Multi-sensor data fusion for improved measurement accuracy in injection molding

摘要

Data fusion enables the integration of multiple sensing data associated with the same physical process for more comprehensive process representation, thereby improving quality control in manufacturing. Based on a correlation analysis of measurement data, the effectiveness of data fusion has been investigated, using precision injection moulding as an application context and the predicted weight of moulded parts as a criterion. The study systematically explains why a multivariate sensor that quantifies four parameters at the same sensor location has consistently outperformed multiple single-parameter commercial sensors under various operation conditions, thereby contributing to the theory of data fusion for measurement enhancement.