Ngoc-Tan Tran

In the context of Industry 4.0, multi-sensor data plays a pivotal role in monitoring, analyzing, and optimizing product quality in real time. The ability to capture and process data from various sensors allows manufacturers to identify deviations, detect anomalies, and improve overall production efficiency. However, raw data collected during the injection molding process often contains redundant, irrelevant, or highly correlated features that can introduce noise and reduce the efficiency of predictive models. Without proper preprocessing, such data can lead to increased computational complexity and diminished model performance. To address these challenges, effective feature extraction techniques are essential for refining the dataset, minimizing prediction errors, and enhancing the interpretability of machine learning models. In this study, we compare two widely used feature extraction methods: Principal Component Analysis (PCA) and an Autoencoder (AE). The primary objective of this research is to assess the effectiveness of these feature extraction methods in monitoring the injection molding process and predicting product quality on an advanced machine learning model LSSVM. The experimental results presented in this study are useful in determining the suitability and disadvantages of each method, with the prediction accuracy of up to 99.62% for the extracted deep feature.

Surface roughness is a very important technical index of mechanical components that meets requirements for improving performance efficiency and reducing corrosion behavior in its working environment. Surface roughness is generally achieved by cutting methods using machine tools and cutting tools. The grinding process is a special finishing method using thousands of abrasives bonded together to form a grinding wheel for the finishing process with cost-effectiveness, productivity, and high quality. By controlling technological parameters, the grinding process produces products with high-quality of the roughness surfaces. However, it is difficult to compose a set of processing parameters for processing a hardened steel material such as the grinding process. This paper demonstrates a method of enhancing the quality of the surface roughness of SKD11 engineering steel material by controlling the grinding process parameters. The optimal grinding condition is conducted by using response surface methodology to analyze practical experiments designed by the Box-Behnken method to minimize the surface roughness of the final product during the grinding process. The results show that the prediction model of the surface roughness can be achieved with the minimum surface roughness of Ra of 0.591 µm and the processing parameters kit of v of 5 m/min, s of 3 mm/stroke, and t of 0.013 mm, respectively, via using the design of experimental method and the regression analysis law. The research hopes that the results will be referenced in the development of manufacturing technology for products that require high-quality index of surface roughness in the near future.