Instantaneous Drill Bit Wear Level Detection in CNC Machine using Wavelet Transform
K Senthil Kumar1, L Saravanan2, A Balaji3
1K Senthil Kumar, Associate Professor, Department of ECE, Rajalakshmi Institute of Technology, Chennai, (Tamil Nadu), India.
2L Saravanan, Assistant Professor, Department of ECE, Rajalakshmi Institute of Technology, Chennai, (Tamil Nadu), India.
3A Balaji, Assistant Professor, Department of ECE, Rajalakshmi Institute of Technology, Chennai, (Tamil Nadu), India.
Manuscript received on November 27, 2019. | Revised Manuscript received on December 15, 2019. | Manuscript published on December 30, 2019. | PP: 918-923 | Volume-9 Issue-2, December, 2019. | Retrieval Number: A2017109119/2020©BEIESP | DOI: 10.35940/ijeat.A2017.129219
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The usage of machine tools is widely increased to industrial automation, manufacturing, production technology and etc. The machine tool wear condition monitoring is playing a key role to increase accuracy of the dimension in the final product. By monitoring the wearing level, the life time of the tool is accurately detected and tools can be replaced at the correct time and it can be used to minimize the process time of the task. But it is difficult to monitor and detect the machine tool weariness level from the direct methods. From the indirect methods, the weariness levels of Computer Numerical Control (CNC) machine tool for Acoustic Emission(AE) property is approached in this paper. The AE signals are recorded and preprocessed to extract the features of different wearing conditions using Wavelet Transform(WT). The WT is used to extract the discriminating features that are indirectly reflecting the wearing levels of machine tools. The CNC machines tool weariness at various stage is evaluated from statistical indexes and analyzed based on the relation between the energy distribution of machined surface and wear state of the bit. This approach effectively detects real-time wearing levels of drilling tools by AE using Wavelet technique.
Keywords: CNC machine, Machine tool, Acoustic emission, Wavelet transform, Statistical parameters.