Multi-Class Anomaly Detection in an Industrial Robot Arm

Abstract:

This paper introduces a specialized Parallel Inception-style 1D-CNN (PINC) architecture designed for real-time condition monitoring of the Universal Robots UR3e platform. Traditional deep learning models for anomaly detection often require substantial computational resources. In contrast, our proposed PINC model uses per-channel parallel feature extraction to identify multi-scale physical anomalies with high accuracy. Using the CASPER dataset, the architecture achieves a diagnostic accuracy of 99.1% while maintaining a low memory footprint of just 152 KB. These findings show that the PINC model effectively captures vibrational signatures without depending on high-latency cloud processing. The results offer a scalable and efficient hardware solution that enables localized, real-time fault detection in human-robot shared workspaces.

• Periodical: Advances in Science and Technology (Volume 181)
• Pages: 287-292
• DOI: https://doi.org/10.4028/p-f9HvN2
• Online since: August 2026
• Authors: David Bodnar*, Károly Jármai
• Keywords: 1D-Inception CNN, Collaborative Robots, Condition Monitoring, Physical Anomaly Detection

References

[1] Moran ME. Evolution of robotic arms. In: Journal of Robotic Surgery. Vol. 1. Springer London; 2007. p.103–111

DOI: 10.1007/s11701-006-0002-x

[2] Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going Deeper with Convolutions. 2014 Sep 17. http://arxiv.org/abs/1409.4842

DOI: 10.1109/cvpr.2015.7298594

[3] Łuczak D. Data-Driven Machine Fault Diagnosis of Multisensor Vibration Data Using Synchrosqueezed Transform and Time-Frequency Image Recognition with Convolutional Neural Network. Electronics (Switzerland). 2024;13(12)

DOI: 10.3390/electronics13122411

[4] Kim YW, Joa KL, Jeong HY, Lee S. Wearable imu-based human activity recognition algorithm for clinical balance assessment using 1D-CNN and GRU ensemble model. Sensors. 2021;21(22)

DOI: 10.3390/s21227628

[5] Vijayalakshmi K, Rajakannu A, Kamarudden M, Ramachandran KP, Sri Rajkavin A V. Intelligent Fault Diagnosis of Rotating Machinery Using Deep Learning Algorithms: A Comparative Analysis of MLP, CNN, RNN, and LSTM. SSRG International Journal of Electrical and Electronics Engineering. 2024;11(9):294–315

DOI: 10.14445/23488379/IJEEE-V11I9P127

[6] Athar A, Mozumder MAI, Abdullah, Ali S, Kim HC. Deep learning-based anomaly detection using one-dimensional convolutional neural networks (1D CNN) in machine centers (MCT) and computer numerical control (CNC) machines. PeerJ Computer Science. 2024;10

DOI: 10.7717/peerj-cs.2389

[7] Hakan Kayan. Industrial Robotic Arm - IMU Data (CASPER 1 & 2) - https://www.kaggle.com/datasets/hkayan/industrial-robotic-arm-imu-data-casper-1-and-2.

[8] Chen WH, Ballance DJ, Gawthrop PJ, O'Reilly J. A nonlinear disturbance observer for robotic manipulators. IEEE Transactions on Industrial Electronics. 2000 [accessed 2026 Jan 10];47(4):932–938. https://ieeexplore.ieee.org/document/857974

DOI: 10.1109/41.857974

[9] Isermann R. Fault-diagnosis systems: An introduction from fault detection to fault tolerance. Fault-Diagnosis Systems: An Introduction from Fault Detection to Fault Tolerance. 2006 [accessed 2026 Jan 10]:1–475

DOI: 10.1007/3-540-30368-5

[10] Ismail Fawaz H, Lucas B, Forestier G, Pelletier C, Schmidt DF, Weber J, Webb GI, Idoumghar L, Muller PA, Petitjean F. InceptionTime: Finding AlexNet for time series classification. Data Mining and Knowledge Discovery. 2020 [accessed 2026 Jan 10];34(6):1936–1962. https://dl.acm.org/doi/10.1007/s10618-020-00710-y

DOI: 10.1007/S10618-020-00710-Y