IT in Manufacturing


Enhanced intelligence at the edge

February 2019 IT in Manufacturing

A new computing model that helps create autonomous edge nodes is changing the IIoT landscape. Edge nodes are data-aggregation points in an IIoT system, where the physical world of sensors and actuators interacts with computational resources such as IIoT gateway computers. This new computing model is based on edge nodes that are enhanced with local storage and computing power, in addition to machine-learning algorithms that enable them to process data locally and make quick decisions. An intelligent edge node enables faster decisions according to local identity management and access control policies, secures data close to its source, and reduces communication costs.

Edge intelligence is edge computing fortified with machine or self-learning algorithms, advanced networking capabilities, and end-to-end security. This article discusses four key elements of a good edge intelligence solution.

1. Localised data processing

The troves of data collected at the edge of a network can quickly lose their relevance. Hence, the data should be processed and useful insights derived from it at the earliest opportunity. Mission critical systems, such as healthcare and factory monitoring, require quality data measurements and instant decisions. In addition to being time consuming, sending data from the edge to the cloud can lead to data corruption and processed data without the required context.

For these reasons, the edge node should be equipped with the ability to process data locally and only key information should be sent to the cloud to develop data models. Edge nodes with local storage and processing capabilities keep the data closer to the source.

2. Real-time decision making at the edge

Edge intelligence enables real-time decision making at the edge nodes. Decision latency can be drastically reduced by enabling edge node analytics. Machine learning or self-learning algorithms can be developed locally or in the cloud and deployed at the edge to make the edge nodes autonomous, enabling quick decision making.

3. Robust edge-to-node communication

Data integrity is key in the edge-computing model because decisions are made at the edge node level. Data that is sensed and measured at these devices is of little use if the communication between the devices and the edge node is not consistent. No data loss or data corruption can be tolerated as the edge node is now responsible for making key process-related decisions. Other communication aspects to consider are range, bandwidth, device-to-device communication, the communication protocols to support, and how to power edge devices. A good edge network is one that is optimised for wireless sensor communication.

4. Secure edge

The lifecycle of an IIoT system is often longer than a traditional computing system as many edge devices remain in operation even decades after they were deployed. While servers and PCs are complex enough to allow for security provisions, IIoT nodes are usually low in power consumption and processing power. Edge-intelligence solutions equip the edge node with local storage and processing power and a varied set of software and hardware options help secure the edge devices and nodes. Some of the methods used to secure the edge nodes include:

• Secure edge platform with end-to-end security.

• Intrusion prevention systems (IPS).

• External hardware security.

• Secure boot capability.

Since edge nodes are the gateways to the physical world, when an edge device or node is compromised it is not just data that is at risk. Cyber attackers can now potentially access unsecure edge nodes and devices to interfere with industrial processes or shut down equipment resulting in financial loss and even life-threatening situations.


Credit(s)



Share this article:
Share via emailShare via LinkedInPrint this page

Further reading:

Reliable gas production
September 2019, Siemens Digital Industries , IT in Manufacturing
Energy supplier uses Siemens technology for optimum information exchange.

Read more...
Automotive supplier relies on Siemens PLM solution
September 2019, Siemens Digital Industries , IT in Manufacturing
Küster Automotive is an internationally active family-run company and a part of Küster Holding. A full-service supplier, Küster manufactures components for the automotive industry. For its production ...

Read more...
Top tips to help you implement 4IR projects that deliver value
September 2019 , Editor's Choice, IT in Manufacturing
In the just over 10 years I have spent working on IT projects in the manufacturing space, the amount of new fads and IT jargon that has to be adopted has reached the heavens, and ascended into other realms. ...

Read more...
Digitisation requires new skills
September 2019, Schneider Electric South Africa , IT in Manufacturing
Smart grid investments by municipal and public power utilities typically focus on electric distribution and customer systems. The expected benefits include lower costs, better customer service and more ...

Read more...
Industry 4.0: Manufacturing Executing Systems
September 2019, S4 Integration , IT in Manufacturing
Industry 4.0 is set to lead the way for digitisation of manufacturing processes. Manufacturing Executing Systems (MES) are a critical component of Industry 4.0 as they act as an enabler for end-to-end ...

Read more...
Intelligent wireless connectivity
September 2019, RJ Connect , Industrial Wireless
The ultimate goal of most industrial automation applications is to obtain actionable insights from data sources for more precise decision-making. To achieve this, businesses need to make their field data ...

Read more...
Safety and cybersecurity convergence goes beyond safety systems
August 2019 , IT in Manufacturing
However, the scope of safety and cybersecurity goes well beyond process safety systems alone. Across the industrial and infrastructure worlds, an increasing number of end users are adopting more sophisticated ...

Read more...
Mobile app configures level transmitters
August 2019, Emerson Automation Solutions , IT in Manufacturing
Emerson has added the Radar Master app for the AMS Trex Device Communicator, making it easier for field technicians to configure Rosemount radar level transmitters. Radar level devices are critical to ...

Read more...
Network management software essential for smart manufacturing
August 2019, RJ Connect , System Integration & Control Systems Design
Visibility of network devices and infrastructure is just as important as production machinery for maintaining reliable and efficient factory operations. For example, an unrecoverable fault in a network ...

Read more...
Yapper: pet food goes digital
August 2019 , IT in Manufacturing
Over the past decade, there has been an increase of the ‘pet humanisation’ trend, which continues to capture the entire world. Pet owners are caring for and spending on their pets as they would do for ...

Read more...