ELSA: a multisensor integration architecture for industrial grading tasks

This paper presents the topology of the Extended Logical Sensor Architectur e (ELSA) for multisensor integration and the methodology for constructing i ndustrial sensor integration systems based on this architecture. ELSA has b een developed for industrial applications, particularly, the on-line gradin g and classification of non-uniform food products. It addresses a number of issues specific to industrial inspection. The system must be modular and s calable to accommodate new processes and changing customer demands. It must be easy to understand so that non-expert users can construct, modify, and maintain the system. Furthermore, a data representation scheme which allows for the quantification of product deviations from an ideal model is requir ed. To address these needs, the sensors are encapsulated by a logical sensor mo del, providing robustness and flexibility. The construction methodology is based upon the object model which represents object classifications through combinations of primary features weighted by fuzzy membership functions. T he features guide the selection of sensors and processing routines; the cla ssifications determine the rulebase used by the inference engine for proces s decisions. Although inspection is the focus of this work, it is intended to be applicable to a variety of automation tasks which may benefit from a multiple sensor perception system. (C) 1999 Elsevier Science Ltd. All right s reserved.