Fault Detection and Isolation in Industrial Networks using Graph Convolutional Neural Networks

Khorasgani, Hamed; Hasanzadeh, Arman; Farahat, Ahmed K.; Gupta, Chetan

doi:10.1109/icphm.2019.8819403

Cited by 23 publications

(15 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In addition, the traditional methods do not consider the network structure when designing the fault diagnosis, which causes over-fitting problems. To solve these problems, the connected components in power systems can be represented as a weighted undirected graph structure [72]. Then, local relationships between power variables in different components of the distribution network are explored by GCNs to improve fault detection and isolation.…”

Section: ) Fault Detection and Isolationmentioning

confidence: 99%

A Review of Graph Neural Networks and Their Applications in Power Systems

Liao

Bak‐Jensen

Pillai

et al. 2022

Journal of Modern Power Systems and Clean Energy

165

View full text Add to dashboard Cite

Deep neural networks have revolutionized many machine learning tasks in power systems, ranging from pattern recognition to signal processing. The data in these tasks are typically represented in Euclidean domains. Nevertheless, there is an increasing number of applications in power systems, where data are collected from non-Euclidean domains and represented as graph-structured data with high-dimensional features and interdependency among nodes. The complexity of graph-structured data has brought significant challenges to the existing deep neural networks defined in Euclidean domains. Recently, many publications generalizing deep neural networks for graphstructured data in power systems have emerged. In this paper, a comprehensive overview of graph neural networks (GNNs) in power systems is proposed. Specifically, several classical paradigms of GNN structures, e. g., graph convolutional networks, are summarized. Key applications in power systems such as fault scenario application, time-series prediction, power flow calculation, and data generation are reviewed in detail. Furthermore, main issues and some research trends about the applications of GNNs in power systems are discussed.

show abstract

Section: ) Fault Detection and Isolationmentioning

confidence: 99%

A Review of Graph Neural Networks and Their Applications in Power Systems

Liao

Bak‐Jensen

Pillai

et al. 2022

Journal of Modern Power Systems and Clean Energy

165

View full text Add to dashboard Cite

show abstract

“…We define a graph with n nodes as, G = { V , Ā}, where V = [v 1 , v 2 , ...v n ] is the matrix of the node embedding in the graph, v i is the node embedding for node i. The edges of a graph are represented by the adjacency matrix, Ā, where each [29] unsupervised 3D shape retrieval [30] Optimization optimize scheduling performance of flexible manufacturing systems [31] find the optimum scheduling policy for job-shop problems [32] Monitoring detect and isolate faulty components in industrial systems [33] improve product failure prediction [34] share multi-level manufacturing knowledge within a system [35] predict the remaining useful life estimation of industrial equipment [36] value a ij corresponds to the relation between nodes i and j.…”

Section: A Preliminaries On Graph Learningmentioning

confidence: 99%

“…In [31], [32], it is shown that graph learning can be used to optimize scheduling performance during operation. In monitoring systems, graph learning has been shown to improve detection and prediction of failures in both products and equipment [33], [34], [36]. While these demonstrations highlight the opportunities that lie for graph learning in manufacturing systems, the graph learning systems that these works develop are restricted to specific applications.…”

Section: B Graph Learning In Manufacturingmentioning

confidence: 99%

Graph Learning for Cognitive Digital Twins in Manufacturing Systems

Mortlock¹,

Muthirayan²,

Yu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Future manufacturing requires complex systems that connect simulation platforms and virtualization with physical data from industrial processes. Digital twins incorporate a physical twin, a digital twin, and the connection between the two. Benefits of using digital twins, especially in manufacturing, are abundant as they can increase efficiency across an entire manufacturing life-cycle. The digital twin concept has become increasingly sophisticated and capable over time, enabled by rises in many technologies. In this paper, we detail the cognitive digital twin as the next stage of advancement of a digital twin that will help realize the vision of Industry 4.0. Cognitive digital twins will allow enterprises to creatively, effectively, and efficiently exploit implicit knowledge drawn from the experience of existing manufacturing systems. They also enable more autonomous decisions and control, while improving the performance across the enterprise (at scale). This paper presents graph learning as one potential pathway towards enabling cognitive functionalities in manufacturing digital twins. A novel approach to realize cognitive digital twins in the product design stage of manufacturing that utilizes graph learning is presented.

show abstract

“…We use the simulated water tank system dataset (Khorasgani et al, 2019) to demonstrate and validate the performance of our method. This dataset includes a network of water tanks.…”

Section: Water Tank Data Studymentioning

confidence: 99%

“…But the responses in all these papers are continuous multivariate variables rather than multivariate binary variables, which are not applicable to failure prediction. Other researchers employ existing network structure of physical models (Khorasgani, Farahat, Hasanzade, & Gupta, 2019) as one of the inputs for failure prediction. However, in reality we may not be able to obtain the graph structure inside a system or among devices.…”

Section: Introductionmentioning

confidence: 99%

Multivariate Bernoulli Logit-Normal Model for Failure Prediction

et al. 2019

Self Cite

View full text Add to dashboard Cite

The failures among connected devices that are geographically close may have correlations and even propagate from one to another. However, there is little research to model this prob- lem due to the lacking of insights of the correlations in such devices. Most existing methods build one model for one de- vice independently so that they are not capable of captur- ing the underlying correlations, which can be important in- formation to leverage for failure prediction. To address this problem, we propose a multivariate Bernoulli Logit-Normal model (MBLN) to explicitly model the correlations of devices and predict failure probabilities of multiple devices simulta- neously. The proposed method is applied to a water tank data set where tanks are connected in a local area. The results indicate that our proposed method outperforms baseline ap- proaches in terms of the prediction performance such as ROC.

show abstract

Fault Detection and Isolation in Industrial Networks using Graph Convolutional Neural Networks

Cited by 23 publications

References 7 publications

A Review of Graph Neural Networks and Their Applications in Power Systems

A Review of Graph Neural Networks and Their Applications in Power Systems

Graph Learning for Cognitive Digital Twins in Manufacturing Systems

Multivariate Bernoulli Logit-Normal Model for Failure Prediction

Contact Info

Product

Resources

About