EVENT VISION 2022
Easy deployment of machine learning on the factory fl oor
G
enerally, line and automation engineers would use machine vision and deep learning to improve their inspection rate
and accuracy, accelerate their production and eliminate the need for manual inspection. However, there is a common misconception that implementing this technology is complex and requires either specifi c technical knowledge or the assistance of machine vision experts. That’s no longer the case. Deep learning is now easier to use than ever, with the introduction of new technologies that process images at the “edge”. Also known as “edge learning”, it is a subset of machine learning in which processing takes place directly on-device with the help of pre-trained algorithms.
Optimised factory automation needs, the Congex’s In-Sight 2800 vision system uses edge learning technology to solve a range of applications, quickly and easily. The system can be deployed within minutes and requires no specialist experience. An engineer can plug in the system, point it at the part that needs inspecting, to capture training images and produce useful output.
In-Sight 2800 is designed for factory
fl oor use, and a signifi cant element of that design is the point-and-click EasyBuilder development environment. The intuitive interface provides the feedback necessary for optimising the process, whilst allowing the user to experiment with the eff ects of various choices, such as diff erent lighting colours or focus points.
Classification “Classifying” is the process of assigning useful categories to parts for purposes of inspection. The categories can be OK/ NG, separating acceptable (passing) from unacceptable (failing) parts when detecting defects. Classifi cation can also involve sorting products into multiple categories, such as diff erent part variations and confi gurations, especially when multiple objects are present. For example, a product is a container that includes a scoop for measuring contents, so each container must have one. When
30 September 2022 | Automation
the containers come down the line, the scoops can be at a variety of angles or partly concealed by the container contents. In-Sight 2800 can capture several images to establish if a scoop is present, or one or more, or none, and then label those that are acceptable and those that are not. The In-Sight 2800 makes its own decisions on how to diff erentiate these, and the EasyBuilder interface shows the degree of confi dence of its categorisation. If an image is miscategorised, the confi dence level will drop, and a further analysis will be needed to establish why: has a scoop been missed and categorised as a “no-scoop”, and so on. In-Sight 2800 will accurately categorise each container after a brief training, to then issue alerts, store data, or send it elsewhere for further analysis.
Technology and staff The only knowledge required to use
In-Sight 2800 is what your staff already has: what distinguishes an acceptable from an unacceptable part, what classes your products come in, and when a product change requires updating inspections and a brief retraining of the In-Sight 2800. So anyone working on your line or factory fl oor can use the In-Sight 2800 with only a few minutes required to familiarise themselves with the interface. The In-Sight 2800 has everything for immediate operation. It includes a high- resolution sensor, fast processor, a multi- colour lighting, a high-speed liquid lens option, and intuitive, point-and-click interface. Its compact size is designed to fi t in even the most space-constrained line.
CONTACT:
Cognex UK
www.cognex.com
Top: IS2800 scent identification Bottom: A closeup of IS2800 scent identification
automationmagazine.co.uk
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64
