Investigation on feasibility of recurrence quantification analysis for detecting flank wear in face milling

Abstract

Flank wear is a critical phenomenon which has direct impact on quality of surface finish, dimensional precision and ultimately cost of the finished product. In any metal cutting operation, cutting tool wear estimation will help in identifying tool state, which is a critical factor in productivity. In this paper, the vibration signals are used for detecting flank wear in face milling .The vibration signals are analyzed using a novel non linear technique called recurrence quantification analysis (RQA). RQA includes time delay and dimensions embedding process so as to reconstruct the time series data of vibration signal, to obtain better information of the changes in nonlinear dynamics underlying the milling process. An investigation of this technique was carried out to see its capability in detecting flank wear in face milling. Experiments were conducted on universal milling machine using AISI H11 steel as work material. The investigation proved that RQA technique has a good potential in detecting flank wear in face milling. The RQA parameters such as percent recurrence (REC), trapping time (TT), percent laminarity (LAM) and entropy (ENT), and also the recurrence plots color patterns for different flank wear, can be used in detecting insert wear in face milling.

Damage detection of composite milling process by recurrence plots and quantifications analysis

“…In paper [7], the feasibility of RQA to detect flank wear in face milling has been investigated. Both qualitative and quantitative approaches were used in order to detect tool wear.…”

Automatic Assessment of Expanded Disability Status Scale (EDSS) in Multiple Sclerosis Using a Decision Tree

“…That may be caused by using a combination of several measures in this model and the combination can reduce the error generated by using only one measure. Meanwhile, we introduced our tree two non-linear measures (TTV and TTA) which are able to evaluate the complexity of a dynamic system, because TT represents the average time in which the system is trapped in a specific state [9]. In our selected decision tree, the root node (in the level 1) is S (node 1) and the nodes in the level 2 are S (node 3) and TTA (node 2).…”

Condition monitoring of face milling tool using K-star algorithm and histogram features of vibration signal

“…Hsueh and Yang [15] used the SVM technique in prediction of breakage in face milling cutter using cutting force signals. Mhalsekar et al [25] investigated the vibration signals during face milling using recurrence quantification analysis (RQA) for monitoring the flank wear of tool insert. They concluded that RQA parameters such as entropy, percent laminarity, trapping time and percent recurrence are useful features for detecting the tool flank wear.…”