Data management
Date with data
Andrew Williams asks how manufacturers can make better use of their machine vision data
@imveurope
www.imveurope.com
M
achine vision devices are now an increasingly common sight in manufacturing facilities, for inspection
and quality control functions across a range of industrial sectors. Some observers are also beginning to explore how companies might make better use of the data they gather from machine vision systems – perhaps by integrating devices into the broader production process, or feeding back the information collected to make ongoing improvements and adjustments to machinery. So, what are the main ways in which
manufacturers use the data collected from machine vision devices used in their facilities? What strategies could manufacturers adopt to improve the processes they use to collect, interpret and act on the data from such systems? What are the challenges, and how best could the data be used in the future?
Beyond the black box Te images captured by machine vision systems don’t necessarily represent the sum total of the data collected – it’s not just about the images, but also the data derived from them. As Patrick Chabot, manufacturing IT manager at Sciemetric Instruments, explained, vision systems were historically black boxes, meaning that users would take a picture of something, leaving a device to do its thing inside the box before producing a result, i.e. an image. In this sense, he argued that early devices were almost like Polaroid cameras, and that the idea that there might be value in tracking what was going on in the black
28 Imaging and Machine Vision Europe • Yearbook 2018/2019
box and understanding how the results were interpreted was not as important as just the results themselves. ‘Te image became the compliance record that
They can use these
data arrays to trend the behaviour of the robot as it applies the sealant, and spot early any indicators of misalignment
showed you that the part was viewed, evaluated and the result was provided based on that image,’ he said. However, as the Industry
4.0 movement has grown, the notion of what exactly is meant by vision data has evolved with it. In Chabot’s view, this means that the users of machine vision systems are no longer content to have the black
box tell the user whether something is good or bad – but instead want to know much more
MVTec Software
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
