Substation control equipment terminal strip drawing identification method, device and equipment
By combining graphic feature analysis and text recognition technologies with a power industry coding rule library, a topological relationship map of substation terminal block drawings is constructed, which solves the problems of data silos and insufficient symbol adaptability in existing technologies, and realizes accurate identification and standardized conversion of terminal block drawings.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- FOSHAN ELECTRIC POWER DESIGN INSTITUTE CO LTD
- Filing Date
- 2026-01-26
- Publication Date
- 2026-06-05
AI Technical Summary
Existing technologies cannot effectively analyze the connection relationships and text information in substation terminal block drawings, resulting in data silos. This makes it difficult to meet the timeliness and accuracy requirements of intelligent transformation. Furthermore, commercial software cannot be adapted to the power industry's specialized symbol system, increasing project implementation costs and extending the transformation cycle.
By using graphic feature analysis and text recognition technology, the spatial coordinates of connection points, line types, and short-circuit symbols in terminal block drawings are accurately identified. Combined with the power industry coding rule library, a topology graph is constructed and converted into a standardized intermediate file.
It establishes a precise data foundation for terminal block drawings, reduces the risk of misjudgment, breaks through the pain point of the disconnect between graphics and semantics, supports multiple scenario requirements, and adapts to complex scenarios where multiple voltage level systems coexist.
Smart Images

Figure CN121564753B_ABST
Abstract
Citation Information
Patent Citations
Intelligent digital conversion method and system for electric power drawing
CN120318845A
Electrical engineering drawing wiring relation intelligent identification system based on multi-modal fusion
CN121366419A