Abstract
A severe tool wear is often encountered during the process of turning/milling difficult-to-cut materials like Inconel 718. To protect the cutting process from the tool failure, the countermeasure is currently limited to frequent tool changes. Such preventive solution increases not only the machine downtime but also the manufacturing cost. Therefore, there is a strong demand for real-time tool life detection in production lines. In this study, we proposed a stacked LSTM encoder-decoder model for tool wear anomaly detection. Our model only requires “normal” datasets for model training and yields the anomaly score based on the deviation between input and output sequences. This aspect is especially valuable for the actual production lines where the operating conditions are optimized and anomalies are rare. The proposed model is also an end-to-end learning architecture and requires no pre-processing for feature extraction and selection. This characteristic enables real-time processing, which is significant for anomaly detection. In this paper, we first validated our model using artificially generated sinusoidal waveforms and demonstrated its high performance in detecting deviations in amplitude, frequency, waveform bias, and added noise components. The proposed model was then implemented into an actual turning process for Inconel 718 to detect the tool wear in real-time. After being trained by AE (Acoustic Emission) or audio signals captured in the “normal” cutting stage, the model can derive appropriate anomaly scores well matched with the cutting stages of “normal,” “transitional” and “anomalous” corresponding to the tool wear. Finally, deep insight into law/rule-based, data-based, and model-based approaches are discussed.
Similar content being viewed by others
References
Chandola V, Banerjee A, Kumar V (2009) Anomaly detection, a survey. ACM Comput Surv 41:1–72
Erhan L, Ndubuaku M, Di Mauro M, Song W, Chen M, Fortino G, Bagdasar O, Liotta A (2021) Smart anomaly detection in sensor systems, A multi-perspective review. Inf Fusion 67:64–79
Xu D, Ricci E, Yan Y, Song J, Sebe N (2015) Learning deep representations of appearance and motion for anomalous event detection. Proceed British Mach Vision Conf 8(1–8):12
Cho S, Jiang J (2019) A fault detection and isolation technique using nonlinear support vectors dichotomizing multi-class parity space residuals. J Process Control 82:31–43
Li C, Mo L, Yan R (2020) Lifelong condition monitoring based on NB-IoT for anomaly detection of machinery equipment. Procedia Manuf 49:144–149
Liu FT, Ting KM, Zhou ZH (2012) Isolation-based anomaly detection. ACM Trans Knowl Discov Data 6(3):1–39
Chalapathy R, Chawla S (2019) Deep learning for anomaly detection: a survey. https://doi.org/10.48550/arXiv.1901.03407
Ying Z, Shu L, Kizaki T, Iwama M, Sugita N (2021) Hybrid approach for onsite monitoring and anomaly detection of cutting tool life. Procedia CIRP 104:1541–1546
Thill M, Konenet W, Wang H, Bäck T (2021) Temporal convolutional autoencoder for unsupervised anomaly detection in time series. Appl Soft Comput 112(107751):1–22
Hashimoto M, Ide Y, Aritsugi M (2021) Anomaly detection for sensor data of semiconductor manufacturing equipment using a GAN. Procedia Comput Sci 192:873–882
Tao H, Cheng L, Qiu J, Stojanovic V (2022) Few shot cross equipment fault diagnosis method based on parameter optimization and feature mertic. Meas Sci Technol 33(11):id.115005
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9:1735–1780
Malhotra P, Vig L, Shroff G, Agarwal P (2015) Long short term memory networks for anomaly detection in time series, ESANN 2015 proceedings, 89–94. Available from http://www.i6doc.com/en/. Accessed 2020/04/01
Vos K, Peng Z, Jenkins C, Shahriar MR, Borghesani P, Wang W (2022) Vibration-based anomaly detection using LSTM/SVM approaches. Mech Syst Signal Process 69(108752):1–17
Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313:504–507
Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks, Proceedings of the 27th International Conference on Neural Information Processing Systems, 2:3104–3112. https://doi.org/10.48550/arXiv.1409.3215
Malhotra P, Ramakrishnan A, Anand G, Vig L, Agarwal P, Shroff G (2016) LSTM-based encoder-decoder for multi-sensor anomaly detection. https://doi.org/10.48550/arXiv.1607.00148
Ahmad S, Styp-Rekowski K, Nedelkoski S, Kao O (2020) Autoencoder-based condition monitoring and anomaly detection method for rotating machines. IEEE Int Conf Big Data (Big Data) 2020:4093–4102
Lindemann B, Fesenmayr F, Jazdi N, Weyrich M (2019) Anomaly detection in discrete manufacturing using self-learning approaches. Procedia CIRP 79:313–318
Zope K, Singh K, Nistala SH, Basak A, Rathore P, Runkana V (2019) Anomaly detection and diagnosis in manufacturing systems: a comparative study of statistical, machine learning and deep learning techniques. Proceed 11th Ann Conf PHM Soc. https://doi.org/10.36001/phmconf.2019.v11i1.815
Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. Proceed Mach Learn Res 9:249–256
Dean J, Corrado GS, Monga R, Chen K, Devin M, Le QV, Mao MZ, Ranzato M, Senior A, Tucker P, Yang K, Ng AY (2012) Large scale distributed deep networks. Adv Neural Inf Process Syst 1:1223–1231
Srivastava N, Hinton G, Krizhevsky A, Sutskever H, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929–1958
Zaremba W, Sutskever H, Vinyals O (2015) Recurrent neural network regularization. https://doi.org/10.48550/arXiv.1409.2329
Scholz-Reiter B, Weimer D, Thamer H (2012) Automated surface inspection of cold-formed micro-parts. CIRP Ann 61:531–534
Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2:359–366
Bengio Y, Courville A, Vincent P (2012) Unsupervised feature learning and deep learning: a review and new perspectives. CoRR, abs/1206.5538(2012)
Pouyanfar S, Sadiq S, Tian H, Tao Y, Reyes MP, Shyu ML, Chen SC, Iyengar SS (2019) A survey on deep learning: algorithms, techniques, and applications. ACM Comput Surv (CSUR) 51(92):1–36
Geiger A, Kiu D, Alnegheimish S, Cuesta-Infante A, Veeramachaneni K (2020) TadGAN: time series anomaly detection using generative adversarial networks. 2020 IEEE International Conference on Big Data. https://doi.org/10.48550/arXiv.2009.07769
Acknowledgements
The supports are acknowledged with thanks.
Funding
This work was financially supported by the JST, A-STEP Try-out program (No. 21447369), and METI Monozukuri R&D Support Grant Program for SMEs Grant (No. JPJ005698) in Japan.
Author information
Authors and Affiliations
Contributions
Taisuke Oshida: methodology, software, formal analysis, visualization, investigation, data acquisition, writing—original draft. Tomohiro Murakoshi: methodology, formal analysis, visualization, investigation, data curation, writing—original draft. Libo Zhou: conceptualization, methodology, formal analysis, writing—review & editing, supervision, project administration, funding acquisition. Hirotaka Ojima: conceptualization, formal analysis, writing—review & editing, supervision, funding acquisition. Kazuki Kaneko: visualization, writing—review & editing, supervision. Teppei Onuki: visualization, data curation, writing—review & editing, supervision. Jun Shimizu: visualization, formal analysis, writing—review & editing, supervision.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Oshida, T., Murakoshi, T., Zhou, L. et al. Development and implementation of real-time anomaly detection on tool wear based on stacked LSTM encoder-decoder model. Int J Adv Manuf Technol 127, 263–278 (2023). https://doi.org/10.1007/s00170-023-11497-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-023-11497-9