journal article·2019-09-18Open access

An Intelligent Milling Tool Wear Monitoring Methodology Based on Convolutional Neural Network with Derived Wavelet Frames Coefficient

Xincheng Cao, Binqiang Chen, Bin Yao, Shiqiang Zhuang

Applied Sciences· Volume 9· Issue 18

Abstract

Tool wear and breakage are inevitable due to the severe stress and high temperature in the cutting zone. A highly reliable tool condition monitoring system is necessary to increase productivity and quality, reduce tool costs and equipment downtime. Although many studies have been conducted, most of them focused on single-step process or continuous cutting. In this paper, a high robust milling tool wear monitoring methodology based on 2-D convolutional neural network (CNN) and derived wavelet frames (DWFs) is presented. The frequency band of high signal-to-noise ratio is extracted via derived wavelet frames, and the spectrum is further folded into a 2-D matrix to train 2-D CNN. The feature extraction ability of the 2-D CNN is fully utilized, bypassing the complex and low-portability feature engineering. The full life test of the end mill was carried out with S45C steel work piece and multiple sets of cutting conditions. The recognition accuracy of the proposed methodology reaches 98.5%, and the performance of 1-D CNN as well as the beneficial effects of the DWFs are verified.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Advanced machining processes and optimization · Advanced Machining and Optimization Techniques · Advanced Surface Polishing Techniques

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

School of Aerospace Engineering, Xiamen University, Xiamen 361005, China

New Jersey Institute of Technology, University Heights Newark, NJ 07102, USA

Funding

National Natural Science Foundation of China · Natural Science Foundation of Guangdong Province · Natural Science Foundation of Fujian Province

References (60)

Show source-provided references
2. Tool condition monitoring in turning by applying machine vision10.1115/1.4031770 ↗
3. A review of flank wear prediction methods for tool condition monitoring in a turning process10.1007/s00170-012-4177-1 ↗
4. Sensor fusion for online tool condition monitoring in milling10.1080/00207540500536913 ↗
5. Flank wear estimation in turning through wavelet representation of acoustic emission signals10.1115/1.538886 ↗
6. Analysis of sound signal generation due to flank wear in turning10.1115/1.1511177 ↗
7. Approach into the use of probabilistic neural networks for automated classification of tool malfunctions in broaching10.1016/j.ijmachtools.2005.09.017 ↗
8. Condition monitoring of railway track
9. Advancing cutting technology10.1016/S0007-8506(07)60200-5 ↗
10. Real-time tool wear monitoring in milling using a cutting condition independent method10.1016/j.ijmachtools.2014.10.011 ↗
11. A sensor fusion and support vector machine based approach for recognition of complex machining conditions10.1007/s10845-016-1209-y ↗
12. Online Monitoring of Tool Wear and Surface Roughness by using Acoustic and Force Sensors10.1016/j.matpr.2017.11.521 ↗
13. Acoustic Emission-Based Tool Condition Classification in a Precision High-Speed Machining of Titanium Alloy: A Machine Learning Approach10.1142/S1469026818500177 ↗
14. State of health monitoring in machining: Extended Kalman filter for tool wear assessment in turning of IN718 hard-to-machine alloy10.1016/j.jmapro.2016.06.015 ↗
15. Face milling tool condition monitoring using sound signal10.1007/s13198-017-0637-1 ↗
16. Tool flank wear monitoring using torsional—Axial vibrations in drilling10.1007/s11740-018-0866-4 ↗
17. Tool condition monitoring in the milling process with vegetable based cutting fluids using vibration signatures10.3139/120.111318 ↗
18. Improving calibration accuracy of a vibration sensor through a closed loop measurement system10.1109/MIM.2016.7384960 ↗
19. Weighted low-rank sparse model via nuclear norm minimization for bearing fault detection10.1016/j.jsv.2017.03.044 ↗
20. Principal component analysis for feature extraction and NN pattern recognition in sensor monitoring of chip form during turning10.1016/j.cirpj.2014.04.005 ↗
21. Repetitive transients extraction algorithm for detecting bearing faults10.1016/j.ymssp.2016.06.035 ↗
22. Automatic feature constructing from vibration signals for machining state monitoring10.1007/s10845-017-1302-x ↗
23. Segreto, T., Caggiano, A., Karam, S., and Teti, R. (2017). Vibration sensor monitoring of nickel-titanium alloy turning for machinability evaluation. Sensors, 17.10.20944/preprints201703.0092.v1 ↗
24. Sparsity-based signal extraction using dual Q-factors for gearbox fault detection10.1016/j.isatra.2018.05.009 ↗
25. Developing automatic recognition system of drill wear in standard laminated chipboard drilling process
26. Tool-wear monitoring during micro-end milling using wavelet packet transform and Fisher’s linear discriminant10.1007/s12541-016-0103-z ↗
27. Tool Condition Monitoring of Single-Point Dresser Using Acoustic Emission and Neural Networks Models10.1109/TIM.2013.2281576 ↗
28. Online incremental learning for tool condition classification using modified Fuzzy ARTMAP network10.1007/s10845-013-0738-x ↗
29. Multimodal Hidden Markov Model-Based Approach for Tool Wear Monitoring10.1109/TIE.2013.2274422 ↗
30. A novel integrated tool condition monitoring system10.1007/s10845-017-1334-2 ↗
31. Force based tool wear monitoring system for milling process based on relevance vector machine10.1016/j.advengsoft.2014.02.002 ↗
32. Hybrid learning based Gaussian ARTMAP network for tool condition monitoring using selected force harmonic features10.1016/j.sna.2013.09.023 ↗
33. CNC machine tool’s wear diagnostic and prognostic by using dynamic Bayesian networks10.1016/j.ymssp.2011.10.018 ↗
34. Imagenet classification with deep convolutional neural networks
35. Traffic sign detection and recognition using fully convolutional network guided proposals10.1016/j.neucom.2016.07.009 ↗
36. Kim, Y. (2014). Convolutional neural networks for sentence classification. arXiv.10.3115/v1/D14-1181 ↗
37. Palaz, D., Collobert, R., and Doss, M.M. (2013). Estimating phoneme class conditional probabilities from raw speech signal using convolutional neural networks. arXiv.10.21437/Interspeech.2013-438 ↗
38. Sun, W., Yao, B., Zeng, N., Chen, B., He, Y., Cao, X., and He, W. (2017). An Intelligent Gear Fault Diagnosis Methodology Using a Complex Wavelet Enhanced Convolutional Neural Network. Materials, 10.10.3390/ma10070790 ↗
39. An adaptive deep convolutional neural network for rolling bearing fault diagnosis
40. Intelligent fault diagnosis of rolling bearing using hierarchical convolutional network based health state classification10.1016/j.aei.2017.02.005 ↗
41. Machining vibration states monitoring based on image representation using convolutional neural networks10.1016/j.engappai.2017.07.024 ↗
42. Sparsity-based algorithm for detecting faults in rotating machines10.1016/j.ymssp.2015.11.027 ↗
43. Enhancement of signal denoising and multiple fault signatures detecting in rotating machinery using dual-tree complex wavelet transform10.1016/j.ymssp.2009.06.015 ↗
44. The dual-tree complex wavelet transform10.1109/MSP.2005.1550194 ↗
45. Wavelets for fault diagnosis of rotary machines: A review with applications10.1016/j.sigpro.2013.04.015 ↗
46. Novel Ensemble Analytic Discrete Framelet Expansion for Machinery Fault Diagnosis10.3901/JME.2014.17.077 ↗
47. Combining translation-invariant wavelet frames and convolutional neural network for intelligent tool wear state identification10.1016/j.compind.2018.12.018 ↗
48. DropSample: A new training method to enhance deep convolutional neural networks for large-scale unconstrained handwritten Chinese character recognition10.1016/j.patcog.2016.04.007 ↗
49. Boureau, Y.L., Ponce, J., and Lecun, Y. (2010, January 21–25). A Theoretical Analysis of Feature Pooling in Visual Recognition. Proceedings of the 27th International Conference on Machine Learning, Haifa, Israel.
50. DropConnect regularization method with sparsity constraint for neural networks10.1049/cje.2016.01.023 ↗
51. The relationship between kurtosis-and envelope-based indexes for the diagnostic of rolling element bearings10.1016/j.ymssp.2013.10.007 ↗
52. Selection of informative frequency band in local damage detection in rotating machinery10.1016/j.ymssp.2014.03.011 ↗
53. The cross-entropy method for combinatorial and continuous optimization10.1023/A:1010091220143 ↗
54. Shang, L., Yang, Q., Wang, J., Li, S., and Lei, W. (2018, January 11–14). Detection of rail surface defects based on CNN image recognition and classification. Proceedings of the 20th International Conference on Advanced Communication Technology (ICACT), Chuncheon-si, Gangwon-do, South Korea.10.23919/ICACT.2018.8323641 ↗
55. Revisiting squared-error and cross-entropy functions for training neural network classifiers10.1007/s00521-005-0467-y ↗
56. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.
57. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press.
58. Lippmann, R., Moody, J., and Touretzky, D.S. (1991). Note on Learning Rate Schedules for Stochastic Optimization. Advances in Neural Information Processing Systems, Morgan Kaufmann.
59. Zeiler, M.D. (2012). ADADELTA: An adaptive learning rate method. arXiv.
60. A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load10.1016/j.ymssp.2017.06.022 ↗