Industrial cameras starting to play a significant role in current industrial environment and they represent a strong tool for robotics mainly in cases when they are combined with high-speed robots. However, there are still some difficulties in vision system integration. The capability of such system (e.g. assembly or technological system) depends on several factors, for instance, the camera position, lightning conditions, pattern recognition algorithms, precise setup, as well as well-trained programmer and engineer. The skills of the engineering staff and the precise analysis of conditions and process requirements seem to be crucial for successful solution, what was proved also in our experimental test. The main aim of the article is development and complex performance analysis of robotized screwing application with integrated vision system, concretely the case study of automated assembly system in automotive industry—bolting tightening robotized station as a part of car seat assembly process. The main key elements of the designed workplace are industrial robot FANUC M-20iA/20M with integrated iRVision system containing the industrial camera Sony XC-56. The real influence of inaccuracies during the design process, gradual “step-by-step” refinement, and final influence of all changings on the final quality and efficiency of designed system was demonstrated. At the end, we reached the point where the total number of screwing operations with NOK results (not OK / negative results) is about six single negative results per day, which represents less than 0.1% of all recognitions (overall reliability is higher than 99.9%).

中文翻译：

---

案例研究：汽车行业集成视觉传感系统的机器人拧紧应用的性能分析和开发

工业相机开始在当前的工业环境中发挥重要作用，它们代表了机器人技术的强大工具，主要是在与高速机器人结合的情况下。但是，视觉系统集成仍然存在一些困难。这种系统（例如装配或技术系统）的能力取决于几个因素，例如，相机位置、闪电条件、模式识别算法、精确设置以及训练有素的程序员和工程师。工程人员的技能以及对条件和工艺要求的精确分析似乎是成功解决方案的关键，我们的实验测试也证明了这一点。本文的主要目的是开发和分析具有集成视觉系统的机器人拧紧应用程序的复杂性能，具体以汽车行业自动化装配系统为例——螺栓拧紧机器人站作为汽车座椅装配过程的一部分。设计工作场所的主要关键元素是工业机器人 FANUC M-20iA/20M，带有集成 iRVision 系统，其中包含工业相机 Sony XC-56。展示了设计过程中不准确的真实影响、逐步“逐步”细化以及所有变化对设计系统的最终质量和效率的最终影响。最终，我们达到了 NOK 结果（不是 OK / 阴性结果）的拧紧操作总数约为每天 6 个单个阴性结果的地步，占所有认可的不到 0.1%（总体可靠性高于 99.9 %）。