Abstract
Unlike the past, the smart factory environment requires many changes from the 2 M (Man and Machine) side to digitalization and intelligence. In other words, as an alternative to the shrinking vacancy of workers for manufacturing competitiveness, the transition to an artificial intelligence-based real-time predictive maintenance environment or an intelligent production system is highly demanded. Therefore, research on intelligent or artificial intelligence-based real-time predictive maintenance of automated processing facilities, which occupies a large proportion in the general production system, is quite significant. In this study, for the intelligent maintenance or intelligent predictive maintenance of such processing equipment, first, the “Conv2d-LSTM” technique, which reduces the parameters of the LSTM network layer and adds a Conv2d layer, is applied to the real-time spindle load data to verify the state judgment of the machining tool. Second, the real-time diagnostic performance for machining quality (status analysis for each tool) was verified by applying the spectrogram image using “STFT” to the “Pretrained Network model” for the machining load data. As a result of the study, it was verified that the learning time was shortened, and the performance was excellent (loss value lowered) compared to the application of “Bi-LSTM” in the state judgment through the prediction of the machining tool load. It was possible to confirm the quality judgment through classification. Based on the results of this study in the future, it is expected that production facility intelligence will be possible through weight reduction and diversification of artificial intelligence models that enable edge analysis for various production facilities such as processing facilities and robots.
This work was supported by the Technology Innovation Program (20019327, Industrial IoT based Lightweight Manufacturing System Technology Development for 24hr unmanned Production System) funded by the Ministry of Trade, Industry & Energy(MOTIE), Korea and the Grand Information Technology Research Center support program (IITP-2022-2020-0-01791) supervised by the IITP (Institute for Information and communications Technology Planning and Evaluation) funded by the Ministry of Science and ICT (MIST), Korea.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
S.H. Lee, B.D. Youn, Industry 4.0 and the direction of failure prediction and health management technology (PHM), J. Korean Soc. Noise Vib. Eng. 25(1), 22–28 (2015)
B.D. Youn, T.W. Hwang, S.H. Jo, D.K. Lee, K.M. Na, Diagnosis and prediction of engineering system status using artificial intelligence. J. Korean Soc. Mech. Eng. 57(3), 38–41 (2017)
W.S. Choi, Deterioration evaluation method of high-temperature parts of power generation equipment based on Deep Learning. Mon. Electr. J. 496, 15–20 (2018)
H.S. Oh, B.C. Jeon, J.H. Jung, B.D. Youn, Smart diagnosis of journal bearing rotor systems: unsupervised feature extraction scheme by deep learning, in Proceedings of the Annual Conference of the PHM Society, vol. 8, no. 1 (2016), pp. 1–8
Y.W. Song, H.S. Lee, H.S. Park, Y.J. Kim, J.Y. Jung, A signal processing technique for predictive fault detection based on vibration data. J. Soc. E-Bus. Stud. 12(2), 111–121 (2018)
J.I. Nam, H.J. Park, A neural network based fault detection and classification system using acoustic measurement. J. Korean Soc. Manuf. Technol. Eng. 29(3), 210–215 (2020)
K.W. Kang, K.M. Lee, CNN-based automatic machine fault diagnosis method using spectrogram images. J. Inst. Converg. Signal Proc. 21(3), 121–126 (2020)
C.H. Hwang, K.W. Shin , CNN-LSTM combination method for improving particular matter contamination (PM2.5) prediction accuracy. J. Korea Inst. Inf. Commun. Eng. 24(1), 57–64 (2020)
B.G. Park, S.H. Bae, B.K. Jung, Speed prediction of urban freeway using LSTM and CNN-LSTM neural network. J. Korea Intell. Trans. Syst. 20(1), 86–99 (2021)
H. Lee, D.H. Kang, S.C. Jeong, A Study on the predictive maintenance system for CNC Facilities based on intelligent cutting tool load prediction. ICIC Express Lett. 16(3), 265–273 (2022)
K. Chen, Denosing Data with Fast Fourier Transform (2020). https://kinder-chen.medium.com/denoising-data-with-fast-fourier-transform-a81d9f38cc4c. Accessed 02 Dec 2021
VMV-TECH, STFT (Short Time Fourier Transform)-Series #1’ (2017). https://m.blog.naver.com/vmv-tech/220936084562. Accessed 15 Dec 2022
Y. Zheng, C. Yang, A. Merkulov, Breast cancer screening using convolutional neural network and follow-up digital mammography, in Proceedings SPIE, Computational Imaging III, vol. 10669 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Lee, H., Kang, D.H., Jeong, S.C. (2023). A Study on Industrial Artificial Intelligence-Based Edge Analysis for Machining Facilities. In: Lee, R. (eds) Emotional Artificial Intelligence and Metaverse. Studies in Computational Intelligence, vol 1067. Springer, Cham. https://doi.org/10.1007/978-3-031-16485-9_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-16485-9_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16484-2
Online ISBN: 978-3-031-16485-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)