Quality Prediction in Injection Molding
For manufacturers needing in-situ quality prediction in injection molding, this work compares methods on real industrial data, but the results are incremental due to the small dataset and lack of SOTA comparison.
The study compares neural network architectures with classical regression algorithms for predicting injection molded part quality from industrial inline measurements, finding that neural networks achieve better prediction scores despite a small dataset.
Injection molded part quality can be improved by precise process adjustment, which could rely on in-situ measurements of part quality. Geometrical and appearance quality (visually and sensory) requirements are increasing. However, direct measurement is often not feasible industrially. Therefore, process control must rely on a prediction of parts quality attributes. This study compares prediction performances of diverse neural networks architectures with "classical" regression algorithms. Dataset comes from inline industrial measurements. Regression was performed on 97 scalar statistical features extracted from multiple acquisitions sources: thermographic images and analog signals. Haralick features were extracted. Convolutional Neural Networks were trained on thermographic images and Long Short Term Memory networks were trained on raw signals. Although the dataset was small, neural networks show better predictions scores than other regression algorithms.