Liu Yan, Cheng Xiang, Zhang Tingting, Xu Yu, Cai Weijia, Han Fengtian
School of Ocean Information Engineering, Jimei University, Xiamen 361021, China.
Pen-Tung Sah Institute of Micro-Nano Science and Technology, Xiamen University, Xiamen 361102, China.
Micromachines (Basel). 2024 Nov 25;15(12):1413. doi: 10.3390/mi15121413.
Scanning micromirrors represent a crucial component in micro-opto-electro-mechanical systems (MOEMS), with a broad range of applications across diverse fields. However, in practical applications, several factors inherent to the fabrication process and the surrounding usage environment exert a considerable influence on the accuracy of measurements obtained with the micromirror. Therefore, it is essential to calibrate the scanning micromirror and its measurement system. This paper presents a novel scanning micromirror calibration method based on the prediction of a particle swarm optimization-least squares support vector machine (PSO-LSSVM). The objective is to establish a correspondence between the actual deflection angle of the micromirror and the output of the measurement system employing a regression algorithm, thereby enabling the prediction of the tilt angle of the micromirror. The decision factor (R2) for this model at the -axis reaches a value of 0.9947.
扫描微镜是微光机电系统（MOEMS）中的关键部件，在多个不同领域有着广泛应用。然而，在实际应用中，制造工艺和周围使用环境中固有的几个因素对通过微镜获得的测量精度有相当大的影响。因此，校准扫描微镜及其测量系统至关重要。本文提出了一种基于粒子群优化-最小二乘支持向量机（PSO-LSSVM）预测的新型扫描微镜校准方法。目的是使用回归算法在微镜的实际偏转角与测量系统的输出之间建立对应关系，从而能够预测微镜的倾斜角。该模型在x轴处的决定系数（R2）达到0.9947。
