The initial design of a novel multivariate sensor is described for the measurement of melt temperature, melt pressure, melt velocity, melt viscosity, and mold temperature. Melt pressure and temperature are respectively obtained through the incorporation of a piezoceramic element and infrared photodetector within the sensor head. Melt velocity is derived from the initial response of the melt temperature as the polymer melt flows across the sensor's lens. The apparent melt viscosity is then derived from the melt velocity and the time derivative of the increasing melt pressure given the cavity thickness. The feasibility of the envisioned sensor is then analyzed using a production-grade mold that is instrumented with commercial piezoelectric pressure sensors, infrared pyrometer, and thermocouples. Several predictive models of part weight are developed using multiple regression of data obtained from a design of experiments to evaluate the capability of the envisioned multivariate sensor. The results indicate a correlation coefficient, R 2 , of 0.79 for a model based on the machine settings, 0.80 for a model based on a cavity pressure sensor, 0.90 for a model based on the multivariate sensor, and 0.98 for a non-linear model based on the multivariate sensor. The implication is that multiple orthogonal sensing streams with high fidelity models are necessary to provide automatic quality assurance sufficient for fully automated plastics manufacturing.