by means of Design of Experiment (DOE) and longterm surveillance (200 hrs). The samples were characterised by light microscopy and different coating testing methods which were chosen with respect to the coatings functions (e.g. wear resistance). The result of this work is a set of parameters that are mostly robust against both noise factors and that are adapted to certain changes by a neural network process control.