一种基于管路特性辨识的循环水系统节能优化控制方法
By combining mechanistic and data models in a hybrid modeling approach, using long short-term memory neural networks for pipeline characteristic identification, and optimizing pump operating frequency through closed-loop adaptive online correction, the problem of low accuracy in predicting pipeline characteristics in the power plant's circulating water system was solved, thus achieving energy-saving optimization control of the power plant.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GUODIAN NANJING ELECTRIC POWER TEST RES CO LTD
- Filing Date
- 2025-09-01
- Publication Date
- 2026-07-17
AI Technical Summary
In existing technologies, the accuracy of predicting pipeline characteristics in power plant circulating water systems is low, leading to increased energy consumption and higher costs, and failing to achieve optimal vacuum.
By using a hybrid modeling approach based on mechanistic and data models, combined with a long short-term memory neural network, a pipeline characteristic identification model is constructed to achieve high-precision pipeline characteristic identification. Furthermore, through a closed-loop adaptive online correction and model iteration mechanism, the operating frequency of the water pumps in the circulating water system is optimized to achieve energy-saving control.
It achieves high-precision pipeline characteristic identification, reduces power plant energy consumption, improves power plant energy efficiency, and ensures that the unit always operates in the optimal economic range.
Smart Images
Figure CN120722766B_ABST