Improving the Accuracy of Mixture Estimation in Peristaltic Continuous Mixing Conveyor Simulating Intestines with Distributed Sensing System

Abstract

We proposed herein a method for estimating the mixing state of the contents of a peristaltic continuous mixing conveyor simulating the intestine, developed for mixing and conveying powders and liquids. This study serves to improve a previously proposed method for estimating the mixing state using a logistic regression model with the pneumatic factor sensors installed in the device as inputs. To improve the estimation method, we changed the method of acquiring training data and labeling in the learning model. Moreover, comparison of the estimation accuracy and the result of the proposed method was better than that of the previous method.