The realization of a “smart factory” using manufacturing machines and Internet of Things (IoT) is desirable at manufacturing sites. Smart factories require intelligent machine tools. Monitoring, analytical, and guidance and control technologies are required for realization of intelligent machine tools. To meet the required machining accuracy for a product, the cutting condition is monitored, and information such as tool wear is detected and analyzed using the three technologies previously mentioned. Adjustments can then be made to the cutting conditions, the tool diameter correction amount, and the tool itself. In this study, an attempt was made to detect the tool wear state by monitoring the cutting process with an on-machine measurement system using the acoustic emission (AE) method. So, the cutting resistance, surface roughness, and abrasion of tool edge were measured during end milling of stainless steel (SUS 304). In addition, the relationship between the measured parameters and the AE signal was investigated. As a result, although the change in the AE signal amplitude was minor with respect to the change in the tool wear, when the tool wear width increased, many AE signal waveforms including the frequency component of 70kHz were observed. Furthermore, in the machining state where chips are adhered to the workpiece, an AE signal waveform including a frequency component of 350 to 1000kHz was observed.
View full abstract