[Background]: Accurate and efficient construction of geometries is crucial for Monte Carlo neutronics calculations. The Constructive Solid Geometry (CSG) descriptions generated by traditional Boundary Representation (B-Rep) to CSG conversion methods are complex and difficult to understand

and they are not always successful because of unstable Boolean operations. Since topologically similar B-Rep models tend to share CSG structures

leveraging geometry reuse can greatly improve modeling efficiency. [Purpose]: This study aims to develop an intelligent auxiliary modeling method that enables automatically convert B-Rep models into CSG geometry by reusing the CSG cell expressions. The method targets fusion reactor similarity modules and seeks to reduce manual effort and improving stability while ensuring physical accuracy in subsequent neutronics calculations. [Methods]: Firstly

a graph-based geometry representation was used

where each B-Rep model was transformed into an attributed adjacency graph (AAG) with topological features. A Graph Attention Network (GAT) was trained to perform graph-level classification

enabling efficient retrieval and reuse of pre-constructed CSG cell expressions from a manually constructed geometry database. To ensure consistency across similar models

a preprocessing pipeline based on the principal axes of inertia was introduced

standardizing node ordering and spatial alignment. Then

the retrieved CSG expressions was transformed into the target geometry using rigid transformation and automatically integrated into Monte Carlo programs’ input files via embedded TRCL cards. The method was tested on two representative blanket modules (#3 inner and #9 outer) and other two complex structures from the China Fusion Engineering Test Reactor (CFETR). [Results]: The average retrieval time was 0.405ms. The generated CSG geometry preserved structural consistency with the original Computer Aided Design (CAD) model

and the neutronics simulation results showed a maximum deviation of less than 0.5% in the Tritium Breeding Ratio (TBR) compared to traditionally converted models. Additionally

the method demonstrated superior time efficiency in CSG construction for the test cases. [Conclusions]: The proposed approach effectively reuses CSG expressions for topologically similar B-Rep models

while maintaining fidelity in Monte Carlo simulations. This method offers potential for similarity geometries’ auxiliary modeling in nuclear fusion engineering applications.