| 李想,钱晶,曾云.基于UPEMD融合RCMCSE和ALWOA-BP的水电机组故障诊断[J].水利学报,2024,55(6):744-755 |
| 基于UPEMD融合RCMCSE和ALWOA-BP的水电机组故障诊断 |
| Fault diagnosis of hydropower units based on UPEMD integrating RCMCSE and ALWOA-BP |
| 投稿时间：2023-11-07 |
| DOI：10.13243/j.cnki.slxb.20230694 |
| 中文关键词: 水电机组 精细复合多尺度熵 余弦相似熵 ALWOA-BP 故障诊断 |
| 英文关键词: hydropower units refined composite multiscale entropy cosine similarity entropy ALWOA-BP fault diagnosis |
| 基金项目:国家自然科学基金项目(52079059，52269020) |
|
| 摘要点击次数: 635 |
| 全文下载次数: 1177 |
| 中文摘要: |
| 水电机组振动信号的诊断对机组安全稳定运行至关重要。本文提出一种基于均匀相位经验模态分解(Uniform Phase EMD，UPEMD)融合精细复合多尺度余弦相似熵(Refined Composite Multiscale CSE，RCMCSE)和改进鲸鱼算法优化反向传播神经网络(ALWOA-BP)的水电机组故障诊断方法。利用UPEMD对原始信号进行分解，然后建立WOA-BP故障诊断模型。针对WOA算法快速陷入局部最优和过早收敛的问题，采用自适应权重和莱维飞行对WOA算法进行优化。实验结果表明，该方法的准确率达到了100%。为探究所提模型的抗噪性能，引入信噪比为2 dB的噪声进行再次分析，诊断结果为94.44%，明显优于其他未优化模型。该项研究可以对现有水电机组故障诊断方法进行有价值的补充。 |
| 英文摘要: |
| The diagnosis of vibration signals in hydropower units is crucial to the safe and stable operation of the units.This article proposes a fault diagnosis method for hydropower units based on uniform phase empirical mode decomposition(UPEMD)combined with refined composite multiscale cosine similarity entropy(RCMCSE)and an improved whale optimization algorithm(ALWOA)optimized back propagation neural network(BP).The UPEMD is used to decompose the original signal，and then a WOA-BP fault diagnosis model is established.To solve the problem of WOA algorithm quickly falling into local optimum and premature convergence，an adaptive weight and Levy flight are used to optimize the WOA algorithm.Experimental results show that the accuracy of this method reached 100%.To explore the noise resistance performance of the proposed model，a noise with a signal-to-noise ratio of 2 dB was introduced for re-analysis，and the diagnostic result was 94.44%，which was significantly better than other unoptimized models.This study can provide a valuable complement to existing fault diagnosis methods for hydropower units. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |