With turbine capacities now reaching 16 megawatts (MW), the manual assembly of large components is becoming increasingly difficult. The study proposes a mobile robotic assistant (MRA) that combines digital twin technology with smartwatch-based interfaces to enable human–robot collaboration (HRC). This hybrid system aims to reduce production costs, accelerate manufacturing, and improve working conditions while offering potential applications across other large-scale manufacturing sectors.
Background
The global wind energy sector has expanded rapidly, with installed capacity reaching 743 gigawatts (GW). Despite this growth, turbine manufacturing remains largely manual and labor-intensive.
As manufacturers develop larger turbines to reduce the levelized cost of energy, assembly processes have become more challenging. Massive component sizes and frequent design changes make traditional fixed automation difficult to implement.
Previous attempts at automation have been constrained by limited flexibility, while most existing cobot applications focus on small components with minimal human interaction.
To address these challenges, the researchers introduced a flexible mobile robotic assistant designed specifically for wind turbine assembly. The system uses digital twin technology to support rapid reconfiguration and integrates a smartwatch-based interface that allows workers to interact with the robot more intuitively. Together, these features enable scalable automation for large-component manufacturing environments.
At the center of this approach is the TwinHRC digital twin framework, which supports the design, validation, commissioning, and operational optimization of collaborative robotic systems in manufacturing.
A Digital Twin Framework for Human–Robot Collaboration
Wind turbines consist of three primary components: tower, nacelle, and blades. The nacelle houses critical drivetrain elements such as the gearbox, generator, and control systems.
Manufacturing processes for both nacelles and blades remain highly manual, relying on tasks such as composite material layup, welding, and mechanical assembly that require significant human labor.
Traditional industrial automation typically uses large, fenced robots with limited flexibility. These systems are not well-suited to wind turbine manufacturing, where frequent design updates require adaptable production processes.
While cobots have emerged as safer alternatives that allow humans and robots to work together, most existing deployments involve small-scale components such as electronics. Their use in large-component manufacturing remains limited.
Mobile robotic assistants, systems that combine articulated robotic arms with autonomous mobile platforms, have shown promise in industries such as automotive and aerospace. However, adapting them for wind turbine manufacturing presents unique challenges.
To address this, the researchers developed TwinHRC, a digital twin framework that guides the development of collaborative robotic systems through six phases:
- Problem identification
- System design
- Digital simulation
- Physical development
- Commissioning
- Operational optimization
The proposed mobile robotic assistant incorporates five core features:
- A robotic manipulator for task execution
- Reconfigurability through automated tool changing
- Autonomous mobility
- Precise localization
- Intuitive human–machine interfaces
To coordinate these functions, the system uses Behavior Trees, a modular control framework that breaks complex tasks into smaller steps. This structure allows robots and human operators to work in synchronized workflows while maintaining flexibility during task execution.
Case Study, Results, and Future Directions
To evaluate the system, the researchers conducted a case study with a leading wind turbine manufacturer. The study focused on the installation of 53 cable trays inside and outside the bed frames of 10 MW offshore nacelles.
Traditionally, this assembly process required operators to work on elevated platforms or in confined spaces and could take up to 40 minutes per installation. The process was also prone to errors. Measuring curved surfaces manually often resulted in cumulative placement errors exceeding ±100 millimeters, sometimes leading to hours of rework when cables were cut too short.
To address these challenges, the team developed a mobile robotic assistant consisting of a cobot arm mounted on a mobile platform prototype, rather than a fully autonomous mobile robot.
A key feature of the system was a custom additively manufactured tool equipped with laser projectors. Using a digital twin generated from computer-aided design (CAD) data, the robot projected precise cable tray outlines directly onto the nacelle bed frame. This eliminated the need for manual measurements.
Workers could control the robot wirelessly through a smartwatch-based interface, enabling intuitive interaction with the system.
Experimental testing demonstrated significant improvements. The robotic assistant achieved assembly accuracy within five millimeters while reducing installation time to 25 minutes, representing a 37% improvement. The system also eliminated cable-length errors during testing.
The robot’s versatility was further demonstrated through the integration of an automated tool changer, allowing it to perform additional tasks such as bolt assembly.
According to the researchers, the results highlight the potential of mobile cobots to enhance both precision and efficiency in large-component wind turbine manufacturing.
Future work will focus on improving vision-based localization, autonomous mobility, and safety certification, which are necessary steps for large-scale industrial deployment.
Conclusion
The study demonstrates that collaborative robots can support the automation of large-component manufacturing tasks in the wind energy industry, despite their payload limitations.
In the nacelle assembly case study, a mobile robotic assistant equipped with digital twin guidance and laser projection reduced assembly time by 37 % while achieving placement accuracy within five millimeters. Workers also responded positively to the smartwatch-based interface, suggesting strong user acceptance.
The researchers note that cobots can improve manufacturing flexibility through rapid tool reconfiguration, helping manufacturers adapt to frequent design changes.
By reducing costs and improving production efficiency, such technologies could support the continued expansion of wind energy and contribute to achieving the United Nations Sustainable Development Goals related to clean energy access.
Journal Reference
Malik, A. A., & Masood, T. (2026). Adaptive human–robot collaboration in wind turbine manufacturing using digital twins. Scientific Reports. DOI:10.1038/s41598-026-40576-6. https://www.nature.com/articles/s41598-026-40576-6
Disclaimer: The views expressed here are those of the author expressed in their private capacity and do not necessarily represent the views of AZoM.com Limited T/A AZoNetwork the owner and operator of this website. This disclaimer forms part of the Terms and conditions of use of this website.