Audio-Based Tool Condition Monitoring in Milling of the Workpiece Material With the Hardness Variation Using Support Vector Machines and Convolutional Neural Networks

2018 ◽  
Vol 140 (11) ◽  
Author(s):  
Achyuth Kothuru ◽  
Sai Prasad Nooka ◽  
Rui Liu
Keyword(s):  
Tool Wear ◽  
Condition Monitoring ◽  
Tool Condition Monitoring ◽  
Classification Model ◽  
Support Vector ◽  
Workpiece Material ◽  
Artificial Intelligent ◽  
Tool Condition ◽  
Hardness Variation ◽  
Audible Sound

Machining industry has been evolving toward implementation of automation into the processes for higher productivity and efficiency. Although many studies have been conducted in the past to develop intelligent monitoring systems in various application scenarios of machining processes, most of them just focused on cutting tools without considering the influence of the nonuniform hardness of workpiece material. This study develops a compact, reliable, and cost-effective tool condition monitoring (TCM) system to detect the cutting tool wear in machining of the workpiece material with hardness variation. The generated audible sound signals during the machining process are analyzed by state-of-the-art artificial intelligent techniques, support vector machine (SVM) and convolutional neural network (CNN), to predict the tool wear and the hardness variation of the workpiece. A four-level classification model is developed for the system to detect the tool wear condition based on the width of the flank wear land and the hardness variation of the workpiece. This study also involves the comparative analysis between two employed artificial intelligent techniques to evaluate the performance of the model in prediction. The proposed TCM system has shown a high prediction accuracy in detecting the tool wear from the audible sound into the proposed multiclassification wear level in end milling of the nonuniform hardened workpiece.

Audio-Based Condition Monitoring in Milling of the Workpiece Material With the Hardness Variation Using Support Vector Machines and Convolutional Neural Networks

2018 ◽  
Author(s):  
Achyuth Kothuru ◽  
Sai Prasad Nooka ◽  
Rui Liu
Keyword(s):  
Neural Networks ◽  
Support Vector Machines ◽  
Tool Wear ◽  
Support Vector ◽  
Workpiece Material ◽  
Artificial Intelligent ◽  
Tool Condition ◽  
Hardness Variation ◽  
Vector Machines ◽  
Audible Sound

Machining industry has been evolving towards implementation of automation into the process for higher productivity and efficiency. Although many studies have been conducted in the past to develop intelligent monitoring systems in various application scenarios of machining processes, most of them just focused on cutting tools without considering the influence due to the non-uniform hardness of workpiece material. This study develops a compact, reliable, and cost-effective intelligent Tool Condition Monitoring (TCM) model to detect the cutting tool wear in machining of the workpiece material with hardness variation. The generated audible sound signals during the machining process will be analyzed by state of the art artificial intelligent techniques, Support Vector Machines (SVMs) and Convolutional Neural Networks (CNNs), to predict the tool condition and the hardness variation of the workpiece. A four-level classification model is developed for the system to detect the tool wear condition based on the width of the flank wear land and hardness variation of the workpiece. The study also involves comparative analysis between two employed artificial intelligent techniques to evaluate the performance of models in predicting the tool wear level condition and workpiece hardness variation. The proposed intelligent models have shown a significant prediction accuracy in detecting the tool wear and from the audible sound into the proposed multi-classification wear class in the end-milling process of non-uniform hardened workpiece.

Tool condition monitoring system based on support vector machine and differential evolution optimization

2016 ◽  
Vol 231 (5) ◽  
pp. 805-813 ◽  
Author(s):  
Guo F Wang ◽  
Qing L Xie ◽  
Yan C Zhang
Keyword(s):  
Support Vector Machine ◽  
Tool Wear ◽  
Differential Evolution ◽  
Condition Monitoring ◽  
Support Vector Machine Classifier ◽  
Tool Condition Monitoring ◽  
Support Vector ◽  
Grid Search ◽  
Tool Condition ◽  
Condition Monitoring System

A tool condition monitoring system based on support vector machine and differential evolution is proposed in this article. In this system, support vector machine is used to realize the mapping between the extracted features and the tool wear states. At the same time, two important parameters of the support vector machine which are called penalty parameter C and kernel parameter [Formula: see text] are optimized simultaneously based on differential evolution algorithm. In order to verify the effectiveness of the proposed system, a multi-tooth milling experiment of titanium alloy was carried out. Cutting force signals related to different tool wear states were collected, and several time domain and frequency domain features were extracted to depict the dynamic characteristics of the milling process. Based on the extracted features, the differential evolution-support vector machine classifier is constructed to realize the tool wear classification. Moreover, to make a comparison, empirical selection method and four kinds of grid search algorithms are also used to select the support vector machine parameters. At the same time, cross validation is utilized to improve the robustness of the classifier evaluation. The results of analysis and comparisons show that the classification accuracy of differential evolution-support vector machine is higher than empirical selection-support vector machine. Moreover, the time consumption of differential evolution-support vector machine classifier is 5 to 12 times less than that of grid search-support vector machine.

Influence of Sensor Positioning in Tool Condition Monitoring of Drilling Process through Vibration Analysis

2014 ◽  
Vol 984-985 ◽  
pp. 564-569 ◽  
Author(s):  
Ramasamay S. Nakandhrakumar ◽  
D. Dinakaran ◽  
S. Satishkumar ◽  
M. Gopal
Keyword(s):  
Tool Wear ◽  
Condition Monitoring ◽  
Vibration Amplitude ◽  
Statistical Parameter ◽  
Tool Condition Monitoring ◽  
Drilling Process ◽  
Workpiece Material ◽  
Vibration Signals ◽  
Tool Condition ◽  
Sensor Positioning

In this study, the relationship between vibration and tool wear and also influence of sensor positioning in tool codition monitoring were investigated during drilling. For this purpose, a series of experiment were conducted in a CNC vertical milling machine using drilling cycle. A 6 mm diameter HSS drill and EN24 as workpiece material were used in these experiments. The vibration was measured in the transverse direction of sensor which is positioned on the workpiece with constant distance from the holes to be drilled for monitoring tool wear as in previous studies. But, positioning of sensor in a constant place with equal distance from all holes to be drilled is not possible for all the workpiece profiles in actual practice. Experiments show that the distance of sensor from the holes in drilling affects the vibration signals for the same state of wear.It shows that the tool wear models presented in previous studies using acceleration signals are sensor location dependent. This work presents a Variance-amplitude of the vibration signals received for tool condition monitoring which is the most sensitive statistical parameter than other statistical parameters such as Root Mean Square (RMS), Exponential, Peak, max-min, mean and standard deviation. Results showed that there was no considerable increase in the vibration amplitude of variance until flank wear value of 0.30 mm was reached, above which the vibration amplitude increased significantly.

Experimental Investigation to Predict Tool Wear and Vibration Displacement in Turning – A Base for Tool Condition Monitoring

2016 ◽  
Vol 16 (2) ◽  
pp. 103-114
Author(s):  
M. Prakash Babu ◽  
Balla Srinivasa Prasad
Keyword(s):  
Mathematical Model ◽  
Tool Wear ◽  
Condition Monitoring ◽  
Cutting Forces ◽  
Cutting Tool ◽  
Tool Condition Monitoring ◽  
Depth Of Cut ◽  
Vibration Displacement ◽  
Tool Condition ◽  
Tool Vibrations

AbstractIn the present work investigation primarily focuses on identifying the presence of cutting tool vibrations during face turning process. For this purpose an online non-contact vibration transducer i. e. laser Doppler Vibrometer is used as part of a novel approach. The revisions in the values of cutting forces, vibrations and acoustic optic emission signals with cutting tool wear are recorded and analyzed. This paper presents a mathematical model in an attempt to understand tool lifeunder vibratory cutting conditions. Tool wear and cutting force data are collected in the dry machiningof AISI 1040 steel at different vibrationinduced test conditions. Identifying the correlation among tool wear, cutting forces and displacement due to vibration is a critical task in the present study. These results are used to predict the evolution of displacement and tool wear in the experiment. Specifically, the research tasks include: to provide an appropriate experimental data to prove the mathematical model of tool wear based on the influence of cutting tool vibrations in turning.The modeling is focused on demonstrating the scientific relationship between the process variables such as vibration displacement, vibration amplitude, feedrate, depth of cut and spindle speed while getting into account machine dynamics effect and the effects such as surface roughness and tool wear generated in the operation. Present work also concentrates on the improvement in machinability during vibration assisted turning with different cutting tools. The effect of work piece displacement due to vibration on the tool wear is critically analyzed. Finally, tool wear is established on the basis of the maximum displacement that can be tolerated in a process for an effective tool condition monitoring system.

Acoustic Emission Signal Analysis for Tool Condition Monitoring in Microturning of Titanium Alloy

2014 ◽  
Vol 984-985 ◽  
pp. 31-36 ◽  
Author(s):  
A. Gopikrishnan ◽  
A.K. Nizamudheen ◽  
M. Kanthababu
Keyword(s):  
Acoustic Emission ◽  
Titanium Alloy ◽  
Tool Wear ◽  
Condition Monitoring ◽  
Dominant Frequency ◽  
Tool Condition Monitoring ◽  
Discrete Wavelet ◽  
Nose Radius ◽  
Emission Signal ◽  
Tool Condition

In this work, an online acoustic emission (AE) monitoring system is developed, to investigate the effect of tool wear during the microturning of titanium alloy with a tungsten carbide insert of nose radius 0.1 mm. The AE signal parameters were analyzed in time domain, frequency domain and discrete wavelet transformation (DWT) techniques to correlate with the tool wear status. The root mean square (AERMS) and specific AE energies are also computed for the decomposed AE signals, using the DWT. The results demonstrated that dominant frequency and DWT techniques are found to be most suitable for online tool condition monitoring, using AE sensors in the microturning of titanium alloy.

Sign in / Sign up

Export Citation Format

Share Document