To improve the reliability of current signal monitoring tool wear status, a method based on Mahalanobis distance to identify tool wear status is proposed. First, the obtained current signal is analysed in time domain, frequency domain and wavelet domain, and several features that have good correlation with tool wear status are selected to form the feature vector. The feature vector of the current signal in normal tool wear status is taken as the reference vector. Then calculate the Mahalanobis distance value of the feature vectors of the current signal of the tool with moderate wear and severe wear, so that two corresponding thresholds T ₁ and T ₂ can be obtained. The feature vector of an unknown wear status is calculated using the Mahalanobis distance and then compared with the two thresholds obtained previously. When the calculated value is between threshold T ₁ and T ₂, the tool is judged to be in moderate wear status. When its Mahalanobis distance value is greater than the threshold T ₂, it is judged that the tool has been seriously worn. Finally, multiple unknown wear status is identified. It is believed that the recognition method based on Mahalanobis distance can accurately determine the tool wear status.

References

1. 1)
  - 9. Luo Zh, G., Li, X.D., Zhao, J.L., et al: ‘Accurate recognition of cracks by Mahalanobis distance discrimination method’, Vib. Shock, 2013, 32, (21), pp. 186–188.
2. 2)
  - 10. Kang, W.X.: ‘Non-linear system fault diagnosis method based on Mahalanobis distance PFCM algorithm’ (Harbin Institute of Technology, Harbin, 2016).
3. 3)
  - 2. Zhu, Y.F., Dai, C.H.H., Chen, W.R.: ‘On-line tool state monitoring based on recursive wavelet neural network’, Mach. Tool Hydraul., 2007, 35, (2), pp. 172–175.
4. 4)
  - 4. Dong, Y.S., Liang, H.B.: ‘Research on tool wear monitoring of five-axis milling’, Mod. Mach. Tool Autom. Manuf. Technol., 2013, 54, (8), pp. 69–72.
5. 5)
  - 6. Dong, Q.C.H.: ‘Extraction and identification of tool spectrum features’ (Jinan University, Jinan, 2007).
6. 6)
  - 8. Liu, Y., Zhang, J.H., Bi, F.R., et al: ‘Diesel engine valve fault diagnosis based on LMD marginal spectrum’, J. Chin. Intern. Combust. Engines, 2014, 35, (6), pp. 96–100.
7. 7)
  - 11. Shen Zh, G.: ‘Intelligent detection technology for high-speed cutting tool wear’ (Nanjing University of Aeronautics and Astronautics, Nanjing, 2009).
8. 8)
  - 3. Xu, Q.: ‘Design of tool condition monitoring data processing platform based on ARM & WinCE’ (Xihua University, Chengdu, 2009).
9. 9)
  - 1. Li, D., Zh, Q.: ‘Analysis and research on the influence of error before processing on machining accuracy’, Education, 2014, 4, (33), p. 134.
10. 10)
  - 7. Cao, H.R., Chen, X.F., Zi, Y.Y., et al: ‘End milling tool breakage detection using lifting scheme and Mahalanobis distance’, Int. J. Mach. Tools Manuf., 2008, 48, (2), pp. 141–151.
11. 11)
  - 12. Zhu, Y.F.: ‘Tool fault diagnosis based on wavelet neural network’ (Southwest Jiaotong University, Chengdu, 2005).
12. 12)
  - 5. Wang, J.Z.H., Wang, X.Y.: ‘Monitoring the main motor current of the machine tool to judge tool wear and damage’, New Technol. New Technol., 1990, 12, (6), p. 21.

Tool wear status recognition based on Mahalanobis distance

References

Related content