The symmetry between different representation spaces plays a crucial role in effectively modeling complex multimodal data. To address the challenge of equipment knowledge graphs containing hierarchical relationships that cannot be fully represented in a single space, this study proposes UMEAD, an unsupervised multimodal entity alignment method based on dual-space embeddings. The method simultaneously learns graph embeddings in both Euclidean and hyperbolic spaces, forming a structural symmetry where the Euclidean space captures local regularities and the hyperbolic space models global hierarchies. Their complementarity achieves a balanced and symmetric representation of multimodal knowledge. An adaptive feature fusion strategy is further employed to dynamically weight semantic and visual modalities, enhancing the symmetry and complementarity between different modalities. To reduce reliance on scarce pre-aligned data, pseudo seed instances are generated from multimodal features, and an iterative constraint mechanism progressively enlarges the training set, enabling unsupervised alignment. Experiments on public datasets, including EMMEAD, FB15K-DB15K, and FB15K-YAGO15K, demonstrate that the combination of dual-space embeddings, adaptive fusion, and iterative constraints significantly improves alignment accuracy. In summary, the proposed method reduces dependence on pre-aligned data, strengthens multimodal and structural alignment, and its symmetric embedding and fusion design offers a promising approach for the construction and application of multimodal knowledge graphs in the equipment domain.

Because of the characteristics of rich semantic information, complex attribute information and simple relational information in the inter-domain entity alignment dataset, the BERT model, attention mechanism and TransH model are used to embed semantics description, attribute and relation respectively, and the final entity is obtained by combining multiple embedding methods. Finds aligned entities by comparing the cosine distance between entity vectors. In this paper, the model is first applied to the domain-specific entity alignment dataset constructed in this study, achieving good performance results, which demonstrates the effectiveness of the model in the civil aviation equipment domain entity alignment task. Then, a comparative experiment is conducted with the current superior translation embedding-based entity alignment model on the domain-specific dataset. Compared with the translation embedding-based entity alignment model currently applied to large-scale datasets, this model has strong advantages. Finally, entity alignment experiments are conducted separately using the semantic information embedding, attribute embedding, and relation embedding of the model, which fully verifies the effectiveness of each part of the model. Compared with the current better entity alignment model based on translation embedding, the model has a specific improvement in the Hist@1 and Hist@10 on the alignment data set between the fields of civil aviation equipment.