Articles | Volume 13, issue 1
https://doi.org/10.5194/ms-13-291-2022
https://doi.org/10.5194/ms-13-291-2022
Short communication
 | 
23 Mar 2022
Short communication |  | 23 Mar 2022

Short communication: A case study of stress monitoring with non-destructive stress measurement and deep learning algorithms

Yaofeng Ji, Qingbo Lu, and Qingyu Yao

Related subject area

Subject: Machining and Manufacturing Processes | Techniques and Approaches: Reliability and Probability Analysis
Design and control of the belt-polishing tool system for the blisk finishing process
Cheng Fan, Caoyang Xue, Lei Zhang, Kejun Wang, Qian Wang, Yapeng Gao, and Lei Lu
Mech. Sci., 12, 237–248, https://doi.org/10.5194/ms-12-237-2021,https://doi.org/10.5194/ms-12-237-2021, 2021
Short summary
Estimation of tool life and cutting burr in high speed milling of the compacted graphite iron by DE based adaptive neuro-fuzzy inference system
Longhua Xu, Chuanzhen Huang, Rui Su, Hongtao Zhu, Hanlian Liu, Yue Liu, Chengwu Li, and Jun Wang
Mech. Sci., 10, 243–254, https://doi.org/10.5194/ms-10-243-2019,https://doi.org/10.5194/ms-10-243-2019, 2019
Short summary

Cited articles

Alessandro, B., Beatrice, C., Bertotti, G., and Montorsi, A.: Domain-wall dynamics and Barkhausen effect in metallic ferromagnetic materials. I. Theory, J. Appl. Phys., 68, 2901, https://doi.org/10.1063/1.346423, 1990. 
Graves, A. and Jaitly, N.: Towards end-to-end speech recognition with recurrent neural networks, in: 31st International Conference on Machine Learning, ICML 2014, Beijing, 21–26 June, Pages 1764–1772, https://dl.acm.org/doi/10.5555/3044805.3045089 (last access: 22 March 2022), 2014. 
Hochreiter, S. and Schmidhuber, J.: Long Short Term Memory, Neural Computat., 9, 8, 1735–1780, https://doi.org/10.1162/neco.1997.9.8.1735, 1997. 
Huang, Y., Qiu, C., Wang, X., Wang, S., and Yuan, K.: A compact convolutional neural network for surface defect inspection, 20, 1974, https://doi.org/10.3390/s20071974, 2020. 
Jiles, D. C.: Coupled Magnetoelastic Theory of Magnetic and Magnetostrictive Hysteresis, IEEE T. Magn., 29, 2113–2123, https://doi.org/10.1109/20.221036, 1993. 
Download
Short summary
During manufacturing, machine failure can lead to fatal damage to both people and the environment, and non-destructive stress measurement is necessary to provide safety maintenance. This paper focuses on the feasibility and capability of deep learning algorithms in stress prediction using Barkhausen noise signals. Our findings pave the way for the implementation of auto-detection devices for metal materials in on-site manufacturing processes.