Edge-cloud collaborative multi-level fault diagnosis based on stacked sparse autoencoder

In industrial applications, detecting a fault in time is critical to ensure production safety. Edge-cloud collaborative condition monitoring provides a more flexible solution to achieve both computational efficiency and accuracy. In this paper, an Edge-cloud collaborative multi-level fault diagnosis model is developed based on stacked sparse autoencoder to minimize the fault detection time, meanwhile, the diagnostic accuracy can also be guaranteed. By filtering most of the normal data and less model inference time, the anomaly detection model on the edge can minimize the fault detection time. When a fault occurs, the fault data will be sent to the cloud to infer the fault details. The experimental results show that the proposed method can detect faults 0.12s earlier on average compared to edge-inferencing after cloud-trained method.