Elman neural network considering dynamic time delay estimation for short-term forecasting of offshore wind power

Applied Energy, Год журнала: 2024, Номер 358, С. 122671 - 122671

Опубликована: Янв. 21, 2024

Язык: Английский

---

Optimized modal decomposition techniques for robust leakage detection in noisy environments: A comparative study

Measurement, Год журнала: 2025, Номер unknown, С. 117390 - 117390

Опубликована: Март 1, 2025

---

Microleakage Acoustic Emission Monitoring of Pipeline Weld Cracks under Complex Noise Interference: A Feasible Framework

Journal of Sound and Vibration, Год журнала: 2025, Номер unknown, С. 118980 - 118980

Опубликована: Янв. 1, 2025

Язык: Английский

---

Leak detection in pipelines based on acoustic emission and growing neural gas network utilizing unlabeled healthy condition data

Flow Measurement and Instrumentation, Год журнала: 2025, Номер unknown, С. 102816 - 102816

Опубликована: Янв. 1, 2025

Язык: Английский

---

Pipeline leak location method based on SSA-VMD with generalized quadratic cross-correlation

Measurement Science and Technology, Год журнала: 2024, Номер 35(11), С. 116105 - 116105

Опубликована: Июль 22, 2024

Abstract Natural gas pipelines are an essential part of the economy. may leak after aging, strong vibration signals be generated in pipeline when leakage occurs, and noisy. Traditional variational mode decomposition (VMD) noise reduction methods need to set parameters advance, so not achieve best effect. To solve this problem, paper proposes a method for location based on sparrow search algorithm (SSA) optimization VMD combined with generalized quadratic cross-correlation. The first calculates original signal-to-noise ratio (SNR), if SNR is low, wavelet threshold denoising used process signal. Then, SSA refine two key (penalty parameter α number K ) sample entropy. Subsequently, signal undergoes into intrinsic function (IMF) components through according obtained analysis combination. IMF screened obtain reconstructed Finally, obtained. delay cross-correlation accurate position using delay. Experiments showed that minimum relative error could reach 0.6%, which was more than traditional method, effectively improved accuracy noisy locations.

Язык: Английский

---

Acoustic emission-based weld crack leakage monitoring via FGI and MCCF-CondenseNet convolutional neural network

NDT & E International, Год журнала: 2024, Номер 148, С. 103232 - 103232

Опубликована: Сен. 3, 2024

Язык: Английский

---

An incremental learning framework for pipeline weld crack damage identification and leakage rate prediction

Engineering Applications of Computational Fluid Mechanics, Год журнала: 2024, Номер 18(1)

Опубликована: Сен. 26, 2024

Язык: Английский

---

Interpretable contour encoding network customized for acoustic emission adaptive cepstrum in laser shock peening monitoring

Journal of Manufacturing Processes, Год журнала: 2024, Номер 132, С. 224 - 237

Опубликована: Ноя. 4, 2024

Язык: Английский

---

A multi-source heterogeneous information fusion network for comprehensive assessment of spot welding quality

Journal of Manufacturing Processes, Год журнала: 2025, Номер 135, С. 142 - 160

Опубликована: Янв. 18, 2025

Язык: Английский

---

Multi-point estimation weldment recognition and estimation of pose with data-driven robotics design

Nonlinear Engineering, Год журнала: 2025, Номер 14(1)

Опубликована: Янв. 1, 2025

Abstract In robotic welding systems, weldment recognition and pose estimation play crucial roles in achieving precision efficiency. Weldment involves identifying classifying different types of weld joints components with high accuracy, often employing computer vision techniques machine learning algorithms trained on diverse datasets. Concurrently, determines the precise position orientation torch relative to weldment, which is for ensuring proper alignment execution tasks. Hence, this study proposed a multi-point entropy (MPEE) model estimation. The MPEE computes design data-driven points. estimates features. With estimated points Weldmart, are tracked fault detection. Through approach, employed robotics. specifically addresses challenge focuses estimating multiple within design. By leveraging integrates models, enhances accuracy reliability point results stated that dataset comprising joint variations, system achieves over 95% real-time applications. geometric hashing iterative closest enables an average error margin less than 1 mm.

Язык: Английский

---