Equipment fault diagnosis method, device and system based on digital twin model

Abstract

The embodiment of the invention discloses an equipment fault diagnosis method, device and system based on a digital twinning model. The method comprises the steps of constructing the initial digital twinning model of target equipment according to state parameter initial data and response parameter data of the target equipment; obtaining a target response parameter of the target equipment and an updating parameter corresponding to the target response parameter, calculating the sensitivity of each updating parameter relative to the target response parameter, and taking the updating parameter ofwhich the sensitivity meets a preset requirement as a correction parameter; constructing a response surface model between the target response parameter and the correction parameter, and determining acorrection value of the correction parameter based on the response surface model; and updating the initial digital twinning model by using the correction value of the correction parameter to obtain adigital twinning model of the target equipment, and performing fault diagnosis on the target equipment by using the digital twinning model. By means of the embodiments of the invention, accurate diagnosis of equipment faults can be realized.

Description

technical field [0001] The present invention relates to the technical field of mechanical equipment diagnosis, in particular, to a method, device and system for equipment fault diagnosis based on a digital twin model. Background technique [0002] The rapid development of information technologies such as the Internet of Things, cyber-physical systems, and big data is leading contemporary manufacturing to a new stage. With the popularization of data and computer intelligence, the manufacturing process is becoming more and more digital. New manufacturing models are beginning to emerge in the form of cyber-physical production systems, the Internet of Things, and big data manufacturing analytics, enabling a deeper understanding of the physical processes of the system, improved environmental awareness of machines and equipment, and better control of the production process. [0003] Due to the high speed, high precision and flexibility requirements of modern manufacturing, equipme...

AI Technical Summary

Problems solved by technology

However, considering the complexity of faults and the complex relationship between faults and corresponding system responses, current methods for fault diagnosis that only utilize data-driven information-based sensing cannot well avoid false alarms (including false positives and Fault Negative) produces

At the same time, when the system performs flexible and adaptive manufacturing operations, it cannot deeply understand the physical process, cannot take into account the surrounding environment when the machine is running, and better control the production process.

Images