Partner:&nbsp;Daikin PilsenProblem:The plant in Pilsen produces over two million air conditioning units per year. A lack of manpower and attempts to minimize human errors are reasons why DAIKIN Industries Czech Republic focuses on process automation in their production plans fulfillment, with continuous attention to high product quality.&nbsp;In one of its assembly lines, there was a specific bottleneck in a mid-assembly quality-check process &nbsp;that required a new approach based on a high-quality 3D vision system – a test of the integrity of heat exchangers. The major motivation to automate the sensitive test and the challenge per se lied in the requirement for high preciseness during the inspection of heat exchangers. Because they are made of thin, fragile metal, &nbsp;human errors in the preceding manual inspection process occurred. The required precision of robot guidance in the planned automation solution was +/- 1 millimeter.&nbsp;Solution:<a href="https://www.photoneo.com/bin-picking-studio/" target="_blank">Bin Picking Studio</a> + PhoXi 3D Scanner model SThe Photoneo solution consists of a tailor-made application based on accurate localization and robot-camera calibration. The heat exchanger, first pressurized with helium, comes to a leak-detection cell&nbsp;on a conveyor belt, where it is positioned randomly.In the cell, the PhoXi 3D Scanner scans the object from two different positions to increase the reliability of measurement and the robustness of localization. The system detects the position of the heat exchanger and adjusts the predefined trajectory of the sniffing detector very precisely and carefully along a complex and fragile surface of the object in order to inspect its quality and notice potential helium leakage without damaging it. In addition, Photoneo simplified its robot-camera calibration process to such an extent that calibration can be done by a trained end-user operator without on-site presence of Photoneo’s specialists.&nbsp;Discussion:The whole solution is demanding in terms of working with glossy aluminum surfaces, the configuration, precision of the scanner, and localization software. Moreover, the component geometry of the pieces coming on the conveyor belt is often not identical, so a robust logic had to be implemented to reflect this. The robotic manipulation with the detector as a tool had to be very gentle and precise given the formability of the thin metal material of the parts.&nbsp;Photoneo’s team tackled a very limited workspace of the leak-detection cell in the brownfield deployment.&nbsp;The solution is installed in a production line with a variable just-in-time production plan which means that several types of heat exchangers are subject to a quality check, not just one. The system is extensible, i.e. even after the initial setup for a set of certain heat exchanger types, new ones may be added and probed later on.&nbsp;There is no programming involved and the change is doable only in configuration by a Photoneo specialist. The addition or alteration of the configuration for a particular type of heat exchanger does not affect the quality of service provided for other existing types.&nbsp;

Precise checking of heat exchangers for Daikin Czech Republic

The solution consists of a tailor-made application based on accurate localization and robot-camera calibration. PhoXi 3D Scanner scans the object from two different positions to increase the reliability of measurement and robustness of localization.

Automated inspection of heat exchangers

Picking of metallic objects belongs to one of the most commonly solved problems within the automation. 
This solution enables the automation of parts picking and their precise placing to a predefined location within the desired cycle time.

Pick and place of flat metal objects

Bin picking – i.e. robotic detecting and picking of randomly arranged objects from within a bin on the basis of CAD models – is a common type of application we deal with even in challenging industrial environments. The <a href="https://www.photoneo.com/bin-picking/" target="_blank">Bin Picking Studio</a> is an all-in-one picking solution for robotic integrators, who do not need to know anything about computer vision to set it up. Its robust features made it possible to enter basically all industrial sectors – the automotive, manufacturing, logistics, and others.However, we gradually started to receive requests from our customers for a solution that would enable them to pick objects of irregular shapes and in random positions within the bin. We set to work on algorithms that would enable us to pick these kinds of objects and after some time of intensive endeavor, our AI-driven solutions first saw the light of day. Thanks to sophisticated algorithms, they enabled us to localize and pick objects of different sizes, various textures, and arbitrary shapes including deformations. What’s more, the objects do not need to be stacked in ordered patterns but can be placed absolutely randomly and the robot is still able to recognize and pick them. The AI-powered solutions enabled by a combination of precise 3D vision and advanced AI algorithms showed the world the immense opportunities for automation of material handling, manufacturing, logistics, and many more.And it was logistics that showed us there was one last gap left to cover all kinds of objects and applications – and this resided in the fact that goods are not always transported in solid boxes but some of them come in bags. These pose a great challenge for automated sorting as they do not keep their shape – they are flexible, wrinkled, easily deformable, and thus very difficult to localize. We decided to utilize our experience, knowledge, and skills to push the performance of our AI-powered solutions even further and “teach” them detect and pick bags. The recognition of boundaries between bags that are chaotically placed in a container can often be difficult even for humans. The task gets even more complicated for transparent bags. Difficult – but possible. We developed a network that is able to recognize bags, sometimes better than we are. They may be overlapping and blocking each other from being picked but our system can handle this with ease and won’t allow the robot to grab fully or partly covered bags.Another common difficulty arises from the nature of the material bags are made of – they are full of folds and wrinkles which often causes them to fall off the gripper just after being successfully detected and lifted. We recommend using a vacuum gripper with feedback to prevent such failures.

Randomly arranged objects of irregular shapes, made of flexible materials that are easily deformable, wrinkled, and thus difficult to localize? This is now a problem of the past.

pick and place robots

Latest Posts

Automated inspection of heat exchangers

Pick and place of flat metal objects

Robotic picking of bags - not so utopic after all