Simulation And Parameters Optimization On Precise Injection Process Of A Plastic Plug

With the development of plastic industry, the plastic parts are applied in many industries, such as exact apparatus and electro-instruments. And they substitute for many conventional metal parts; meanwhile, the requirement of their precision has become more and more strict. The precision injection molding becomes the inevitability of plastic molding. But in the process, the effects of process conditions on molding quality have many transient changes and uncertain factors, so the process optimization becomes a difficult problem in this field. Shrinkage and warpage affect the dimensional precision and the shape precision of plastic part respectively; thus analyzing the shrinkage and warpage of parts and optimizing the process parameters are effective to improve the part's precision.In this paper, taking precise electronic plastic plug produced in a factory as an example, as well as analyzing the effects of the cooling system on part's quality, the MPI/Cool-Flow-Warp module was applied to simulate the part's surface temperature, the circuit coolant temperature and warpage under the different cooling schemes, which have different diameter of cooling water pipes, the different distance between the centres of cooling pipes and the surface of cavity, the different space between two centre of cooling pipes as well as different layout of cooling pipes. The optimum one was chosen according to analytical results of simulation. Ultimately, the favorable cooling effects were obtained by use of this method.On this foundation, the Taguchi design and CAE technology were applied to research the effects of mold temperature, melt temperature, injection time, hold pressure and packing time on part's quality. Two optimum parameter combinations for shrinkage and warpage were obtained by ANOM. And then, the degree of each process parameter's effect on quality was obtained by ANOVA. The process parameter combination giving attention to both shrinkage and warpage was selected by the synthetical weighted method of point.Finally, taking data from CAE as samples, the BP neural network for predicting the part's quality was established by designing the right structure of network, selecting the suitable learning algorithm and so on. And the non-linear relationship between the injection process parameters and shrinkage as well as warpage was got. The comparison and error analysis were carried out between the network predictive results and the date from CAE. The research showed that the neural network can make correct prediction. Changing a certain process parameter, and holding the rest, the effects of process parameters on part's quality can be researched by the output of the trained BP neural network. So it can provide guidance for the prediction of part's quality, the optimization of process parameters and the control of quality.