To obtain optimal injection process parameters, GA was used to optimize BP network structure based on Moldflow simulation results. The BP network was set up which considering the relationship between volume shrinkage of plastic parts and injection parameters, such as mold temperature, melt temperature, holding pressure and holding time etc. And the optimal process parameters are obtained, which is agreed with actual results. Using BP network to predict injection parameters impact on parts quality can effectively reduce the difficulty and workload of other modeling methods. This method can be extended to other quality prediction in the process of plastic parts.Keyword: Genetic algorithm (GA);Neural network algorithm (BP);Injection molding process optimization;The axial deformation
Abstract. In this paper injection process for industry production is just a grey system which have problems of complex representation and discrete data. Orthogonal experiments have been designed to obtain the value of shrinkage and warp. The lower value of the two objects is better. After data obtained in experiments are dealt with by grey theory, relational degree had been calculated. With variance analysis the optimal level of the factors influencing the value of the two objects have been find out, then a optimal group of the process parameters has been obtained. Through simulation in computer, the warp is less than 0.5 mm, the shrinkage is less than 0.5%. The requirements of the product have been satisfied. In this method the factors had been considered before mould is tested comprehensively. Time and cost of product development have been decreased greatly. It is believed that the method is valuable in actual product.
By doing Erichsen experiments, samples of hot-dip galvanized sheet under different Erichsen depths (ED) were got. Surface and cross-section of these samples were analyzed by using SEM and EDS, which can show morphology and chemical composition respectively. Failure modes of galvanized sheet under different ED were researched. Then evolution process of zinc coating failure and effects of it on galvanized sheet formability were discussed. The results indicate that during hot-dip galvanized sheet stamping, zinc coating will pulverize, exfoliate and fracture for influence of friction and forming force, which leads to decrease of galvanized sheet formability.
The precision control is the key technology for reverse development. Focus on analyzing the reasons of the error of the reverse rapid mold development, the factors affecting the precision of the mold reverse development through four stages which including reverse model, development & design, mold design, mold manufacture, are proposed. By the example, we can see that through distributing and controlling precision rationally, the accuracy requirement of the reverse rapid mold development can be met effectively.
In this paper a new approach for the optimization of the multi-objective injection molding process based on the Taguchi robust design combined with the grey relational analysis has been studied. A grey relational grade obtained from the multi-objective grey relational analysis is used to solve the injection molding process with the multiple performance characteristics including volume shrinkage (R1) and axial deformation (R2), the injecting parameters, namely mold temperature, melt temperature, holding pressure and holding time are optimized. By orthogonal polar difference analysis and statistical analysis of variance (ANOVA) of grey relational grade, main factors influencing and the best process parameters were determined: A=50°C,B=250°C,C=30MPa,D=9s.Under the case of continuity factor, Fitting the response surface further the optimal combination of in continuous space r is identified: A=50.3°C,B=250°C,C=29MPa,D=8.3s. Experimental results have shown that the Taguchi combined with the grey relational analysis can avoid human evaluation of the multi-objective optimization, and Injection molding multi-objective optimization is implemented more objectively, and product performance in the process can be improved effectively through this approach.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.