SENSOR TECHNOLOGY INTEGRATION IN AN INTELLIGENT MACHINE FOR HERRING ROE GRADING

In this paper, the development and integration of sensor technology fo r herring roe grading is described. In this application, by and large, grading is presently done by hand. Shape, firmness/texture, color and weight all play key roles in determining the grade of a roe skein. Fu rthermore, a number of these variables are quite subjective both in th e way they are determined by human graders, and in the way they affect the overall grade of a skein. Thus, in the present system an ''intell igent'' decision-making system, with multiple levels of abstraction, i s used to determine the final grade of the product, The system uses a model base and also a knowledge base developed through interactive acq uisition of knowledge from grading experts and off-line experiments, T hese are implemented as a set of fuzzy-logic rules and model matching procedures. A prototype grading machine has been developed and tested at an industrial plant. Typical experimental results are presented and studied.