EVENT MVC 2022
Machine vision: can it ever be “plug and play”?
Advances in digitilisation have brought new opportunities to ‘democratise’ machine vision through ‘off the shelf’ solutions, writes Neil Sandhu, SICK’s national product manager for imaging, measurement and ranging
M
achine vision has been considered in the past as something of a “black art”. As a result, some automation
projects remained forever on the “to do” list or ended up in the “graveyard” of stalled applications. Vision systems had to be created from the
ground up, custom designed and engineered. Specialist programming skills and knowledge were needed to turn the raw data streamed by a sophisticated camera into a fi nished application. That took time and money, as well as work to enable communication and integration with machine and robot controls. Now, advances in vision sensor hardware
have provided a platform to widen and speed up the adoption of 2D and 3D vision. Vision sensors have become smaller and more intelligent, with onboard processing power so they can be programmed to run applications on the device, or through more localised, edge integrations.
Sensor suppliers have evolved from
hardware manufacturers into software and solution providers. Common vision tasks, such as quality inspection of a printed code or label or a robot picking from a conveyor belt or bin, can be sourced by end users as plug- and-play systems and confi gured without specialist support.
SICK AppSpace SICK’s AppSpace software ‘ecosystem’ has proved particularly useful for simplifying machine-vision applications and especially 3D vision. SICK’s foresight was that it should be as easy to confi gure a programmable vision sensor as it would be to download an app from a mobile phone. Production teams, machine-builders and systems integrators alike are now reaping the rewards of cheaper, quicker and easier integration. Generic Apps like SICK’s Quality
22 March 2022 | Automation
Inspection, or Colour Inspection and Sorting, or the SICK Label Checker, have cut down the set-up time dramatically for common tasks in a wide variety of production environments. SICK has also gone further to deliver ready-made ‘plug and play’ systems for specifi c applications that arrive in a box, possibly with other hardware where required, ready to be powered up in just a few steps. Guided through set-up with an intuitive graphic interface, users can confi gure an application with minimal eff ort and no specialist skills. Examples include: • Electronics: Combining SICK’s well-
proven Ranger series vision cameras, SICK laser profi ling devices and specially- developed software, the SICK Pinspector is a specialist 3D vision solution that brings new levels of repeatability and accuracy for high- speed precision inspection of connector pins and press-fi tted pins in printed circuit board and electronics manufacturing applications. • Robot guidance: The SICK PLOC2D is an out-of-the-box robot guidance vision system for 2D parts localisation that is easy to set up and operate without specialist machine vision expertise. With the Belt Pick Toolkit App SICK’s Trispector P programmable 3D vision camera becomes a standalone, belt-picking sensor for both industrial and collaborative robots, including robot brands such as Universal Robots. The SICK PLB 520 is a 3D vision-guided bin picking solution designed for precise localisation of parts stored in boxes or on pallets. It is adaptable for a range of applications, from small-part handling and depalletising through to handling of large foundry parts. Operating on several SICK 3D vision cameras including stereovision technology, the software and the
SICK’s Colour Inspection and Sorting App checks the quality of baked goods
pre-calibrated cameras are used right out of the box, so the system can be ready within minutes. • AGVs: There are also SICK solutions for existing or new automated guided vehicles (AGVs). For example, the recently released SICK Pallet Pocket Detection and SICK Dolly Positioning SensorApps come loaded onto the SICK’s Visionary-T AP 3D time-of-fl ight snapshot camera, ready for use as precision systems for fi ne positioning. As self-contained hardware components, they are easy to fi t to existing machinery, as well as being available for use in new industrial truck designs.
Power to the people
Even a few years ago, these advances in machine vision accessibility would have been unthinkable. Even experienced engineers could be understandably nervous about the prospect of integrating vision systems. Now, even setting up challenging inspections using deep learning requires radically reduced set-up time and cost by enabling artifi cial intelligence image classifi cation to run directly onboard SICK smart devices. Whether you are an end-user, system integrator or machine builder, vision systems stand ready to truly bring ‘power to the people’.
CONTACT:
SICK
www.sick.co.uk
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 |
Page 65 |
Page 66
