한국정밀공학회지 제15권 제4호 (1998년 4월)
절삭조건과 절삭력 파라메타를 이용한 공구상태 진단에 관한 연구 (II)
A Study on the Diagnosis of Cutting Tool States Using Cutting Conditions and Cutting Force Parameters (II) ABSTRACT
In this study, statistical and neural network methods were used to recognize the cutting tool states. This
system employed the tool dynamometer and cutting force signals which are processed from the tool
dynamometer sensor using linear discriminent function. To learn the necessary input/output mapping for
turning operation diagnosis, the weights and thresholds of the neural network were adjusted according to
the error back propagation method during off-line training. The cutting conditions, cutting force ratios and
statistical values(standard deviation, coefficient of variation) abtained from the cutting force signals were
used as the inputs to the neural network. Key Words :error back propagation(오차역전파), neural network(신경회로망), cutting condition(절삭조건) cutting force parameter(절삭력 파라메타)
#
논문의 全文
|
