Explaining deep neural networks processing raw diagnostic signals

被引:6
作者
Herwig, Nico [1 ]
Borghesani, Pietro [1 ]
机构
[1] UNSW Sydney, Sch Mech & Mfg Engn, Sydney, NSW 2052, Australia
关键词
Explainable artificial intelligence; Rotating machinery; Fault detection; Neural network;
D O I
10.1016/j.ymssp.2023.110584
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
Neural networks (NN) have spurred significant interest in automating machine condition moni-toring, with many recent studies focusing on networks that take raw diagnostic signals as input. However, the complexity of these NNs has raised concerns about their physical justification and trustworthiness. Although explainable artificial intelligence (XAI) has developed promising tools to address these issues, the nature and size of raw diagnostic inputs have limited the effectiveness of XAI techniques in condition monitoring.This paper proposes a novel approach combining domain transformation and discretisation techniques with the XAI technique of Shapely value additive explanation (SHAP). This method-ology allows the input domain for the network to remain in the original time-domain, while the explanation domain can be chosen as frequency or time-frequency and its discretisation adapted to the specific diagnostic case. This flexibility makes networks trained on raw signals more interpretable, while the controllable domain discretisation facilitates the implementation of XAI with manageable computational costs. The proposed methodology is tested on numerical cases and experimental signals, including the UNSW gear-wear and CWRU bearing-fault datasets. This enhancement of XAI is applicable to common black-box classifiers, providing researchers with an effective tool to give physical justification to their models and bolster trust in AI for machine condition monitoring applications.
引用
收藏
页数:21
相关论文
共 29 条
  • [1] Achanta R., 2010, SLIC SUPERPIXELS
  • [2] Verifying domain knowledge and theories on Fire-induced spalling of concrete through eXplainable artificial intelligence
    al-Bashiti, Mohammad Khaled
    Naser, M. Z.
    [J]. CONSTRUCTION AND BUILDING MATERIALS, 2022, 348
  • [3] Ancona M., 2017, Towards Better Understanding of Gradient-Based Attribution Methods for Deep Neural Networks
  • [4] [Anonymous], 2021, Case western reserve university bearing dataset
  • [5] Cyclic spectral analysis in practice
    Antoni, Jerome
    [J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2007, 21 (02) : 597 - 630
  • [6] On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
    Bach, Sebastian
    Binder, Alexander
    Montavon, Gregoire
    Klauschen, Frederick
    Mueller, Klaus-Robert
    Samek, Wojciech
    [J]. PLOS ONE, 2015, 10 (07):
  • [7] Vibration Signals Analysis by Explainable Artificial Intelligence (XAI) Approach: Application on Bearing Faults Diagnosis
    Chen, Han-Yun
    Lee, Ching-Hung
    [J]. IEEE ACCESS, 2020, 8 : 134246 - 134256
  • [8] Chin Jacky, 2022, THESIS UNSW SYDNEY
  • [9] Chin Zhan Yie, 2022, UNSW TMCM GEAR CRACK
  • [10] Decker Thomas, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), P1, DOI 10.1109/ICASSP49357.2023.10096396