Intelligent Fusion of Sensor Data for Product Quality Assessment in a Fishcutting Machine

Abstract

This article presents three techniques of knowledge-based fuzzy sensor fusion, which are based on (1) Mamdani sup-prod composition, (2) degree of certainty, and (3) compatibility of data. The first method of sensor fusion uses Mamdani's sup-prod (or max-prod) composition, and it places equal weights on all the data sources, without considering their merit or importance. The second method uses the concept of degree of certainty. It assigns weights proportional to the degree of certainty of sensor data, and in addition to the fused output, it provides information about the certainty of the output. The third method of sensor fusion uses the idea of compatibility of data. It provides a fused output and additional knowledge about the degree of confidence in that output. This method is particularly effective when sensors provide conflicting information. The three techniques are implemented in an automated machine for mechanical processing of salmon, to determine the level of product quality (i.e., the quality of processed fish), and thereby evaluate the relative performance of the techniques. In this machine, process information is available from disparate sensors like CCD cameras, optical encoders, and an ultrasonic displacement sensor. Three sets of fish-cut data for a good, a bad, and a conflicting data cut are used in the illustrative example. The results indicate that the three methods are equally effective, but method 2, which is more sophisticated, has a slight advantage in performance over the other, at the expense of added complexity.