This work presents a new scheme to measure both fluidic viscosity and density simultaneously using PMUTs (piezoelectric micromachined ultrasonic transducers) with the assistance of machine learning. Advancements as compared to the state-of-art works include: (1) using PMUT pulse-echo signals to extract multiple fluid properties simultaneously with the assistance of machine learning; (2) differentiating viscosity and density successfully; and (3) sensing results with an error of 1.6 ± 1.57 % for viscosity and 0.20 ± 0.17 % for density for testing fluids in the viscosity range of 0.9 to 1.9 cp and density range of 1 to 1.05 g/mm. As such, this sensing technique could be applicable for continuous and precision monitoring of liquid property changes versus time such as engine oil degradations in oil and marine industry.
Keywords: Viscosity, Density, ultrasound measurement, pulse-echo method, pMUTs, Machine Learning.