MONITORING MANUFACTURING PROCESSES BY UTILIZING EMPIRICAL MODELING

Application of acoustic emission analysis to the characterization of m anufacturing processes and produces is demonstrated. The relations bet ween characteristics of AE signals and process parameters are modeled empirically. The model is built nonparametrically by a self-organized information processing system which resembles a neural network. The ne twork structure is derived based on the statistical description of nat ural phenomena. During learning the modeler creates a set of represent ative data which comprise acoustic emission and process characteristic s. These data are utilized at the process monitoring for an associativ e estimation of process characteristics from the input acoustic signal s. The performance of the complete sensory-neural network is demonstra ted using examples of turning, grinding and friction processes. It is shown how the cutting tool wear, the roughness of the ground surface a nd the quality of the surface which is generating friction can be esti mated on-line. (C) 1998 Elsevier Science B.V.