Search

The global push for sustainable energy has heightened the demand for green hydrogen, which is crucial for decarbonizing heavy industry. However, current electrolysis plant capacities are insufficient. This research addresses the challenge through optimizing large-scale electrolysis construction via standardization, modularization, process optimization, and automation. This paper introduces H2Giga, a project for mass-producing electrolyzers, and HyPLANT100, investigating large-scale electrolysis plant structure and construction processes. Modularizing electrolyzers enhances production efficiency and scalability. The integration of AutomationML facilitates seamless information exchange. A digital twin concept enables simulations, optimizations, and error identification before assembly. While construction site automation provides advantages, tasks like connection technologies and handling cables, tubes, and hoses require pre-assembly. This study identifies key tasks suitable for automation and estimating required components. The Enapter Multicore electrolyzer serves as a case study, showcasing robotic technology for tube fittings. In conclusion, this research underscores the significance of standardization, modularization, and automation in boosting the electrolysis production capacity for green hydrogen, contributing to ongoing efforts in decarbonizing the industrial sector and advancing the global energy transition.

Human activity recognition (HAR) and brain-machine interface (BMI) are two emerging technologies that can enhance human-robot collaboration (HRC) in domains such as industry or healthcare. HAR uses sensors or cameras to capture and analyze the movements and actions of humans, while BMI uses human brain signals to decode action intentions. Both technologies face challenges impacting accuracy, reliability, and usability. In this article, we review the state-of-the-art techniques and methods for HAR and BMI and highlight their strengths and limitations. We then propose a hybrid framework that fuses HAR and BMI data, which can integrate the complementary information from the brain and body motion signals and improve the performance of human state decoding. We also discuss our hybrid method’s potential benefits and implications for HRC.

Affective computing (AC), like most other areas of computational research, has benefited tremendously from advances in deep learning (DL). These advances have opened up new horizons in AC research and practice. Yet, as DL dominates the community’s attention, there is a danger of overlooking other emerging trends in artificial intelligence (AI) research. Furthermore, over-reliance on one particular technology may lead to stagnating progress. In an attempt to foster the exploration of complementary directions, we provide a concise, easily digestible overview of emerging trends in AI research that stand to play a vital role in solving some of the remaining challenges in AC research. Our overview is driven by the limitations of the current state of the art as it pertains to AC.