Optimisation of process chains and production plants using hybrid, AI- and simulation based general process models

The paper describes a novel approach for generating multipurpose models of machining operations, combining machine learning and search techniques. A block-oriented framework for modelling and optimisation of process chains is introduced and its applicability is shown by the results of the optimisation of cutting processes. The paper illustrates how the framework can support the simulation- based optimisation of whole production plants. The benefits of substituting the time-consuming simulation by ANN models are also outlined. The applicability of the proposed solution is demonstrated by the results of an industrial project where the task was to optimise the size spectrum of the ordered raw material at a plant producing one- and multi-layered printed wires.