Process simulation is a critical cornerstone of chemical engineering design. Current automated chemical design methodologies focus mainly on various representations of process flow diagrams. However, transforming these diagrams into executable simulation flowsheets remains a time-consuming and labor-intensive endeavor, requiring extensive manual parameter configuration within simulation software. In this work, we propose a novel multi-agent workflow that leverages the semantic understanding capabilities of large language models(LLMs) and enables iterative interactions with chemical process simulation software, achieving end-to-end automated simulation from textual process specifications to computationally validated software configurations for design enhancement. Our approach integrates four specialized agents responsible for task understanding, topology generation, parameter configuration, and evaluation analysis, respectively, coupled with Enhanced Monte Carlo Tree Search to accurately interpret semantics and robustly generate configurations. Evaluated on Simona, a large-scale process description dataset, our method achieves a 31. 1% improvement in the simulation convergence rate compared to state-of-the-art baselines and reduces the design time by 89. 0% compared to the expert manual design. This work demonstrates the potential of AI-assisted chemical process design, which bridges the gap between conceptual design and practical implementation. Our workflow is applicable to diverse process-oriented industries, including pharmaceuticals, petrochemicals, food processing, and manufacturing, offering a generalizable solution for automated process design.

The collaborative construction method of knowledge graph based on blockchain is crucial for the safe and efficient construction of biomedical knowledge graph (BioKG), and has received widespread attention from the academic and medical circles. At present, the data sources of BioKG are very wide. While using multi-source data to collaboratively build a knowledge graph, data redundancy problems often occur. Once data from a large number of sources is available, it becomes difficult for the system to ensure data consistency in a reliable way. In addition, the increase in inconsistent and redundant data also reduces the efficiency of collaboration in the system. The traditional blockchain-based collaborative construction method of BioKG is difficult to effectively solve these problems. Multi-blockchain technology provides a new solution for the construction of collaborative knowledge graphs in the biomedical field, which is characterized by good scalability and diversified applications. To this end, we propose a multi-person collaboration construction method for BioKG based on multi-blockchain, named collaborative construction method chain (CCMC). CCMC uses the multi-chain structure and clock cycle control method of the blockchain to separate user operations and system verification, and uses the read-write separation function to improve the consistency of the collaborative version. In addition, we propose a semantic fusion method that effectively reduces data redundancy in the collaborative process and improves the efficiency of BioKG collaborative construction. Performance testing and comparative evaluation confirmed that compared with previous methods, CCMC significantly improves the creation of collaborative knowledge graphs and meets the requirements of multi-person collaborative construction.