An unsupervised fault diagnosis method for rolling bearing using STFT and generative neural networks.
Hongfeng TaoPeng WangYiyang ChenVladimir StojanovicHuizhong YangPublished in: J. Frankl. Inst. (2020)
Keyphrases
- neural network
- unsupervised learning
- monitoring and fault diagnosis
- competitive learning
- fault diagnosis
- data driven
- artificial neural networks
- pattern recognition
- generative model
- back propagation
- semi supervised
- fuzzy logic
- machine learning
- neural network model
- supervised learning
- self organizing maps
- multi layer
- frequency domain
- semisupervised learning
- network architecture
- fuzzy systems
- feed forward
- pairwise
- hidden layer
- training algorithm
- mathematical model
- topic modeling
- activation function
- expert systems
- unsupervised manner
- adaptive resonance theory
- probabilistic topic models
- neural network is trained
- feature vectors
- completely unsupervised
- short time fourier transform
- genetic algorithm