Frequency and time domain analyses of sensor signals in drilling—II. Investigation on some problems associated with sensor integration

摘要: Abstract Sensor integration has received considerable attention recently for monitoring machining processes. This is because it similar to the action of an experienced machinist, who uses his different sensory devices such as hearing, sight, etc. monitor cutting operation. Different neural network paradigms have been attempted by researchers this purpose. In investigation, a multisensor approach drill wear was studied. Four sensors, namely, thrust, torque, and strains on machine table in two orthogonal directions perpendicular axis, were used. As shown Part I [A. Noori-Khajavi R. Komanduri, Int. J. Mach. Tools Manufact . 35 , 000-000 (1995)] three sensor signals, strain X -direction, showed good correlation frequency domain with wear. addition, signal-to-noise ratio analysis at states that increased, noise also increased. paper, will be when signals are noisy integrated using network, system could actually result deterioration correct estimation Consequently, there appears no need under conditions