IFD from the cradle to the bloom and to guide the future development. In this paper, to fill in this gap, commonly used UDTL-based settings and algorithms are discussed and a new taxonomy of UDTL-based IFD is constructed. In each separate category, we also give a comprehensive review about recent development of UDTL-based IFD.

Intelligent fault diagnosis (IFD) refers to applications of machine learning theories to machine fault diagnosis. This is a promising way to release the contribution from human labor and automatically recognize the health states of machines, thus it has attracted much …

2021年9月28日 · Recent progress on intelligent fault diagnosis (IFD) has greatly depended on deep representation learning and plenty of labeled data. However, machines often operate...

2017年10月1日 · In this paper, a novel deep autoencoder feature learning method is developed to diagnose rotating machinery fault. Firstly, the maximum correntropy is adopted to design the new deep autoencoder loss function for the enhancement of feature learning from the measured vibration signals.

2019年5月1日 · Intelligent fault diagnosis (IFD) refers to applications of machine learning theories to machine fault diagnosis. This is a promising way to release the contribution from human labor and automatically recognize the health states of machines, thus it has attracted much attention in the last two or three decades.

2020年4月1日 · 摘要 智能故障诊断（ifd）是指将机器学习理论应用于机器故障诊断。 这是一种释放人类劳动贡献并自动识别机器健康状态的有前途的方法，因此在最近两三年内引起了广泛关注。

2023年6月22日 · 通过对一些典型方法和数据集的比较分析，揭示了基于udtl的ifd中一些尚未被研究的开放性和本质问题，包括特征的可转移性、主干网络的影响、负迁移、物理先验等。为了强调基于udtl的ifd的重要性和可重复性，将向研 究界发布整个测试框架，以促进未来的研究 ...

Intelligent fault diagnosis (IFD) refers to applications of machine learning theories to machine fault diagnosis. This is a promising way to release the contribution from human labor and automatically recognize the health states of machines, thus it has attracted much …

2024年10月21日 · To bridge the gap, this article presents a review and roadmap to systematically cover the development of IFD following the progress of machine learning theories and offer a future perspective.

2023年9月24日 · 利用 IFD指标 自动筛选樱桃数据，再利用樱桃数据进行模型指令微调，获取更好地微调模型，主要涉及三个步骤： Retraining from Self-Guided Experience：利用樱桃数据进行模型重训练。 如下图所示， 利用少量数据进行模型初学习的原因如下： 如果采用大量数据进行学习，时间成本和资源成本较高。 而在少量数据的选择上，数量选择1k条样本，为了保证数据的多样性，采用K-Means方法对指令进行聚类，共聚出100个簇，每个簇里选择10个样本。 并且仅在初 …