Neuron-Compressed Deep Neural Network and Its Application in Industrial Anomaly Detection

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

View graph of relations


  • Kai Wang
  • Caoyin Yan
  • Yanfang Mo
  • Xiaofeng Yuan
  • Yalin Wang
  • And 1 others
  • Chunhua Yang

Related Research Unit(s)


Original languageEnglish
Journal / PublicationIEEE Transactions on Industrial Informatics
Publication statusOnline published - 12 Oct 2022


Data modeling and online monitoring are two critical stages for data-driven anomaly detection. Regarding data modeling, deep neural networks (DNNs) can learn good decision boundaries to separate the anomaly and normal regions, due to its flexible model structures and excellent fitting ability. However, DNNs, using nonlinear activations with specific boundaries, may indirectly cause a limited anomaly detection margin, especially when there are samples far from centroids. Moreover, an anomaly detection model with a narrow detection margin is deemed insensitive to general faults.An anomaly detection model with a tight detection margin will suffer a severe performance degradation. To mitigate the intrinsic drawbacks of DNNs, we develop a new regularizer based on the maximum likelihood of complete data (i.e., observations and latent variables). The regularizer is neuron-wise and mathematically acts as compressing neurons, dragging the marginal points into the centroids. Combining the regularizer with the encoding-decoding structure networks, we perform an industrial case study to verify the superiority of the proposed method.

Research Area(s)

  • Anomaly detection, Data models, deep neural network, Feature extraction, Kernel, Neurons, Principal component analysis, regularization, stacked autoencoder, Training

Citation Format(s)