Optimization of Injection-Molding Process Parameters for Weight Control: Converting Optimization Problem to Classification Problem

Abstract

Product weight is one of the most important properties for an injection-molded part. The determination of process parameters for obtaining an accurate weight is therefore essential. This study proposed a new optimization strategy for the injection-molding process in which the parameter optimization problem is converted to a weight classification problem. Injection-molded parts are produced under varying parameters and labeled as positive or negative compared with the standard weight, and the weight error of each sample is calculated. A support vector classifier (SVC) method is applied to construct a classification hyperplane in which the weight error is supposed to be zero. A particle swarm optimization (PSO) algorithm contributes to the tuning of the hyperparameters of the SVC model in order to minimize the error between the SVC prediction results and the experimental results. The proposed method is verified to be highly accurate, and its average weight error is 0.0212%. This method only requires a small amount of experiment samples and thus can reduce cost and time. This method has the potential to be widely promoted in the optimization of injection-molding process parameters.

Optimisation of Shrinkage and Strength on Thick Plate Part Using Recycled LDPE Materials

“…The use of trial-and-error is one of the options available to optimize the associated parameters, but this approach is not suitable for current industries using complex manufacturing processes, as it is time-consuming and costly [ 3 ]. Therefore, applying optimisation methods such as the Response Surface Methodology (RSM), Genetic Algorithm (GA), Particle Swarm Optimisation (PSO) and Taguchi is a good option to optimise the setting of processing parameters to mould parts with better quality [ 4 , 5 , 6 , 7 , 8 , 9 , 10 , 11 , 12 ].…”

“…Azman et al [ 11 ] applied the PSO to optimise the injection mould parameters by obtaining the minimum warpage, whereby the parameters studied were cooling temperature, V/P switchover, injection time and mould temperature. The regression model that represents the relationship between the response and processing parameters was acquired from the previous researches [ 12 ]. As compared to the warpage value from the previous study, the warpage recorded a reduction of 2.21%, proving the ability of PSO to optimise the warpage problem.…”

“…Variables such as the materials, processing parameter and design were seen to have an impact on the finished moulded part [ 13 ]. Optimisation methods such as the Taguchi process and RSM have been used over the years and have shown exceptional performance in the production of better quality of moulded parts [ 6 , 7 , 12 , 14 , 15 ]. However, only a few researchers have applied these optimisation methods to reduce shrinkage and improvise the tensile properties of a recycled material [ 16 , 17 ].…”

Intelligent Injection Molding on Sensing, Optimization, and Control

“…ere are many other surrogate models that are utilized for constructing approximation functions based on experiments or simulation such as support vector machines (SVM) [143] and the Kriging model. ey have similar roles in optimization and will not be specifically introduced here.…”

“…In brief, a PID controller makes use of the error to adjust the output to obtain the set variables. Researchers have achieved control of mold temperature [176], servohydraulic systems [177], and the stability of product quality [143] using PID controllers.…”