Tool Wear State Recognition Based on 1D-CNN

DOI: https://doi.org/10.62517/jbdc.202301206

Author(s)

Wenji Wang

Affiliation(s)

Zibo Vocational Institute, Zibo, Shandong, China

Abstract

Machine learning classification models have the problems of complex feature engineering and unsatisfactory state recognition. In this paper, a deep learning network, One-dimensional convolutional neural networks (1D-CNN), is proposed to recognize the state of tool wear. After the original data is cleaned and pre-processed, it is directly put into the 1D-CNN model for feature self-extraction and state recognition, which improves the automation, accuracy and efficiency of the whole recognition process.

Keywords

Data preprocessing; Deep Learning; 1D-CNN; State Recognition.

References

[1] Simon G D, Deivanathan R. Early detection of drilling tool wear by vibration data acquisition and classification[J]. Manufacturing Letters, 2019, 21: 60-65. [2] Gomes M C, Brito L C, da Silva M B, et al. Tool wear monitoring in micromilling using Support Vector Machine with vibration and sound sensors[J]. Precision Engineering, 2021, 67: 137-151. [3] Dou J, Xu C, Jiao S, et al. An unsupervised online monitoring method for tool wear using a sparse auto-encoder[J]. The International Journal of Advanced Manufacturing Technology, 2020, 106(5): 2493-2507.