基于数字孪生的输变电工程建设成本动态监控与预警方法及系统
By constructing a dual-state mapping model for power transmission and transformation engineering construction using digital twin technology, and combining Kalman filtering and graph neural networks, the problem of monitoring lag caused by static setting of cost baseline in power transmission and transformation engineering construction is solved, and accurate attribution of cost deviations and forward-looking early warning of risks are realized.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HUBEI JINGLI ELECTRIC POWER GROUP CO LTD GENERAL CONTRACTING BRANCH
- Filing Date
- 2026-04-22
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies are unable to achieve dynamic correction of the target cost baseline and accurate attribution of cost deviations in power transmission and transformation engineering construction under conditions of frequent design changes, complex process coupling, and dynamic changes in construction resources. This results in delayed, distorted, or misjudged cost monitoring results.
By adopting a digital twin-based approach, a dual-state mapping digital twin state set is constructed by acquiring multi-source heterogeneous raw data of the project. Combined with an adaptive reconstruction mechanism for the target cost baseline, a dual-channel separation mechanism for reasonable change costs and unreasonable loss costs, and cost runaway trend prediction driven by graph neural networks and time-series prediction networks, dynamic correction of the cost baseline and risk identification are achieved.
It enables real-time correction of cost baselines under conditions of frequent design changes, improves the dynamic adaptability and accuracy of cost monitoring, accurately locates the sources of cost risks, and improves the accuracy of cost risk identification and the timeliness of early warning response.
Smart Images
Figure CN122415146A_ABST