![](/sites/default/files/editorial_images/xact-1000.jpg)
Indexable inserts are interchangeable cutting tools that are indispensable in various industrial applications, especially in metalworking. They are used as cutting material carriers for machining metals, plastics, or wood.
ADVERTISEMENT |
Manufacturing indexable inserts requires high-precision production processes to ensure exact geometries and perfect surface finish. Even minimal deviations affect not only the service life but also the performance of the cutting insert. The smallest defects, invisible to the human eye, can cause immense damage—for example, when milling or cutting high-quality components—and that’s including consequential costs.
Careful quality control is essential to ensure that only flawless indexable inserts leave the production process and meet the highest requirements in terms of durability and reliability.
A flagship project by automation and measurement technology specialist Xactools demonstrates how artificial intelligence can help visual inspection make quantum leaps. The medium-size German company has developed a fully automated handling and inspection system for a global manufacturer of indexable inserts based in Scandinavia, in which the IDS DENKnet solution for AI-based image evaluation plays a decisive role and sets new standards in performance, zero-defect production, and speed.
Application
About 1.2 million indexable inserts leave the Scandinavian company’s production halls every week to be used where process reliability and productivity are critically important, such as metalworking, automotive, and aerospace industries.
The inserts are manufactured using a sintering process in which powdered metals, hard metals, and other materials are pressed into the desired shape and then sintered, i.e., bonded under heat and pressure. The strong and robust structure this creates makes it possible to combine materials with different properties to achieve the desired cutting and wear resistance properties. After the sintering process, the edges of the indexable inserts are rounded and ground, and their surfaces are blasted, ground, and coated.
The robot vision system is used directly after the sintering process. “The earlier that defects are detected in the process, the better and cheaper it is to rectify them,” says Marvin Krebs, director of technical sales at Xactools. Eight high-resolution industrial cameras and two spider robots are used to handle and inspect the indexable inserts for defects. DENKnet’s AI forms the heart of the complex image processing system between cameras, robots, and a multi-GPU computing rack.
Requirements
The small tool parts come in a variety of properties and geometries. The Scandinavian manufacturer alone has about 2,800 products in its portfolio, which can be divided into almost 100 geometry families. The aim was to automate handling and defect inspection for all of these.
“The first challenge results from the numerous color variations within the powder used in the pressing process,” says Krebs. “If certain parameters such as time, pressure, or positioning vary, you can get different color or gloss-level deviations, or a different distribution of speckles on the surface, but these are not defects.” The AI-based image evaluation software had to be trained to correctly recognize the numerous possible color deviations of the surfaces and rate them as “OK.”
On the other hand, the smallest irregularities, such as cracks, scratches, inclusions, or other anomalies must be recognized as such and classified as “NOK,” or not OK. The inspection of metal surfaces is considered one of the highest skills of surface inspection, as the texture can be matte, shiny, or even reflective. “The AI had to be trained to recognize variations and lighting conditions for this application,” says Krebs.
The AI recognizes the contour of the indexable inserts and also differentiates between OK and NOK for new parts.
In addition to the visual appearance, one must factor in the insert geometry. Triangles, rectangles, rhombi, or squares can be found in countless variations and are therefore divided into manageable subcategories, so-called geometry families. Xactools made the preselection for the training of the meshes; almost 100 geometry families were defined and then taught by the manufacturer itself.
What sounds like a laborious undertaking was surprisingly quick. “No more than 20 to 30 images were needed to teach each geometry family,” says Krebs. The DENKnet palletizing AI for this purpose uses the DENKnet segmentation and classification network. The customer trained the customized image analysis solution with the DENK VISION AI Hub.
The AI was integrated into the production line in just a few months and achieved almost perfectly reliable AI results for the metal components to be tested right from the start. “Indexable inserts identified as defective are sorted out and grouped according to the size and position of the defect,” says Daniel Routschka, sales manager for artificial intelligence at IDS Imaging Development Systems. “The AI image analysis detects more than 99% of production errors.”
But how exactly does the system work?
Eight cameras with resolutions between 5 and 30 megapixels provide live images of the indexable inserts, which are positioned by magnetic or interchangeable grippers. For example, a camera records the individual indexable inserts from below and from above to check them for surface defects. Two other cameras check their cutting edge. A lighting screen measuring 1 sq m provides extremely high illumination at the palletizing stations.
![]() |
“The system detects defects in the thousandth of a millimeter range,” says Krebs. This ensures that any damage to high-end surfaces can be detected before moving on to later processing. This is because uneven and faulty milling processes can potentially impair profitability and competitiveness.
To prevent this from happening during the production process, and to exercise the greatest possible caution, the system also records images of the contour and position of the panels after inspecting the surfaces and edges.
It can see exactly where and in which rotational position the indexable insert is positioned so the magnetic gripper can finally place it on pin pallets. To ensure this, the gripper, to which the indexable insert is attached, moves over a camera that detects the exact position of the hole from below. At the same time, the contour of the insert and the outer edge of the gripper are detected to correct the position of the indexable insert and hit the pin if necessary. In addition, each individual pin position is detected to recognize bent and broken pins so they are not palletized in the first place.
The AI image analysis recognizes the drill holes and thus the component center for pick-up with a magnetic or internal gripper.
“The system has been running for six months, and the self-learning, global AI now recognizes parts that it has never seen before,” says Krebs. “After just three to four months, new versions of indexable inserts no longer had to be [introduced] for inspection. The underlying geometry is no longer relevant for the AI; it knows the contour and can also differentiate between OK and NOK for new parts.”
High-performance AI image analysis with 99% picking efficiency
For Krebs, the added value of the DENKnet system compared to conventional image processing is obvious: “Without AI, the creation of part families and defect detection would be completely unthinkable. With rule-based image processing, the robot would also recognize parts within the standard range as NOK and sort them out,” he says.
Thanks to the Vision AI Hub, no hard coding is necessary. The flexibility of the networks was another selection criterion for the intelligent DENKnet software. “We were able to easily embed the DENKnet palletizing AI and several object classes for defects into our own Xactools image processing software via an API,” says Krebs.
The entire inspection process takes place in a cycle time of four seconds, with almost 100% picking efficiency. The image analysis of live images from eight cameras via a DLL (dynamic link library) requires enormous computing power.
“We work with DENKnet for a good reason. The performance is not comparable with that of other providers; it is truly excellent,” says Krebs. “Using artificial intelligence in the most diverse variants on this scale has never been done before.” Further variations are currently being tested, for example, to further simplify hole detection.
Detection of the component center from below for position correction before placement on the pin pallet.
Outlook
The extremely varied surfaces and geometries as well as tolerances in the thousandths of a millimeter range make the visual inspection of indexable inserts a demanding discipline that can be transferred to many other applications. DENKnet’s self-explanatory training environment serves as a simple, high-performance tool because it can be operated with no programming knowledge and enables the automated training of AI with just a few clicks. A wide range of vision AI technologies is available for this purpose.
“This solution can be customized to any use case and there are no limits—no matter how many classes, which camera technology, how large or small the images, or even how mixed the data sets are in terms of resolution and type,” says Routschka.
Krebs says, “Over 95% of our measuring and testing systems have at least one AI object class integrated. The potential areas of application are getting bigger and bigger for us. The market is growing.”
Add new comment