: An activation function with vanishing gradient resistance for SAE-based DNNs and its application to rotating machinery fault diagnosis.
Xin WangYi QinYi WangSheng XiangHaizhou ChenPublished in: Neurocomputing (2019)
Keyphrases
- rotating machinery
- fault diagnosis
- activation function
- neural network
- rbf neural network
- fault detection
- hidden layer
- feed forward
- back propagation
- feed forward neural networks
- artificial neural networks
- bp neural network
- operating conditions
- error function
- fuzzy logic
- expert systems
- network size
- feedforward neural networks
- neural nets
- multilayer perceptron
- radial basis function
- basis functions
- chemical process
- learning rate
- recurrent neural networks
- power plant
- neural network model
- monitoring and fault diagnosis
- bp algorithm
- multi sensor information fusion
- training phase
- network architecture
- artificial intelligence
- training algorithm
- machine learning
- real time
- prediction model