January 2022

TECHNOLOGY n 19 p Delta Electronics has announced a time- of-flight machine vision camera that can provide 3D information from a single exposure. The DMV-T camera offers frame rates up to 60 fps. It obtains depth information by calculating phase differences between the carrier frequency of emitted light and its reflection from an object, to acquire 3D information at high speeds. It can generate depth maps and point cloud outputs. It offers a choice of acquisition modes including continuous, single-shot and multiple-shot. www.delta-emea.com p Cloudrail , the German company that connects factories rapidly to the cloud for large IIoT projects, no longer requires customers to use its own CloudRail.Box edge gateway with a central management cloud and a service such as AWS or Azure. With its new CloudRail.OS, they can use hardware from any edge gateway provider, or run CloudRail virtualised in their own data centres. CloudRail CEO Felix Kollmar, explains:“With the increasing relevance of edge computing, especially in the context of machine learning, our hardware reached its limits. With CloudRail.OS, we solve this dependency and enable customers to freely choose suitable hardware resources.” https://cloudrail.com p ODVA has enhanced its EtherNet/IP specification to enable EtherNet/IP networks to support the Ethernet-APL physical layer for process automation. Licensed EtherNet/IP vendors can now develop EtherNet/IP components for Ethernet-APL, including controllers, power switches, field switches and instruments. Ethernet-APL is a new intrinsically-safe, two-wire extension of 10Base- T1L (IEEE 802.3cg-2019) single-pair Ethernet for process applications. It supports speeds up to 10 Mbit/s, cable runs of up to 1km, hazardous area protection, and power for instruments in the field. www.odva.org p The US-based AMR (autonomous mobile robot) manufacturer Seegrid Corporation , has announced what it claims is the only lift truck AMR with 3D perception. The Seegrid Palion – the company’s first lift truck – can plan and control its movements to operate safely in complex, fast-moving industrial settings. It automates the movement of palletised loads of up to 1,600kg, retrieving and placing them securely at heights of up to 2m. https://seegrid.com p The US automation and IIoT manufacturer Opto 22 has announced two I/Omodules for its groov Epic edge programmable industrial controller that indicate signal quality and offer intelligent functions such as scaling, averaging, and totalising. The GRV-IVAPM-3 provides Cat III three-phase AC power monitoring up to 600V AC; while the GRV-MM1001-10 provides universal I/O sensing and control. The modules allow users to collect power, energy and machine performance data, as well as asset status reports, directly from field equipment and transport it securely to back-end systems. www.opto22.com TECHNOLOGY BRIEFS MITSUBISHI ELECTRIC and Japan’s National Institute of Advanced Industrial Science and Technology (AIST) have developed an AI technology that makes real-time adjustments to factory automation (FA) equipment as it is running. As well as eliminating the need for time-consuming manual adjustments, the AI estimates the confidence level of inferences regarding factors such as machining errors, and then controls the FA equipment based on suitable levels of confidence. The partners predict that the technology will lead to more stable, reliable and productive operations, especially in agile manufacturing. To optimise conditions in this type of manufacturing, parameters such as operating speeds need to be adjusted frequently. However, doing so by hand is laborious and time-consuming, affecting productivity. In response, Mitsubishi and AIST – who have been collaborating on AI since 2017 – have developed a technology that uses AI to predict variations inmanufacturing processes, such as changes in shapes as workpieces are machined, and then adjusts the FA equipment’s operation automatically in real time. In addition, the confidence levels of the AI inferences are indexed and the FA equipment is controlled to ensure high reliability and productivity. The two organisations cite examples of how their AI technology is being applied in practice: n Mitsubishi has used it to develop a method for estimating loads on robotic arms . Various load parameters are used to calculate acceleration and deceleration speeds. The AI function infers load values using information about the robot, such as motor currents, joint angles, and so on. Simultaneously, the confidence levels of the inferences are calculated. The robot’s acceleration and deceleration are adjusted based on estimated values and confidence levels. A test that compared differences in robot motion when using and not using the load inferences, found that robot operating times were cut by 20% when inferences were used. n A second example is an AI-based error- correction system for CNC cuttingmachines . The AI estimates changing machining errors – the difference between the cutting machine’s current position and a command value – to enable correction even during dynamic machining. Tests have shown that machining accuracy can be improved by 51% compared to using error correction that is not being supported by AI. According to Mitsubishi and AIST, their technology has several key attractions: n It is fast, achieving high-speed inferences for dynamic control of FA equipment. In conventional manufacturing, skilled workers must adjust operating parameters to achieve required specifications, such as accuracy levels. The AI technology simultaneously performs high-speed inferences and equipment control for real-time FA operation. It can achieve high-level inference accuracy while simultaneously guiding FA equipment control. n It can adapt to constantly changing production factors . Workpiece shapes change during manufacturing and this can lengthen manufacturing times or reduce processing quality. These changes can vary for each workpiece, making it difficult for FA equipment to learn in advance. The new technology uses AI to learn work factors while operating the FA equipment and to make real- time adjustments. It also formulates physical phenomena, such as friction, and incorporates mathematical expressions to adapt to constantly changing processing factors. n It performs adjustments reliably . AI inferences must be reliable to ensure that real- time control of FA equipment leads to stable product quality and efficient processing. Mitsubishi’s new algorithm calculates the confidence level of inferences by learning the characteristics of each process and each target device, ensuring high reliability. Mitsubishi plans to incorporate its Maisart AI technology increasingly into its FA equipment and systems to improve manufacturing productivity“significantly”. www.mitsubishielectric.com/en/index AI optimises automation processes in real time The Mitsubishi/AIST AI technology will provide real-time optimisation of automation equipment www.drivesncontrols.com January 2022