Edge Computing In contrast to cloud computing, this takes place on the network near the data sources or devices, machines or systems in the network. With the decentralized data processing the analysis and evaluation of data becomes faster and productivity more efficient. Here we present innovations and applications from various manufacturers for edge computing such as the brand new software Melsoft Mailab from Mitsubishi Electric.
Contents
07.02.2023 | The edge computing software Melsoft Mailab (Mitsubishi Electric AI Laboratory) supports companies with the digital transformation their production and promotes their increase in productivity. The data science tool is intuitive and operator-centric. The intelligent platform uses Artificial intelligence (AI) to optimize automated processes. For example, through preventive maintenance, waste can be avoided, rejects reduced, downtime reduced and energy consumption reduced.
15.12.2020 | The digital transformation of industry has connection of OT | operational level and IT | superior information technology gave new impetus to the corporate level. In order to be able to fully exploit the potential of digitization, however, more than just a network connection between these two levels is required. Edge Computing by Mitsubishi Electric offers the solution for this. Relevant business processes can be linked via the intermediate level with intelligence.
02.03.2020 | Industrial applications of AI (Artificial Intelligence) in the Automation have so far not been convincing in data processing due to latency times and high data volumes with the cloud connection. You have to bring AI directly to the machine and interpret data in real time at the source. With the AI platform Scraitec, this makes the Festo Group belonging Resolto Computer science, for example, at a household appliance manufacturer or car manufacturer.
IP67 PLC with cloud connection and Edge Gateway function
Resolto supports Festo with artificial intelligence that pneumatic and electric automation fit for Industry 4.0 close. For this purpose, data is interpreted in the machine-related field. This results in shorter cycle times, energy savings and machine failures as well as production errors are reduced.
The AI software solution Scraitec knows the health of a plant and detects any anomaly through real-time analysis of data from sensors. Scraitec provides precise forecasts at an early stage, makes diagnoses and gives recommendations for action. "The topic of analytics and artificial intelligence will influence Festo's product portfolio, for example by integrating artificial intelligence algorithms into the cloud and into Festo's components," explains Tanya Maass, Managing Director of Resolto.
For example, users can use the Festo IoT Gateway CPX IOT monitor your machines and systems as hardware at field level. The field level is supported with the AI software component Scraifield. It always runs close to the machine in a small controller. The model used is pre-trained and only has minimal hardware requirements. The artificial intelligence software reliably interprets data streams even without any data connection to the central component located in the cloud (Scraibrain). If necessary, the IoT Gateway connects to the cloud, the Festo Dashboards. The Scraibrain is embedded there with access to many preconfigured application models.
Predictive maintenance with artificial intelligence for robots
"The AI platform continuously learns from actual operation and also incorporates the knowledge of the engineers and technical experts at the customer. "We call it that Human in the loop principle“, explains Ms. Maass. The machine learning (machine learning) and AI product either interprets information in a foresighted manner for the active optimization of system parameters or sends concrete human instructions to the smartphone, for example.
Anyone who connects the Scraitec AI to systems and machines closes them digital tools. New service concepts offer great added value through the automated, early coordination of your own maintenance teams.
Brain like computing should significantly reduce energy consumption
Scraitec supports end customers in automatically optimizing the utilization of their systems. Maintenance costs are reduced because maintenance plans can be adjusted by predicting events and recommending actions for known error patterns. The platform improves all system parameters with defined target criteria and increases productivity the plant.
For example, joined in manufacturing Honey different product qualities over a certain period of time, the causes of which could not be identified. The household appliance manufacturer operates complex production lines on which products are manufactured sequentially. Here it is not enough to look at individual stations separately.
The production managers therefore wanted a system for the automatic detection of anomalies in complex production flows. "Deep learning seemed to be the right approach," explains Tanja Maaß. It was necessary to develop a holistic database that connects different measurement systems. Additional measuring points had to be set up for this. Scraitec modeled the production lines as a holistic system, thereby increasing throughput by 1,5%.
Second example: A pneumatic clamping system costs one AutomobileManufacturer just 100 €, but an unforeseen production standstill costs several 100.000 €. An early warning system for wear and slowdowns in cycle times was therefore ideal - more precisely, a learning system for predictive maintenance for all types of clamping systems. The solution with Scraitec for real-time data analysis and fast data processing directly integrates the Festo Controller CPX-E-CEC. A connection to the cloud is not necessary.
02.12.2019 | Companies whose goal is to connect the operational technology (OT) of their production environment to their IT systems now have a new option Mitsubishi Electric available: the edge computing solution Melipc opens up optimization potential through preventive condition monitoring (predictive maintenance) or quality assurance with real-time data evaluation and immediate feedback to the operator.
04.04.2019 | The industrial edge computer Mica from Harting is now also available with a secondary Ethernet interface. This allows data to be easily exchanged and processed between two Ethernet protocols, also for wired-to-wireless gateway applications.
Many Industry 4.0 applications make it necessary to separate networks and easily move data back and forth between Ethernet protocols without external applications having direct access to a corporate network. For such edge computing applications, the Mica, which received the Hermes Award in 2016, has been supplemented with a second Ethernet interface. An additional USB interface can be used to upgrade additional capabilities or storage space via USB. Because unlike one Router Mica also handles complex data transformations and aggregations at the network edge.
Ctrlx automation platform | Innovations & further developments
The secondary Ethernet interface is provided via the function board and complements the modular system of the Mica platform. In particular, Mica Wireless with Wi-Fi, BLE and LTE connectivity with additional Ethernet interface is a compact and easy-to-manage solution for many industrial and transportation projects, for example
20.11.2018 | Pepperl + Fuchs, Software AG and Dell are showing the seamless integration of automation technology and IT systems within an Industry 4.0 production environment under the title "Smart Industrial IoT". An international SMD production can be based on edge computing by implementing communication-capable sensors, high-performance hardware Gateways and intelligent IIoT software solutions.
General technical knowledge
edge computing is the opposite of cloud computing. In central data processing at the edge of the network, the so-called edge, the data and services are relocated away from the data center. With edge computing, the data is processed and analyzed where it is generated, e.g. B. on the sensors themselves. This enables higher speeds with a higher data throughput. This in turn contributes to increased productivity.