首页|Findings from Beijing Jiaotong University in the Area of Machine Learning Descri bed (Machine Learning Based Laser Homogenization Method)
Findings from Beijing Jiaotong University in the Area of Machine Learning Descri bed (Machine Learning Based Laser Homogenization Method)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A new study on Machine Learning is now available. According to news reporting originating from Beijing, People's Repub lic of China, by NewsRx correspondents, research stated, "Laser is widely used i n various fields such as laser processing, optical imaging, and optical trapping due to its high monochromaticity, directionality, and high energy density. Howe ver, the beam generated by the laser is a Gaussian beam with non-uniform distrib ution of optical energy, and this non-uniform distribution affects the interacti on between the laser and the matter." Financial support for this research came from National Natural Science Foundatio n of China (NSFC). Our news editors obtained a quote from the research from Beijing Jiaotong Univer sity, "Therefore, it is necessary to reshape the Gaussian beam into homogenized light spots with uniform distribution of optical energy. Laser beam homogenizati on method aims to change the spatial distribution of the Gaussian beam, precisel y controlling the shape and intensity of the laser beam to achieve homogenized l ight spots. However, the existing laser beam homogenization methods encounter so me problems such as complicated component preparation and poor flexibility. They also fail to address experimental errors caused by stray light and zero-order l ight interference, leading to discrepancies between the experimental results and the expected results. These limitations seriously restrict the widespread appli cation of laser technology in various fields. A laser homogenization method base d on machine learning is proposed for spatial light modulator (SLM) laser homoge nization in this work. The preliminary approach to laser homogenization is to ge nerate a phase hologram by using the Gerchberg-Saxton (G-S) algorithm and modula te the incident light beam into homogenized light spots by using an SLM. However , the inherent homogenization error of the SLM prevents laser homogenization fro m improving uniformity. The machine learning method is proposed as a means of co mpensating for homogenization errors, thereby improving the uniformity of the li ght spot. The corresponding supervised learning regression task on the experimen tal dataset establishes mapping relationships between the homogenization target images and the experimental detection images. The results of homogenization erro r compensation are validated through experiments. Compared with the traditional SLM laser homogenization methods, the proposed method reduces the non-uniformity of the light spot by 13%. The laser homogenization method based on machine learning is an efficient way to achieve laser beam homogenization. The proposed laser beam homogenization method can serve as a reference for machine l earning-based method. This method possesses significant technical value for lase r applications such as laser processing, optical imaging, and optical manipulati on."
BeijingPeople's Republic of ChinaAsi aCyborgsEmerging TechnologiesMachine LearningBeijing Jiaotong University
NETL
NSTL
