Data Super-Network Fault Prediction Model and Maintenance Strategy for Mechanical Product Based on Digital Twin

Zhifeng Liu,Caixia Zhang,Congbin Yang,Hongyan Chu,Wei Chen

doi:10.1109/access.2019.2957202

Zhifeng Liu, Caixia Zhang + Show 3 more

Open Access

https://doi.org/10.1109/access.2019.2957202

Copy DOI

Abstract

When mechanical products work in complex environments, it is imperative to build an optimal maintenance strategy, based on accurate positioning of fault locations and prediction of fault conditions. Based on digital twinning technology, this paper proposes a “super-network-warning features” fault prediction and maintenance method. According to the digital twin five-dimensional structure, a three-layer super-network model is constructed, providing a quantitative research for data among heterogeneous subjects in digital twinning. Early-warning-features in the physical layer, virtual layer and service layer are selected as input parameters of the fault prediction model to accurately predict the cause of the fault. Then, using the simulation and optimization functions of the virtual model in digital twinning, a real-time maintenance strategy is formulated for the causes of the fault. It supplements the missing link between fault prediction and maintenance. Taking an aero-engine bearing as an example, this method is compared with a traditional method. The results show that the model prediction error of this method is better than the traditional method.

Highlights

Manufacturing technology is continuously improving [1], while more and more mechanical products operate, for long periods of time, in various complex environments (e.g. Bearings, marine propulsion, robots)
When mechanical products work in complex environment, they are faced with problems, such as unreliable prediction of product failure, precise location of fault and unreasonable construction of optimal maintenance strategy, which reduces the stability and life of the project at hand
: 1) In order to quantitatively study the interaction among heterogeneous agents in the digital twin model

Summary

Introduction

Manufacturing technology is continuously improving [1], while more and more mechanical products operate, for long periods of time, in various complex environments (e.g. Bearings, marine propulsion, robots). INDEX TERMS Digital twinning, data super-network, fault prediction, maintenance strategy. The characteristic of digital twin technology is to reflect the working process of physical entity in real time through virtual model.

Results

Conclusion