Desai Ashish A, Khan S N, Bagane Pooja, Patil Sagar Dnyandev
Mechanical Engineering Department, Rajarshi Shahu College of Engineering, Tathawade, Pune, Maharashtra, India.
Department of Automation and Robotics, Sharad Institute of Technology, College of Engineering, Yadrav, Ichalkaranji, Maharashtra, India.
MethodsX. 2024 Nov 19;13:103066. doi: 10.1016/j.mex.2024.103066. eCollection 2024 Dec.
This research aims to improve the accuracy of cutting fiber-reinforced polymers (FRPs) utilizing CO2 laser processing techniques, with a particular focus on carbon-glass fiber-reinforced hybrid composites (CGFRP) using epoxy resin. Establishing CO laser machining as a dependable and effective process for creating superior CGFRP components is the main goal. This research intends to optimize laser machining parameters to enhance surface quality and machining efficiency for these composites by a thorough parametric analysis. In order to model and improve the correlations between important machining parameters, the research combines regression models, multi-objective gray relational analysis (MOGRA), and Artificial Neural Networks (ANNs). When linked together, these methods enable efficient multi-objective optimization, which enhances laser cutting operations for CGFRP materials in terms of accuracy and economy. Using the Taguchi L27 orthogonal array, one can methodically investigate how different parameters affect CGFRP cutting. GRA is used in optimization to find the best parameter combinations and highlight important parameters. After determining that LPW3CSD1FOL1GPR1 and LPW3CSD2FOL1GPR2 were the ultimate ideal settings, the initial machining parameters were set at LPW3CSD1FOL1GPR1. Predictions and trials confirm that these adjusted parameters result in a 6.125% improvement in grade. Also, ANN structured approach enhances predictive accuracy and provides valuable insights for optimizing machining processes. Accordingly, a strong framework for enhancing hybrid composite laser machining is provided by this research. The research aims to develop a robust framework for optimizing CO2 laser cutting of CGFRP composites, ultimately leading to more efficient, cost-effective manufacturing solutions for high-performance applications in aerospace, automotive, and marine sectors.
本研究旨在利用二氧化碳激光加工技术提高切割纤维增强聚合物（FRP）的精度，特别关注使用环氧树脂的碳 - 玻璃纤维增强混合复合材料（CGFRP）。将二氧化碳激光加工确立为制造优质CGFRP部件的可靠且有效的工艺是主要目标。本研究旨在通过全面的参数分析优化激光加工参数，以提高这些复合材料的表面质量和加工效率。为了对重要加工参数之间的相关性进行建模和改进，该研究结合了回归模型、多目标灰色关联分析（MOGRA）和人工神经网络（ANN）。当这些方法结合在一起时，能够实现高效的多目标优化，从而在精度和经济性方面增强CGFRP材料的激光切割操作。使用田口L27正交阵列，可以系统地研究不同参数如何影响CGFRP切割。在优化过程中使用灰色关联分析来找到最佳参数组合并突出重要参数。在确定LPW3CSD1FOL1GPR1和LPW3CSD2FOL1GPR2是最终理想设置后，将初始加工参数设置为LPW3CSD1FOL1GPR1。预测和试验证实，这些调整后的参数使等级提高了6.125%。此外，人工神经网络结构化方法提高了预测准确性，并为优化加工过程提供了有价值的见解。因此，本研究提供了一个强大的框架来增强混合复合材料的激光加工。该研究旨在开发一个强大的框架，用于优化CGFRP复合材料的二氧化碳激光切割，最终为航空航天、汽车和船舶领域的高性能应用带来更高效、更具成本效益的制造解决方案。
