Anomaly Detection in Hobbing Tool Images: : Using An Unsupervised Deep Learning Approach in Manufacturing Industry
Authors: 
Daniel Kiefer, Stefan Wezel, Alexander Böttcher, Florian Grimm, Tim Straub, Günter Bitsch, Clemens Van DintherAuthors Info & Claims
Abstract
This study explores the application of the PatchCore algorithm for anomaly classification in hobbing tools, an area of keen interest in industrial artificial intelligence application. Despite utilizing limited training images, the algorithm demonstrates capability in recognizing a variety of anomalies, promising to reduce the time-intensive labeling process traditionally undertaken by domain experts. The algorithm demonstrated an accuracy of 92%, precision of 84%, recall of 100%, and a balanced F1 score of 91%, showcasing its proficiency in identifying anomalies. However, the investigation also highlights that while the algorithm effectively identifies anomalies, it doesn't primarily recognize domain-specific wear issues. Thus, the presented approach is used only for pre-classification, with domain experts subsequently segmenting the images indicating significant wear. The intention is to employ a supervised learning procedure to identify actual wear. This premise will be further investigated in future research studies.
References
[1]
The democratization of artificial intelligence: Net politics in the era of learning algorithms, , Bielefeld, 2019, Transcript.
[2]
F Pedregosa, G Varoquaux, A Gramfort, Scikit-learn: Machine Learning in Python, Journal of Machine Learning Research (2011).
[3]
Abadi M, Agarwal A, Barham P, et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems; 2016 Mar 14.
[4]
Paszke A, Gross S, Massa F, et al. PyTorch: An Imperative Style, High-Performance Deep Learning Library. arxiv.
[5]
Erickson N, Mueller J, Shirkov A, et al. AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data. arxiv.
[6]
GE. Moore, Cramming more components onto integrated circuits, Reprinted from Electronics 38 (8) (1965) 33–35. April 19114 ff. IEEE Solid-State Circuits Society 200611(3).
[7]
Sulistio A, Reich C. Towards a Self-protecting Cloud. In: Meersman R, editor. On the move to meaningful internet systems: CoopIS, DOA-Trusted Cloud, and ODBASE. Heidelberg: Springer 2013; 395–402.
[8]
V Gudivada, A Apon, J. Ding, Data quality considerations for big data and machine learning: Going beyond data cleaning and transformations, International Journal on Advances in Software 10 (1) (2017) 1–20.
[9]
S Wang, Y Yang, X Li, J Zhou, L. Kang, Research on thermal deformation of large-scale computer numerical control gear hobbing machines, Journal of Mechanical Science and Technology 27 (5) (2013) 1393–1405.
[10]
P Bergmann, K Batzner, M Fauser, D Sattlegger, C. Steger, The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection, International Journal of Computer Vision 129 (4) (2021) 1038–1059.
[11]
Bergman L, Cohen N, Hoshen Y. Deep Nearest Neighbor Anomaly Detection. arxiv.
[12]
J Deng, W Dong, R Socher, L-J Li, K Li, L. Fei-Fei, ImageNet: A large-scale hierarchical image database, IEEE, 2009, pp. 248–255. ImageNet: A large-scale hierarchical image database.
[13]
Cohen N, Hoshen Y. Sub-Image Anomaly Detection with Deep Pyramid Correspondences. arxiv.
[14]
Defard T, Setkov A, Loesch A, Audigier R. PaDiM: A Patch Distribution Modeling Framework for Anomaly Detection and Localization. In: Del Bimbo A, editor. Pattern recognition: ICPR international workshops and challenges. Cham, Switzerland: Springer 2021; 475–89.
[15]
W Brendel, M. Bethge, Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet, arxiv (2019).
[16]
G Hinton, J Dean, O. Vinyals, Distilling the Knowledge in a Neural Network, arxiv (2014).
[17]
Dinh L, Sohl-Dickstein J, Bengio S. Density estimation using Real NVP. arxiv.
[18]
Rudolph M, Wandt B, Rosenhahn B. Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows. arxiv.
[19]
V Chandola, A Banerjee, V. Kumar, Anomaly detection, ACM Computing Surveys 41 (3) (2009) 1–58.
[20]
K Roth, L Pemula, J Zepeda, B Scholkopf, T Brox, P. Gehler, Towards Total Recall in Industrial Anomaly Detection, IEEE CVF Conference on Computer (2022) 14298–14308.
[21]
Liu J, Xie G, Wang J, et al. Deep Industrial Image Anomaly Detection: A Survey. arxiv.
[22]
A Diro, N Chilamkurti, V-D Nguyen, W. Heyne, A Comprehensive Study of Anomaly Detection Schemes in IoT Networks Using Machine Learning Algorithms, Sensors 21 (24) (2021).
[23]
B Lindemann, B Maschler, N Sahlab, M. Weyrich, A survey on anomaly detection for technical systems using LSTM networks, Computers in Industry 131 (2021).
[24]
Burr Settles. From Theories to Queries: Active Learning in Practice. In: Guyon G, Cawley G, Dror V, Lemaire A, Statnikov A, editors. From Theories to Queries: Active Learning in Practice; 2011.
[25]
S Amershi, M Cakmak, WB Knox, T. Kulesza, Power to the People: The Role of Humans in Interactive Machine Learning, AIMag 35 (4) (2015) 105–120.
Recommendations
Towards Practical Unsupervised Anomaly Detection on Retinal Images
Domain Adaptation and Representation Transfer and Medical Image Learning with Less Labels and Imperfect DataAbstractSupervised deep learning approaches provide state-of-the-art performance on medical image classification tasks for disease screening. However, these methods require large labeled datasets that involve resource-intensive expert annotation. Further, ...
Autoencoding Binary Classifiers for Supervised Anomaly Detection
PRICAI 2019: Trends in Artificial IntelligenceAbstractWe propose the Autoencoding Binary Classifiers (ABC), a novel supervised anomaly detector based on the Autoencoder (AE). There are two main approaches in anomaly detection: supervised and unsupervised. The supervised approach accurately detects ...
Variational Autoencoder Anomaly-Detection of Avalanche Deposits in Satellite SAR Imagery
CI2020: Proceedings of the 10th International Conference on Climate InformaticsThis work demonstrates that deep unsupervised learning holds much promise for rare event detection, even when labeled data is limited. Rare event detection is challenging for traditional supervised learning approaches due to high class-imbalance. We ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Copyright © 2024.
Publisher
Elsevier Science Publishers B. V.
Netherlands
Publication History
Published: 02 July 2024
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 07 Jan 2025