基于旋转机械多图形卷积的域自适应故障诊断算法
Yixiang Lu1, Yuelong Huang1, De Zhu1
1Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment, School of Electrical Engineering and Automation, Anhui University, Hefei 230601, China.
一个新的域适应多图形卷积网络 (DAM-GCN) 在可变条件下改善轴承故障诊断. 这种方法捕获复杂的数据结构,增强概括性和优于当前最先进的技术.
科学领域:
- 机械工程 机械工程
- 人工智能的人工智能
- 信号处理 信号处理
背景情况:
- 工业轴承面临着变化的操作条件,挑战现有的故障诊断方法.
- 当前的深度学习方法往往无法捕捉故障数据中的复杂结构关系,限制了概括.
- 缺乏领域适应性阻碍了不同工作环境中的模型性能.
研究的目的:
- 提出一个新的域调整多图形卷积网络 (DAM-GCN),用于稳固的轴承故障诊断.
- 提高深度学习模型的概括能力,以在不同条件下进行故障检测.
- 提高工业环境中轴承故障诊断的准确性和可靠性.
主要方法:
- 使用卷积神经网络 (CNN) 提取特征.
- 多图形构造 (Top-k,k-NN,半径图) 来捕获局部,相似性和密度数据特征.
- 进行对比学习以提高特征的区分能力和表现力.
- 联合优化分类和域调整损失,用于域调整.
主要成果:
- DAM-GCN有效地捕捉了多视角断层结构特征.
- 对比式学习增强了特征的区分能力,以便更好地进行比较.
- 域调整最小化了源域和目标域之间的分布和图形结构差异.
- 实验结果表明,与现有的最先进的方法相比,性能优越.
结论:
- 拟议的DAM-GCN方法在可变的操作条件下显著提高了轴承故障诊断.
- 多图形方法与对比学习和域调整相结合,可以提高概括性.
- 这种方法为工业轴承故障诊断提供了更强大,更有效的解决方案.
更多相关视频
08:27Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
Published on: January 5, 2024
10:52Design, Instrumentation and Usage Protocols for Distributed In Situ Thermal Hot Spots Monitoring in Electric Coils using FBG Sensor Multiplexing
Published on: March 8, 2020
相关概念视频
Multimachine Stability
In analyzing the system, the nodal equations represent the relationship between bus voltages, machine voltages, and machine currents. The nodal equation is given by:
Relative Motion Analysis using Rotating Axes-Problem Solving
Here, in order to determine the magnitude of velocity and acceleration for point...
Three-Phase Short Circuit—Unloaded Synchronous Machine
This behavior occurs due to the magnetic flux produced by the short-circuit armature currents. Initially, these currents follow high-reluctance paths but eventually shift to...
Sequence Networks of Rotating Machines
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
Node Analysis for AC Circuits
To unravel the complexities of this system, nodal analysis is employed, a powerful technique founded on Kirchhoff's current law (KCL), which remains valid for phasors. AC circuits can effectively be...
Distributed Loads: Problem Solving
