Neural network model for the analysis and representation of data in concrete manufacturing

The problem of extracting information from several sources of information is a very important issue in intelligent systems. In the field of manufacturing concrete, which is one of the most common construction material in Hong Kong, this problem is well known. There is no direct formulation of concrete mix for specified properties, and all of the mixes are designed by experience and subject to quality inconsistency due to many possible mixing variations. The paper describes our experience in applying neural network techniques for acquiring the qualitative knowledge during the production of concrete. It shows the capabilities of the developed model for the analysis and representation of data and for aiding the prediction the quality of concrete under different mixing formulations. The simulation results indicate that neural network´s prediction is generally superior to that of the conventional methods