Implementation of remote monitoring system for prediction of tool wear and failure using ART2

Abstract

Remote monitoring of tools for prediction of tool wear in cutting processes was considered, and a method of implementation of a remote-monitoring system previously developed was proposed. Sensor signals were received and tool wear was predicted in the local system using an ART2 algorithm, while the monitoring result was transferred to the remote system via internet. The monitoring system was installed at an on-site machine tool for monitoring three kinds of tools cutting titanium alloys, and the tool wear was evaluated on the basis of vigilances, similarities between vibration signals received and the normal patterns previously trained. A number of experiments were carried out to evaluate the performance of the proposed system, and the results show that the wears of finishing-cut tools are successfully detected when the moving average vigilance becomes lower than the critical vigilance, thus the appropriate tool replacement time is notified before the breakage.

Keywords

tool wear / remote monitoring system / ART2 neural network / machine tool / tool replacement time

References

[1] JantunenE.. A summary of methods applied to tool condition monitoring in drilling [J]. International Journal of Machine Tools & Manufacture, 2002, 42(9): 997-1010

[2] WuB., ZhouB.-h., XiL.-feng.. Remote multi-robot monitoring and control system based on MMS and web services [J]. The Industrial Robot, 2007, 34(3): 225-239

[3] MullerA., CrespoM. A., IingB.. On the concept of e-maintenance: Review and current research [J]. Reliability Engineering & System Safety, 2008, 93(8): 1165-1187

[4] KimD. H., LeeY. S., KimS. H.. Study on the design of risk management web-monitoring system using AANN [J]. Journal of Control, Automation and Systems Engineering, 2004, 10(6): 545-550

[5] AliustaogluC., ErtuncH. M., OcakH.. Tool wear condition monitoring using a sensor fusion model based on fuzzy inference system [J]. Mechanical Systems and Signal Processing, 2009, 23(2): 539-546

[6] XieM., GohT. N., WiklundH.. Statistical monitoring and control of tool wear processes [J]. International Journal of Reliability, Quality, and Safety Engineering, 2000, 7(4): 331-340

[7] El-WardanyT. I., GaoD., WlbestawiM. A.. Tool condition monitoring in drilling using vibration signature analysis [J]. International Journal of Machine Tools & Manufacture, 1996, 36(6): 687-711

[8] ZhuK. P., WongY. S., HongG. S.. Wavelet analysis of sensor signals for tool condition monitoring: A review and some new results [J]. International Journal of Machine Tools & Manufacture, 2009, 49(7/8): 537-553

[9] AlonsoF. J., SalgadoD. R.. Analysis of the structure of vibration signals for tool wear detection [J]. Mechanical Systems and Signal Processing, 2008, 22(3): 735-748

[10] JANG U-Il, NHO Min-Seok, CHOI Kook-Jin, HONG Dae Sun. Development of a web-based remote monitoring system for evaluating degradation of machine tools Using ART2 [C]// IEEE/ASME International Conference on Mechatronics and Embedded Systems and Applications, 2008: 315–320.

[11] NHO Min-Seok, KWON Jung-Hee, JANG U-Il, HONG Dae Sun, JUNG Hae Yong. Real time monitoring system for prediction of tool wear and failure in machining processes using ART2 [C]// ICROS-SICE International Joint Conference, 2009: 3105–3106.

[12] AsakuraT., KobayashiT., XuB., HayashiS.. Fault diagnosis system for machines using neural networks [J]. Journal of the Japan Society of Mechanical Engineering, 2000, 43(2): 364-371

[13] YuD. H.. A fault diagnosis based on multilayer ART2 neural network [J]. Journal of Korean Institute of Intelligent Systems, 2004, 14(7): 830-837

[14] LeeI. S., ShinP. J., JeonG. J.. Multiple faults diagnosis of a linear system using ART2 neural networks [J]. Journal of Control, Automation and Systems Engineering, 1997, 3(3): 244-251

[15] WILLIAMS A S. Statistics for business and economics [M]. Thomson South-Western, 2005: 783–786.

[16] CarpenterG. A., GrosbergS.. ART2: Self-organization of stable category recognition codes for analog input patterns [J]. Applied Optics, 1987, 26(23): 4919-4930

[17] CarpenterG. A., GrosbergS.. A massively parallel architecture for a self-organizing neural pattern recognition machine [J]. Computer Vision, Graphics, and Image Processing, 1987, 37(1): 54-115