LAUSR

The rich information from the input electrical signal of the injection molding machine can independently reflect the characteristics of the whole state of the equipment, which is an ideal signal for analyzing the manufacturing process. In this study, a method of analyzing the injection molding process by input electrical signal is presented, and the related applications of this method are discussed. Eight kinds of electrical signals during the molding process are measured for this method. The principal components analysis (PCA), optimum segmentation method, and continuous wavelet transform (CWT) are introduced to build the multivariate ordered time series segmentation method. After segmenting the processes, a mathematical model is established to investigate the relationship between the electrical power consumption and screw speed. The injection energy is divided into kinetic energy and internal energy, which is equal to the electrical energy. The results show that the accuracy of this segmentation method can reach 92.6% under appropriate parameters. Moreover, the results of the model show that the error between the calculated results and the measured results is less than 10% in the initial stage of injection. The methods provide a new way of analyzing the injection molding process for improving molding quality stability.