Husain Afsar, Danish Mohd, Khan Sanan H, Mourad Abdel-Hamid I
Department of Mechanical and Aerospace engineering, United Arab Emirates University, Al-Ain, Abu Dhabi, 15551, United Arab Emirates.
University Polytechnic, Aligarh Muslim University, Aligarh, U.P., 202002, India.
Heliyon. 2024 May 31;10(11):e32149. doi: 10.1016/j.heliyon.2024.e32149. eCollection 2024 Jun 15.
In this research, we delve into the fascinating dynamics of projectiles and their interactions with materials, with a keen focus on residual velocity - the speed a projectile retains after striking a target. This parameter is pivotal, especially when considering the design of protective barriers in various environments. Traditional methods of gauging residual velocity have been cumbersome, resource-intensive, and occasionally inconsistent. To address these challenges, we introduce an innovative approach using an Artificial Neural Network (ANN) model through MATLAB R2021a. This computerized tool, trained on a rich dataset from prior research, can predict residual velocities by considering multiple factors, including the initial speed of the projectile, its material and shape, and the thickness of the target. This paper meticulously details the development, training, and validation of the ANN model, highlighting its superior accuracy when compared to traditional methods like the Recht-Ipson model. The developed ANN model demonstrated remarkable performance compared to the Recht-Ipson model. During training, it exhibited a Mean Absolute Percentage Error (MAPE) of 0.0259 and a Root Mean Squared Error (RMSE) of 1.5993. For validation, MAPE was 0.0295, and RMSE was 2.2056. In contrast, the Recht-Ipson model displayed higher errors, with MAPE and RMSE values of 0.2349 and 14.1791, respectively. Furthermore, we discuss the potential of the ANN model in predicting not just residual velocities but also absorbed energy, showcasing its versatility. The practical implications of our findings are vast. From designing safer infrastructures in urban settings to enhancing armour systems in military applications, the ANN model's predictions can be a cornerstone for innovation.
在本研究中，我们深入探究抛射体的迷人动力学及其与材料的相互作用，特别关注残余速度——抛射体撞击目标后保留的速度。该参数至关重要，尤其是在考虑各种环境中防护屏障的设计时。传统测量残余速度的方法既繁琐、资源密集，又偶尔不一致。为应对这些挑战，我们通过MATLAB R2021a引入了一种使用人工神经网络（ANN）模型的创新方法。这个计算机化工具基于先前研究的丰富数据集进行训练，通过考虑多个因素，包括抛射体的初始速度、其材料和形状以及目标的厚度，来预测残余速度。本文详细阐述了ANN模型的开发、训练和验证，突出了其与Recht - Ipson模型等传统方法相比的卓越准确性。与Recht - Ipson模型相比时，所开发的ANN模型表现出色。在训练期间，它的平均绝对百分比误差（MAPE）为0.0259，均方根误差（RMSE）为1.5993。在验证时，MAPE为0.0295，RMSE为2.2056。相比之下，Recht - Ipson模型显示出更高的误差，MAPE和RMSE值分别为0.2349和14.1791。此外，我们讨论了ANN模型不仅在预测残余速度方面，而且在预测吸收能量方面的潜力，展示了其多功能性。我们研究结果的实际意义广泛。从在城市环境中设计更安全的基础设施到增强军事应用中的装甲系统，ANN模型的预测可以成为创新的基石。
