Development of a GPU-enabled production line inspection system

开发基于GPU的生产线检测系统

• 批准号: 486588-2015
• 负责人: Bidinosti, Christopher
• 金额: $ 1.82万
• 依托单位: University of Winnipeg
• 依托单位国家: 加拿大
• 项目类别: Engage Grants Program
• 财政年份: 2015
• 资助国家: 加拿大
• 起止时间: 2015-01-01 至 2016-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=585685
• 关键词: Development; GPU; enabled; production; line

Graphics processing units (GPUs), originally developed for the electronic games industry to improve the rendering speed and quality of computer graphics, have proven extremely useful for general computations as well. As a result, the average desktop computer can now achieve a level of computing power that was once available only at a handful of supercomputing facilities worldwide. This revolution is bringing high performance computing to the masses, driving innovation, and transforming what businesses, both large and small, can achieve. Sightline Innovation is a Canadian company that sells a production line inspection system (called Verify) that utilizes software to sort, assess, and finally make automated decisions about parts on a continuously moving conveyor belt. It is important to make the correct decision - whether or not to reject a potentially defective part, say - and to make this decision in as short a time as possible to maintain factory workflow. There are several factors, such as the random alignment of parts along the belt or variable lighting levels and direction, that add to the challenge of this problem. The objective of this project is to harness the new computing power of GPUs to tackle these problems and to improve further the speed, accuracy, and functionality of the Verify software.

图形处理单元（GPU），最初是为电子游戏行业开发的，用于提高 渲染速度和质量的计算机图形，已被证明是非常有用的一般计算， 好.因此，普通的台式计算机现在可以达到曾经 仅在全球少数超级计算设施中可用。这场革命带来了 高性能计算，推动创新，改变大型和 小，可以实现。 Sightline Innovation是一家加拿大公司，销售生产线检测系统（称为Verify）， 利用软件进行分类，评估，并最终对连续移动的零件做出自动决策。 传送带重要的是要做出正确的决定-是否拒绝一个潜在的有缺陷的部分， 比如说-并在尽可能短的时间内做出这一决定，以维持工厂的工作流程。有几 这些因素，例如沿着传送带的部件的随机排列或可变的照明水平和方向， to the challenge挑战of this problem问题.该项目的目标是利用GPU的新计算能力 解决这些问题并进一步提高Verify软件的速度、准确性和功能。