Smart Inspection System for Wiring Harness
Keywords:
Automation, Computer vision, Defect detection, Machine, Quality controlAbstract
The smart inspection system for wiring harness manufacturing leverages machine learning to enhance the accuracy and efficiency of quality control processes. Traditional inspection methods, often reliant on manual checks and basic automated systems, struggle with high variability and complexity in wiring harnesses, which can lead to overlooked defects and increased production costs. This system introduces a machine learning-based approach to automate and refine the inspection process, utilizing advanced image recognition and anomaly detection algorithms to identify defects and deviations from design specifications with high precision. By integrating real-time data analysis and feedback mechanisms, the system not only detects defects but also adapts and improves its performance over time. This results in a significant reduction in false positives and negatives, higher throughput, and improved overall product quality. The system’s ability to provide actionable insights and predictive maintenance recommendations further supports efficient manufacturing processes and enhances operational reliability. This approach represents a transformative advancement in wiring harness quality control, addressing current limitations, and setting new standards for manufacturing excellence.
References
B. Reis, H. D. Cella, M. Ferreira, “A systematic review of automotive wiring harness innovations,” SAE Technical Paper Series, Jan. 2024, doi: https://doi.org/10.4271/2023-36-0057
Strategic Market Research, “Automotive wiring harness market size, global share, 2030,” Strategicmarketresearch.com, 2022. Available: https://www.strategicmarketresearch.com/market-report/automotive-wiring-harness-market
H. Wang and B. Johansson, “Deep learning-based connector detection for robotized assembly of automotive wire harnesses,” 2022 IEEE 18th International Conference on Automation Science and Engineering (CASE), Auckland, New Zealand, pp. 1–8, Aug. 2023, doi: https://doi.org/10.1109/case56687.2023.10260619
P. M. Fresnillo, S. Vasudevan, W. M. Mohammed, J. Antonio, and J. L. Martinez, “An approach for the automatic assembly of multi-branch wire harnesses in the automotive industry using a dual-arm robot,” SSRN, Jan. 2024, doi: https://doi.org/10.2139/ssrn.5010742
M. M. Alam, M. J. Hossain, M. A. Habib, M. Y. Arafat, and M. A. Hannan, “Artificial intelligence integrated grid systems: Technologies, potential frameworks, challenges, and research directions,” Renewable and Sustainable Energy Reviews, vol. 211, p. 115251, Jan. 2025, doi: https://doi.org/10.1016/j.rser.2024.115251
J. Song, P. Kumar, Y. Kim, and H. S. Kim, “A fault detection system for wiring harness manufacturing using artificial intelligence,” Mathematics, vol. 12, no. 4, p. 537, Jan. 2024, doi: https://doi.org/10.3390/math12040537
C. Chen, “Deep learning for automobile predictive maintenance under Industry 4.0,” School of Engineering Cardiff University, 2020. Available: https://orca.cardiff.ac.uk/id/eprint/137968/1/2021ChenCPhD.pdf
H. G. Nguyen, M. Kuhn, and J. Franke, “Manufacturing automation for automotive wiring harnesses,” Procedia CIRP, vol. 97, pp. 379–384, 2021, doi: https://doi.org/10.1016/j.procir.2020.05.254
G. M. Shi and W. Jian, “Wiring harness assembly detection system based on image processing technology,” 2011 International Conference on Electronics, Communications, and Control (ICECC), pp. 2397–2400, Sep. 2011, doi: https://doi.org/10.1109/icecc.2011.6066493
H. G. Nguyen and J. Franke, “Deep learning-based optical inspection of rigid and deformable linear objects in wiring harnesses,” Procedia CIRP, vol. 104, pp. 1765–1770, Nov. 2021, doi: https://doi.org/10.1016/j.procir.2021.11.297
