Precision prediction model in FDM by the combination of genetic algorithm and BP neural network algorithm.

The accuracy of fused deposition modeling (FDM) prototype is affected by many factors, which process parameters are the most important factor. It is difficult to establish mathematical model accurately; the reason is that process parameters in FDM are coupled and the forming process is nonlinear. In order to define the effect of various process parameters on the forming precision and improve the precision of FDM printing, this paper established the precision prediction model based on process parameters by genetic algorithm optimizing the BP neural network's weight and threshold. Compared with BP prediction model, the result has shown that the precision of the prediction model is better than those of BP prediction model. [ABSTRACT FROM AUTHOR]