Two important aspects of the purification process in the iron, aluminium, magnesium and tin industries are computation of the target percentage of each mineral purified and the different target percentage using an expert control strategy to compute and track the target percentages accurately. First, neural networks, mathematical models and rule models are constructed based on statistical data and empirical knowledge on the process. Then a methodology is proposed for computing the target percentages that combines the neural networks, mathematical models and rule models and uses a model-based reasoning. Finally, the tracking control of the target percentages is carried out by the neural network.