.png){kind=icon}
.png){kind=icon}
Return
Data-Driven Distributed Diagnosis and Optimization Control for Cascaded Systems
.png){kind=icon}
PRE
AI
DOI：10.1109/TSMC.2024.3352609.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Due to limitations in large-area communication and computation, it can be challenging to apply centralized diagnosis and optimization control design approaches to cascaded systems. This work proposes a distributed diagnosis and optimization control approach, which is realized using data-driven techniques. Specifically, an adaptive observer-based subdiagnosis system design approach is proposed for cascaded systems using only the local input/output (I/O) data and the state estimations of adjacent subsystems. The state estimations from neighboring subsystems are treated as known inputs in the local subsystem. In the centralized design approach, the residual signals generated by all subsystem observers need to be sent to the central computing node to reconstruct controller parameters. The learning process of the local optimization controller only needs to be driven by the residual signals from local and adjacent subsystems, avoiding centralized calculation and reducing the computational burden of the central node. The learning process of the locally optimal controller only needs to be driven by residual signals from the local and neighboring subsystems. In the end, the simulation results verify the effectiveness of the proposed distributed approach.
Keywords:
Cascaded systems
data-driven
distributed diagnosis
optimization control
Journal
IF:
10.5
Papers:
1.1W
Citations:
5.0W