Effective Adversarial Examples Detection Improves Screw Detection in Dust Pollution Within Industry System
Pages 1963 - 1971
Abstract
Screws play a critical role as essential components across various industries. To meet market demands and standards, screw manufacturers are embracing digital transformation and leveraging artificial intelligence (AI) techniques. AI models have also been proposed for identifying defective products. However, most studies are limited to controlled environments, and the presence of dust particles during screw manufacturing poses challenges for visual-based AI applications. To address this, we propose a solution involving the use of adversarial examples (AE). These examples are employed to simulate dust particles on camera lenses. We introduce a robust AE detection method designed to enhance the accuracy of screw recognition. This approach aims to improve the overall efficiency of the screw manufacturing industry. Experimental results show that our proposed mechanism can effectively improve screw identification accuracy in dust-polluted environments.
References
[1]
M. Niu, S. Ma, W. Cai, J. Zhang, and G. Liu, “Fault diagnosis of planetary roller screw mechanism based on bird swarm algorithm and support vector machine,” in Proc. 4th Int. Conf. Mech., Aeronaut. Autom. Eng. (ICMAA), Feb. 2020, Bangkok, Thailand, 2020, Art. no.
[2]
T.-K. Liu, Y.-P. Chen, and J.-H. Chou, “Developing a multiobjective optimization scheduling system for a screw manufacturer: A refined genetic algorithm approach,” IEEE Access, vol. 2, pp. 356–364, 2014.
[3]
C.-S. Lin, C.-Y. Hsu, P.-Y. Chen, and C.-M. Yu, “Real-world adversarial examples via makeup,” in Proc. IEEE Int. Conf. Acoust. Speech Signal Process. (ICASSP), 2022, pp. 2854–2858.
[4]
H. Kuo, J. Xu, C. Yu, and J. Yan, “Screw defect detection system based on AI image recognition technology,” in Proc. Int. Symp. Comput. Consum. Control (IS3C), 2020, pp. 493–496.
[5]
D. Sauter, C. Atik, C. Schenk, R. Buettner, and H. Baumgartl, “Visual defect detection of metal screws using a deep convolutional neural network,” in Proc. IEEE 45th Annu. Comput. Softw. Appl. Conf. (COMPSAC), 2021, pp. 303–311.
[6]
D. Medak, F. Milković, L. Posilović, M. Subašić, M. Budimir, and S. Lončarić, “Detection of defective bolts from rotational ultrasonic scans using convolutional neural networks,” in Proc. 27th Int. Conf. Autom. Comput. (ICAC), Sep. 2022, pp. 1–6.
[7]
P. Bergmann, M. Fauser, D. Sattlegger, and C. Steger, “MVTec AD—A comprehensive real-world dataset for unsupervised anomaly detection,” in Proc. IEEE/CVF CVPR, 2019, pp. 9584–9592.
[8]
K. Ishida, Y. Takena, Y. Nota, R. Mochizuki, I. Matsumura, and G. Ohashi, “SA-PatchCore: Anomaly detection in dataset with co-occurrence relationships using self-attention,” IEEE Access, vol. 11, pp. 3232–3240, 2023.
[9]
Q. Wan, Y. Cao, L. Gao, W. Shen, and X. Li, “Position encoding enhanced feature mapping for image anomaly detection,” in Proc. IEEE Int. Conf. Autom. Sci. Eng. (CASE), 2022, pp. 876–881.
[10]
M. Nicolaeet al., “Adversarial robustness toolbox v1.0.0,” 2018, arXiv:1807.01069.
[11]
I. J. Goodfellow, J. Shlens, and C. Szegedy, “Explaining and harnessing adversarial examples,” in Proc. Int. Conf. Learn. Represent., 2015, pp. 1–11.
[12]
A. Madry, A. Makelov, L. Schmidt, D. Tsipras, and A. Vladu, “Towards deep learning models resistant to adversarial attacks,” 2018, arXiv:1706.06083.
[13]
A. Kurakin, I. Goodfellow, and S. Bengio, “Adversarial examples in the physical world,” in Proc. Int. Conf. Learn. Represent., 2017, pp. 1–14.
[14]
N. Carlini and D. Wagner, “Towards evaluating the robustness of neural networks,” in Proc. IEEE Symp. Security Privacy, May 2017, pp. 39–57.
[15]
S.-M. Moosavi-Dezfooli, A. Fawzi, and P. Frossard, “DeepFool: A simple and accurate method to fool deep neural networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2016, pp. 2574–2582.
[16]
S. Kotyan and D. V. Vargas, “Adversarial robustness assessment: Why both L₀ and L∞ attacks are necessary,” 2019, arXiv:1906.06026.
[17]
Z. Wang, Z. Zhang, T. Zhang, Y. Yuan, and Y. Liu, “A high-efficiency regenerative shock absorber considering twin ball screws transmissions for application in range-extended electric vehicles,” Energy Built Environ., vol. 1, pp. 36–49, Jan. 2020.
[18]
B. Gowrish and R. R. Mansour, “A novel bandwidth reconfigurable waveguide filter for aerospace applications,” IEEE Microw. Wireless Compon. Lett., vol. 30, no. 6, pp. 577–580, Jun. 2020.
[19]
R. Liet al., “Unfastening of hexagonal headed screws by a collaborative robot,” IEEE Trans. Autom. Sci. Eng., vol. 17, no. 3, pp. 1455–1468, Jul. 2020. 10.1109/TASE.2019.2958712.
[20]
F. Alambeigiet al., “On the use of a continuum manipulator and a bendable medical screw for minimally invasive interventions in orthopedic surgery,” IEEE Trans. Med. Robot. Bionics, vol. 1, no. 1, pp. 14–21, Feb. 2019.
[21]
Y.-C. Chen, R.-H. Hwang, M.-Y. Chen, C.-C. Wen, and C.-P. Hsu, “Screw slot quality inspection system based on tactile network,” ACM Trans. Internet Technol., vol. 21, no. 90, pp. 1–17, 2021.
[22]
P. H. Tsai and H. Y. Chu, “Design of the surface powder removing device for the wire coil used in the screw or nut manufacturing process,” in Advances in Science and Technology, vol. 111. Zürich, Switzerland: Trans Tech Publ. Ltd., 2021, pp. 47–52.
[23]
R. M. Park, “Risk assessment for metalworking fluids and respiratory outcomes,” Safety Health Work, vol. 10, no. 4, pp. 428–436, 2019.
[24]
J.-Y. Zeng, C.-Y. Chen, and H.-H. Cho, “Detection of adversarial examples based on the neurons distribution,” in Proc. 17th Int. Conf. Inf. Security Pract. Exp. (ISPEC), Taipei, Taiwan, Nov. 2022, pp. 397–405.
[25]
J. Zhang and C. Li, “Adversarial examples: Opportunities and challenges,” IEEE Trans. Neural Netw. Learn. Syst., vol. 31, no. 7, pp. 2578–2593, Jul. 2020. 10.1109/TNNLS.2019.2933524.
[26]
M. Yang, P. Wu, and H. Feng, “MEMSEG: A semi-supervised method for image surface defect detection using differences and commonalities,” Eng. Appl. Artif. Intell., vol. 119, Mar. 2023, Art. no. 10.1016/j.engappai.2023.105835.
[27]
R. Wagner, M. Matuschek, P. Knaack, M. Zwick, and M. Geiß, “IndustrialEdgeML—End-to-end edge-based Computer Vision System for Industry 5.0,” Procedia Compute. Sci., vol. 217, pp. 594–603, Jan. 2023. 10.1016/j.procs.2022.12.255.
[28]
T. Matsubara, K. Sato, K. Hama, R. Tachibana, and K. Uehara, “Deep generative model using unregularized score for anomaly detection with heterogeneous complexity,” IEEE Trans. Cybern., vol. 52, no. 6, pp. 5161–5173, Jun. 2022. 10.1109/tcyb.2020.3027724.
Recommendations
Explainable AI based Adversarial Examples and its Evaluation
ICECC '23: Proceedings of the 2023 6th International Conference on Electronics, Communications and Control EngineeringWith the advancement of AI technology, AI can be applied to various fields. Currently, AI is used for vital decision such as medical diagnosis. Therefore, the accountability for the decision by AI has become more important. The explainable AI (XAI) is a ...
Tiny Screw and Screw Hole Detection for Automated Maintenance Processes
2022 IEEE International Conference on Mechatronics and Automation (ICMA)Accurate detection of the tiny screw and screw hole is the prerequisite and foundation for screw disassembly and assembly. In recent years, the combination of deep learning and machine vision has become the mainstream method for tiny screw and screw hole ...
Devising a Dust and Noise Pollution Monitoring System for Textile Industry
NSysS '21: Proceedings of the 8th International Conference on Networking, Systems and SecurityTextile industry is one of the most labor-intensive manufacturing sectors in developing countries such as Bangladesh, India, Pakistan, etc. During the manufacturing process, the textile machinery produces a high concentration of cotton dust as well as ...
Comments
Information & Contributors
Information
Published In
0098-3063 © 2023 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.
Publisher
IEEE Press
Publication History
Published: 17 October 2023
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 27 Dec 2024