In a recent article published in the journal CIRP Journal of Manufacturing Science and Technology, researchers introduced a novel cognitive robotic system capable of automating manual tasks in brownfield production environments without requiring extensive changes to the existing control systems and machine tools. Their system aims to simulate the behavior of human operators through a perception system, handling and skill modules, and a skill-based control mechanism.
Study: Cognitive Robots Transform Brownfield Production. Image Credit: Red ivory/Shutterstock.com
Background
Brownfield production refers to the linking and automation of existing stand-alone machines, such as those used for milling or drilling, within a production environment. While these machines are known for their high quality and reliability, they lack the communication capabilities, sensors, and actuators needed for integration into connected and adaptable processes. This creates challenges for small and medium enterprises (SMEs) that must adapt to volatile demand, employee turnover, or shortages and seek short-term, cost-effective automation solutions.
Current automation solutions are often impractical for SMEs as they require extensive and expensive modifications to the existing programmable logic controllers (PLCs) and data interfaces. Additionally, these solutions are usually task-specific, focusing mainly on pick-and-place applications, and struggle to adapt to new tasks, products, processes, or machine tools. Therefore, there is a need for a robust system that can provide flexible and economical automation without requiring major modifications to the existing infrastructure.
About the Research
In this paper, the authors proposed a new concept for a cognitive robotic system designed to address the challenges of integrating automation into machine tools in brownfield environments. This system mimics the cognitive capabilities of human operators to overcome these obstacles. It employs a camera-based perception system to recognize, locate, and interpret objects and equipment, such as parts, clamping devices, and control panels. Additionally, the system utilizes handling devices and skill modules to execute various actions, including gripping, opening, and pushing.
The system is managed by a skill-based control (SBC) mechanism that adjusts the skills of the robotic components according to the specific automation tasks. It is designed on a compact, manually movable platform, allowing it to be positioned approximately in front of the machine tool and automatically adjust its movements based on input from the perception system. Furthermore, the system features an adaptive safety concept that employs laser scanners and safety doors to create a safety-zone-free operating area, eliminating safety restrictions.
The researchers implemented and validated the novel cognitive robotic system on a machine tending process within a real production environment. This process involved loading, interacting with, and unloading a machine tool, as well as blowing off lubricants from the manufactured parts. The system was initially tested on a Haas VF machine tool and transferred to a Maho MH_800C_Janus machine tool to demonstrate its adaptability and flexibility.
Research Findings
The authors evaluated the novel system's effectiveness in addressing key challenges of brownfield automation: rapid commissioning, robustness to changing tasks and boundary conditions, and interaction with existing assets. The outcomes demonstrated that the system significantly outperformed state-of-the-art solutions in all these areas.
Firstly, the system reduced the initial setup time for a new machine tool from several weeks to just 2 to 5 days. It also cut the recommissioning time from several hours to under 10 minutes. Secondly, it enhanced process robustness by using its perception system to adapt to varying positions of parts, buffers, and machine tools. Additionally, the system's modular skill modules allowed it to extend its capabilities to new tasks, such as blowing off lubricants.
Lastly, the system facilitated low-effort interaction with machine tools by utilizing a vision interface to interpret the machine's state and operate the control panel. This approach eliminated the need for additional interfaces with the existing control systems, streamlining the integration process.
Applications
The cognitive robotic system has potential implications across various industrial sectors that need flexible and cost-effective automation solutions for brownfield production. It can automate tasks traditionally performed by human operators, such as machine tending, pre-and post-processing of manufactured parts, and quality inspection.
Additionally, the paper addresses challenges like volatile demand, employee turnover, or labor shortages by providing a short-term and adaptable automation solution that can be quickly deployed and reconfigured. The system enhances productivity and quality by employing cognitive skills to optimize process parameters and promptly detect and correct errors. Its ability to adjust to different tasks and conditions makes it a valuable tool for improving the efficiency and consistency of production processes.
Conclusion
In summary, the novel system demonstrated its effectiveness, robustness, and flexibility in automating tasks in brownfield production environments. It showed great potential in overcoming the specific challenges faced in brownfield production, particularly for SMEs. This system could significantly enhance automation capabilities, leading to more efficient and agile manufacturing processes.
For future work, the authors suggested some directions, such as validating the system in different industrial settings, integrating additional cognitive skills to further increase its autonomy, and developing a continuously updating environment model specifically for machine-tending applications.
Journal Reference
Abicht, J., Hellmich, A., Wiese, T., Harst, S., Ihlenfeldt, S. New automation solution for brownfield production-Cognitive robots for the emulation of operator capabilities. CIRP Journal of Manufacturing Science and Technology, 2024, 50, 104-112. DOI: 10.1016/j.cirpj.2024.02.007, https://www.sciencedirect.com/science/article/pii/S1755581724000270
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.