基于小波熵理论的动力发电设备故障自动检测方法  

Automatic Fault Detection Method of Power Generation Equipment Based on Wavelet Entropy Theory

作　　者：叶志晖 石钉科 王柳婧 钱杰[1] YE Zhi-hui;SHI Ding-ke;WANG Liu-jing;QIAN Jie(China Tobacco Zhejiang Industrial Co.,Ltd.,Hangzhou 310000 China)

机构地区：[1]浙江中烟工业有限责任公司,浙江杭州310000

出　　处：《自动化技术与应用》2023年第6期66-69,共4页Techniques of Automation and Applications

摘　　要：传统方法检测动力发电设备存在检测效率低、检测灵敏度低且抗噪能力差的问题,基于此提出基于小波熵理论的动力发电设备故障自动检测方法。首先采用小波熵理论中的小波函数,即信号时间熵和信号频率熵,对原始故障数据分别进行故障分类和特征提取,再利用Softmax分类器“数据带”和阶跃函数,对已提取的故障特征样本分别进行内、外故障特征分类,最终根据分类结果实现动力发电设备故障的自动检测。实验结果表明方法效率高、灵敏度高、抗噪能力强且不受故障距离的干扰。Traditional methods for detecting power generation equipment have the problems of low detection efficiency,low detection sensitivity and poor anti-noise ability.Based on this,an automatic fault detection method for power generation equipment based on wavelet entropy theory is proposed.First it uses the wavelet function in the wavelet entropy theory,namely signal time entropy and signal frequency entropy,to perform fault classification and feature extraction on the original fault data,and then use the Softmax classifier "data band" and step function to analyze the extracted fault features.The samples are classified into internal and external fault characteristics respectively,and the automatic detection of power generation equipment faults is finally realized according to the classification results.The experimental results show that the proposed method has high efficiency,high sensitivity,strong anti-noise ability and is not affected by the distance of the fault.

关 键 词：小波熵 特征提取 Softmax分类器 故障检测 故障暂态电流均值 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置] TP206.3[自动化与计算机技术—控制科学与工程]