Tan, Bitong (China North Vehicle Research Institute), He, Xiaoqing (Dalian Maritime University), Li, Yuzeng (Dalian University of Technology), Zhao, Ying (Dalian Maritime University), Sun, Yang (China North Vehicle Research Institute), Hu, Lianxin (Huzhou University), XU, Changyi (Dalian University of Technology)

Fault Diagnosis Based on Edge Cloud Computing for Aero-Engine Bearing

Scheduled for presentation during the Regular session "Fault Diagnosis and Simulaton Technoqies " (ThA1), Thursday, October 31, 2024, 10:30−10:50, Room T1

7th IFAC Conference on Engine and Powertrain Control, Simulation and Modeling, Oct 30 - Nov 1, 2024, Dalian, China

This information is tentative and subject to change. Compiled on May 16, 2025

Abstract

This paper investigates the fault diagnosis problem of aero-engine bearings based on the edge cloud computing approach. Firstly, to enhance the efficiency of fault diagnosis for aero-engine bearings, an edge cloud computing is utilized. Secondly, the faults of aero-engine bearings are classified by combining edge cloud computing as well as deep learning. Thirdly, the traditional Stochastic Gradient Descent (SGD) algorithm is optimized during model training process by exploiting the AdamW method. The experimental results show that utilizing edge cloud computing for fault diagnosis not only saves time but also achieves a 96char% accuracy rate. This implies that edge cloud computing can enhance the efficiency of fault diagnosis while maintaining high diagnosis accuracy.