After having established an offline process control based on the optical process diagnostic system PFI (Particle Flux Imaging) the process robustness has been increased by 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 process controller into a GTV APS process control center. In combination with the PFI system a tool was installed in the process center that is able to predict coating quality by analyzing some characteristics of the plasma and the particle plume. The neural network can be trained for all applications and all feedstock materials. An offline controller is instructing the operator through a desktop in order to train the network. The training, that means the monitoring of the process through different parameter setups and its reactions, is generated and executed automatically. Due to the fact that controlling the process parameters cannot influence every aspect of the coating quality, noise factors have to be regarded. For the APS process the electrode wear and the injector wear were identified as the most influencing noise factors. Both were analyzed by means of Design of Experiment (DOE) and long-term monitoring (200 hrs). The samples were characterized by light microscopy and different coating test methods that were chosen with respect to the coatings functions (e.g. wear resistance). The result of this work is a set of parameters that are as robust against both noise factors as possible and that are adapted to certain changes by a neural network process control.

Previous investigations of thermal spraying processes have shown that the relations between process parameters and the objective measurements are very complex. An approved approach to control complex processes is the application of Neural Networks (NN). Thus, Neural Networks have been designed to control the process of APS and HVOF spraying. Feed forward Neural Networks (Multi Layer Perceptron, MLP) are used. They are able to control a process. The way to train the Neural Network is to conduct as many experiments as possible, this is the major difficulty for the industrial use of Neural Networks. To save time and money DoE (Design of Experiments) is used to create an optimal experimental plan for the training. For testing the implementation of Neural Networks coatings are sprayed with APS, using DoE. The Neural Networks are combined with the particle flux imaging (PFI) tool. In future this combination will be able to provide an open loop control for thermal spray processes. The Neural Networks will be integrated with the software of the PFI-unit in order to create an easy to handle and affordable process control device. First experiments have been done with the APS process by spraying ZrO 2 onto steel substrates. Afterwards the porosity of the coating was correlated to the recorded images and to the process parameters.