FORECASTING AND PREVENTING TOWER CRANE FAILURES USING AI TECHNOLOGIES UNDER WIND LOAD CONDITIONS
DOI:
https://doi.org/10.36910/acm.vi51.1841Keywords:
tower crane, accidents, stability, external loads, safety system, forecasting, artificial intelligence, neural networkAbstract
The article discusses the application of artificial intelligence technologies for forecasting and preventing tower crane failures caused by wind loads. It analyzes data processing methods from sensors measuring wind loads and their integration with crane control systems for real-time monitoring and prediction of hazardous situations. Special attention is given to the use of machine learning algorithms to process large volumes of data and identify critical parameters that could lead to an accident. The implementation of such systems allows for the timely detection of potential threats, automatic adjustment of crane operating parameters, and the adoption of necessary measures to prevent accidents. The study results confirm that the integration of AI technologies into the operation of tower cranes can significantly improve their safety and efficiency.
The issue of tower crane safety under wind loads is also examined. The shortcomings of existing protection methods are analyzed, particularly their inadequate effectiveness during strong wind gusts. An intelligent system based on adaptive neural networks is proposed for forecasting wind loads and preventing accidents. The system’s operating principles and algorithms are described. The importance of timely response to changes in wind conditions to ensure the safety of the crane and personnel is emphasized. The results of the study can be used to develop modern crane control systems, improving work safety. It is noted that the risk of dangerous wind loads exists not only in areas with strong winds but also in regions with moderate climates.
Analysis of long-term observations indicates not only the existence of the problem of dangerous dynamic wind loads but also a trend towards its intensification. The problem of ensuring the stability of tower cranes under strong winds remains relevant, as the loss of dynamic stability can lead to accidents and material damage. Especially dangerous are sudden wind gusts and squalls, which can significantly increase wind loads. These short-term wind impacts, along with other factors, may cause crane overturning, creating a threat to operational safety. Therefore, it is important to develop an effective method for ensuring crane stability during dynamic wind disturbances
References
Pryor S. C., Barthelmie R. J. A global assessment of extreme wind speeds for wind energy applications // Nature Energy. 2021. Vol. 6. P. 268–276. DOI: https://doi.org/10.1038/s41560-020-00773-7.
Державна служба України з надзвичайних ситуацій. Надзвичайні події [Електронний ресурс]. URL: https://dsns.gov.ua/news/nadzvicaini-podiyi/20926 (дата звернення: 04.09.2024).
Sun N., Fang Y., Chen H., Lu B., Fu Y. Slew/translation positioning and swing suppression for 4-DOF tower cranes with parametric uncertainties: design and hardware experimentation // IEEE Transactions on Industrial Electronics. 2016. Vol. 63. P. 6407–6418.
Lawrence J., Singhose W. Command shaping slewing motions for tower cranes // Journal of Vibration and Acoustics. 2010. Vol. 132. Article 011002.
Duong S. C., Uezato E., Kinjo H., Yamamoto T. A hybrid evolutionary algorithm for recurrent neural network control of a three-dimensional tower crane // Automation in Construction. 2012. Vol. 23. P. 55–63.
Omar H. M., Nayfeh A. H. Gain scheduling feedback control for tower cranes // Journal of Vibration and Control. 2003. Vol. 9. P. 399–418.
Böck M., Kugi A. Real-time nonlinear model predictive path-following control of a laboratory tower crane // IEEE Transactions of Control Systems Technology. 2014. Vol. 22. P. 1461–1473.
Zhang M., Jing X. Adaptive Neural Network Control for Double-Pendulum Tower Crane Systems // 2020. DOI: 10.1007/978-981-15-7670-6_8.
Wang K., Ma X., Li J. Neural Network-Based Adaptive Swing Suppression Control for Tower Cranes With Obstacle Avoidance // IEEE/ASME Transactions on Mechatronics. 2024. P. 1–12. DOI: 10.1109/TMECH.2024.3435794.
Widrow B., Lehr M. A. Perceptrons, Adalines, and backpropagation // Arbib. 1995. Vol. 4. P. 719–724.
Zhu Q., Du B., Yan P. Boundary-weighted domain adaptive neural network for prostate MR image segmentation // IEEE Transactions on Medical Imaging. 2019. Vol. 39, No. 3. P. 753–763.
Ebhota V. C., Isabona J., Srivastava V. M. Investigating signal power loss prediction in a metropolitan island using ADALINE and multi-layer perceptron back propagation networks // International Journal of Applied Engineering Research. 2018. Vol. 13, No. 18. P. 13409–13420.
Sutawinaya I. P., Astawa I. N. G. A., Hariyanti N. K. D. Comparison of Adaline and multiple linear regression methods for rainfall forecasting // Journal of Physics: Conference Series. 2018. Vol. 953, No. 1. Article 012046. DOI: 10.1088/1742-6596/953/1/012046.
Valladares S., et al. Performance evaluation of the Nvidia Jetson Nano through a real-time machine learning application // Intelligent Human Systems Integration 2021: Proceedings of the 4th International Conference on Intelligent Human Systems Integration (IHSI 2021): Integrating People and Intelligent Systems, February 22–24, 2021, Palermo, Italy. Springer International Publishing, 2021.
References:
Pryor, S. C., Barthelmie, R. J. (2021). A global assessment of extreme wind speeds for wind energy applications. Nature Energy, 6, 268–276. DOI: https://doi.org/10.1038/s41560-020-00773-7. [in English].
Derzhavna sluzhba Ukraїni z nadzvichajnih situacіj [State Emergency Service of Ukraine]. dsns.gov.ua Retrieved from https://dsns.gov.ua/news/nadzvicaini-podiyi/20926 [in Ukrainian].
Sun, N., Fang, Y., Chen, H., Lu, B., Fu, Y. (2016). Slew/translation positioning and swing suppression for 4-DOF tower cranes with parametric uncertainties: design and hardware experimentation. IEEE Transactions on Industrial Electronics, 63, 6407–6418 [in English].
Lawrence, J., Singhose, W. (2010). Command shaping slewing motions for tower cranes. Journal of Vibration and Acoustics, 132, 011002. [in English].
Duong S. C., Uezato E., Kinjo H., Yamamoto T. A hybrid evolutionary algorithm for recurrent neural network control of a three-dimensional tower crane // Automation in Construction. 2012. Vol. 23. P. 55–63 [in English].
Omar H. M., Nayfeh A. H. Gain scheduling feedback control for tower cranes // Journal of Vibration and Control. 2003. Vol. 9. P. 399–418 [in English].
Böck M., Kugi A. Real-time nonlinear model predictive path-following control of a laboratory tower crane // IEEE Transactions of Control Systems Technology. 2014. Vol. 22. P. 1461–1473 [in English].
Zhang M., Jing X. Adaptive Neural Network Control for Double-Pendulum Tower Crane Systems // 2020. DOI: 10.1007/978-981-15-7670-6_8. [in English].
Wang K., Ma X., Li J. Neural Network-Based Adaptive Swing Suppression Control for Tower Cranes With Obstacle Avoidance // IEEE/ASME Transactions on Mechatronics. 2024. P. 1–12. DOI: 10.1109/TMECH.2024.3435794. [in English].
Widrow B., Lehr M. A. Perceptrons, Adalines, and backpropagation // Arbib. 1995. Vol. 4. P. 719–724 [in English].
Zhu Q., Du B., Yan P. Boundary-weighted domain adaptive neural network for prostate MR image segmentation // IEEE Transactions on Medical Imaging. 2019. Vol. 39, No. 3. P. 753–763 [in English].
Ebhota V. C., Isabona J., Srivastava V. M. Investigating signal power loss prediction in a metropolitan island using ADALINE and multi-layer perceptron back propagation networks // International Journal of Applied Engineering Research. 2018. Vol. 13, No. 18. P. 13409–13420 [in English].
Sutawinaya I. P., Astawa I. N. G. A., Hariyanti N. K. D. Comparison of Adaline and multiple linear regression methods for rainfall forecasting // Journal of Physics: Conference Series. 2018. Vol. 953, No. 1. Article 012046. DOI: 10.1088/1742-6596/953/1/012046. [in English].
Valladares S., et al. Performance evaluation of the Nvidia Jetson Nano through a real-time machine learning application // Intelligent Human Systems Integration 2021: Proceedings of the 4th International Conference on Intelligent Human Systems Integration (IHSI 2021): Integrating People and Intelligent Systems, February 22–24, 2021, Palermo, Italy. Springer International Publishing, 2021. [in English].
