Objective To address the challenge of effectively expressing and extracting implicit knowledge from ship design drawings, this study aims to discover potential design rules from existing design data, providing data support for the optimization of ship fire protection design.

Methods This study analyzed 400 fire protection design drawings of civil passenger ships operating in inland river basins. The drawings were first standardized and preprocessed to extract key indicators such as fire compartment area, safety exit width, and fire wall fire resistance rating, forming a transaction dataset. After comparing the runtime performance of three association rule algorithms (Apriori, FP-growth, and Eclat) on small datasets, the Apriori algorithm was selected. The dataset was split into a training set of 300 samples and a test set of 100 samples. Appropriate minimum support and confidence thresholds were set to mine frequent itemsets and strong association rules from the data.

Results The proposed method effectively uncovers implicit knowledge in design drawings. Key rules identified include: "the layout of service desks is closely associated with escape exits", "the proportion of fire compartment area ranges from 10% to 30%", and "the fire resistance rating of fire walls increases with building area expansion". Moreover, the minimum accuracy of 8 key rules tested on the test set reached 95%.

Conclusion The study confirms the effectiveness of the Apriori algorithm in extracting implicit knowledge from ship design drawings. The discovered rules complement existing explicit design specifications, provide decision support for optimizing the fire protection design, and promote the transformation from experience-driven to data-driven ship design. In addition, the method can be extended to other domains within ship design.