Development of Sound Based Tool Wear Monitoring System in Micro-Milling

2010 ◽  
Author(s):  
Ming-Hsing Lee ◽  
Ming-Chyuan Lu ◽  
Jhy-Cherng Tsai
Keyword(s):  
Tool Wear ◽  
Monitoring System ◽  
System Development ◽  
Micro Milling ◽  
Tool Wear Monitoring ◽  
Classification Rate ◽  
Linear Discriminant ◽  
Audible Sound ◽  
Micro Tool ◽  
Wear Monitoring

A micro tool wear monitoring system based on the audible sound signal was developed and studied in this report. Three modules featuring the signal transformation, feature selection and classification, respectively, were included in this system. A micro milling experiment was conducted on a research platform and the audible sound signals collected by the microphone during the cutting processes were obtained for system development and verification. In the system development, the audible sound was first transformed to the frequency domain and the best features for condition classification was selected based on the class scatter criteria. In classifier design, the Fisher Linear Discriminant (FLD) was used to identify the tool wear condition from the selected features. This study shows that the performance of system was affected by the bandwidth of the feature, as well as the number of features selected for classification. With carefully selecting the parameters, higher than 90% classification rate can be obtained by this system for micro tool condition monitoring.

Study of AE Signal for Tool Wear Monitoring in Micro Milling Based on LVQ Algorithm

2010 ◽  
Vol 126-128 ◽  
pp. 719-725 ◽  
Author(s):  
Chia Liang Yen ◽  
Ming Chyuan Lu ◽  
Jau Liang Chen
Keyword(s):  
Acoustic Emission ◽  
Tool Wear ◽  
Frequency Domain ◽  
Micro Milling ◽  
Tool Wear Monitoring ◽  
Characteristic Analysis ◽  
Classification Rate ◽  
Ae Signal ◽  
Wear Monitoring ◽  
Wear Condition

The Acoustic Emission signal was studied in this report for tool wear monitoring in micro milling. An experiment was conducted first to collect the AE signal generated from the workpiece during cutting process for characteristic analysis, training the system model and finally testing the system performance. In the system development, Acoustic Emission (AE) signals were first transformed to the frequency domain with different feature bandwidth, and then the Learning Vector Quantization (LVQ) algorithms was adopted for classifying the tool wear condition based on the generated AE spectral features. The results show that the frequency domain signal provides the better characteristics for monitoring tool wear condition than the time domain signal. In considering the capability of the AE signal combined with LVQ algorithms, the sharp tool condition can be detected successfully. At the same time, 80% to 95% of the classification rate can be obtained in this study for the worn tool test. Moreover, the increase of the feature bandwidth improved the classification rate for the worn tool case and 95% of classification rate for the case with 10 kHz feature bandwidth.

Application of Audible Sound Signals for Tool Wear Monitoring and Workpiece Hardness Identification in Gear Milling Using Machine Learning Techniques

2017 ◽  
Author(s):  
Achyuth Kothuru ◽  
Sai Prasad Nooka ◽  
Patricia Iglesias Victoria ◽  
Rui Liu
Keyword(s):  
Machine Learning ◽  
Tool Wear ◽  
Learning Algorithm ◽  
Machining Process ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Process Conditions ◽  
Tool Wear Monitoring ◽  
Audible Sound ◽  
Wear Monitoring

The machining process monitoring, especially the tool wear monitoring, is very critical in modern automated gear machining environment which needs instant detection of cutting tool state and/or process conditions, quick final diagnosis and appropriate actions. It has been realized that the non-uniform hardness of the workpiece material due to the improper heat treatment can cause expedited tool wear and unexpected tool breakage, which greatly increases difficulties and complexities in monitoring the tool conditions in gear cutting. This paper provides a solution to detect the wear conditions of the gear milling cutter in the cutting of workpiece materials with hardness variations using the audible sound signals. In this study, cutting tools and workpieces are prepared to have different flank wear classes and hardness variations respectively. A series of gear milling experiments are operated with a broad range of cutting conditions to collect sound signals. A machine learning algorithm that incorporates support vector machine (SVM) approach coupled with the application of time and frequency domain analysis is developed to correlate observed sound signals’ signatures to specified tool wear classes and workpiece hardness levels. The performance evaluation results of the proposed monitoring system have shown accurate predictions in detecting tool wear conditions and workpiece hardness variations from the sound signals in gear milling.

Sign in / Sign up

Export Citation Format

Share Document