AI is among the advances simplifying vision systems for users
By David Tillett
Scanners and machine vision systems are becoming more important for manufacturers as automation and data requirements increase and demands on skilled machinery operators leave them less time to devote to quality-control tasks. Representatives from Inspekto, Cognex, Omron, Zebra Technologies and Datalogic discussed some of their companies’ newest offerings.
Inspekto touts S70’s ease of use
Because machine vision systems tend to be complicated and expensive to implement, they were traditionally only practical for stable production runs of a single product over long periods of time.
Ofer Nir, VP products and marketing for Inspekto, said machine vision falls into three general categories, in ascending order of complexity: vision sensors, smart cameras and full vision systems. He said his company’s Inspekto S70 Gen. 2 system, which launched this spring, has a three-layered AI software that mimics the way human vision works. Its capabilities overlap much of what can be done by the three traditional types of vision systems, but it stands in a category of its own.
“We call it the AMV-AI — autonomous machine vision AI,” Nir said. “It’s a completely different approach.”
The AMV-AI has three layers of AI engines: The Acquisition AI layer adjusts the hardware settings to optimize the image that it captures; the Detection AI analyzes images to detect the part; and the Inspection AI checks the part for defects. According to the company’s website, the Inspekto S70 Gen. 2 can be set up in about 45 minutes by users without any machine vision or AI expertise. To begin inspections, the system needs to be shown an average of 20 to 30 samples of good parts.
The technology offers two major benefits, Nir said. First, it allows the use of a single electro-optic system for a wide range of applications, and second, it dramatically simplifies the deployment process for the end user.
The S70 Gen. 2 features a new array of LEDs that can project light from multiple directions at varying intensities and different intervals. It can compensate for vibrations in the work environment and inspect up to three parts per second.
Nir highlighted the system’s adaptability. “Today, you need this quality inspection, then you use the Inspekto S70 for this. Tomorrow, suddenly there is a different need. … Here, what I’m telling you: ‘Hey, you have Inspekto S70 monitoring Part [SKU] A, let’s try to monitor Part SKU B — most likely it will succeed.’ ”
Cognex simplifies vision system for users
Implementing traditional vision systems requires a level of sophistication that can be daunting for most manufacturers, said Brian Benoit, a senior product manager with Cognex.
Benoit contrasted that with Cognex’s In-Sight D900 smart camera vision system, which launched last year and integrates the camera, lighting and software in one platform. “The D900 is a product that's bringing really complex deep learning applications into a much broader audience,” because it doesn’t require in-depth programming skills. It is available in monochrome and color models with resolutions of 2.3 megapixels or 5 megapixels.
Benoit identified three main applications for the D900: defect detection, optical character recognition and verification of assembly.
Scratches, deformations and flash on molded parts are among the problems the D900 can spot.
“That flash could be incredibly variable from one to the next in size and location, even in the way that the camera interacts with it from a lighting perspective,” Benoit said.
For more metric-driven needs, Benoit pointed to Cognex’s In-Sight 3D-L4000, a 3-D vision system that uses a blue laser and camera to handle very accurate measurement and inspection tasks on automated production lines.
The L4000’s blue laser allows it to capture speckle-free images of a higher quality than traditional systems. It can be used for a wide variety of tasks, from checking geometries and making measurements, to inspecting fill levels and verifying that caps are properly sealed.
Omron promotes flexible system
Felix Klebe, marketing manager for sensors and advanced sensing with Omron Automation Americas, said that, while many companies offer systems that have some level of AI capability, the ease of use of AI is all over the map. Omron’s AI is intended to be very easy for someone at a technician level to implement, and Klebe highlighted the company’s FH-series vision system, which launched last fall. A PC-based system that can support as many as eight cameras with resolutions up to 20 megapixels, the FH can be used many ways, including in 3-D robotic bin-picking applications.
Klebe said the FH system offers two levels of AI. The first, Fine Matching, can learn to discern defects after being shown a pool of between 100 and 200 images of good parts. Its image filter focuses on defects, such as the presence of foreign material, and excludes irrelevant details, such as minor positional differences. The second level of AI is Scratch Detection, which users can add with a one-time software license fee. This tool extracts and highlights the pixels it considers to be a defect, and is especially useful in identifying scratches and blemishes that are difficult to detect, such as on textured surfaces.
Klebe said the “baby brother” of the FH is the FHV7, an all-in-one smart camera with lighting, lens and sensor in a single package with a resolution of up to 12 megapixels. The FHV7 can toggle between different lighting colors for the best contrast with the materials and environmental lighting conditions it is working with.
Klebe said Omron’s smart cameras can conduct vision tasks as well as bar-code reading and optical character recognition. “You’re saving the cost of the hardware, the physical space, and you may be checking at an earlier point in the production so that it can be flagged,” he said. “The further downstream you go, the more cost there is to resolve the issue.”
And these capabilities can be integrated into other equipment. Omron’s V275 series of print quality inspection systems can be used with a laser marker or a thermal printer to make sure what’s being printed meets all required metrics.
Zebra Technologies enters scanner, camera market
While Zebra Technologies has a long history supplying products to manufacturers, it made a splash this spring by announcing a full portfolio of fixed industrial scanners (FIS), machine vision smart cameras and a software platform that can run both.
Donato Montanari, VP of machine vision solutions at Zebra, said simplicity is one of the main advantages of his company’s products. The majority of Zebra’s scanner and camera hardware can be used interchangeably for either scanning or machine vision tasks, and its Aurora software platform lets users control both sets of tasks with an intuitive, user-friendly interface.
Montanari said this flexibility means users could start with simple scanning tasks and eventually move on to rules-based machine vision by simply upgrading their software license.
He said that as automation grows, especially for medical device production, it will be harder for human inspection to keep up. “First of all, it’s very hard to find labor,” Montanari said. “Second of all … because of the pandemic it’s even harder to put labor next to each other. So, the question is, why are these companies still choosing to do human inspection?” He said scanners can also help with traceability issues.
Montanari also said Zebra has taken steps to boost data security. The company’s higher-end camera models have two physically separated ethernet IP ports, with a different chip controlling each port. This allows one port to connect to the cloud, while the other port, which connects to a machine’s PLC, is not discoverable from outside.
Datalogic’s P2X-series has advanced capabilities
Jose Vega, marketing manager for Datalogic, said the introduction of AI is giving more devices plug-and-play capabilities, allowing manufacturers to focus on production instead of issues with managing their technology. He said Datalogic’s new P2X–series camera has advanced capabilities and can discern subtle differences in the color it inspects, regardless of problems in environmental lighting. It can be used to decode laser markings on difficult-to-read products, including reflective or clear plastic parts.
As demand for traceability increases, Vega said the plug-and-play capabilities of the P2X will be critical for regulatory and recall-prevention needs. For high-demand applications that require high-speed detection, he pointed to Datalogic’s MX series.
AI also has automated the installation process. Defects and problems can be directed using smart cameras and sensors that have all the processing power built in for instant addition to production lines. It makes implementation of the technology easy.
David Tillett, associate editor
Contact:
Cognex Corp., Natick, Mass., 855-426-4639, www.cognex.com
Datalogic USA Inc., Eugene, Ore., 800-227-2633, www.datalogic.com
Inspekto, Ramat Gan, Israel, 972-73-3678187, www.inspekto.com
Omron Automation Americas, Hoffmann Estates, Ill., 847-843-7900, automation.omron.com
Zebra Technologies Corp., Lincolnshire, Ill., 877-208-7756, www.zebra.com
David Tillett
Associate Editor David Tillett writes and edits for Plastics Machinery & Manufacturing, Plastics Recycling and The Journal of Blow Molding. He covers new products, industry news, patents and consumer and business equipment. He has more than 20 years of experience in daily newspaper, online and magazine journalism.
