摘要
由一名新闻记者兼机器人与机器学习的新闻编辑每日新闻-一项关于机器人的新研究现在开始了。据NewsRx Comresponden TS从加拿大温哥华发回的新闻报道，研究表明：“预编程焊接机器人显著提高了大批量生产中焊缝的效率和质量。在中小型批量生产中，机器人需要合适的传感器才能表现良好，并适应噪音焊接环境中的变化和不确定性。”我们的新闻记者从不列颠哥伦比亚大学的研究中获得了一句话：“机器学习使基于视觉的传感器能够感知以前无法测量的过程。一个挑战是开发能够实时跟踪焊缝的人工智能模型，特别是在角焊缝中，视觉分析受到非垂直入射角和圆弧反射的阻碍。”提出了一种基于视觉的深度学习分类模型,该模型能够实现协同机器人的焊缝自动跟踪。该系统基于关键点检测深度学习模型，解决了实时气体保护焊过程中管子与管子之间的角焊缝变形和噪声图像中的难题，实现了非粘着图像中焊缝位置的跟踪，并提出了合适的输入图像尺寸，实现了焊缝实时跟踪。该方法考虑了多幅图像和多点的LSO，以较小的误差和野值提供焊缝位置的可控信号，对于误差小于0.3mm的角焊缝，该方法可以以80%以上的精度跟踪焊缝，该方法具有较高的精度，减少了焊缝的缺陷和缺陷，减少了计算量。从而大大节省了制造成本。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – A new study on Robotics is now availab le. According to news originating from Vancouver, Canada, by NewsRx corresponden ts, research stated, “Pre-programmed welding robots significantly improved the e fficiency and quality of the welds in large batch production. In small and mediu m batch production, the robots need appropriate sensors to perform well and adap t to the changes and uncertainties in a noisy welding environment.” Our news journalists obtained a quote from the research from the University of B ritish Columbia, “Vision-based sensors enabled by machine learning are making it possible to sense in process previously not measurable. One challenge is develo ping artificial intelligent models capable of real-time seam tracking, particula rly in fillet joints where visual analysis is hindered by non-perpendicular came ra angles and arc reflections. In this paper, we propose a vision system that en ables automated seam tracking with a collaborative robot. The vision-based deep learning classification model detects the tacks, where the seam is not visible. It is based on a keypoint detection deep learning model that addresses the chall enges in distorted and noisy images of fillet joints between the pipes and flang es during the real-time Gas Metal Arc Welding to track the location of the seam in non tack images. The system is optimized for real time seam tracking by propo sing the appropriate input image size. Multiple images and multiple points are a lso considered to provide a controllable signal of the location of the seam with less errors and outliers. Our proposed model can track the seam with more than 80 percent accuracy for errors less than 0.3 mm in fillet joints. The high accur acy of the proposed method would result in fewer flaws and defects and reduced r ework, resulting in significant cost saving in manufacturing.”
NETL
NSTL