Machine Parameters Optimisation Using Soft Computing Techniques for a Dental Milling Process

摘要

The optimisation of machine parameters in the fabrication process could potentially improve the flexibility of the process, adjustments of machine parameters, the research in new materials and its implementation in the fabrication process and it also improves future designs. Nowadays, this is achieved with the help of experts -units of R&D in companies work to adjust parameters from the experimental design, by carrying out lots of trials in machines and their own experiences-. Machine optimisation parameters in the fabrication process includes the models development to assess the behaviour of the variables in the process and to find the fitness function that can be optimised. The machine parameters optimisation should help the experts to know the own production process to produce products using new materials in a short period of time. This highly relevant issue in the industrial sector is approached through a novel intelligent procedure in the present study. It is based on the following phases. Firstly, a neural model extracts the internal structure and the relevant features of the data set which represents the system. Secondly, the dynamic system performance of different variables is specifically modeled using a supervised neural model and identification techniques. This constitutes the model for the fitness function of the production process, using relevant features of the data set. Finally, a genetic algorithm is used to optimise the machine parameters from a non parametric fitness function. The reliability of the novel method proposed is validated with a real interesting case study, which is the optimisation of a high-precision machining centre with five axes for dental milling.