当前位置: X-MOL 学术Int. J. Robust Nonlinear Control › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Layer-wise contribution-filtered propagation for deep learning-based fault isolation
International Journal of Robust and Nonlinear Control ( IF 3.2 ) Pub Date : 2022-08-14 , DOI: 10.1002/rnc.6328
Zhuofu Pan 1, 2 , Yalin Wang 1 , Kai Wang 1 , Guangtao Ran 3 , Hongtian Chen 2 , Weihua Gui 1
Affiliation  

Deep learning is gradually mainstreaming into data-driven methods, relying on the advantages of extracting complicated nonlinear features. However, the black-box property makes its decision rules non-transparent, resulting in difficulty in attribution tasks, which aim to backtrack the contribution of network inputs to the outputs. Fault isolation and localization are techniques for diagnosing the root cause of system failures, which have a consistent objective with attribution for a deep learning-based fault observer or classifier. Unfortunately, most fault isolation methods are based on shallow learning methods. Also, many attribution algorithms are linear without considering the influence of nonlinear activation functions. The related concerns motivate us to propose a new approach, namely layer-wise contribution-filtered propagation (LCP), for deep learning-based fault isolation. In LCP, reasonable contributions are defined based on the influence of each layer input on maximizing the absolute output activation. A symbolic function is designed to identify neurons with negative contributions, which are then filtered and forbidden to backpropagate to the previous layer. By guiding correct attribution, LCP is available for any nonlinear activation functions and their combinations. It also provides a solution for fault isolation with stacked sample inputs, in which one single variable has several attributions associated with different times. Finally, two chemical simulations verify the effectiveness of the proposed method.

中文翻译:

基于深度学习的故障隔离的逐层贡献过滤传播

依靠提取复杂非线性特征的优势,深度学习逐渐成为数据驱动方法的主流。然而,黑盒属性使其决策规则不透明,导致归因任务难以进行,该任务旨在回溯网络输入对输出的贡献。故障隔离和定位是诊断系统故障根本原因的技术,其目标与基于深度学习的故障观察器或分类器的归因一致。不幸的是,大多数故障隔离方法都是基于浅层学习方法。此外,许多归因算法是线性的,没有考虑非线性激活函数的影响。相关问题促使我们提出一种新方法,即逐层贡献过滤传播(LCP),用于基于深度学习的故障隔离。在 LCP 中,合理的贡献是根据每一层输入对最大化绝对输出激活的影响来定义的。符号函数旨在识别具有负贡献的神经元,然后对其进行过滤并禁止反向传播到前一层。通过引导正确的归因,LCP 可用于任何非线性激活函数及其组合。它还提供了一种具有堆叠样本输入的故障隔离解决方案,其中一个变量具有与不同时间相关的多个属性。最后,两个化学模拟验证了所提方法的有效性。符号函数旨在识别具有负贡献的神经元,然后对其进行过滤并禁止反向传播到前一层。通过引导正确的归因,LCP 可用于任何非线性激活函数及其组合。它还提供了一种具有堆叠样本输入的故障隔离解决方案,其中一个变量具有与不同时间相关的多个属性。最后,两个化学模拟验证了所提方法的有效性。符号函数旨在识别具有负贡献的神经元,然后对其进行过滤并禁止反向传播到前一层。通过引导正确的归因,LCP 可用于任何非线性激活函数及其组合。它还提供了一种具有堆叠样本输入的故障隔离解决方案,其中一个变量具有与不同时间相关的多个属性。最后,两个化学模拟验证了所提方法的有效性。它还提供了一种具有堆叠样本输入的故障隔离解决方案,其中一个变量具有与不同时间相关的多个属性。最后,两个化学模拟验证了所提方法的有效性。它还提供了一种具有堆叠样本输入的故障隔离解决方案,其中一个变量具有与不同时间相关的多个属性。最后,两个化学模拟验证了所提方法的有效性。
更新日期:2022-08-14
down
wechat
bug