Quality Classification of Injection-Molded Components by Using Quality Indices, Grading, and Machine Learning

Abstract

Conventional methods for assessing the quality of components mass produced using injection molding are expensive and time-consuming or involve imprecise statistical process control parameters. A suitable alternative would be to employ machine learning to classify the quality of parts by using quality indices and quality grading. In this study, we used a multilayer perceptron (MLP) neural network along with a few quality indices to accurately predict the quality of “qualified” and “unqualified” geometric shapes of a finished product. These quality indices, which exhibited a strong correlation with part quality, were extracted from pressure curves and input into the MLP model for learning and prediction. By filtering outliers from the input data and converting the measured quality into quality grades used as output data, we increased the prediction accuracy of the MLP model and classified the quality of finished parts into various quality levels. The MLP model may misjudge datapoints in the “to-be-confirmed” area, which is located between the “qualified” and “unqualified” areas. We classified the “to-be-confirmed” area, and only the quality of products in this area were evaluated further, which reduced the cost of quality control considerably. An integrated circuit tray was manufactured to experimentally demonstrate the feasibility of the proposed method.

A Review on Machine Learning Models in Injection Molding Machines

“…Another advantage of injection molding is that complex parts can also be molded. us, injection molding offers design flexibility [26]. Injection molding is capable of producing accurate parts, maintaining good dimensional stability.…”

Application of Machine Learning Techniques in Injection Molding Quality Prediction: Implications on Sustainable Manufacturing Industry

“…Ke, K.-C. et al (2021) [18] filtered out outliers in the input data and converted the measured quality into a quality class used as output data. the prediction accuracy of the MLP model was improved, and the quality of finished parts was classified into various quality levels.…”

Enhancement of Multilayer Perceptron Model Training Accuracy through the Optimization of Hyperparameters: A Case Study of the Quality Prediction of Injection Molded Parts

“…Those that correlated highly were selected as input parameters to improve the prediction accuracy and effectively reduce the amount of calculation required during model training. The following four main quality indices were introduced in this study [16,17]:…”

“…(2) Outlier filtering: The standard score was used as the basis for judgment, with the z value of 1.78 selected as the standard to eliminate outlier values under the same molding parameters. Among them, the 1.78 standard score is equivalent to retaining 92.5% of the data volume [17]. 3.…”

“…Artificial neural networks (ANNs) enable users to rapidly create artificial networks and quality prediction solutions through appropriate hyperparameter adjustments. These adjustments link a large amount of process parameter information with resultant molding quality [15][16][17][18][19]. ANN technology can be employed in the learning process of different data types from large volumes of data to achieve clustering, classification, prediction, and regression functions.…”