A new system uses AI to predict torque levels in industrial hand tools, making them compatible with Industry 4.0 standards.
Researchers developed a system that integrates AI with industrial hand tools, using data from multiple sensors to predict torque levels in real-time. The system achieved high accuracy rates, with an LSTM model reaching 94.8% accuracy and an embedded MLP model achieving 92.3% binary classification success. The system also demonstrated low network latency and reliable data delivery.
Abstract
In this study, a novel system has been developed to adapt legacy equipment widely used in industrial production lines to Industry 4.0 standards. This research, which aims to digitalize electro-mechanical hand tools used in critical assembly operations and integrate them with higher-level system software, presents an innovative approach based on the hybrid use of artificial neural networks and embedded systems. The developed system can perform real-time torque level prediction by analyzing integrated data from multiple sensors, including voltage measurements, motor current readings, accelerometer data, and gyroscope measurements. The artificial intelligence component of the system consists of the integration of Long Short-Term Memory (LSTM) models running on the server side and optimized Multilayer Perceptron (MLP) models running on the embedded system. In tests conducted on a balanced dataset of 6000 samples, the LSTM model achieved an accuracy rate of 94.8%. Additionally, the embedded MLP model demonstrated a 92.3% binary classification success with a response time lower than 100ms. The system integration implemented using TCP/IP Open Protocol achieved network latency values below 50ms and successfully delivered 99.9% of data packets without loss or corruption. The system developed as a result of this study has demonstrated that legacy equipment can be made compatible with Industry 4.0 with minimal hardware modifications, while automating quality control processes and establishing data-driven decision-making mechanisms. This approach stands out as a cost-effective and scalable solution in industrial digital transformation projects.
References
- 1.Fan, Y. C., & Chang, J. Y. J. (2018). Embedded smart box for legacy machines to approach to I 4.0 in smart manufacturing. In MATEC Web of Conferences (Vol. 185, p. 00027). EDP Sciences.
- 2.Dini, P., Diana, L., Elhanashi, A., & Saponara, S. (2024). Overview of AI-Models and Tools in Embedded IIoT Applications. Electronics, 13(12), 2322.
- 3.Chaurasia, A., Parashar, B., & Kautish, S. (2023). Artificial Intelligence and Automation for Industry 4.0. In Computational Intelligence for Modern Business Systems: Emerging Applications and Strategies (pp. 357-373). Singapore: Springer Nature Singapore.
- 4.Korodi, A., Nițulescu, I. V., Fülöp, A. A., Vesa, V. C., Demian, P., Braneci, R. A., & Popescu, D. (2024). Integration of Legacy Industrial Equipment in a Building-Management System Industry 5.0 Scenario. Electronics, 13(16), 3229.
- 5.Kwok, T. H., & Gaasenbeek, T. (2023). A production interface to enable legacy factories for industry 4.0. Engineering Research Express, 5(4), 045019.
- 6.Inanc, E., Gurses, Y., Habboush, A., Yildiz, Y., & Annaswamy, A. M. (2023). Neural network adaptive control with long short-term memory. arXiv preprint arXiv:2301.02316.
- 7.Adhau, S., Patil, S., Ingole, D., & Sonawane, D. (2019, December). Embedded implementation of deep learning-based linear model predictive control. In 2019 sixth Indian control conference (ICC) (pp. 200-205). IEEE.
- 8.Tcheumchoua, K. B., Nam, S., & Chung, W. K. (2022, October). Torque Control of Hydraulic Pressure Servo Valve Driven Actuator with Deep Neural Network. In 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 12512-12519). IEEE.
- 9.Shan, F., & Li, B. (2023, October). Development of virtual motor integrated state platform based on data driven and LSTM. In Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023) (Vol. 12800, pp. 1564-1570). SPIE.
- 10.Mojica, F., Villaseñor, C., Alanis, A. Y., & Arana-Daniel, N. (2019, November). Long short-term memory with smooth adaptation. In 2019 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC) (pp. 1-6). IEEE.
- 11.Ma, C., & Molnár, B. (2019). A Legacy ERP System Integration Framework based on Ontology Learning. In ICEIS (1) (pp. 231-237).
- 12.Coppolino, L., D’Antonio, S., Massei, C., & Romano, L. (2015). Efficient Supply Chain Management via Federation-Based Integration of Legacy ERP Systems. In Intelligent Software Methodologies, Tools and Techniques: 14th International Conference, SoMet 2015, Naples, Italy, September 15-17, 2015. Proceedings 14 (pp. 378-387). Springer International Publishing.
- 13.Knapper, R. J., & Brouse, P. S. (2011, June). 10.1. 2 Legacy Software System Integration. In INCOSE International Symposium (Vol. 21, No. 1, pp. 1170-1184).
- 14.Tang, Y., Zhang, J. B., Tan, C. H., Wong, M. M., & Ng, B. T. J. (2004). A Multi-Stage Approach to Asymmetric Legacy Information Integration. In VVEIS (pp. 50-59).