Automating the Edge with Robotics

The rise of edge-enabled digital twins in industrial environments

Categories Edge Computing News  |  Guest Posts
The rise of edge-enabled digital twins in industrial environments

By David Purón CEO of Barbara

Digital twins, the virtual replicas of physical entities, are revolutionizing industrial environments by enabling enhanced monitoring, simulation, and optimization of assets and processes. According to Gartner, 13 percent of organizations implementing IoT projects already use digital twins, while 62 percent are in the process of establishing digital twin use or plan to do so.

Challenges in industrial adoption

Despite the promising growth, industrial companies, particularly in sectors like energy, water infrastructure, and process manufacturing, face significant challenges in adopting digital twin solutions. Most digital twin platforms are cloud-oriented, which poses problems for these sectors. Concerns about cost, data privacy, security, and processing response times make cloud solutions less appealing. A recent study by Citrix revealed that 25 percent of organizations surveyed in the United Kingdom have already moved half or more of their cloud-based applications out of the cloud.

The opportunity for edge-enabled digital twins

The reluctance to embrace cloud-based solutions opens up a substantial opportunity for a new category of digital twins: Edge-enabled digital twins. These solutions operate independently of cloud infrastructure, maintaining data privacy and sovereignty while providing real-time data analytics and asset control. Edge computing allows processing to occur close to the physical location of the data source, thus minimizing latency and enhancing the security of the whole digital twin infrastructure.

Edge-enabled digital twins can be particularly advantageous in industrial environments where real-time decision-making and immediate feedback are crucial. For instance, in process manufacturing, immediate detection and correction of anomalies can prevent costly downtimes. In water infrastructure, real-time monitoring and control of chemicals can ensure efficient resource management and compliance with regulations.

Tracking success with KPIs

For a successful edge-enabled digital twin implementation, it is essential to track the performance of digital twin projects using Key Performance Indicators (KPIs). Industrial digital twin projects may be evaluated based on various relevant KPIs.

Asset performance is crucial, with metrics such as uptime, downtime, and mean time between failures (MTBF) providing insights into the reliability and efficiency of assets.

Process efficiency is another critical aspect, where KPIs like production yield, energy consumption, and waste generation help evaluate the effectiveness of process improvements.

Cost savings play a significant role in assessing the financial benefits of digital twins. Tracking maintenance costs, operational costs, and cost avoidance due to predictive maintenance can quantify these benefits.

Safety and compliance are paramount concerns. Monitoring incidents, near-misses, and compliance with safety regulations ensure that digital twins contribute to a safer work environment.

User engagement is vital for the successful utilization of digital twin solutions by staff. Metrics such as user adoption rates, feedback, and satisfaction scores can indicate how effectively the solutions are being utilized.

The importance of a multidisciplinary team

Implementing a digital twin requires a multidisciplinary team comprising experts from both Information Technology (IT) and Operational Technology (OT) domains. IT professionals bring expertise in data analytics, cybersecurity, and edge software orchestration, while OT experts provide deep knowledge of industrial processes and systems, as well as integration with the real field assets.

However, it is also critical to include external technology expert partners as part of the team. There is a common misconception that organizations can handle digital twin projects entirely in-house using open-source software. While this might seem cost-effective initially, the Total Cost of Operation (TCO) for such projects can be significantly higher—up to 500 percent more over a three-year product lifetime—due to complexities in integration, maintenance, and scaling.

External partners bring specialized knowledge, products, and experience that can streamline the implementation process, mitigate risks, and ensure the edge-enabled digital twin solution is robust and scalable.

Final thought

The industrial sector stands on the brink of a digital revolution with the advent of digital twins. While challenges exist, particularly concerning cloud dependency, the rise of edge-enabled digital twins offers a promising solution. By focusing on a reliable industrial-oriented edge computing infrastructure to provide real-time analytics and asset control, and leveraging a multidisciplinary team of internal experts and external partners, industrial organizations can harness the full potential of digital twins with no risk to their business continuity and security.

About the author

David Puron is the Founder and CEO of Barbara, a company at the forefront of  Edge AI technology. With over 20 years of experience in telecommunications and executive management, David is recognized as one of Spain’s leading entrepreneurs and cybersecurity experts.

His contributions to the industrial tech ecosystem have earned him a spot on the Forbes 100 list of top entrepreneurs in 2021.

He is currently leading Barbara, a company that specializes in enabling AI deployments for industrial companies through cyber-secure edge computing. Under his leadership, Barbara serves  major corporations in manufacturing and critical infrastructures in particular, in the energy distribution, water management and process manufacturing.

Article Topics

 |   |   | 

Comments

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Featured Edge Computing Company

Edge Ecosystem Videos

Automating the Edge

“Automating

Deploying AI Models at the Edge

“Deploying

Latest News