一个零射击属性嵌入式模型,具有特征差异映射sigmoid函数,用于旋转机械的复合故障诊断
Lv Wang1, Dingliang Chen1, Yongfang Mao2
1State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing University, Chongqing 400044, PR China.
本研究引入了用于复合故障诊断的零射击属性嵌入式模型 (ZSAECFD). 该模型只使用单个故障数据成功诊断未见的复合故障,在轴承和变速箱方面实现了高精度.
科学领域:
- 机械工程 机械工程
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 由于训练数据的稀缺性,机械复合故障检测具有挑战性.
- 现有的方法通常需要大量的复合故障样本,收集这些样本是不切实际的.
研究的目的:
- 开发一种零射击学习模型,用于诊断未见的复合故障,而不需要复合故障数据.
- 在多标签分类任务中提高属性识别的准确性.
主要方法:
- 为复合故障诊断 (ZSAECFD) 提出了一个零射击属性嵌入式模型.
- 仅使用单个故障数据,为单个和复合故障构建属性原型.
- 引入了一个新的激活功能,特征差异映射sigmoid (F-sigmoid),以增强特征差异和减轻梯度消失.
主要成果:
- 采用ZSAECFD模型实现了81.82%的诊断准确度,用于未见的轴承组合故障.
- 该模型在未见的变速箱组合故障方面达到88.17%的诊断准确率.
- 与经典和先进的零射击学习方法相比,表现优越.
结论:
- 拟议的ZSAECFD模型有效地通过仅使用单个故障数据来诊断未见的复合故障.
- 通过放大特征差异,F - 信号体激活功能提高了诊断的准确性.
- 该方法在现实工程场景中为复合故障诊断提供了一种实际的解决方案.
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
07:46Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
Published on: August 9, 2024
相关概念视频
Simplified Synchronous Machine Model
In this model, each generator is connected to a...
Sequence Networks of Rotating Machines
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
Fault Types
For line-to-line faults occurring between phases B and C, the...
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:
Deformation in a Circular Shaft
Relative Motion Analysis using Rotating Axes-Problem Solving
Here, in order to determine the magnitude of velocity and acceleration for point...
