Loading...

Investigation on Application of Vibration and Sound Signals for Tool Condition Monitoring

Rafezi, Hamed | 2011

761 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: English
  3. Document No: 41524 (58)
  4. University: Sharif University of Technology, International Campus, Kish Island
  5. Department: Science and Engineering
  6. Advisor(s): Behzad, Mehdi; Akbari, Javad
  7. Abstract:
  8. Tool Condition Monitoring (TCM) is a vital demand of advanced manufacturing in order to develop automated unmanned production. Tool condition has an essential influence on machined surface quality and dimension of manufactured parts. Continuing machining operation with a worn or damaged tool will result in damages to workpiece and even the machine tool itself. This problem becomes more important in supplementary machining processes like drilling in which the workpiece is usually at the final stages of production and any damage to workpiece at this stage is irreparable and results in high production losses. In this thesis, sound and vibrations signals are analyzed for drill wear detection. Signals are analyzed in a wide range of frequency compared to previous TCM approaches. Features of sound signal and vibration signals (in horizontal and vertical directions) from drilling process are analyzed to detect tool wear. At first, signal features are extracted and analyzed in the time domain. Then, frequency spectrum of signals is calculated using Fast Fourier Transform (FFT). The effect of cutting conditions and the tool diameter on signal features and frequency spectrum of signal are inspected. Signal frequency bands that are affected by tool wear are detected by frequency spectrum analysis. According to detected frequency bands, a novel member of wavelet transform family, i.e. Wavelet Packet Decomposition (WPD) is implemented to focus on specific frequency bands which are affected by tool wear. WPD is also used for elimination of environmental noise from sound signal. In order to develop a comprehensive and reliable TCM system for industrial applications, experiments were repeated with different cutting conditions and tool diameters to study the effect of these parameters on signal features and wear detection. Capability of inspected features for drill wear detection is evaluated and most informative features are introduced. Finally, a Feedforward Backpropagation Neural Network (FBNN) is designed and trained based on sound and vibration signals features obtained from wavelet packets. The FBNN provides a sensor fusion system to classify the drill wear state and to identify the worn drill before breakage. The sensor fusion approach increases the robustness of the wear detection system against environmental noise
  9. Keywords:
  10. Hole Drilling ; Vibration ; Sound ; Frequency Domain ; Feedforward Neural Network ; Tool Condition Monitoring ; Wavelet Packet Decomposition

 Digital Object List

  • محتواي پايان نامه
  •   view

 Bookmark

No TOC