发电技术 ›› 2026, Vol. 47 ›› Issue (1): 176-184.DOI: 10.12096/j.2096-4528.pgt.260116

• 发电及环境保护 • 上一篇    

基于能量-熵特征和改进堆叠降噪自编码器的水轮机空化状态识别方法

刘圳, 刘忠, 邹淑云, 周泽华, 乔帅程   

  1. 长沙理工大学能源与动力工程学院,湖南省 长沙市 410114
  • 收稿日期:2025-06-28 修回日期:2025-08-31 出版日期:2026-02-28 发布日期:2026-02-12
  • 通讯作者: 刘忠
  • 作者简介:刘圳(1998),男,硕士研究生,研究方向为水力机械状态监测与故障诊断,1203235718@qq.com
    刘忠(1978),男,博士,教授,研究方向为水力机械状态监测与故障诊断,本文通信作者,drliuzhong@csust.edu.cn
    邹淑云(1979),女,硕士,讲师,研究方向为流体机械内部流动与优化设计,cslgdxzsy@csust.edu.cn;
    周泽华(1999),男,硕士研究生,研究方向为水力机械状态监测与故障诊断,93748226@qq.com
    乔帅程(1998),男,硕士研究生,研究方向为水力机械状态监测与故障诊断,1771862910@qq.com
  • 基金资助:
    国家自然科学基金项目(52079011);湖南省自然科学基金项目(2023JJ30032)

Cavitation State Recognition Method of Hydraulic Turbine Based on Energy-Entropy Features and Improved Stacked Denoising Auto Encoder

Zhen LIU, Zhong LIU, Shuyun ZOU, Zehua ZHOU, Shuaicheng QIAO   

  1. School of Energy and Power Engineering, Changsha University of Science and Technology, Changsha 410114, Hunan Province, China
  • Received:2025-06-28 Revised:2025-08-31 Published:2026-02-28 Online:2026-02-12
  • Contact: Zhong LIU
  • Supported by:
    National Natural Science Foundation of China(52079011);Natural Science Foundation of Hunan Province(2023JJ30032)

摘要:

目的 针对混流式水轮机空化声发射(acoustic emission,AE)信号受背景噪声干扰、故障难以识别的问题,提出一种基于能量-熵特征和哈里斯鹰优化(Harris hawks optimization,HHO)算法联合3折交叉验证(3-fold cross-validation,3Fold)优化堆叠降噪自编码器(stacked denoising auto encoder,SDAE)的状态识别方法。 方法 首先,利用变分模态分解算法对信号进行分解,得到一系列固有模态函数。其次,提取相关系数最大的2个固有模态函数的能量和熵特征,构建12维特征向量,输入识别模型。再次,利用HHO算法联合3Fold,对SDAE的超参数进行优化。最后,将HHO-3Fold-SDAE算法与其他算法寻优得到的最优参数分别输入模型中运行,并进行对比分析。 结果 与其他算法相比,HHO-3Fold-SDAE算法具有更小的准确率方差、损失率以及更高的平均准确率;相较于SDAE,其测试集平均准确率提高了6%;相较于HHO-SDAE,其测试集平均准确率提高了4%,准确率方差降低了17%。 结论 所提方法可用于水轮机空化AE信号的分类识别,可为水力机械状态监测提供参考。

关键词: 水力发电, 水轮机, 空化状态识别, 哈里斯鹰优化(HHO)算法, 堆叠降噪自编码器(SDAE),

Abstract:

Objectives Aiming at the problem that the acoustic emission (AE) signal induced by the cavitation of a hydraulic turbine is disturbed by background noise and the fault is difficult to identify, a state recognition method based on energy-entropy features and Harris hawks optimization (HHO) algorithm combined with 3-fold cross-validation (3Fold) to optimize stacked denoising auto encoder (SDAE) is proposed. Methods First, the variational mode decomposition algorithm is used to decompose the signal, and then a series of intrinsic mode functions are obtained. Second, the energy and entropy features of the two intrinsic mode functions are extracted, which have the largest correlation coefficient with the original signal. A 12-dimensional feature vector is constructed and then the vector is imported into the recognition model. Third, the HHO algorithm combined with 3Fold is used to optimize the hyper-parameters of SDAE. Finally, the optimal parameters obtained by the HHO-3Fold-SDAE algorithm and other algorithms are input into the model for comparison. Results Compared with other algorithms, the HHO-3Fold-SDAE algorithm has smaller loss rate and accuracy variance, and higher average accuracy. Compared with SDAE, its test set average accuracy is increased by 6%. Compared with HHO-SDAE, its test set average accuracy is increased by 4% and accuracy variance is decreased by 17%. Conclusions The proposed method can be used to classify and recognize AE signals induced by cavitation of hydraulic turbine, and provide reference for the condition monitoring of hydraulic machinery.

Key words: hydropower, hydraulic turbine, cavitation state recognition, Harris hawks optimization (HHO) algorithm, stacked denoising auto encoder (SDAE), entropy

中图分类号: