Reducing shrinkage in injection moldings via the Taguchi, ANOVA and neural network methods

Abstract

Plastic injection molding is suitable for mass production articles since complex geometries can be obtained in a single production step. However, the difficulty in setting optimal process conditions may cause defects in parts, such as shrinkage. In this study, optimal injection molding conditions for minimum shrinkage were determined by the Taguchi, experimental design and the analysis of variance (ANOVA) methods. Polypropylene (PP) and polystyrene (PS) were injected in rectangular-shaped specimens under various processing parameters: melt temperature, injection pressure, packing pressure and packing time. S/N ratios were utilized for determining the optimal set of parameters. According to the results, 260 °C of melt temperature, 60 MPa of injection pressure, 50 MPa of packing pressure and 15 s of packing time gave minimum shrinkage of 0.937% for PP and 1.224% for PS. Statically the most significant parameters were found to be as packing pressure and melt temperature for the PP and PS moldings, respectively. Injection pressure had the least effect on the shrinkage of either material. After the degree of significance of the studied process parameters was determined, the neural network (NN) model was generated and was shown to be an efficient predictive tool for shrinkage.

Introduction

Injection molding represents one of the most important processes in the mass production of manufactured plastic parts with complex geometries. The quality of the injection moldings depends on the material characteristics, the mold design and the process conditions [1], [2]. Defects in the dimensional stability of the parts result in shrinkage and warpage. In order to minimize such defects in plastic injection molding, design of experiment, the Taguchi method is applied. In experimental design, there are many variable factors that affect the functional characteristics of the product. Design parameter values that minimize the effect of noise factors on the product’s quality are determined. In order to find optimum levels, fractional factorial designs using orthogonal arrays are used. In this way, an optimal set of process conditions can be obtained from very few experiments [3], [4].

There are several researchers that have studied the effects of injection molding process parameters on the shrinkage of moldings [5], [6], [7], [8]. Since many process parameters affect the shrinkage, parameter optimization and experimental design are needed to produce high quality products. Some researchers have been conducted on optimizing shrinkage in plastic injection moldings. In thin-shelled plastic component production, Oktem et al. [9] used the Taguchi method to reduce warpage problems that were related to a variation in the process-parameters dependent on the shrinkage. They improved the warpage and the shrinkage by determining the optimal packing time, packing pressure, injection time and cooling time. The packing pressure and the packing time were found to be the most important parameters. Vaatainen et al. [10] investigated the effect of the injection molding parameters on the visual quality of the moldings using the Taguchi method. They focused on the shrinkage with three more quality characteristics: weight, weld lines and sink marks. They were able to optimize many quality characteristics with very few experiments, which could lead to cost savings. Shen et al. [11] studied the effects of the process parameters on the shrinkage by utilizing a combination of the CAE and the Taguchi technique. Chang and Faison [12] studied the shrinkage behavior and optimization of PS, HDPE and ABS parts by using the Taguchi and ANOVA methods. They stated that the mold and melt temperatures along with the holding pressure and the holding time were the most significant factors affecting the shrinkage behavior of the three materials studied. Liao et al. [13] determined the optimal process conditions for a thin-walled injection molding, for cellular phone covers, by the Taguchi method. Based on the results of the analysis of variables and the F-test, packing pressure was found to be the most important parameter affecting the shrinkage and the warpage.

In this work, the effects of the process conditions on the shrinkage of injection molded polypropylene and polystyrene were determined by the Taguchi and ANOVA methods. Signal-to-noise ratio was used to obtain the optimal set of process parameters. Furthermore, a neural network model was generated to predict the shrinkage results for the optimal process conditions of the PP and PS moldings.