An edge intelligence-based industrial internet of things device anomaly detection system and method

Abstract

The application discloses an industrial Internet of Things equipment anomaly detection system and method based on edge intelligence, relates to the technical field of Internet of Things and artificial intelligence, and aims to solve the problems of large bandwidth consumption, poor real-time performance and privacy leakage in industrial Internet of Things anomaly detection. The system is composed of a physical perception layer, an edge intelligence layer and a cloud collaborative layer; the edge intelligence layer adopts deep separable convolution to extract features, and combines with autoencoder reconstruction error to perform local anomaly determination and multistage decision; the cloud collaborative layer migrates the global model capability to the edge end by using the knowledge distillation technology. Through the above technical scheme, the application realizes deep sinking of detection capability and millisecond-level real-time response, significantly reduces the uplink data volume, guarantees the data privacy and safety, continuously evolves the cloud-edge collaborative driving model, and improves the system robustness.

Images