Detecting and evaluating operation-dependent processes in automated production utilizing fuzzy operators and neural network system
OwnerGünther Battenberginventor
Life of this patent
Estimating the term…
Abstract
A system (10) testing and rating operation-dependent processes and/or components (20) in automated production and test sequences comprises a robot (12) which by means of a minimum of one sensor (14, 16) detects test/measured values (M) of at least one operating and/or display element (22, 24) of the component (20) to be tested respectively rated and transmits to an analyzer (40) analyzing and rating the measured values (M) by means of defined quality functions (50), said quality functions by means of operators (52) imitating human rating schematics respectively rules and based on this processing result generating at least one rating.
Claims32
System (10) to test and rate operation-dependent processes or components (20) in automated production and test sequences, comprising a robot (12) that by means of at least one sensor (14, 18) at a minimum of one operating or display element (22, 24) detects measurement/test values (M) of the component (20) to be tested respectively be rated and transmits said values to an computer (40) which by means of quality functions (50) analyzes and rates said measured values (M), by means of fuzzy operators (52) imitating human rating schematics respectively fuzzy rules and based on them generate at least one rating as the result, wherein a rating diagram taking into account gradual transitions between the fixed boundary values criteria is formally reproduced by means of the quality functions, and further wherein the rating of the quality functions is implemented using a neuronal network.
Dependencies are inferred from the claim text.