Comparative Study on Vibration Prediction Methods of Reactor Internals Based on Neutron Noise Characteristic Frequency Time-Series Signal
-
摘要: 反应堆堆内构件的振动状态直接关系到核电的运行安全与维修节点的确定，因此如何对堆内构件振动情况进行分析和预测至关重要。本文提出了基于中子噪声特征频段时序信号的堆内构件振动预测方法。该方法从单周期与双周期2个角度，利用统计学习和机器学习模型进行预测，并结合某核电厂采集到的中子噪声信号进行实验验证。实验结果表明，分析方法上，特征频段时序信号处理能有效地利用信号中的时间信息；预测方法上，单周期预测采用统计学习模型、双周期预测采用机器学习模型的准确度更高。因此特征频段时序信号分析方法与合适的预测模型相结合能为核电厂维修节点的预测和确定提供指导。Abstract: The vibration status of reactor internals is directly related to the operational safety and the maintenance node of nuclear power plant. Therefore, it is important to analyze and predict the vibration of these internals. This paper proposes a method for predicting the vibration of reactor internals based on the time-series signals of neutron noise characteristic frequency bands. The method, from two perspectives of single-cycle and double-cycle, utilizes statistical learning and machine learning methods for prediction, and an experiment was conducted using neutron noise signals collected from a nuclear power plant. The results show that, in terms of analysis methods, the processing of characteristic frequency band time-series signals can effectively utilize the temporal information in the signals. In terms of prediction methods, statistical learning models achieve higher accuracy for single-cycle prediction while machine learning models achieve higher accuracy for double-cycle prediction.Therefore, the combination of characteristic frequency band time-series signal analysis methods and appropriate prediction models can provide guidance for the prediction and determination of maintenance nodes in nuclear power plants.
-
图 1 中子噪声测量原理示意图
x1、x2—堆芯吊篮振动前、后冷却剂的厚度。
Figure 1. Schematic Diagram of Neutron Noise Monitoring Principle
图 3 传感器采集的堆内构件振动时序信号
Figure 3. Vibration Time-series Signals from the Reactor Internals Collected by Sensors
图 4 燃料组件振动和堆芯吊篮一阶振动单周期指数平滑预测模型预测结果
Figure 4. Single-Cycle Prediction Results of Exponential Smoothing Model for Fuel Assembly Vibration and Core Barrel 1st-Order Vibration
图 5 燃料组件振动和堆芯吊篮一阶振动单周期决策树回归模型预测结果
Figure 5. Single-Cycle Prediction Results of Decision Tree Model for Fuel Assembly Vibration and Core Barrel 1st-Order Vibration
图 6 燃料组件振动和堆芯吊篮一阶振动双周期指数平滑预测模型预测结果
Figure 6. Double-Cycle Prediction Results of Exponential Smoothing Model for Fuel Assembly Vibration and Core Barrel 1st-Order Vibration
图 7 燃料组件振动和堆芯吊篮一阶振动双周期决策树回归模型预测结果
Figure 7. Double-Cycle Prediction Results of Decision Tree Model for Fuel Assembly Vibration and Core Barrel 1st-Order Vibration
表 1 单周期振动预测R2值 %
Table 1. Summary of R2 for Single-Cycle Prediction
预测方法 预测模型 燃料组件
振动R2堆芯吊篮
一阶振动R2统计学习 指数平滑预测模型 93.51 90.50 GM(1.1)模型 85.29 89.00 ARIMA模型 95.02 90.50 机器学习 决策树回归模型 84.43 86.00 随机森林回归模型 90.70 80.39 KNN模型 77.61 75.86 
下载: 导出CSV
表 2 双周期振动预测R2值 %
Table 2. Summary of R2 for Double-Cycle Prediction
预测方法 预测模型 燃料组件
振动R2堆芯吊篮
一阶振动R2统计学习 指数平滑预测模型 46.07 −1.29 GM(1.1)模型 −3.70 −11.41 ARIMA模型 58.77 −1.06 机器学习 决策树回归模型 95.92 89.96 随机森林回归模型 96.43 92.00 KNN模型 89.50 85.87
下载: 导出CSV
-
[1] 杨泰波,刘才学,罗婷,等. 基于功率密度谱的压水堆核电厂中子噪声特性研究[J]. 核动力工程,2018, 39(3): 181-183. [2] 周正平. 核电厂反应堆燃料组件振动监测和诊断[J]. 中国核电,2023, 16(3): 411-416. [3] 龚禾林,陈长,赵文博,等. 基于SP3方法的动力堆中子噪声分析程序研究[J]. 核科学与工程,2021, 41(3): 491-499. doi: 10.3969/j.issn.0258-0918.2021.03.007 [4] 刘才学,罗能,何攀,等. 反应堆关键设备健康监测与故障诊断技术研究进展[J]. 核动力工程,2023, 44(3): 8-20. [5] LIU J X, YU D P, YANG T B, et al. Discovering the causes for the change of the vibration characteristics of the core support barrel in PWR nuclear power plants: a combined investigation based on ex-core neutron noise analysis and numerical modal analysis[J]. Reliability Engineering & System Safety, 2023, 234: 109190. [6] 杨泰波,刘才学,罗婷,等. 基于中子噪声分析的某核电厂堆芯吊篮梁型振动特征研究[J]. 核科学与工程,2017, 37(1): 42-47. doi: 10.3969/j.issn.0258-0918.2017.01.008 [7] 童强,张克功,杜吉梁. 指数平滑预测法及其在经济预测中的应用[J]. 经济研究导刊,2013(4): 11-12,74. doi: 10.3969/j.issn.1673-291X.2013.04.005 [8] 邓聚龙. 社会经济灰色系统的理论与方法[J]. 中国社会科学,1984(6): 47-60. [9] KONTOPOULOU V I, PANAGOPOULOS A D, KAKKOS I, et al. A review of ARIMA vs. machine learning approaches for time series forecasting in data driven networks[J]. Future Internet, 2023, 15(8): 255. doi: 10.3390/fi15080255 [10] NUÑEZ Y, LOVISOLO L, DA SILVA MELLO L, et al. On the interpretability of machine learning regression for path-loss prediction of millimeter-wave links[J]. Expert Systems with Applications, 2023, 215: 119324. doi: 10.1016/j.eswa.2022.119324 [11] AKSHAY A, ABEDI M, SHEKARCHIZADEH N, et al. MLcps: machine learning cumulative performance score for classification problems[J]. GigaScience, 2023, 12: giad108. [12] ZHOU C N, XIAO N C, ZUO M J, et al. An active Kriging-based learning method for hybrid reliability analysis[J]. IEEE Transactions on Reliability, 2022, 71(4): 1567-1576. doi: 10.1109/TR.2021.3111926 [13] 武永强,刘正刚. 基于决策树的工业通信网全链路数据异常检测方法[J]. 电子设计工程,2024, 32(9): 138-141,146. [14] 孙永平,王立峰,张震伟,等. 基于随机森林回归的火电机组供电煤耗遗传优化模型[J]. 信息通信技术与政策,2021, 47(3): 76-82. doi: 10.12267/j.issn.2096-5931.2021.03.013 [15] 王钰涵,郑旭,周南,等. 基于EMD和KNN的发动机辐射噪声预测研究[J]. 现代机械,2024(1): 1-5. -
计量
- 文章访问数: 10
- HTML全文浏览量: 4
- PDF下载量: 0
- 被引次数: 0
