Modeling IoT Equipment With Graph Neural Networks

Zhang, Weishan; Zhang, Yafei; Xu, Liang; Zhou, Jiehan; Liu, Yan; Gu, Mu; Liu, Xin; Yang, Su

doi:10.1109/access.2019.2902865

Cited by 32 publications

(21 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, (Huang, Zanni-Merk, and Crémilleux 2019) propose using dense layers connected as per the ontology of the manufacturing line, followed by an RNN at the top to capture the temporal dependencies. Similarly, (Zhang et al 2019) attempt to model an equipment as a graph of sensor nodes: they assume a fully-connected graph where nodes correspond to sensors, and edges capture the dependencies across sensors. However, they do not explicitly model the dependence between various modules of an equipment.…”

Section: Related Workmentioning

confidence: 99%

Graph Neural Networks for Leveraging Industrial Equipment Structure: An application to Remaining Useful Life Estimation

Narwariya,

Malhotra,

et al. 2020

Preprint

View full text Add to dashboard Cite

Automated equipment health monitoring from streaming multi-sensor time series data can be used to enable conditionbased maintenance, avoid sudden catastrophic failures, and ensure high operational availability. We note that most complex machinery has a well-documented and readily accessible underlying structure capturing the inter-dependencies between sub-systems or modules. Deep learning models such as those based on recurrent neural networks (RNNs) or convolutional neural networks (CNNs) fail to explicitly leverage this potentially rich source of domain-knowledge into the learning procedure. In this work, we propose to capture the structure of a complex equipment in the form of a graph, and use graph neural networks (GNNs) to model multi-sensor time series data. Using remaining useful life estimation as an application task, we evaluate the advantage of incorporating the graph structure via GNNs on the publicly available turbofan engine benchmark dataset. We observe that the proposed GNN-based RUL estimation model compares favorably to several strong baselines from literature such as those based on RNNs and CNNs. Additionally, we observe that the learned network is able to focus on the module (node) with impending failure through a simple attention mechanism, potentially paving the way for actionable diagnosis.

show abstract

Section: Related Workmentioning

confidence: 99%

Graph Neural Networks for Leveraging Industrial Equipment Structure: An application to Remaining Useful Life Estimation

Narwariya,

Malhotra,

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…[34]. The graph neural networks are widely used in different domains due to its convincing performance and interpretability [35]. Convolutional neural networks (CNNs) can be considered as the first motivation for the GNNs, as CNNs have the ability to extract multi-scale localized spatial features and compose them to construct highly expressive representation [34].…”

Section: B: Graph Neural Network (Gnn)mentioning

confidence: 99%

Additive Angular Margin Loss in Deep Graph Neural Network Classifier for Learning Graph Edit Distance

et al. 2020

View full text Add to dashboard Cite

The recent success of graph neural networks (GNNs) in the area of pattern recognition (PR) has increased the interest of researchers to use these frameworks in non-euclidean structures. This noneuclidean structure includes graphs or manifolds that are called geometric deep learning (GDL). It has opened a new direction for researchers to deal with graphs using deep learning in document processing, outperforming conventional methods. We propose a Deep Graph Neural Network (DGNN) classifier-based on additive angular margin loss for the classification task in document analysis. Another contribution of this work is to investigate the performance of a DGNN as a classifier using different loss functions, which helps to minimize the loss for the document analysis problem. We compare additive angular margin loss, Cosine angular margin loss, and multiplicative angular margin loss. Furthermore, we give a comparison between the mentioned loss functions and the Softmax loss function. We also present the comparisons of results using different graph edit distance (GED) methods. Our quantitative results suggest, that by applying the additive angular marginal loss function makes more compact intra-class ability and increases the inter-class discrepancy which enhances the discriminating power of the DGNN. Enhancing the decision boundaries between the classes increase the intra-class compactness and inter-class discrimination power of the model.

show abstract

“…However, most of the non-linear models ignored global information of the system. In addition, complicated models [24] are easy to get overfitted when training data are relatively in a small size.…”

Section: B Non-linear Algorithmmentioning

confidence: 99%

MetroEye: A Weather-Aware System for Real-Time Metro Passenger Flow Prediction

Wang

Leng

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Real-time passenger flow prediction plays an important role in subway network design and management. Most of the existing prediction algorithms only consider the sequence of passenger flow volume, however, ignore the influence of other outer factors, for example, the weather conditions, air quality and temperature. In this paper, a systematic framework, MetroEye, is proposed for weather-aware prediction of real-time passenger flow. The framework contains an offline system and an online system. The offline system adopts a conditional random field (CRF) model to establish the relationship between passenger flow volume and weather factors. Experimental results show the superior prediction accuracy of the model, especially in large stations. The online system provides efficient methods to simulate the real-time passenger flow volume. Due to its high practicality, MetroEye has been adopted by Beijing Urban Rail Transit Control Center to monitor the passenger flow status of the Beijing subway system.

show abstract

Modeling IoT Equipment With Graph Neural Networks

Cited by 32 publications

References 33 publications

Graph Neural Networks for Leveraging Industrial Equipment Structure: An application to Remaining Useful Life Estimation

Graph Neural Networks for Leveraging Industrial Equipment Structure: An application to Remaining Useful Life Estimation

Additive Angular Margin Loss in Deep Graph Neural Network Classifier for Learning Graph Edit Distance

MetroEye: A Weather-Aware System for Real-Time Metro Passenger Flow Prediction

Contact Info

Product

Resources

About