Acoustic Emission-Based Pipeline Leak Detection and Size Identification Using a Customized One-Dimensional DenseNet

Sensors, Journal Year: 2025, Volume and Issue: 25(4), P. 1112 - 1112

Published: Feb. 12, 2025

Effective leak detection and size identification are essential for maintaining the operational safety, integrity, longevity of industrial pipelines. Traditional methods often suffer from high noise sensitivity, limited adaptability to non-stationary signals, excessive computational costs, which limits their feasibility real-time monitoring applications. This study presents a novel acoustic emission (AE)-based pipeline approach, integrating Empirical Wavelet Transform (EWT) adaptive frequency decomposition with customized one-dimensional DenseNet architecture achieve precise classification. The methodology begins EWT-based signal segmentation, isolates meaningful bands enhance leak-related feature extraction. To further improve quality, thresholding denoising techniques applied, filtering out low-amplitude while preserving critical diagnostic information. denoised signals processed using DenseNet-based deep learning model, combines convolutional layers densely connected propagation extract fine-grained temporal dependencies, ensuring accurate classification presence severity. Experimental validation was conducted on real-world AE data collected under controlled non-leak conditions at varying pressure levels. proposed model achieved an exceptional accuracy 99.76%, demonstrating its ability reliably differentiate between normal operation multiple severities. method effectively reduces costs robust performance across diverse operating environments.

Language: Английский

---

Application of machine learning to leakage detection of fluid pipelines in recent years: A review and prospect

Measurement, Journal Year: 2025, Volume and Issue: unknown, P. 116857 - 116857

Published: Jan. 1, 2025

Language: Английский

---

Leak detection and localization in water distribution systems using advanced feature analysis and an Artificial Neural Network

Desalination and Water Treatment, Journal Year: 2024, Volume and Issue: 320, P. 100685 - 100685

Published: Aug. 3, 2024

This study capitalizes on a dataset, originally including 280 sensory measurements from laboratory-scale water distribution system, to advance the concept of leakage diagnosis and localization. The test rig are formulated in two configurations, namely looped branched layouts. paper processed time-domain data accelerometers dynamic pressure sensors into advanced statistical features of: Autocorrelation Coefficient (Au-C), Signal Energy (Sig-E), detect localize leakage. By Employment these features, research developed an expert system Artificial Neural Network (ANN) model designed with optimal parameters, neurons, hidden layers classify presence pinpoint location leaks within rig. effectiveness current approach is quantitatively evaluated using F1-scores accuracy metrics. A robust capability for both detecting localizing under varying conditions was established highest F1-score 86.5 % 86.2 %, respectively. findings underscore potential integrating Intelligence (AI) enhancing reliability dependability management systems. contributes broader application AI managing resources infrastructure resilience its support improve whereabouts.

Language: Английский

---

Condition-based monitoring techniques and algorithms in 3d printing and additive manufacturing: a state-of-the-art review

Progress in Additive Manufacturing, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 15, 2024

Language: Английский

---

Parallel Multi-Layer Sensor Fusion for Pipe Leak Detection Using Multi-Sensors and Machine Learning

Published: Jan. 1, 2025

Pipe leak detection is essential for maintaining the integrity and efficiency of water distribution systems, preventing structural damages such as sinkholes caused by leakage. Sensor-based approaches have proven effective in accurately identifying locating leaks. However, existing techniques typically rely on single sensors, despite potential advantages multi-sensor systems that can leverage diverse phenomena associated with This study introduces a machine learning-based sensor fusion method pipe provides comprehensive experimental validation using three widely used sensors: hydrophone, acoustic emission, vibration sensors. The compares performance single-sensor approach proposed approach, evaluating classification accuracy across various locations. results show significantly improves accuracy, especially complex environments multiple noise sources. research offers valuable insights into optimal sensor-machine learning pairings, providing robust framework developing more reliable efficient systems.

Language: Английский

---

A Lightweight Drone Detection Method Integrated into a Linear Attention Mechanism Based on Improved YOLOv11

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(4), P. 705 - 705

Published: Feb. 19, 2025

The timely and accurate detection of unidentified drones is vital for public safety. However, the unique characteristics in complex environments varied postures they may adopt during approach present significant challenges. Additionally, deep learning algorithms often require large models substantial computational resources, limiting their use on low-capacity platforms. To address these challenges, we propose LAMS-YOLO, a lightweight drone method based linear attention mechanisms adaptive downsampling. model’s design, inspired by CPU optimization, reduces parameters using depthwise separable convolutions efficient activation functions. A novel mechanism, incorporating an LSTM-like gating system, enhances semantic extraction efficiency, improving performance scenarios. Building insights from dynamic convolution multi-scale fusion, new downsampling module developed. This efficiently compresses features while retaining critical information. improved bounding box loss function introduced to enhance localization accuracy. Experimental results demonstrate that LAMS-YOLO outperforms YOLOv11n, achieving 3.89% increase mAP 9.35% reduction parameters. model also exhibits strong cross-dataset generalization, striking balance between accuracy efficiency. These advancements provide robust technical support real-time monitoring.

Language: Английский

---

Smart Water Distribution Management Using Machine Learning Techniques

Lecture notes on data engineering and communications technologies, Journal Year: 2025, Volume and Issue: unknown, P. 275 - 284

Published: Jan. 1, 2025

---

Machine learning‐based leakage identification in water distribution system

Water and Environment Journal, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 26, 2025

Abstract Ensuring access to clean water in urban areas is challenging due leaks and contamination complex distribution systems (WDS). Traditional leak detection methods are slow, costly, time‐consuming not very efficient, motivating the need for advanced solutions. Therefore, this study mainly focuses on Machine learning (ML)‐based method localization by leveraging network data. Method uses emitter coefficients simulate loss evaluates ML models, including K‐nearest neighbour (KNN), Random Forest Support Vector (SVM), two example networks EPANET Network 3 real‐life of National Institute Technology Kurukshetra campus. achieved accuracy scores 88.13% 95.84% NIT network, with Area Under Curve (AUC) 0.87 0.98, respectively. The results highlight model's effectiveness detecting localizing leaks, contributing efficient management. Further, advantages limitations discussed. future applications these models real‐world problem.

Language: Английский

---

Combined L-Band Polarimetric SAR and GPR Data to Develop Models for Leak Detection in the Water Pipeline Networks

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(8), P. 1386 - 1386

Published: April 14, 2025

Water pipeline leak detection in a fast and accurate way is of much importance for water utility companies the general public. At present, rapid development remote sensing computer technologies makes it possible to detect leaks on large scale efficiently timely. The leakage will cause an increase content dielectric constant soil around pipeline, so feasible determine site by measuring subsurface relative (SSRDC). In this paper, we combine SAOCOM-1A L-band synthetic-aperture radar (SAR) ground-penetrating (GPR) data develop regression models that predict SSRDC values. model features are selected with Boruta wrapper algorithm based images after pre-processing, values at sampling locations within research area calculated reflected wave method GPR data. We evaluate multiple linear (MLR), random forest (RF), multi-layer perceptron neural network (MLPNN) their ability using features. experimental results show MLPNN (R2 = 0.705, RMSE 1.936, MAE 1.664) can better estimate Further, main urban Tianjin, China, which has system, SSDRC obtained best model, where predicted exceeded certain threshold were considered potential locations. empirical indicate encouraging proposed locate leaks. This provide new avenue monitoring treatment

Language: Английский

---

Frequency-informed transformer for real-time water pipeline leak detection

Autonomous Intelligent Systems, Journal Year: 2025, Volume and Issue: 5(1)

Published: April 27, 2025

Abstract Water pipeline leaks pose significant risks to urban infrastructure, leading water wastage and potential structural damage. Existing leak detection methods often face challenges, such as heavily relying on the manual selection of frequency bands or complex feature extraction, which can be both labour-intensive less effective. To address these limitations, this paper introduces a Frequency-Informed Transformer model, integrates Fast Fourier Transform self-attention mechanisms enhance pipe accuracy. Experimental results show that FiT achieves 99.9% accuracy in 98.7% type classification, surpassing other models processing speed, with an efficient response time 0.25 seconds. By significantly simplifying key features band improving time, proposed method offers solution for real-time detection, enabling timely interventions more effective safety management.

Language: Английский

---