Self-supervised learning for time series analysis: Taxonomy, progress, and prospects
Self-supervised learning (SSL) has recently achieved impressive performance on various
time series tasks. The most prominent advantage of SSL is that it reduces the dependence …
time series tasks. The most prominent advantage of SSL is that it reduces the dependence …
Self-supervised learning for time series analysis: Taxonomy, progress, and prospects
Self-supervised learning (SSL) has recently achieved impressive performance on various
time series tasks. The most prominent advantage of SSL is that it reduces the dependence …
time series tasks. The most prominent advantage of SSL is that it reduces the dependence …
Optimization of the control performance of a novel 3/2 water proportional directional valve with a special position following servo mechanism
Y Liao, W Zhao, J Feng, Z Lian - IEEE/ASME Transactions on …, 2024 - ieeexplore.ieee.org
The 3/2 water proportional directional valve (PDV) is an important hydraulic component to
ensure a precise, low impact, and safety control of hydraulic powered roof support, which …
ensure a precise, low impact, and safety control of hydraulic powered roof support, which …
Debiased Contrastive Learning With Supervision Guidance for Industrial Fault Detection
The time series self-supervised contrastive learning framework has succeeded significantly
in industrial fault detection scenarios. It typically consists of pretraining on abundant …
in industrial fault detection scenarios. It typically consists of pretraining on abundant …
Unraveling the 'Anomaly'in time series anomaly detection: a self-supervised tri-domain solution
The ongoing challenges in time series anomaly detection (TSAD), including the scarcity of
anomaly labels and the variability in anomaly lengths and shapes, have led to the need for a …
anomaly labels and the variability in anomaly lengths and shapes, have led to the need for a …
Unraveling theAnomaly'in Time Series Anomaly Detection: A Self-supervised Tri-domain Solution
The ongoing challenges in time series anomaly detection (TSAD), notably the scarcity of
anomaly labels and the variability in anomaly lengths and shapes, have led to the need for a …
anomaly labels and the variability in anomaly lengths and shapes, have led to the need for a …
Stiction detection and recurrence analysis for control valves by phase space reconstruction method
A Guan, F **ang, Z Li, C Liu, Z Lin, Z **… - Advanced Engineering …, 2025 - Elsevier
Valve stiction is a common and persistent fault of industrial loops in process control. The
loop oscillations caused by valve stiction pose economic and safety risks to the production …
loop oscillations caused by valve stiction pose economic and safety risks to the production …
An Automated Diagnostic Framework for Multiple Oscillations With Median Complementary EEMD
The detection and diagnosis of oscillation are of great importance to maintain the control
performance of the process plant. Even though some algorithms based on time-frequency …
performance of the process plant. Even though some algorithms based on time-frequency …
Debiased Contrastive Learning for Time-Series Representation Learning and Fault Detection
Building reliable fault detection systems through deep neural networks is an appealing topic
in industrial scenarios. In these contexts, the representations extracted by neural networks …
in industrial scenarios. In these contexts, the representations extracted by neural networks …
Self-Supervised Multiple Faults Detection Method Based on Time–Frequency Feature Fusion With Unlabeled Wind Turbine Samples
Q Xu, D Ma, Y Liu, Q Wang - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Fault detection is an essential aspect of power generation in wind turbines (WTs). However,
existing fault detection methods are developed specifically for identifying a single type of …
existing fault detection methods are developed specifically for identifying a single type of …