一种多级往复式压缩机的优化控制方法、系统、设备及存储介质
By combining operating condition identification, thermodynamic models, and machine learning to optimize control, the optimization problem of multi-stage reciprocating compressors under different operating conditions has been solved, achieving more efficient adjustment of operating parameters and improvement of overall machine efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHAMBROAD CHEM IND RES INST CO LTD
- Filing Date
- 2026-04-27
- Publication Date
- 2026-07-17
AI Technical Summary
Existing optimization control methods for multi-stage reciprocating compressors rely on fixed parameters, making it difficult to adapt to different operating conditions. This results in a tradeoff between energy efficiency and safety margin, uneven load distribution between stages, and low overall efficiency. Furthermore, traditional optimization methods do not consider the impact of seasonal changes on cooling water temperature, making it easy for optimization results to fall into local optima.
Seasonal operating conditions are determined by the operating condition identification center, and a thermodynamic power determination model and a current prediction machine learning model are constructed. Combined with the global optimization solution center, the operating parameters are dynamically adjusted to meet dynamic constraints, minimize the total shaft power, and optimize the operation of the multi-stage reciprocating compressor.
The optimized control efficiency of multi-stage reciprocating compressors has been improved, enhancing the safety of the production process and the overall efficiency of the machine, and ensuring the physical rationality and engineering feasibility of the optimization results.
Smart Images
Figure CN122407528A_ABST