Cavitation state recognition method of centrifugal pump based on multi-dimensional feature fusion and convolutional gate recurrent unit

离心泵 空化 人工智能 卷积神经网络 模式识别(心理学) 自编码 特征提取 主成分分析 特征(语言学) 计算 物理 深度学习 计算机科学 声学 算法 叶轮 热力学 哲学 语言学
作者
Tonghe Zhang,Yongxing Song,Qiang Liu,Yi Ge,Linhua Zhang,Jingting Liu
出处
期刊:Physics of Fluids [American Institute of Physics]
卷期号:36 (10) 被引量:1
标识
DOI:10.1063/5.0232330
摘要

The rapid and accurate recognition of cavitation in centrifugal pumps has become essential for improving production efficiency and ensuring machinery longevity. To address the limitations of existing methods in terms of applicability, accuracy, and efficiency, a new method based on multi-dimensional feature fusion and convolutional gate recurrent unit (MCGN) was proposed. Experimental monitoring of cavitation of centrifugal pumps was conducted. Five signals at different water temperatures and operating frequencies were collected. Key modulating features were extracted by time-frequency analysis and principal component analysis. The multi-dimensional features are fused by one and two dimensional convolutional neural networks. The cavitation state label was used to label the sample set by cavitation number, net positive suction head, and cavitation evolution images captured by high-speed cameras. Finally, the neural network based on the convolutional gate recurrent unit was used to classify the cavitation state of the centrifugal pump. The experimental results demonstrate that the proposed method achieves recognition accuracies exceeding 98% for vibration signals, noise signals, outlet pressure pulsation signals, and torque signals. Compared with the short-time Fourier transform-autoencoder model, MCGN model can improve the recognition accuracy by 4.03%, computation efficiency by 20%, and loss by 87%. These advances underscore the potential of the method in monitoring and maintenance practices for centrifugal pumps.

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
天天快乐应助天降采纳,获得10
1秒前
梨梨发布了新的文献求助10
2秒前
大模型应助huvy采纳,获得10
3秒前
3秒前
无花果应助灯火采纳,获得10
8秒前
8秒前
8秒前
bosslin完成签到,获得积分10
8秒前
晓旭完成签到 ,获得积分10
10秒前
魔幻的雪碧完成签到,获得积分20
10秒前
Akim应助粗暴的遥采纳,获得10
11秒前
syy发布了新的文献求助10
14秒前
请叫我鬼才完成签到,获得积分10
14秒前
15秒前
yi完成签到 ,获得积分10
17秒前
易不毛完成签到,获得积分10
17秒前
17秒前
19秒前
lt0217发布了新的文献求助10
22秒前
corazon完成签到,获得积分10
22秒前
安小象完成签到,获得积分10
23秒前
独孤孤独咕噜犊子完成签到,获得积分20
24秒前
lanshi1008发布了新的文献求助20
25秒前
25秒前
syy完成签到,获得积分10
25秒前
QQ完成签到,获得积分10
27秒前
28秒前
lt0217完成签到,获得积分10
29秒前
粉鳍发布了新的文献求助10
29秒前
30秒前
31秒前
小马甲应助仁爱的雁芙采纳,获得10
31秒前
美满朝雪发布了新的文献求助30
33秒前
心灵美绯发布了新的文献求助10
36秒前
三黑猫完成签到,获得积分0
36秒前
37秒前
40秒前
40秒前
40秒前
高分求助中
The Oxford Handbook of Social Cognition (Second Edition, 2024) 1050
The Young builders of New china : the visit of the delegation of the WFDY to the Chinese People's Republic 1000
юрские динозавры восточного забайкалья 800
English Wealden Fossils 700
Chen Hansheng: China’s Last Romantic Revolutionary 500
COSMETIC DERMATOLOGY & SKINCARE PRACTICE 388
Case Research: The Case Writing Process 300
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3141416
求助须知:如何正确求助?哪些是违规求助? 2792460
关于积分的说明 7802733
捐赠科研通 2448629
什么是DOI,文献DOI怎么找? 1302677
科研通“疑难数据库(出版商)”最低求助积分说明 626650
版权声明 601237