In recent years, the manufacturing industry faces increasing demands for productivity improvement due to labor shortages and rising raw material costs. To enhance productivity while ensuring machining quality, it is essential to implement automated monitoring systems that can detect tool anomalies during the machining process. This study aims to develop an automatic detection method for machining marks during BTA deep hole drilling using Acoustic Emission (AE) signals. An AE sensor and a photoelectric rotation detector were installed on the deep hole drilling machine to measure AE signals and rotational pulse signals at high sampling rates (1 MHz). This study focused on enhancing the signal-to-noise ratio (S/N) through band-pass filtering and analyzing the phase of rotationally synchronized components to detect machining marks. The developed detection method was validated through tests on approximately 10,000 holes. The authors found that the phase trend of the rotational synchronization component of the AE signal becomes a stripe pattern when machining marks occur. To quantify the strength of the stripe pattern, we devised an indicator “phase difference concentration”. It was confirmed that all machining marks could be detected by using the indicator. As a future work, the authors are planning to develop the system which can detect the machining mark automatically during machining in real time.
Kumagai et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: