HeMTAN: Hybrid task-adapted experts-based multi-task attention network for unseen compound fault decoupling diagnosis of rotating machinery.
Jimeng LiWei WangSai ZhongZong MengLixiao CaoPublished in: Expert Syst. Appl. (2024)
Keyphrases
- rotating machinery
- fault diagnosis
- fault detection
- multi task
- multi task learning
- learning tasks
- fault management
- expert systems
- multiple tasks
- network structure
- multitask learning
- neural network
- transfer learning
- gaussian processes
- feature selection
- learning problems
- training examples
- multi class
- sparse learning
- genetic algorithm
- high order
- collaborative filtering
- training set
- image segmentation
- normal operation