Multi-Sensor Data Fusioning of Monitoring Deep-Hole Drill Bit

Abstract

For the deep-hole drilling bit works in closed or half-closed condition and the cutting situation can not be observed and controlled directly, it brings a big challenge to monitor the cutting tools and the cutting process. To solve the problem, improved testing methods and data processing techniques were developed. A new condition monitoring method of deep-hole drilling based on multi-sensor data fusion was discussed in the paper. The signals of vibration and cutting force were collected when the condition of deep-hole drilling on stainless steel was normal and abnormal. Four eigenvectors were extracted on time-domain analysis and frequency-domain analysis of the signals. Then the combined four eigenvectors were sent to BP neural networks data fusioning center. The fusioning results indicate that cutting force signal can reflect the condition of drill bit better than vibration signal and multi-sensor data fusion is superior to single-sensor.