A sparse auto-encoder-based deep neural network approach for induction motor faults classification

By Wenjun Sun, Siyu Shao, Rui Zhao, Ruqiang Yan, Xingwu Zhang, Xuefeng Chen. 2016

675 citations recorded by the source corpus.

Subfields: Control and Systems Engineering, Industrial and Manufacturing Engineering

View Paper: https://www.semanticscholar.org/paper/3c530d31da57c6c3d97f76c18f4c65a14d50e341

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Control and Systems Engineering

1. Liang Gao
2. Xinyu Li
3. Long Wen
4. Xiang Li
5. Ruqiang Yan
6. Qian Ding
7. Dong Yang
8. Weiting Zhang

In Industrial and Manufacturing Engineering

1. Long Wen
2. Xinyu Li
3. Ruqiang Yan
4. Liang Gao
5. Xiang Li
6. Qian Ding
7. Rui Zhao
8. Qingbo He

Citations in the corpus

• Data-Driven Methods for Predictive Maintenance of Industrial Equipment: A Survey (2019, methodology): “An effective approach utilizing sparse AE was developed in [112] for the fault diagnosis of induction motor.”
• DCNN-Based Multi-Signal Induction Motor Fault Diagnosis (2020, methodology): “A one-layer sparse autoencoder (SAE)-based DL approach has been proven to be effective in induction motor fault diagnosis [37], and a DBN-based fault diagnosis framework is proposed and the influence of model configuration is investigated [38].”
• An enhancement deep feature fusion method for rotating machinery fault diagnosis (2017, methodology): “designed sparse auto-encoder-based deep neural network approach for induction motor faults classification [23].”
• Intelligent Bearing Fault Diagnosis Method Combining Compressed Data Acquisition and Deep Learning (2018, methodology): “example, DNN is employed to deal with the raw data [36]–[39] and the transform domain data [40].”
• Learning to Monitor Machine Health with Convolutional Bi-Directional LSTM Networks (2017, methodology): “Before feeding raw data into the neural network, feature extraction and selection are performed firstly [32–35, 41 , 42 ].”
• Machine Health Monitoring Using Local Feature-Based Gated Recurrent Unit Networks (2018, background): “Although these pretrained DNN models can directly work on raw sensory time-series data, input dimensionality is easily over 100, even 1000, which will increase model size [19].”
• Cross-Domain Fault Diagnosis of Rolling Element Bearings Using Deep Generative Neural Networks (2019, neutral): “5 to avoid overfitting [32].”