Online measurement systems of the material properties already exist but they are not located in a stage of process which allows providing their results back into the automation. Two popular online measuring systems for material properties, which are commercially available, are the Impulse Magnetic Process Online Controller (IMPOC)] and the Harmonic Analysis Coil Online Measurement System (HACOM).
Neural Networks are applied to predict the relationship between available input process variables and the target to be forecasted. Data pre-processing is an important step in developing a neural network application, which could affect the accuracy and the results of the developed models and applications.
Papers:
Cateni, S., Colla, V.: The importance of variable selection for neural networks based classification in an industrial context. International Workshop on Neural Networks, WIRN 2015. Smart Innovation, Systems and Technologies, vol. 54, 2015, pp. 363–370.
Van-Den-Berg, F., Kok, P., Yang, H., Aarnts, M.P., Meilland, P., Kebe, T., Stolzemberg, M., Krix, D., Zhou, W., Peyton, A., Martinez-De-Guerenu, A., Gutierrez, I., Jorge-Badiola, D., Mamstrom, M., Volker, A., Duijster, A., Bostrom, H.W.A., Mocci, C., Vannucci, M., Colla, V., Davis, C., Zhou, L., Schmidt, R., Labbe, S., Reboud, C., Skarlatos, A., Leconte, V., Lombard, P.: Product uniformity control - a research collaboration of european steel industries to nondestructive evaluation of microstructure and mechanical properties. In: 22nd International Workshop on Electromagnetic Nondestructive Evaluation, ENDE 2017. Studies in Applied Electromagnetics and Mechanics, vol. 43, 2018, pp. 120–12.