Physics-informed machine learning in prognostics and health management: State of the art and challenges

D Weikun, KTP Nguyen, K Medjaher, G Christian… - Applied Mathematical …, 2023 - Elsevier
Prognostics and health management (PHM) plays a constructive role in the equipment's
entire life health service. It has long benefited from intensive research into physics modeling …

Learning distribution grid topologies: A tutorial

D Deka, V Kekatos, G Cavraro - IEEE Transactions on Smart …, 2023 - ieeexplore.ieee.org
Unveiling feeder topologies from data is of paramount importance to advance situational
awareness and proper utilization of smart resources in power distribution grids. This tutorial …

Grid-graph signal processing (grid-GSP): A graph signal processing framework for the power grid

R Ramakrishna, A Scaglione - IEEE Transactions on Signal …, 2021 - ieeexplore.ieee.org
The underlying theme of this paper is to explore the various facets of power systems data
through the lens of graph signal processing (GSP), laying down the foundations of the Grid …

Data-driven control: Overview and perspectives

W Tang, P Daoutidis - 2022 American Control Conference …, 2022 - ieeexplore.ieee.org
Process systems are characterized by nonlinearity, uncertainty, large scales, and also the
need of pursuing both safety and economic optimality in operations. As a result they are …

Topology learning of linear dynamical systems with latent nodes using matrix decomposition

MS Veedu, H Doddi… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
In this article, we present a novel approach to reconstruct the topology of networked linear
dynamical systems with latent nodes. The network is allowed to have directed loops and bi …

Physics-informed learning for high impedance faults detection

W Li, D Deka - 2021 IEEE Madrid PowerTech, 2021 - ieeexplore.ieee.org
High impedance faults (HIFs) in distribution grids may cause wildfires and threaten human
lives. Conventional protection relays at substations fail to detect more than 10% HIFs since …

Information Theoretically Optimal Sample Complexity of Learning Dynamical Directed Acyclic Graphs

MS Veedu, D Deka, M Salapaka - … Conference on Artificial …, 2024 - proceedings.mlr.press
In this article, the optimal sample complexity of learning the underlying interactions or
dependencies of a Linear Dynamical System (LDS) over a Directed Acyclic Graph (DAG) is …

Causal Discovery for Topology Reconstruction in Industrial Chemical Processes

H Dewantoro, A Smith, P Daoutidis - Industrial & Engineering …, 2024 - ACS Publications
This paper explores the application of causal discovery frameworks to infer the topology of
industrial chemical processes, which is crucial for operational decision-making and system …

Distributed network reconstruction based on binary compressed sensing via ADMM

Y Liu, K Huang, C Yang, Z Wang - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
At present, network model is a general framework for the representation of complex system,
and its structure is the fundamental and prerequisite for control and other applications of …

Topology identification under spatially correlated noise

MS Veedu, MV Salapaka - Automatica, 2023 - Elsevier
This article addresses the problem of reconstructing the topology of a network of agents
interacting via linear dynamics, while being excited by exogenous stochastic sources that …