A 3D vision system that can instantly detect when bakery and confectionery products exceed dimensional tolerances prior to packaging is claimed to be achieving new performance levels of quality inspection, linked to real-time production correction and rapid return on investment.
The Sentinel Vision system, developed by Adbro in partnership with Sick UK, provides fast savings by reducing packing line downtime and achieving better yields through reduced material wastage. High levels of system functionality achieve a wide range of inspection parameters including length, width, height, volume and surface profile, which can be tracked at a cost that is said to be less than 50 per cent that of other available products.
Adaptable to a wide variety of applications, the system delivers real-time information upstream to an easy-to-use graphical user interface with touch-screen controls. The system enables production operators to track products and correct defects much more quickly than was previously possible.
Avoiding tolerance stacks
David Hannaby, Sick UK's Vision Systems Specialist, explains: "The Sick/Adbro team was challenged to solve a problem in tracking the height and shape of biscuits products prior to wrapping. The biscuits' profiles were straying out of tolerance, accumulating an oversize, which led to whole batches of product being wasted as they were difficult or impossible to pack.
"Unsatisfactory packs could easily escalate into major line downtime, as the packs often burst under handling. In addition, checking back on all the production tolerances up the line to determine the exact problem, recalibrating the process machinery – moulds, depositors, extruders, mix recipes, oven cooking times and so on – could cause expensive and time-costly hold-ups in production.
"A significant amount of product may be out of specification, before the defect in production is corrected. With cooked product in particular, there is no opportunity for the product to be recycled."
Hardware and software
In the system, up to four Sick IVP IVC 3D Smart cameras can communicate with the specially developed Adbro PC Windows-based control interface to provide real-time values for a number of parameters. Any drift in specifications can be quickly identified and corrective action can then be taken much more rapidly than before.
Located over the conveyor belt, the Sick IVP IVC 3D Smart camera comprises a vertically-mounted eye-safe laser with the camera detection mounted at an acute angle. This angle enables the camera to detect the detailed profile of the item passing through the laser beam and enables the depth of profile and any surface defects to be detected. This capability was not previously possible with 2D vision technology.
Typical parameters for a round biscuit could be to find the height profile, find the centre (for exact positioning) or find the edges, measure the dimensions or look at ovality. The volume of the biscuit can then be calculated and compared against a check weight and known volume to determine dough consistency.
The data for each parameter can be compared to product specifications and displayed as trends. Setpoints for alarms alert the operative to excessive drift. The lag between detecting a fault and alerting is very fast, typically in the order of two seconds.
With typical line speeds of 0.5m a second, any delay in process amelioration could be costly, but the Sentinel system is claimed to reduce the time lag significantly. In addition, as the line position of the out-of-specification product is 'tagged' by the camera and software, it can easily be tracked and removed from the line.
David Hannaby concludes: "The system is a cost-effective and robust solution to a significant problem for any bakery or food product where tight tolerances for packing are important."