相关实验视频
在内燃机中使用多传感器数据进行跨域故障诊断,并使用传输联合和基于变压器的联合传输学习
A Srinivaas1, N R Sakthivel2, Binoy B Nair3
1Department of Mechanical Engineering, Amrita School of Engineering, Amrita Vishwa Vidyapeetham, Coimbatore, 641112, India. a_srinivaas@cb.amrita.edu.
Scientific reports
|October 21, 2025
概括
本研究介绍了用于发动机故障诊断的高级转移学习和联合学习. 将这些方法与变压器-深度神经网络混合架构集成,可以提高准确性和稳定性,特别是在大型引擎中.
科学领域:
- 工程 工程师 工程师 工程师
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 发动机故障诊断对于可靠性和安全性至关重要.
- 不同质的引擎数据集对传统的诊断模型构成挑战.
- 数据隐私问题限制了集中式模型培训.
研究的目的:
- 为各种发动机类型 (小型和大型) 开发有效的故障诊断系统.
- 通过联合学习来增强数据隐私和模型概括.
- 为了提高分布外 (OOD) 故障检测的准确性.
主要方法:
- 使用双向转移学习与深度神经网络 (DNN) 调整异构的引擎数据集.
- 开发了一个联合学习系统,用于保护隐私的协作DNN培训.
- 提出了一个联合转移学习方法,将变压器和DNN架构结合起来,用于顺序和歧视性特征提取.
主要成果:
- 转移学习和联合转移学习在诊断小型发动机故障方面表现出高效.
- 具有OOD测试的变压器-DNN混合架构显著提高了大型发动机的故障检测精度.
- 对比实验显示,与基线DNN模型相比,分类准确性和稳定性得到了实质性的改进.
结论:
- 联合转移学习对于发动机故障诊断非常有效,特别是对于小型发动机.
- 混合变压器-DNN架构增强了大型发动机中的OOD故障检测.
- 该研究支持用于各种发动机应用的可扩展,保护隐私的预测性维护系统的开发.
相关概念视频
Internal Combustion Engine
2.5K
The internal combustion engine is a heat engine that uses the byproducts of combustion as the working fluid instead of using a heat transfer medium to transfer heat. The combustion is done in a way that produces high-pressure combustion products that can be expanded through a turbine or piston to create work. Internal combustion engines can again be categorized into three kinds: (1) spark ignition gasoline engines, most commonly used in automobiles, (2) compression ignition diesel engines that...
2.5K
Improving Translational Accuracy
14.1K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
14.1K
Improving Translational Accuracy
3.5K
3.5K