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

Abstract

With sustainable growth highlighted as a key to success in Industry 4.0, manufacturing companies attempt to optimize production efficiency. In this study, we investigated whether machine learning has explanatory power for quality prediction problems in the injection molding industry. One concern in the injection molding industry is how to predict, and what affects, the quality of the molding products. While this is a large concern, prior studies have not yet examined such issues especially using machine learning techniques. The objective of this article, therefore, is to utilize several machine learning algorithms to test and compare their performances in quality prediction. Using several machine learning algorithms such as tree-based algorithms, regression-based algorithms, and autoencoder, we confirmed that machine learning models capture the complex relationship and that autoencoder outperforms comparing accuracy, precision, recall, and F1-score. Feature importance tests also revealed that temperature and time are influential factors that affect the quality. These findings have strong implications for enhancing sustainability in the injection molding industry. Sustainable management in Industry 4.0 requires adapting artificial intelligence techniques. In this manner, this article may be helpful for businesses that are considering the significance of machine learning algorithms in their manufacturing processes.

Neural network feature and architecture optimization for injection molding surface defect prediction of model polypropylene

“…However, it is vital to understand that optimization methods that depend exclusively on CAE simulation data are not 100% accurate as they do not fully capture all the physics involved in polymer processing. For that reason, research has been conducted in predicting occurrences within injection molding by developing predictive frameworks [18,19] and including real experimental data as training data. For example, Saad Mukras' optimization framework, based on the Kriging Model, predicted cycle time, warpage, and volumetric shrinkage with an error of 6.7%, 3.2%, and 8%, respectively, by analyzing samples from real injection molding trials.…”

Machine Learning Methods for Quality Prediction in Thermoplastics Injection Molding

“…Saleh et al [12] identify that the variables that have the most impact on the injection process are melt temperature, plastification time, maximum pressure, mold wall temperature, and injection time. Jung [9] concluded that temperature, injection time, and cycle time are important variables commonly selected by machine learning techniques. As we can see in these and other research works, there are variables that are transversal in the researcher's opinion to be monitored.…”

“…This means that other types of approaches may have been considered to complement the analysis. Lately, studies are not restricted only to the use of separate machine learning methods but have started to integrate the use of combinations of methods (ensemble methods [15]) and also the use of deep learning techniques such as, for example, autoencoders, to improve the efficiency of classification/regression [9], [16]. Thus, in this work, we compare different classifiers, the use of ensemble methods, and a first approach to the use of a deep learning technique to solve classification problems directly related to the injection process.…”

“…That is, in the past, we expected that a problem would occur for it to be identified and corrected, which implied the production of non-conforming parts that only serve to material and production time-wasting, and then the machine was stopped and the problem was solved upon. With this new approach, the objective is to detect the problem even before it occurs so that the process can be intervened before nonconforming parts are produced [9]. It is an important step because often machine operators do not immediately detect the problem of non-compliance, because they may be on another machine, or defects may not be easily seen with the naked eye until the process is very degraded.…”

Development of an Efficient Cement Production Monitoring System Based on the Improved Random Forest Algorithm

“…To execute a given task, machine learning employs several algorithms or models. These algorithms are mostly used in several elds, including medical prediction (1)(2)(3), psychology (4,5), object recognition (6-8), quality monitoring (9) industry (10)(11)(12), and many other domains. However, our technical work focus is on the application of several algorithms to anticipate and classify diverse sorts of industrial process failures utilizing machine learning approaches.…”