Robotic parts sorting with machine vision

利用机器视觉进行机器人零件分类

• 批准号: 568684-2021
• 负责人: Larsen, Paul
• 金额: $ 1.79万
• 依托单位: Sault College
• 依托单位国家: 加拿大
• 项目类别: Applied Research and Development Grants - Level 1
• 财政年份: 2021
• 资助国家: 加拿大
• 起止时间: 2021-01-01 至 2022-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=724316
• 关键词: Robotic; parts; sorting; machine; vision

Rector Machine Works. is a modernized machine and fabrication shop, and the manufacturer of anchor plates, precision steel consumables used in advanced technology steel production. With Canada's recent commitment to modernizing the steel industry, Rector Machine Works would like to stay competitive by continuing to develop and expand its manufacturing capacity and automation. While Rector Machine Works uses precision automated machining stations, untangling rough-cut steel anchor blanks is a production bottleneck. Currently the heavy, rough anchor blanks are untangled by hand, a slow, difficult process. Since anchor plates are technically complex, it is fitting that the most cost-effective solution is employing an industrial robot. The collaborative project with Sault College will involve using a vision camera and custom software to capture the position of the tangled anchor blanks on a pallet adjacent to the robot. The vision camera will then transfer the lateral and rotational offsets of the steel parts to the robot. The robot will then apply these offsets which will result in the careful freeing of each interlocked part, requiring no manual intervention. This will result in faster throughput of the entire process. Sault College's robot lab is ideal for this project. The college has an industrial robot large enough to lift the heavy anchor for the proof-of-concept project.

校长机器厂是一家现代化的机械加工厂，生产锚板，精密钢材消耗品，用于先进技术的钢铁生产。随着加拿大最近对钢铁工业现代化的承诺，Rector Machine Works希望通过继续发展和扩大其制造能力和自动化来保持竞争力。虽然雷克托机械厂使用精密自动化加工站，解开粗切钢锚坯是一个生产瓶颈。目前，沉重，粗糙的锚空白解开手，一个缓慢，困难的过程。由于锚板在技术上很复杂，因此最具成本效益的解决方案是采用工业机器人。 与索尔特学院的合作项目将涉及使用视觉摄像机和定制软件来捕捉机器人附近托盘上缠结的锚坯的位置。然后，视觉摄像机将钢部件的横向和旋转偏移传输到机器人。 然后，机器人将应用这些偏移，这将导致每个互锁部件的小心释放，不需要手动干预。 这将导致整个过程的更快吞吐量。Sault College的机器人实验室是这个项目的理想选择。该学院有一个工业机器人足够大，可以为概念验证项目举起沉重的锚。