Establishing a reliable mechanism model of the digital twin machining system: An adaptive evaluation network approach

2022 ◽  
Vol 62 ◽  
pp. 390-401
Author(s):  
Shimin Liu ◽  
Yicheng Sun ◽  
Pai Zheng ◽  
Yuqian Lu ◽  
Jinsong Bao
2022 ◽  
Vol 12 (1) ◽  
Author(s):  
Jiajie Jiang ◽  
Hui Li ◽  
Zhiwei Mao ◽  
Fengchun Liu ◽  
Jinjie Zhang ◽  
...  

AbstractCondition monitoring and fault diagnosis of diesel engines are of great significance for safety production and maintenance cost control. The digital twin method based on data-driven and physical model fusion has attracted more and more attention. However, the existing methods lack deeper integration and optimization facing complex physical systems. Most of the algorithms based on deep learning transform the data into the substitution of the physical model. The lack of interpretability of the deep learning diagnosis model limits its practical application. The attention mechanism is gradually developed to access interpretability. In this study, a digital twin auxiliary approach based on adaptive sparse attention network for diesel engine fault diagnosis is proposed with considering its signal characteristics of strong angle domain correlation and transient non-stationary, in which a new soft threshold filter is designed to draw more attention to multi decentralized local fault information dynamically in real time. Based on this attention mechanism, the distribution of fault information in the original signal can be better visualized to help explain the fault mechanism. The valve failure experiment on a diesel engine test rig is conducted, of which the results show that the proposed adaptive sparse attention mechanism model has better training efficiency and clearer interpretability on the premise of maintaining performance.


Author(s):  
Chenzhao Li ◽  
Sankaran Mahadevan ◽  
You Ling ◽  
Liping Wang ◽  
Sergio Choze

2019 ◽  
Vol 3 (1) ◽  
pp. 97-105
Author(s):  
Mary Zuccato ◽  
Dustin Shilling ◽  
David C. Fajgenbaum

Abstract There are ∼7000 rare diseases affecting 30 000 000 individuals in the U.S.A. 95% of these rare diseases do not have a single Food and Drug Administration-approved therapy. Relatively, limited progress has been made to develop new or repurpose existing therapies for these disorders, in part because traditional funding models are not as effective when applied to rare diseases. Due to the suboptimal research infrastructure and treatment options for Castleman disease, the Castleman Disease Collaborative Network (CDCN), founded in 2012, spearheaded a novel strategy for advancing biomedical research, the ‘Collaborative Network Approach’. At its heart, the Collaborative Network Approach leverages and integrates the entire community of stakeholders — patients, physicians and researchers — to identify and prioritize high-impact research questions. It then recruits the most qualified researchers to conduct these studies. In parallel, patients are empowered to fight back by supporting research through fundraising and providing their biospecimens and clinical data. This approach democratizes research, allowing the entire community to identify the most clinically relevant and pressing questions; any idea can be translated into a study rather than limiting research to the ideas proposed by researchers in grant applications. Preliminary results from the CDCN and other organizations that have followed its Collaborative Network Approach suggest that this model is generalizable across rare diseases.


Sign in / Sign up

Export Citation Format

Share Document