Multi-source data-driven approach for prediction of melt density during polymer compounding

Melt density is a crucial quality indicator for polymer composites, yet real-time measurement remains challenging due to processing complexities. While existing machine learning methods offer solutions, they often fall short in complex compounding scenarios. This study presents a novel multi-source data-driven approach for measuring melt density in polycarbonate/acrylonitrile butadiene styrene blends. By incorporating ultrasonic, near-infrared, and Raman spectra data acquired during melt processing, a deep separable convolutional neural network model is developed to predict melt density accurately. The model effectively fuses multi-source data to establish the mapping relationship between input data and melt density output. Results demonstrate the model's ability to monitor melt density in real-time, achieving a prediction accuracy with RMSE and R2 indexes of 0.005 g/cm3 and 0.9841, respectively. The proposed approach outperforms existing methods, showcasing its effectiveness and superiority in melt density prediction for polymer compounding processes.Highlights Establishment of the real-time monitoring system for polymer extrusion processes. Conversion of multi-sensor signals into time-frequency images using wavelet decomposition. Fusion of sensor data into a three-channel tensor-image. Development of a data-driven DSCNN model for predicting melt density. Implementation for online monitoring and prediction in PC/ABS compounding system. Sensor data acquisition and DSCNN model monitoring process diagram. image