|
|
智能优化算法在核电厂运行数字孪生系统自动调试中的应用研究
|
Abstract:
核电厂运行数字孪生系统需要具备和机组指定状态相匹配的能力，这个过程中需要对仿真模型的参数进行调试，这是一个高维度、带约束的优化问题。本文开发了针对数字孪生系统的自动调试引擎AFE，利用差分进化算法对某核电机组二回路蒸汽系统进行自动调试，通过对有初值问题和无初值问题的测试，以及针对优化算法的改进方案研究，证明了智能优化算法能够较好地应对自动调试的需求。
In order to match the specified state of nuclear power plant, the parameters of the simulation mod-el need to be finetuned. This is a high-dimensional, restrained optimization problem. In this paper, an automatic finetune engine (AFE) is developed for the digital twin system. Differential evolution algorithm is used to finetune the secondary loop steam system. By testing the problems with and without initial value, and studying the improvement of the optimization algorithm, it is proved that the intelligent optimization algorithm can meet the needs of automatic finetune.
| [1] | 胡梦岩, 孔繁丽, 余大利, 杨军. 数字孪生在先进核能领域中的关键技术与应用前瞻[J]. 电网技术, 2021, 45(452): 2514-2522. |
| [2] | Storn, R. and Price, K. (1995) Differential Evolution: A Simple and Efficient Adaptive Scheme for Global Optimization over Continuous Spaces. Technical Report, International Computer Science Institute, Berkeley. |
| [3] | Storn, R. (1996) On the Usage of Differential Evolution for Function Optimization. Proceedings of North American Fuzzy Information Processing, Berkeley, CA, 19-22 June 1996, 519-523.
https://doi.org/10.1109/NAFIPS.1996.534789 |
| [4] | 丹·西蒙. 进化优化算法: 基于仿生和种群的计算智能方法[M]. 陈曦, 译. 北京: 清华大学出版社, 2018. |
| [5] | Kirkpatrick, S., Gelatt, C.D. and Vecchi, M.P. (1983) Optimiza-tion by Simulated Annealing. Science, 220, 671-680.
https://doi.org/10.1126/science.220.4598.671 |
