Active image-based feeding of small parts using aerodynamic chicanes

使用空气动力学弯道基于主动图像的小零件进给

• 批准号: 528450120
• 负责人: Professorin Dr.-Ing. Annika Raatz
• 金额: --
• 依托单位: Institut für Montagetechnik (match)
• 依托单位国家: 德国
• 项目类别: Research Grants
• 资助国家: 德国
• 项目状态: 未结题
• 来源: https://gepris.dfg.de/gepris/projekt/528450120?language=en
• 关键词: Active; image; based; feeding; small

Modern production systems are exposed to a variety of requirements with regard to variant flexibility and planning uncertainties, as well as an increased cost pressure. The feeding technology as a decisive component of automated assembly systems must meet these requirements. The aim of this project is therefore to research methods for an active, image-based feeding of components using aerodynamic orientation modules. The active method allows for high feeding rates, while the use of image processing and aerodynamic actuators provides a high degree of flexibility with regard to the component shape. Within the scope of the proposed project, the development of a simulation model for planning the orientation process and the training of the image processing with the aid of CAD data is intended to drastically reduce set-up time and thus significantly increase the flexibility and plannability of the feeding system. Due to the use of aerodynamic chicanes, no changes to the hardware will be necessary to convert the system, which in addition to increased flexibility also contributes to resource conservation and thereby increased sustainability. There is a concrete need for research in the development of a simulation model that can calculate stable component positions and derive the necessary orientation steps. Likewise, the number, type and position of the aerodynamic chicanes must be derived from the component spectrum to be defined, so that maximum flexibility on the hardware side is guaranteed. In order to enable the image processing to be trained offline with the aid of CAD data, a robust method for generating the necessary training data sets in the form of rendered images must also be developed. A particular challenge is to close the domain gap between the artificially generated images of the workpieces and those captured by the real image processing. Finally, the researched methods are combined in a functional model that meets the requirements of modern production systems. The methods and functional model will be evaluated with the help of previously derived validation workpieces, based on defined criteria.

现代生产系统面临着各种各样的要求，涉及变化的灵活性和计划的不确定性，以及增加的成本压力。送料技术作为自动化装配系统的决定性组成部分，必须满足这些要求。因此，该项目的目的是研究使用气动定向模块的基于图像的主动进给部件的方法。主动方法允许高进给速率，而图像处理和空气动力学致动器的使用提供了关于部件形状的高度灵活性。在拟议项目的范围内，借助CAD数据开发用于规划定位过程和图像处理培训的模拟模型，目的是大幅减少安装时间，从而显著提高供料系统的灵活性和可规划性。由于使用了空气动力学变速箱，改装系统不需要改变硬件，这除了增加灵活性外，还有助于节约资源，从而提高可持续性。特别需要研究开发一种模拟模型，该模型可以计算稳定的部件位置并推导出必要的定位步骤。同样，气动变速箱的数量、类型和位置必须从要定义的部件谱中得出，以便在硬件方面保证最大的灵活性。为了能够借助CAD数据离线训练图像处理，还必须开发一种稳健的方法，用于以渲染图像的形式生成必要的训练数据集。一个特别的挑战是弥合人工生成的工件图像和由真实图像处理捕获的图像之间的域差距。最后，将所研究的方法结合到一个符合现代生产系统要求的功能模型中。这些方法和功能模型将根据定义的标准，借助先前派生的验证工作件进行评估。