Abstract
This paper presents neural network model used for designing the thickness of carbon layer after carbonizing car drive cross in fluidized bed. This process is very complicated and difficult as multi-parameters changes are non linear and car drive cross structure is non homogeneous. This fact and lack of mathematical algorithms describing this process makes modeling required curve of hardness by traditional numerical methods difficult or even impossible. In this case it is possible to try using artificial neural network. The neural network structure is designed and prepared by choosing input and output parameters of process. The method of learning and testing neural network, the way of limiting nets structure and minimizing learning and testing error are discussed. Such prepared neural network model, after putting expected values of thickness of carbon layer in output layer, can give answers to a lot of questions about running carbonizing process in fluidized bed. The neural network model can be used to build control system capable of on-line controlling running process and supporting engineering decision in real time. This paper presents different conception to obtain assumed material's thickness of carbonizing layer in fluidized bed. The specially prepared neural networks model could be a help for engineering decisions and may be used in designing carbonizing process in fluidized bed as well as in controlling changes of this process.
