Acoustic Emission Monitoring of the Cutting Process—Negating the Influence of Varying Conditions

Abstract

Earlier work has shown tool failure monitoring using frequency-based pattern recognition analysis of acoustic emission signals to be feasible while machining under fixed cutting conditions. However, cutting conditions change quite frequently in industrial production, and since AE signals are affected by varying conditions, a model is developed based on Taylor’s expansion using experimental data obtained for various process variables and their output AE spectra, and is used to filter the influence of varying conditions on signal classification. The experimental study involved a fractional factorial experimental design which delineated effects of variables on AE generation during machining. Normalized AE spectra within the 100 to 1000 kHz range were used as system output along with the AE power. While the normalized spectra were found unaffected by changes in the depth of cut, the total AE power was also little affected by the mixed flank and crater wear, and feed rate changes. Using the model and filter designed, performance of the tool wear, chip noise and tool breakage classifier improved to 83, 99, and 97 percent classification, respectively.

The effects of progressive wear on the frequency characteristic of acoustic emission acquired during face milling

“…Many authors have reported on frequency analysis of AE acquired by PZTs using different cutting conditions, mostly applied to steady state cutting [3,[5][6][7][8].…”

Acoustic emission and force sensor fusion for monitoring the cutting process

“…To enhance the izapability of a sensor system for monitoring all the relevant aspects of the cutting process, we consider, in this paper, a multi-sensor strategy based on AE and force signals. The analysis emphasizes the sensitivity of force signals, since a similar sensitivity study has already been done for AE [16]. In that study, AE signals were shown to be related to the shearing, frictional and fracture processes during machining.…”

“…In earlier work [16], we used AE for monitoring the turning process and achieved over 90% success in detecting tool breakage and chip segmentation, and over 85% success in identifying a threshold of flank wear under varying cutting conditions. These results were obtained when the classifier was tested with the same data used in designing it and are therefore optimistic.…”

Power signal separation in milling process based on wavelet transform and independent component analysis

“…spindle power consumption varies with the change of the depth of cut induced by workpiece geometry and material property variations. Generally, how to identify variations of cutting parameters is a major challenge in the development of tool condition monitoring techniques [13]. To overcome the problem, researchers have developed many signal processing methods based on FFT [14], time series analysis [15], wavelet analysis [16][17][18], sensor fusion [19], fuzzy recognition [20], neural network [21,22], genetic algorithm [23], etc.…”