时空融合深度神经网络的锅炉再热器温度偏差预测方法
By using a spatiotemporal fusion deep neural network model, combined with the lightweight network Mobilenet v2, the attention mechanism, and the gated recurrent neural network GRU, the complexity of predicting boiler reheater temperature deviation was solved, achieving high-precision, low-cost real-time monitoring and dynamic updates, thus ensuring the safe and stable operation of the boiler.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA JILIANG UNIV
- Filing Date
- 2022-10-19
- Publication Date
- 2026-07-17
AI Technical Summary
Existing mechanistic modeling methods are ineffective in addressing the temperature deviation between the two outlets of a boiler reheater, leading to frequent tube rupture accidents. Furthermore, traditional data-driven modeling is limited in its effectiveness in complex industrial processes.
A spatiotemporal fusion deep neural network model is adopted, which combines the lightweight network Mobilenet v2, the attention mechanism, and the gated recurrent neural network GRU. Through feature fusion and multi-model integration, the temperature deviation of the boiler reheater is predicted.
The model's prediction accuracy and precision were improved, computational complexity and cost were reduced, real-time monitoring and dynamic updates were achieved, and the safe and stable operation of the boiler was ensured.
Smart Images
Figure CN115700330B_ABST