Ilse Büter 09-08-2017
In most of today’s production, manual inspection (inspection performed by operators) is still an indispensable part of the production process, even when other production steps are automated to a high extent. It is remarkable what a human mind can do in assessing the product surface quality. How can you add the intelligence of an operator’s assessment to the automated inspection process?
The current production process involved manual inspection by 15 experienced and trained operators. The product runs in over a 1000 different variants. Whether it was even remotely possible to automate the inspection process, was the question posed by our customer.
ROBOT HANDLING OF DELICATE MEDICAL PRODUCTS
When considering automating the inspection process, roughly two types of inspection can be distinguished: first, the inspection of physical and measurable properties such as length and diameters, and second, the inspection of product quality that goes one step further than measurable properties. One can think of deviations on the product’s surface such as scratches, variations in roughness or shininess. Assessing such properties of the product quality in an automated manner becomes a real challenge. It is difficult, especially if there is a large product variation in terms of shape, material, and color.
Aiming for a fully automated inspection brings the second challenge. Products that are inspected need to be handled, also after the inspection takes place. This means that the automated handling can never damage the product because it simply won’t be detected anymore. Handling of the product is thus a very delicate aspect, which needs to be taken into consideration when automating production.
1. Product handling
An industrial robot with special grippers handles the delicate product during the production process. We developed a special set of grippers for this machine, making it possible to inspect every product variant. The grippers assure prevention of damages and prints on the product.
2. Image Acquisition
During the production process, three types of images are taken. An image of the upper side, the bottom side and several simultaneous images of the product 360 degrees around. For a reliable result, it is important to generate stable and reproducible images; the hardware (the cameras) and the software (for image processing and deep learning) must communicate in the correct way. Only then, we can assure our customer that a reliable inspection and quality assurance takes place.
THE GRIPPERS ASSURE PREVENTION OF DAMAGES
IMAGE PROCESSING AND ASSESSMENT
3. Image processing
Multiple software packages are used in this step, which processes the images from 3 cameras. We developed a special solution to show the results of all the inspection steps in 1 overview screen: using a software shell that makes it possible to show the results from the hardware and software systems combined into one, intuitive graphical user interface (GUI).
4. Deep learning
After the inspection, the machine needs to be able to use the results for a subsequent inspection of the same or a different product variant. That is why our system uses deep learning. By using algorithms that search for deviations in the images and comparing these with images of products with normal variations and products with known damages, the system can learn itself to recognize more and more defects.
IMS developed and built this stand-alone machine, which is integrated into a fully automated and unmanned production line also delivered and installed by IMS.
This production line can handle over 1500 product variants.
Automating the quality inspection of this delicate product resulted in the following benefits for our customer:
FULLY AUTOMATED AND UNMANNED PRODUCTION LINE
Sales Manager
SMALL, ASSEMBLED PRODUCTS CALL FOR A SMART AND SCALABLE PRODUCTION LINE
IMS is your partner in enhancing your production capabilities. Do you want to know more about production automation or do you have a specific automation challenge for your innovative product? We are happy to assist you further!
Give us a call Contact salesSales Manager
