Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Insufficient Data Generative Model for Pipeline Network Leak Detection Using Generative Adversarial Networks.

Huaguang Zhang, Xuguang Hu, Dazhong Ma

IEEE Transactions on Cybernetics

|December 9, 2020

Summary

This summary is machine-generated.

Related Concept Videos

Leaky Scanning

Leaky Scanning

During most eukaryotic translation processes, the small 40S ribosome subunit scans an mRNA from its 5' end until it encounters the first start AUG codon. The large 60S ribosomal subunit then joins the smaller one to initiate protein synthesis. The location of the translation initiation is largely determined by the nucleotides near the start codon as there may be multiple translation initiation sites present on the mRNA. Marilyn Kozak discovered that the sequence RCCAUGG (where R...

Minor Losses in Pipes

Minor Losses in Pipes

In pipe systems, minor losses refer to energy losses arising from components such as valves, bends, fittings, expansions, and other features that disrupt the steady flow of fluid. These disturbances cause energy dissipation through turbulence and resistance, which engineers quantify to manage system efficiency effectively.
Valves play a significant role in generating minor losses by obstructing or redirecting the fluid flow. When a valve is closed or partially closed, it restricts the flow...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Anti-Disturbance Intermediate Observer-Based Fault Estimation and Fault-Tolerant Control for Markovian Jump Systems.

IEEE transactions on cybernetics·2026

Same author

A novel dynamic signal Lemma for predefined-time stabilization of high-order nonlinear systems with dynamic uncertainties.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

Observer-Based Fuzzy Secure Control for High-Order MASs Against Communication Delays Under Jointly Connected Switching Topology.

IEEE transactions on cybernetics·2026

Same author

TSFA: A Two-Stage Feature Alignment Method for Unsupervised Open-Set Domain Adaptation in Time-Series Classification.

IEEE transactions on neural networks and learning systems·2026

Same author

Optimal Containment Control for Stochastic Multiagent Systems via Simplified ADP Under Secure Communication.

IEEE transactions on cybernetics·2026

Same author

Constraint-Based Fuzzy Adaptive Security Formation Control for Nonlinear Multiagent Systems Against Deception Attacks.

IEEE transactions on cybernetics·2025

Same journal

An Evolutionary Algorithm Assisted by an Ensemble of Pareto-Optimal Surrogate Models.

IEEE transactions on cybernetics·2026

Same journal

A Quantum Self-Attention Neural Network Model on Quantum Circuits.

IEEE transactions on cybernetics·2026

Same journal

Semi-Explicit Solution of Some Discrete-Time Higher-Order-Cost Mean-Field-Type Control.

IEEE transactions on cybernetics·2026

Same journal

A Novel One-Step Small Object Detector for Autonomous Aerial Vehicles.

IEEE transactions on cybernetics·2026

Same journal

Online Data-Driven-Based Optimal Output Tracking Control Without Initial Stabilizing Policy.

IEEE transactions on cybernetics·2026

Same journal

Digital Redesign-Based Interval State Estimation for Continuous Systems With Aperiodic Discrete Measurements.

IEEE transactions on cybernetics·2026

See all related articles

This study introduces mixed generative adversarial networks (mixed-GANs) to generate reliable synthetic leak data for pipeline leak detection. This approach enhances data quantity, credibility, and variety, improving model accuracy.

Area of Science:

Engineering
Artificial Intelligence
Data Science

Background:

Existing datasets lack sufficient effective leak data for training accurate pipeline leak detection models.
The scarcity of reliable data hinders the development of robust machine learning solutions.

Purpose of the Study:

To propose a novel method for generating synthetic leak data to overcome data limitations in pipeline leak detection.
To enhance the accuracy and reliability of pipeline leak detection models through data augmentation.

Main Methods:

Development of multitype generative networks with heterogeneous parameter-updating mechanisms.
Incorporation of expert-driven data constraints to evaluate generated leak data quality.
Integration of particle swarm optimization (PSO) for generative model training, outperforming gradient descent.

Related Experiment Videos

Main Results:

Mixed-GANs successfully generated satisfactory leak data across various scenarios.
The proposed method demonstrated superior generation performance compared to conventional algorithms.
Generated data contributed to increased data quantity, credibility, and variety for training.

Conclusions:

The mixed-GANs approach effectively addresses the data scarcity issue in pipeline leak detection.
The method provides a reliable way to augment datasets, leading to improved model performance.
This work offers a valuable contribution to the field of intelligent pipeline monitoring and safety.