Nishad D K, Tiwari A N, Khalid Saifullah, Gupta Sandeep, Shukla Anand
Department of Electrical Engineering, Madan Mohan Malaviya University of Technology, Gorakhpur, UP, India.
Airport Authority of India, New Delhi, India.
Sci Rep. 2024 Aug 2;14(1):17935. doi: 10.1038/s41598-024-68575-5.
Metro trains have non-linear load characteristics, which means that the power sent to them gets distorted. Problems are caused by changes in power, swells, harmonics, and other disturbances. In this research, an artificial intelligence-driven control method was used on a unified power quality conditioner (UPQC) to help reduce power quality problems and improve power quality. Three advanced control methods are built and compared using MATLAB Simulink. Some of these methods are the ANN Controller, the NARMA-L2 Controller, and the PI Controller, improved using the Adaptive Lizard Algorithm. The controls' usefulness is judged by how well they lower the total harmonic distortion (THD) in the source current. The results show that all three AI-based controls work much better than the system that was not paid for. The ANN Controller works the best, followed by the NARMA-L2 Controller, and the PI Controller improved with the Adaptive Lizard Algorithm. These AI-driven control methods can enhance power quality and ensure that metro rail systems run smoothly and efficiently, as shown by how well they work. Modern transportation networks need more advanced ways to handle power quality, and this research helps make those solutions come together.
地铁列车具有非线性负载特性，这意味着输送给它们的电力会发生畸变。功率变化、电压骤升、谐波及其他干扰会引发问题。在本研究中，一种人工智能驱动的控制方法应用于统一电能质量调节器（UPQC），以帮助减少电能质量问题并改善电能质量。使用MATLAB Simulink构建并比较了三种先进的控制方法。其中一些方法包括ANN控制器、NARMA-L2控制器以及采用自适应蜥蜴算法改进的PI控制器。通过降低源电流中的总谐波失真（THD）程度来判断这些控制方法的有效性。结果表明，所有三种基于人工智能的控制方法都比未采用的系统效果好得多。ANN控制器效果最佳，其次是NARMA-L2控制器，以及采用自适应蜥蜴算法改进的PI控制器。这些人工智能驱动的控制方法能够提高电能质量，并确保地铁轨道系统平稳高效运行，从其运行效果可见一斑。现代交通网络需要更先进的方法来处理电能质量问题，而本研究有助于促成这些解决方案。
