Edge Computing and IoT Trends In Smart Manufacturing

The Internet of Things (IoT) and edge computing are transforming the manufacturing sector by facilitating real-time, data-informed decision-making. By utilizing IoT sensors integrated into equipment, manufacturers can gather operational data and analyze it locally via edge computing. This in-field evaluation minimizes latency, boosts automation, and facilitates predictive maintenance, quality assurance, and productivity enhancements. By reducing their reliance on the cloud, manufacturers gain faster insights, strengthen data security, and lower operational costs, ultimately driving more innovative and efficient production.

Key Components of IoT and Edge Computing

The Internet of Things (IoT) in industrial environments refers to a collection of interconnected intelligent devices, equipment, and systems that work together seamlessly. These technologies utilize sensors, data analysis, and internet connectivity to collect and distribute information, enabling businesses to oversee and enhance their operations. The concept began to take shape in the 1990s, when internet technology started to blend with industrial automation. As internet access became more widespread, companies began using it to monitor and control their equipment remotely. IoT further comprises connectivity, sensors, and data analytics, focused mainly on linking machines to central control systems.

• Connectivity Advancements: Wireless technologies, such as Wi-Fi, Bluetooth, and mobile networks, have played a crucial role in enabling devices and systems to stay connected effortlessly. These connectivity advancements enabled the gathering and analysis of data in real-time, even from challenging and remote locations.
• Sensor Technology: The miniaturization and price decrease of sensors have played a crucial role in the expansion of IoT. Sophisticated sensors that can detect temperature, pressure, humidity, vibration, and other variables are now integrated into various industrial machinery, facilitating real-time monitoring and predictive maintenance.
• Data and Analytics: The capability to gather and analyze vast quantities of data from IoT sensors and devices has led to the growth of data analytics. Analytical techniques, such as artificial intelligence (AI) and machine learning (ML), provide rapid insights, predictive maintenance, and improvements in manufacturing processes.

Edge computing addresses the challenges of centralized computing (such as latency, bandwidth, data privacy, and autonomy) by relocating processing closer to the source of data creation, devices, and users. With reduced internet load, fewer latency problems, quicker response times, reduced security threats, enhanced application performance, greater insights, and essential data analysis leading to superior customer experiences, edge computing provides a sensible solution that the majority of businesses require.

Even though edge computing occurs locally, the cloud can still play a significant role. It can retain historical data, provide additional processing capability, or facilitate communication among edge locations.

Enablers for Smart Manufacturing

Key enablers for smart manufacturing, making use of edge computing and the internet of things, along with their use case, are discussed below:

• Autonomous Robots: By processing information using edge computing, robots and IoT devices can quickly act, reducing the necessary amount of data transfer and cloud processing requirements. This can reduce network congestion and lower costs, making it a more cost-effective solution for robotics applications.

Use case – BMW’s production facility utilized an edge computing system to revolutionize the management of its robotic and machine operations. The implementation resulted in a 30% reduction in downtime, a 25% decrease in maintenance costs, and a 7% increase in production efficiency.¹

• Smart IoT Sensors: A manufacturing execution system (MES) utilizes IoT sensors to provide real-time visibility and control over the manufacturing floor. These systems collect data from various locations within the manufacturing process, including the machine’s operational status, product quality metrics, and the operator’s performance.

Use case – GE Aviation’s Brilliant Factory in Massachusetts utilized IoT sensor integration in its manufacturing process. The manufacturing facility makes use of a vast range of IoT sensors to monitor and optimize every aspect of the manufacturing process for their jet engines. The implementation of IoT sensors has resulted in significant cost savings, improved operational efficiency, and enhanced product reliability.

• Edge AI Server: Edge AI servers are specifically designed for smart manufacturing, driving artificial intelligence in digital transformation to enhance production flexibility and responsiveness. It enables the detection of anomalies and potential failures, recommending predictive maintenance actions to minimize downtime and maximize asset utilization.

Use case – ADLINK’s AI Edge Server MEC-AI7400 series provides advantages in smart manufacturing applications. It provides fast delivery to ensure high-quality products and a diverse and flexible product portfolio. The products are designed to fulfill customer requirements and changing manufacturing demands. By integrating ADLINK’s GPU cards and servers, users can select the most suitable solutions tailored to their specific needs.³

• Cognitive Digital Twin: A cognitive digital twin (CDT) is an advanced digital twin augmented with cognitive capabilities—such as perception, attention, memory, and reasoning—enabled by artificial intelligence (AI) and machine learning. When combined with edge AI, CDTs can deliver real-time, autonomous, and adaptive manufacturing solutions.

Use case – A cognitive digital twin in a steel pipe manufacturing factory utilized machine learning models to train data-driven AI models for anomaly detection and predictive maintenance, resulting in a 10% decrease in energy consumption, reduced downtime, and increased production efficiency.⁴

Research Innovations

Key research innovations utilizing edge computing and IoT in smart manufacturing are discussed below:

Innovation 1: Edge computing-assisted IoT framework with an autoencoder for fault detection in manufacturing predictive maintenance

• Brief: A multi-layered design comprising an edge layer, cloud layer, and application layer that enables intelligent, scalable, and reliable industrial IoT operations. The edge infrastructure dynamically distributes workloads between the edge and cloud, ensuring low latency and improved resilience. To enhance efficiency, an autoencoder-based deep learning model is deployed at the edge in a distributed manner, allowing real-time data compression and anomaly detection. (Source)
• Assignee/University: La Trobe University
• Application: Manufacturing machines
• Value Proposition: It reduces latency, enhances anomaly detection, and supports efficient deployment through API-based integration, delivering tangible value in industrial environments.

Innovation 2: Smart manufacturing based on swarm intelligence and edge computing

• Brief: A group learning architecture that enables intelligent manufacturing equipment to adapt to frequent production line reconfigurations collaboratively. By leveraging swarm intelligence and edge computing, the system enhances data acquisition, cyber-physical integration, knowledge sharing, and self-optimization. This distributed intelligence framework significantly improves processing efficiency and responsiveness in dynamic, customized manufacturing environments. (Source: ScienceDirect)
• Assignee/University: Shanxi Lanling Software Development Co., Ltd.
• Application: Reconfigurable production lines
• Value Proposition: It enhances production flexibility, reduces downtime during reconfiguration, and improves overall equipment effectiveness (OEE) by allowing machines to learn, share, and optimize performance collaboratively without relying heavily on centralized control.

Innovation 3: Edge IOT multi-protocol intelligent terminal manufacturing system based on OPC object link

• Brief: An edge IoT-based multi-protocol intelligent terminal manufacturing system that leverages OPC object linking for seamless communication and control. The system integrates edge gateways, protocol converters, equipment management, and data analytics to enable real-time equipment monitoring, multi-protocol interoperability, and predictive maintenance. (Source: worldwide.espacenet)
• Assignee/University: Chengdu Zhongchuang Yijia Technology Co., Ltd.
• Application: Manufacturing environments
• Value Proposition: It enables seamless communication between diverse manufacturing equipment through multi-protocol conversion, real-time monitoring, and predictive fault detection that helps in boosting interoperability, reducing downtime, and enhancing operational efficiency in smart factories.

Innovation 4: CPS-based industrial internet intelligent production system

• Brief: The CPS-based (Cyber-Physical System) industrial internet intelligent production system integrates equipment, edge execution, and platform layers to enable intelligent task allocation and execution in manufacturing. It uses semantic matching to interpret external production requirements and deploys tasks to the most suitable terminals via the edge layer. (Source)
• Assignee/University: Chengdu Zhongchuang Yijia Technology Co., Ltd.
• Application: Cyber-physical production systems
• Value Proposition: It intelligently interprets and translates external production demands into actionable machine instructions using semantic analysis and CPS integration. By leveraging real-time data execution at the edge and smart orchestration at the platform level, it improves production responsiveness, minimizes human intervention, and supports scalable, demand-driven manufacturing operations.

Benefits

The following are the major benefits of edge computing and IoT in smart manufacturing:

• Improved Decision Making: Edge computing handles data locally on devices such as cameras or sensors, minimizing latency that occurs when transmitting data to a central server. This enables immediate insights and faster decision-making, essential for applications such as industrial automation.
• Predictive Maintenance: By utilizing IoT-enabled sensors and edge computing, machines can monitor their health, allowing manufacturers to anticipate potential equipment failures before they occur.
• Better Performance: Edge computing minimizes network congestion and bandwidth consumption by processing data near its source. This results in more seamless performance for applications that rely on real-time data.
• Increased Security: With edge computing, reduced data travels across networks, lowering the chances of interception by hackers. Additionally, sensitive information is handled locally, enhancing data security and privacy.
• Reliability: Edge computing systems operate effectively, even when internet access is restricted or unavailable. This ensures ongoing functionality in cases where the central server may be inaccessible, thereby enhancing overall system reliability.

Challenges

Apart from the benefits of the usage of IoT and edge computing in smart manufacturing, some of the challenges faced in their implementation are discussed below:

• Interoperability: In various manufacturing environments, diverse machines and systems originate from different vendors, resulting in interoperability issues. Incorporating various IoT devices and platforms may require additional effort and resources.
• Implementation Cost: Although IoT offers considerable advantages, the upfront expense of establishing a comprehensive IoT infrastructure can be substantial. Manufacturers must thoroughly assess the return on investment (ROI) and long-term benefits before proceeding with significant deployments.
• Compatible Workforce: Implementing IoT in manufacturing requires a skilled workforce capable of handling and sustaining the new technologies. Manufacturers might have to invest in employee training or recruit IoT specialists to address significant skill gaps

Key Solutions

Siemens Industrial Edge is an open, ready-to-use edge computing platform that includes applications, connectivity for both OT and IT, devices, and a central management system for all components. Industrial Edge streamlines the gathering, handling, and examination of data from industrial equipment, facilitating rapid and reliable software deployment on the shop floor and informed decision-making, all while maintaining IT workload and expenses at a reasonable level.

ABB Ability™ Edgenius reduces latency, the time needed for data to travel from source to destination, thereby achieving enhanced speeds. It offers three operational modes, providing connected edge, connect on demand edge, and disconnected edge for locally managed edge computing.

Schneider Ecostruxure Edge provides new levels of productivity by leveraging compute-edge technologies to optimize plant, process, or machinery effectiveness, reducing latency and enhancing real-time decision-making.

Adlink EdgeGO® is a robust software platform for remote device management in edge computing environments. It prioritizes quick deployment and user-friendly operation while ensuring scalability and security. The platform offers real-time notifications, remote desktop access, and a customizable interface.

Fujitsu Manufacturing IoT Solution INTELLIEDGE™ Appliance and Gateway systems offer an expandable platform for a diverse range of edge computing applications and usage in the Industry 4.0 and IoT context.

Edge Signal edge computing offers privacy and data sovereignty through a secure edge computing platform, along with a no-code feature that allows workflow automation with minimal effort.

Future Perspective

Future developments in edge computing, combined with the capabilities of the Internet of Things, will enable the quick processing of data, identification of trends, and independent resolution of any operational problems that arise. This change will enable more adaptable, self-optimizing systems, ultimately reducing the need for human intervention. Edge AI models will enhance predictive maintenance and anomaly detection, yielding more optimized outcomes in real-time. The implementation of 5G, combined with enhanced connectivity, will enable faster and more reliable communication in industrial applications that are sensitive to latency. The future of edge computing and IoT in smart manufacturing is characterized by real-time analytics, AI-driven automation, improved security, and scalable, sustainable methods, thus establishing the foundation for the next wave of smart factories.

Conclusion

Edge computing, combined with the integration of the Internet of Things (IoT), is transforming the present landscape of smart manufacturing. Placing data processing close to the origin promotes immediate decision-making along with improved security. Through the use of edge AI, manufacturers can enhance their overall quality by implementing predictive maintenance, thereby minimizing system downtime. As these technologies progress, they will enable manufacturers to reach extraordinary levels of efficiency and adaptability, setting the stage for future-oriented factories.