Abstract: A system and method for monitoring vibrations of a cutting tool uses a neural network for classifying signal features as break or non-break or, in another embodiment, as non-break or abnormal. A vibration signal is produced by an accelerometer, positioned to sense vibrations at the tool-workpiece interface. The signal is pre-processed to extract low frequency machining noise and detect the energy in a higher frequency band. The signal is then sampled and segments of the digitized signals are processed by digital logic into feature vectors for input to a trained neural net having two output nodes for classification. The use of a neural net provides performance improvement and economies over previously known heuristic methods of signal analysis.

Abstract: Breaking of a cutter insert in a multiple insert metal cutter is detected by selecting a periodic vibration generated electrical signal having components which track individual insert contribution. These components are filtered to provide RMS values whose predetermined ratio values indicate insert breakage.

Abstract: A composite low frequency high frequency electrical signal from a metal cutting tool in a metal cutting operation is processed through separate high frequency and low frequency systems and the resulting signals digitized and combined for analysis of a tool break event.

Abstract: In a metal cutting tool wear indicator system, a ratio of an estimated ultrasonic emission signal from a metal cutting process to a measured ultrasonic emission signal, e.g. UE/UE is utilized in place of a prior ratio of horsepower to ultrasonic emission, e.g. HP/UE, together with a continuous revision of the estimator during the cutting process.