A Bi-Transformer Networks for the KKS Generation Algorithm of the Power Plant Designation System

Digital twins technology present the real-time status of physical entities through a virtual digital world. This technology is widely used in fields such as industrial automation, intelligent buildings, smart transportation, and smart energy. It helps enterprises better understand and control physical systems, improve operational efficiency, and enhance core competitiveness. As the level of informatization and intelligence in power plants increases, existing coding systems, due to their lack of flexibility and scalability, require significant human resources for maintenance and have become inadequate for the deployment and implementation of new technologies. To address this issue, this study proposes a power plant coding generation algorithm based on bidirectional Transformers, grounded in natural language technology. The algorithm achieves coding migration by learning the implicit relationships between source and target codes. Additionally, the model incorporates various reconstruction features to enhance training accuracy. Experimental results indicate that this model can establish orderly connections between all equipment in the power plant within the information and physical spaces, thereby reducing a substantial amount of repetitive work that would otherwise require specialized personnel.