The monitoring of tool wear plays an important role in improving the processing e ciency and reducing the production cost of enterprises. This paper is focused on the detection of electroplated diamond millgrinding tools by using the acoustic emission sensor. The wear stages of mill-grinding tools are divided into three parts, namely initial wear stage, normal wear stage, and severe wear stage. The characteristic parameter method and the waveform analysis method are applied to analyze the acoustic emission signals. The wear characteristics of the tool and workpiece in different wear stages are observed and analyzed. The results indicate that the acoustic emission waveform is relatively stable in the initial wear stage, and the continuous acoustic emission signal is dominated. Moreover, the diamond abrasive grains are mainly worn and slightly broken in the normal wear stage, and there are some pits on the machined workpiece surface after the initial wear stage. In the severe wear stage, most of the abrasive grains are broken or broken in a large area, and there are burst acoustic emission signals in the waveform.
1.introductionIn recent years, acoustic emission technology, as a mature non-destructive testing method, has been more and more widely used in many elds, such as various industries in national defense and the economy [1]. With the continuous improvement of acoustic emission technology, it has also been applied in the eld of mechanical structures [2, 3].In the aspect of mechanical equipment operating condition and fault diagnosis identi cation, Faris et al. [4] explored the characteristics of acoustic emission and vibration signals in diagnosing a bearing defect in the planetary gearbox. What's more, the application of acoustic emission testing technology to fatigue and crack detection of components can effectively predict other types of faults such as crack initiation and propagation. He et al. [5] studied the noise interference in the acoustic emission signal of rotor crack, and he also analyzed the acoustic emission signal characteristics of propagation under different working conditions by using wavelet packet technology. Zhang et al. [6] used the acoustic emission detection technology to record the acoustic emission signals of rail defects. Meanwhile, the wavelet transform and Shannon entropy were employed to process the signals. When monitoring the micro-fracture process of ssured rocks, a series of biaxial compression tests was carried out on sandstone specimens with two parallel lled aws exploiting the acoustic emission (AE) [7]. By analyzing the acoustic emission signal data, Elforjani et al. [8] investigated the crack propagation, subsurface crack initiation, and location of natural defects in rolling bearings. In the eld of machining, metal burn is a common problem. Different degrees of metal burns will cause different degrees of damage to related components. Gao et al. [9] used an infrared thermal imager and acoustic emission sensor to explore the relationship between the combustion degree of 1...