From Model, Signal to Knowledge: A Data-Driven Perspective of Fault Detection and Diagnosis

By Xuewu Dai, Zhiwei Gao. IEEE Transactions on Industrial Informatics, 2013

651 citations recorded by the source corpus.

Subfields: Control and Systems Engineering, Mechanical Engineering

View Paper: https://www.semanticscholar.org/paper/edb8803e25d280a799023c46dd1ab9531b86c03a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Control and Systems Engineering

In Mechanical Engineering

Citations in the corpus

Real-Time Motor Fault Detection by 1-D Convolutional Neural Networks (2016, methodology): “quantitative methods on the basis of machine-learning intelligence [3].”
A New Convolutional Neural Network-Based Data-Driven Fault Diagnosis Method (2018, background): “FAULT diagnosis has attracted many studies in the recent years [1], [2].”
A Review on Basic Data-Driven Approaches for Industrial Process Monitoring (2014, positive): “Because of their simple forms and low design efforts compared with the model-based techniques, the multivariate statistical methods are widely used for process monitoring in numerous industrial applications [35]–[40].”
MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks (2019, background): “However, they are only effective for highly correlated data, and require the data to follow multivariate Gaussian distribution [16].”
A transfer convolutional neural network for fault diagnosis based on ResNet-50 (2019, background): “The intelligent learning ability from a vast volume of historic data is the key characteristic of data-driven fault diagnosis method [5, 6].”
A Survey of Fault Diagnosis and Fault-Tolerant Techniques—Part II: Fault Diagnosis With Knowledge-Based and Hybrid/Active Approaches (2015, background): “in the late 1960s as a branch of artificial intelligence, which is a rule-based system by presenting a human’s expertise in a set of rules [2], [3].”
A Review of Fault Detection and Diagnosis for the Traction System in High-Speed Trains (2020, methodology): “ods for high-speed trains fall into three main categories [55]: time-domain methods, frequency-domain methods, and timefrequency-domain methods.”
Understanding and Learning Discriminant Features based on Multiattention 1DCNN for Wheelset Bearing Fault Diagnosis (2020, methodology): “domain, and time–frequency domain [1] are extracted from monitoring signals by Hilbert–Huang transform [2], empirical mode decomposition [3], or local mean decomposition [4].”
Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series (2018, methodology): “However, these unsupervised methods are only effective to highly correlated data, and require the data to follow multivariate Gaussian distribution [28].”
Adaptive Fault-Tolerant Tracking Control for Linear and Lipschitz Nonlinear Multi-Agent Systems (2015, background): “For large-scale multi-agent networks, the actuator in every agent may not work in the ideal way due to the presence of unexpected failures [5], [6].”
A New Deep Transfer Learning Based on Sparse Auto-Encoder for Fault Diagnosis (2019, methodology): “As a typical kind of fault diagnosis, datadriven fault diagnosis has attracted many studies in recent years [2].”