Improved Representations for Continual Learning of Novel Motor Health Conditions through Few-Shot Prototypical Networks
Improved Representations for Continual Learning of Novel Motor Health Conditions through Few-Shot Prototypical Networks
复制标题
DOI：
10.1109/case49997.2022.9926567
复制
发表时间：
2022-08
期刊：
影响因子：
--
通讯作者：
Matthew Russell;P. Wang
中科院分区：
文献类型：
--
作者：
Matthew Russell;P. Wang
用于自动故障诊断的智能机器状态监控（CM）依赖于数据驱动的算法来表征机器健康状况，以便在智能工厂车间进行预测性维护活动。由于数据收集可能是昂贵的，CM数据集可能无法覆盖所有可能的故障条件，因此需要CM算法不断学习新的条件。最先进的CM研究集中在检测未知条件，而不是将未知条件整合到未来的预测中。因此，CM就绪的持续学习（CL）解决方案应该学会对新条件进行分类，并使用改进的表示，以最大限度地减少未来微调的需要。元学习方法，如少镜头原型网络（FSPN），规范基本任务学习，以找到这些更普遍的表示。在电机数据集上的实验表明，只有5或10个新故障的FSPN始终优于静态，微调和弹性权重合并（EWC）的CL方法，提高了高达19个点（53%至72%）的整体精度。与最近的FSPN图像分类工作相比，这些结果表明，FSPN可能是有利的CM由于有限的类的多样性的CM数据集。未来的工作应该扩展FSPN架构，包括开集识别和定量分析不同数量的基本任务类。
Intelligent machine condition monitoring (CM) for automatic fault diagnosis relies on data-driven algorithms to characterize machine health for predictive maintenance activities on smart factory floors. Since data collection can be expensive, CM data sets may not cover all the possible fault conditions, necessitating that CM algorithms continually learn new conditions. State-of-the-art CM research has focused on detecting unknown conditions rather than integrating unknown conditions into future predictions. Therefore, CM-ready Continual Learning (CL) solutions should learn to classify new conditions and use improved representations that minimize the need for future fine-tuning. Meta-learning approaches like Few-Shot Prototypical Networks (FSPN) regularize base-task learning to find these more generalizable representations. Experiments on a motor data set demonstrate that FSPN with only 5 or 10 examples of the novel fault consistently outperforms static, fine-tuning, and Elastic Weight Consolidation (EWC) approaches for CL, increasing the overall accuracy by up to 19 points (53% to 72%). Compared to recent FSPN work for image classification, these results show that FSPN may be advantageous for CM due to the limited class diversity of CM data sets. Future work should extend the FSPN architecture to include open set recognition and quantitatively analyze varying numbers of base-task classes.