摘要
为提高小样本条件下的流型识别精度和时效性,提出了一种融合小波包分解(WPD)、主元分析(PCA)、遗传算法(GA)和支持向量机(SVM)的优化识别模型,并成功应用在竖直下降两相流流型辨识工作中。利用WPD对非平稳电导波动信号进行分解、重构,提取小波包能量构造特征向量;通过PCA对特征向量进行降维,降低特征输入的复杂性;同时采取GA全局迭代寻优的方式确定SVM的关键参数惩罚因子(C)和核函数参数(g)。对PCA-GA-SVM识别效果进行验证后与SVM、PCA-SVM、GASVM网络进行对比。结果表明,经过PCA和GA优化后的SVM网络在流型识别精度和时效性方面均提升显著,对泡状流、弹状流、搅拌流和环状流的总体预测精度达到了94.87%,耗时仅3.95 s,可满足在线识别需求。
In order to improve the accuracy and timeliness of flow pattern identification under the condition of small samples,an optimized identification model integrating wavelet packet decomposition(WPD),principal component analysis(PCA),genetic algorithm(GA)and support vector machine(SVM)is proposed and successfully applied to the flow pattern recognition of vertical-downward two-phase flow.WPD is used to decompose and reconstruct the non-stationary conductivity fluctuation signal,extract the wavelet packet energy and construct the feature vector;The dimension of feature vector is reduced by PCA to reduce the complexity of feature input;At the same time,the key parameters penalty factor(C)and kernel function parameter(g)of SVM are determined by GA global iterative optimization.After verifying the identification effect of PCA-GA-SVM,it is compared with SVM,PCA-SVM and GA-SVM networks.The results show that the SVM network optimized by PCA and GA is significantly improved in terms of flow pattern identification accuracy and timeliness.The overall prediction accuracy of bubble flow,slug flow,stirred flow and annular flow reaches 94.87%,and the time consumed is only 3.95 s,which can meet the needs of on-line identification.
作者
乔守旭
钟文义
谭思超
李旭鹏
郝思佳
Qiao Shouxu;Zhong Wenyi;Tan Sichao;Li Xupeng;Hao Sijia(Heilongjiang Provincial Key Laboratory of Nuclear Power System&Equipment,Harbin Engineering University,Harbin,150001,China;China Institute of Atomic Energy,Beijing,102413,China)
出处
《核动力工程》
EI
CAS
CSCD
北大核心
2022年第3期85-93,共9页
Nuclear Power Engineering
基金
国家自然科学基金(11905039)
国家博士后基金(2021T140148,2019M651267)。
