Comparison and analysis of audible sound energy emissions during single point machining of HSTS with PVD TiCN cutter insert across full tool life

Abstract

In precision engineering, tool wear affects the dimensional accuracy and surface finish of machined components. Currently, errors associated with tool wear remain uncompensated for and are usually only detected at the end of the machine cycle, by which time the product may be scrap. If real-time, accurate monitoring were available, machine parameters could be adjusted to compensate for tool wear thereby minimising waste. Experienced machinists in Schivo Precision have been able to detect a poorly performing cutting operation through the sound emitted from the machining centre during the various phases of the cutting cycle and, although not a precise science, appear capable of informally differentiating between a good process and a degraded one. In this article experimental work was undertaken on a single point machining operation whereby the sound energy emissions from the machine were logged and analysed for the full life of the tools. The experiments demonstrated consistent acoustic signatures, which are specific to the tool in a known good cutting state, and distinct, but also consistent sound energy signatures, in a known bad cutting state. The experimental measurements replicated the audible range of human hearing and sought to determine what encouraged experienced machinists to declare a machining process to be in a state of degradation.

An Integration of Neural Network and Shuffled Frog-Leaping Algorithm for CNC Machining Monitoring

“…One of the well-known techniques is to measure and analyze Acoustic Emission (AE) from machining operations. AE has already been employed in numerous engineering systems with the aim of fault recognition [20,14]. Guo and Ammula [19] described the basic information required in the development of applied on-line AE monitoring system to check the surface integrity in hard machining.…”

Wear state evaluation of inner-diameter saw blade based on vibration and noise signals during processing

“…11 Aggregate spectral difference approach is commonly used to analyze noise signals spectrum change to detect tool wear. 12 Feature extraction method based on time–frequency domain analysis and adaptive kernel principal components analysis (AKPCA) can process noise-reduced audio signals to monitor tool wear. 13 Based on decision tree (J48 algorithm) technology, Madhusudana et al used discrete wavelet transform (DWT) method to extract a set of discrete wavelet features from the noise signals of milling tool for fault diagnosis of face milling cutters.…”

Monitoring of microturning process using acoustic emission signals

“…AE techniques are exact and can be used, for example, for carrying out instrumented tests in the sliding contact stress in several processes. Downey et al [7] developed a study to determine whether it was possible to monitor and predict the cutting tool integrity using a simple audio sensor of acoustic emission. The results showed that the analysis performed had a high capability to define the tool wear.…”