Ultrasonic Data Research Articles

Deep learning for full-field ultrasonic characterization

This study takes advantage of recent advances in machine learning to establish a physics-based data analytic platform for distributed reconstruction of mechanical properties in layered components from full waveform data. In this vein, two logics, namely the direct inversion and physics-informed neural networks (PINNs), are explored. The direct inversion entails three steps: (i) spectral denoising and differentiation of the full-field data, (ii) building appropriate neural maps to approximate the profile of unknown physical and regularization parameters on their respective domains, and (iii) simultaneous training of the neural networks by minimizing the Tikhonov-regularized PDE loss using data from (i). PINNs furnish efficient surrogate models of complex systems with predictive capabilities via multitask learning where the field variables are modeled by neural maps endowed with (scaler or distributed) auxiliary parameters such as physical unknowns and loss function weights. PINNs are then trained by minimizing a measure of data misfit subject to the underlying physical laws as constraints. In this study, to facilitate learning from ultrasonic data, the PINNs loss adopts (a) wavenumber-dependent Sobolev norms to compute the data misfit, and (b) non-adaptive weights in a specific scaling framework to naturally balance the loss objectives by leveraging the form of PDEs germane to elastic-wave propagation. Both paradigms are examined via synthetic and laboratory test data. In the latter case, the reconstructions are performed at multiple frequencies and the results are verified by a set of complementary experiments highlighting the importance of verification and validation in data-driven modeling.

Retracted: Detection and Analysis of Man-Machine Interactive Software Vulnerabilities Based on Ultrasonic Data Acquisition and Signal Processing Algorithms

Retracted: Detection and Analysis of Man-Machine Interactive Software Vulnerabilities Based on Ultrasonic Data Acquisition and Signal Processing Algorithms

In Situ Ultrasonic Measurements as a Tool to Characterize the Stages of the Zeolite A Crystallization Process

AbstractZeolite A (LTA) was synthesized at 80 °C under hydrothermal conditions from a gel with the molar composition of 2.5 Na2O : 2 SiO2 : Al2O3 : 80 H2O. In the present study, we report the use of home‐made ultrasound devices as a real‐time, in situ diagnostic tool for monitoring the progress of zeolite formation. In addition, the specific aim of this study was to show that the measured ultrasound parameters – ultrasonic (US) velocity and attenuation – simultaneously provide independent information about the changes in the liquid and solid phase, respectively, during the crystallization process. Both views are necessary for extracting kinetic data about the zeolite crystallization processes and allow elucidating the different stages of zeolite LTA formation process. The obtained in situ US data were compared with conventional ex situ powder X‐ray diffraction measurements following the formation of zeolite LTA from dense gels. The results demonstrate that a good correlation exists between the crystallization progress of zeolite LTA in terms of crystallinity changes and the ultrasonic attenuation and velocity.

Damage localization method using ultrasonic lamb waves and Wav2Vec2.0 neural network

In this paper, a Wav2Vec2.0 neural network based on an attention mechanism is proposed to locate defects in array ultrasonic testing signals. This method does not require knowledge of the a priori condition of the sample sound velocity or the feature extraction of ultrasonic scattering signals. First, an array piezoelectric ultrasonic testing system is used to detect a signal through hole defects at different positions in the plate structure. Then, three different neural networks—1D-CNN, Muti-Transformer, and Wav2Vec2.0—are used to locate the defects in the collected ultrasonic testing data. The performance of the network is verified with the data set collected through finite element simulation and the experimental system, and the identification accuracy and the calculation efficiency of different networks are compared and analyzed. To provide a solution for the poor balance of the experimental data set and the weak noise resistance of the simulation data set, a data set expansion method based on time domain transformation technology is proposed. The research results show that, the positioning accuracy of the Wav2Vec2.0 neural network proposed in this article is 98.46%, and the positioning accuracy is superior to Muti Transformer and ID-CNN.

XRD, FTIR and ultrasonic investigations of cadmium lead bismuthate glasses

Cadmium lead bismuthate glasses in the system xCdO–(1−x)[0.5PbO + 0.5Bi2O3](40 mol% ≤ x ≤ 90 mol%) were successfully prepared by melt-quenching method. The structural and elastic properties have been investigated using XRD, FTIR and ultrasonic pulse–echo techniques. The XRD patterns confirmed the amorphous nature of the samples prepared. Density and ultrasonic velocity data were used to evaluate various elastic properties. Addition of CdO gave rise to decreased density and molar volume and increased elastic moduli, micro-hardness, and Debye temperature. The FTIR analysis revealed that increasing CdO content enhances the BiO6 octahedral sites at the expense of the BiO3 and PbO4 units. This results in the formation of Pb–O–Bi(6) and Bi(3)–O–Bi(6) linkages in the glass network, which stiffen the structure and improve the elastic properties. A correlation between elastic and compositional parameters was achieved on the basis of theories and approaches in the field.

A Machine Learning Based-Guided Wave Approach for Damage Detection and Assessment in Composite Overwrapped Pressure Vessels

The applications of composite overwrapped pressure vessels (COPVs) in extreme conditions, such as storing hydrogen gases at very high pressure, impose new requirements related to the system's integrity and safety. The development of a structural health monitoring (SHM) system that allows for continuous monitoring of the COPVs provides rich information about the structural integrity of the component. Furthermore, the collected data can be used for different purposes such as increasing the periodic inspection intervals, providing a remaining lifetime prognosis, and also ensuring optimal operating conditions. Ultimately this information can be complementary to the development of the envisioned digital twin of the monitored COPVs. Guided waves (GWs) are preferred to be used in continuous SHM given their ability to travel in complex structures for long distances. However, obtained GW signals are complex and require advanced processing techniques. Machine learning (ML) is increasingly utilized as the main part of the processing pipeline to automatically detect anomalies in the system's integrity. Hence, in this study, we are scrutinizing the potential of using ML to provide continuous monitoring of COPVs based on ultrasonic GW data. Data is collected from a network of sensors consisting of fifteen Piezoelectric (PZT) wafers that were surface mounted on the COPV. Two ML algorithms are used in the automated evaluation procedure (i) a long short-term memory (LSTM) autoencoder for anomaly detection (defects/impact), and (ii) a convolutional neural network (CNN) model for feature extraction and classification of the artificial damage sizes and locations. Additional data augmentation steps are introduced such as modification and addition of random noise to original signals to enhance the model's robustness to uncertainties. Overall, it was shown that the ML algorithms used were able to detect and classify the simulated damage with high accuracy.

Viscometric, ultrasonic and FTIR approach of streptomycin sulphate in the aqueous medium of K3Cit and Na3Cit at various temperatures: A Drug-Drug intermolecular interaction study

The effect of electrolyte on antibiotic drug streptomycin sulfate has been investigated at five temperatures (298.15–318.15) K and 0.1 MPa atmospheric pressure. The influence of concentrations and temperatures on the viscometric and ultrasonic properties of K3Cit and Na3Cit with water has been studied. The experimentally obtained data of ultrasonic speed (u) and viscosity (η) of the solutions have been used to evaluate different parameters at the studied temperatures. A, called the Falkenhagen coefficient, and B, is the Jones-Dole coefficient, transfer viscosity B-Coefficient, ΔtrB, at various temperatures (298.15–318.15) K were assessed by viscosity data. The ultrasonic data and the parameter for instance apparent molar isentropic compressibility,Kϕ,S, limiting apparent molar isentropic compressibility,Kϕ,S0, and limiting apparent molar isentropic compressibility of transfer, ΔtrKϕ,S0 have been analysed to study the presence of molecular interactions at different temperatures. The spectroscopic data have been used to know the existence of Hydrogen-bonding and other types of solute and solvent interactions in the solution. All these parameters have been taken to observe the different forces of attraction, association, dissociation, and structure-making/breaking properties of the drug streptomycin sulphate in the K3Cit + Water and Na3Cit + Water solutions at said temperatures.

Tracking Sensor Location by Video Analysis in Double-Shell Tank Inspections

Double-shell tanks (DSTs) are a critical part of the infrastructure for nuclear waste management at the U.S. Department of Energy’s Hanford site. They are expected to be used for the interim storage of partially liquid nuclear waste until 2050, which is the target date for completing the immobilization process for all Hanford nuclear waste. At that time, DSTs will have been used about 15 years beyond their original projected lifetime. Consequently, for the next approximately 30 years, Hanford DSTs will undergo periodic nondestructive evaluation (NDE) to ensure their integrity. One approach to perform NDE is to use ultrasonic data from a robot moving through air slots, originally designed for cooling, in the confined space between primary and secondary tanks. Interpreting ultrasonic sensor output requires knowing where measurements were taken with a precision of approximately one inch. Analyzing video acquired during inspection is one approach to tracking sensor location. The top edge of an air slot is easily detected due to the difference in color and texture between the primary tank bottom and the air slot walls. A line fit to this edge is used in a model to calculate the apparent width of the air slot in pixels at targets near the top edge that can be recognized in video images. The apparent width of the air slot at the chosen target in a later video frame determines how far the robot has moved between those frames. Algorithms have been developed that automate target selection and matching in later frames. Tests in a laboratory mockup demonstrated that the method tracks the location of the ultrasonic sensor with the required precision.

Prediction of resilience and cohesion of deep-fried tofu by ultrasonic detection and LightGBM regression

An ultrasonic detection method combined with machine learning algorithms was proposed for the resilience and cohesion prediction as well as visualization of tofu during the deep-frying process. The ultrasonic data underwent preprocessing techniques including discrete wavelet transform, dimensionality reduction through PCA, and outlier handling using MCCV. Subsequently, four machine learning algorithms, namely XGBoost, Random Forest, LightGBM, and Artificial Neural Network, were employed to construct the model, and their prediction performances were compared. Results indicated that the combination of LightGBM and discrete wavelet transform yielded the best performance, with Rp2 values of 0.969 and 0.956, and RMSEP values of 1.81 and 2.11, respectively. These results satisfy the requirements for predicting the texture properties of deep-fried tofu. This method provided a novel, rapid, and efficient non-destructive approach for detecting the texture properties of deep-fried tofu, which could have practical applications in the food industry.

Real-Time AI driven Interpretation of Ultrasonic Data from Resistance Spot Weld Process Monitoring For Adaptive Welding

Adaptive resistance spot welding systems typically rely on real-time analysis of dynamic resistance curves and other indirect measurements to estimate weld progress and guide adaptive weld control algorithms. Though efficient, these approaches are not always reliable, and consequently there is a need for improved feedback systems to drive adaptive welding algorithms. As an alternative, an advanced in-line integrated ultrasonic monitoring system is proposed, with real-time weld process characterization driven by artificial intelligence (AI) to create actionable feedback for the weld controller. Such a system would require real-time ultrasonic data interpretation, and for this a solution using deep learning was investigated. The proposed solution monitors the ultrasonic data for key process events and estimates the vertical size of the weld nugget proportional to the stack size throughout the welding process. This study shows that adaptive welding using ultrasonic process monitoring backed by AI-based data interpretation has immense potential. This research highlights the importance of nondestructive evaluation (NDE) in the zero-defect manufacturing paradigm.

Bayesian and ultrasonic sensor aided multi-objective optimisation for sustainable clean-in-place processes

In food and drink manufacturing, clean-in-place procedures are essential for hygienic and efficient operations but often over-clean process equipment leading to unnecessary use of energy, water, and chemicals. Previous attempts in the literature to optimise clean-in-place processes have focused on trialling cleaning over a range of parameter (e.g. temperature and chemical concentration) combinations or modelling the process using equations. However, these methods do not aim to minimise the number of experimental trials that a manufacturer must conduct and only determine the optimal cleaning parameters for the average fouling condition. In this work, Bayesian optimisation is used to minimise the number of cleaning parameter combinations that require trialling thereby reducing the disruption to a manufacturing process during the optimisation procedure. Secondly, ultrasonic sensors are used to monitor the cleaning process and enable real-time optimisation of the parameters to adapt to variations in the fouling condition. Multi-objective optimisation was used in both tasks to simultaneously minimise the economic cost, carbon footprint, and water usage of a clean-in-place process. Bayesian optimisation was able to optimise the process after trialling only nine cleaning parameter combinations (achieving between 98.7% and 100% optimisation of the objective function compared with the global optimum). Bayesian optimisation displayed a small advantage (0.0–4.7% decrease in the objective function) compared with methods used in previous literature. Real-time optimisation of the cleaning parameters using ultrasonic sensor data improved the optimisation objective function by 0.0 – 4.8% for all fouling instances tested when utilising results from ten trials conducted during the Bayesian optimisation procedure along with five additional cleaning processes under normal operation.

Anomalous origin of the fetal pulmonary artery.

This study aims to investigate the efficacy of prenatal ultrasonography in diagnosing the anomalous origin of the fetal pulmonary artery (AOFPA). A total of 26 AOFPA cases were retrospectively analyzed from January 2014 to January 2023. The features of the AOFPA were characterized by comparing the prenatal ultrasonic data with the results of anatomical casting after pregnancy termination or postnatal imaging and surgical intervention. Missed diagnoses and misdiagnoses were expounded. Of the 26 AOFPA cases, there were 13 cases of pulmonary artery sling, 8 cases of anomalous origin of the unilateral pulmonary artery, and five cases of unilateral absence of the pulmonary artery; 17 cases received pathological anatomy and casting after pregnancy termination, and nine cases were confirmed by postnatal imaging and surgery. Nineteen cases were accurately prenatally diagnosed (19/26, 73.1%), and seven cases were missed or misdiagnosed (7/26, 26.9%). Prenatal ultrasonography has a favorable diagnostic efficacy for anomalous origin of the fetal pulmonary artery. The absence of either the left or right pulmonary artery from the image of pulmonary artery bifurcation may indicate origin abnormalities of the pulmonary artery in fetuses, which signifies the necessity to detect the abnormal origin of the pulmonary artery on the affected side and other potential intracardiac malformation complications.

Characterization of the mechanical properties of high-moisture meat analogues using low-intensity ultrasound: Linking mechanical properties to textural and nutritional quality attributes

Plant-based meat analogues offer possible alternatives to meat consumption. However, many challenges remain to produce a palatable meat analogue as well as to understand the roles of different processing steps and ingredients on both the texture and nutritional properties of the final product. The goal of this paper is to help with addressing these challenges by using a low-intensity ultrasonic transmission technique, both online and 24 h after production, to investigate high-moisture meat analogues made from a blend of soy and wheat proteins. To understand the ultrasonic data in the context of traditional characterization methods, physical properties (meat analogue thickness, density, peak cutting force) and protein nutritional quality attributes of the meat analogues were also characterized separately. The ultrasonic velocity was found to decrease with the feed moisture content and to be strongly correlated (r = 0.97) with peak cutting force. This strong correlation extends over a wide range of moisture contents from 58% to 70%, with the velocity decreasing from about 1730 m/s to 1660 m/s over this range. The protein quality was high for all moistures, with the highest amino acid score and in vitro protein digestibility being observed for the highest moisture content treatment. The accuracy of the ultrasonic measurements was enhanced by the development of an innovative non-contact method, suitable for materials exhibiting low ultrasonic attenuation, to measure the meat analogue thickness ultrasonically and in a sanitary fashion – an advance that is potentially useful for online monitoring of production problems (e.g., extruder barrel-fill and cooling-die temperature issues). This study demonstrates, for the first time, the feasibility of using ultrasonic transmission techniques to measure both velocity and sample thickness simultaneously and provide information in real time during production that is well correlated with some textural and nutritional attributes of meat analogues.

Effect of vitamin energy drinks on relieving exercise-induced fatigue in muscle group by ultrasonic bioimaging data analysis.

This work was aimed to analyze the effect of vitamin energy drink on muscle fatigue by surface electromyography (SEMG) and ultrasonic bioimaging (USBI). 20 healthy men were selected to do increasing load fatigue test. Surface electromyographic signals and ultrasonic biological images were collected based on wavelet threshold function with improved thresholds. Time domain and frequency domain characteristic integrated electromyography (IEMG), root mean square amplitude (RMS), average power frequency (MPF), and surface and deep muscle morphological changes were analyzed. Hemoglobin concentration (HB), red blood cell number (RBC), mean volume of red blood cell (MCV), blood lactic acid (BLA), malondialdehyde (MDA), and phosphocreatine kinase (CK) were measured. 1) the Accuracy (94.10%), Sensitivity (94.43%), Specificity (93.75%), and Precision (94.07%) of the long and short-term memory (LSTM) specificity for muscle fatigue recognition were higher than those of other models. 2) Compared with the control group, the levels of BLA, MDA, and CK in the experimental group were decreased and HB levels were increased after exercise (P < 0.05). 3) IEMG and RMS of the experimental group were higher than those of the control group, and increased with time (P < 0.05). 4) The mean amplitude of the response signal decreased with time. Compared with the control group, the surface muscle thickness, deep muscle thickness, total muscle thickness, contrast, and homogeneity (HOM) decreased in the experimental group; while the angular second moment (ASM) and contrast increased, showing great differences (P < 0.05). Surface electromyographic signal and ultrasonic biological image can be used as auxiliary monitoring techniques for muscle fatigue during exercise. Drinking vitamin energy drinks before exercise can relieve physical fatigue to a certain extent and promote the maintenance of muscle microstructure.

Characterization of ultrasound and postnatal pathology in fetuses with heterotaxy syndrome.

To explore the diagnostic clues and abnormality spectrum of heterotaxy syndrome by prenatal ultrasonography and postnatal verification. The prenatal ultrasonic data of 88 heterotaxy syndrome fetuses were analyzed retrospectively as left isomerism (LI) and right isomerism (RI). Prenatal ultrasound compared with the anatomical casting of the fetal body after labor induction, and the confirmatory postnatal diagnosis after delivery. Fetal LI showed typical malformations of gastric vesicles on different sides from the heart, absence of hepatic segment of the inferior vena cava (IVC), abdominal aorta (AO) parallel with the azygos vein (AV), bilateral left bronchus, bilateral left atrial appendages, and polysplenia; intracardiac malformations of AV septal defects (AVSD), single atrium (SA), left ventricular outflow tract obstruction (LVOTO), and double-outlet right ventricle (DORV); and cardiac conduction abnormalities of sinus bradycardia and AV blockage. Fetal RI reported typical malformations of gastric vesicles on different sides from the heart, juxtaposition of the IVC with AO, anomalous pulmonary venous connection (APVC), asplenia, and bilateral right atrial appendages; intracardiac malformations of AVSD, SA, single ventricle, pulmonary atresia and stenosis, and DORV. The postnatal verification revealed 3 malformations misdiagnoses and 4 malformations missed diagnoses in LI fetuses and 10 misdiagnoses and 8 missed diagnoses in RI fetuses. The proposed five-step prenatal ultrasonography has an important diagnostic value for the identification and classification of heterotaxy syndrome. The different sides of gastric vesicles and cardiac apex are important diagnostic clues for heterotaxy syndrome, featuring disconnected or hypoplastic IVC, typical complex cardiac malformation, and atrioventricular block in fetal LI, and shown APVC, juxtaposition of IVC and AO, and intracardiac malformations such as AVSD, DORV, and LVOTO in fetal RI.

Using a physics-informed neural network and fault zone acoustic monitoring to predict lab earthquakes

Predicting failure in solids has broad applications including earthquake prediction which remains an unattainable goal. However, recent machine learning work shows that laboratory earthquakes can be predicted using micro-failure events and temporal evolution of fault zone elastic properties. Remarkably, these results come from purely data-driven models trained with large datasets. Such data are equivalent to centuries of fault motion rendering application to tectonic faulting unclear. In addition, the underlying physics of such predictions is poorly understood. Here, we address scalability using a novel Physics-Informed Neural Network (PINN). Our model encodes fault physics in the deep learning loss function using time-lapse ultrasonic data. PINN models outperform data-driven models and significantly improve transfer learning for small training datasets and conditions outside those used in training. Our work suggests that PINN offers a promising path for machine learning-based failure prediction and, ultimately for improving our understanding of earthquake physics and prediction.

UAV patrol path planning based on machine vision and multi-sensor fusion

Abstract With the rapid development of unmanned aerial vehicle (UAV) technology, there are more and more fields of UAV application. This research mainly discusses the UAV patrol path planning based on machine vision and multi-sensor fusion. This article studies how to apply ultrasonic, a classic ranging sensor, to obstacle avoidance of UAVs. The designed ultrasonic obstacle avoidance system is a complete set of hardware and software systems. The hardware part consists of a forward ultrasonic module and a central signal processing module. Among them, a single-axis stabilization gimbal is designed for the forward ultrasonic module, which decouples the attitude angle of the UAV and the pitch detection angle of the ultrasonic sensor. In the central signal processing module, Kalman filtering is performed on the ultrasonic data in the four directions of front, rear, left, right, and left, and the obstacle avoidance control signal is sent to the flight controller according to the filtered sensor data. At the same time, a human–computer interaction interface is also designed to set various parameters of the obstacle avoidance system. For the route planning method of the tower, the routine steps are used to inspect the tower with a single-circuit line, and the specific targets are the insulator string, the ground wire, and the conductor. In this study, the average statistical result of the straight-line distance of the UAV patrolling 100 m is 99.80 m, and the error is only 0.2%. The fusion obstacle avoidance control method based on machine vision is suitable for the engineering application of UAV perception obstacle avoidance. The obstacle avoidance method adopted in this article can be extended to most flight control platforms, and it is a control method with broad application prospects.

Compressive sensing of ultrasonic array data with full matrix capture in nozzle welds inspection

The phased array ultrasonic technique (PAUT) with full matrix capture (FMC) exhibits the advantages of high imaging accuracy and great defect characterization ability, which play important roles in the nondestructive testing of welded structures. To address the problem of a large amount of signal acquisition, storage, and transmission data in nozzle weld defect monitoring, a PAUT with an FMC data compression method based on compressive sensing (CS) was proposed. To accomplish this, the detection of nozzle welds using PAUT with FMC was performed by simulation and experiment, and the obtained FMC data were compressed and reconstructed. A suitable sparse representation was found dedicated to the FMC data of nozzle welds, and the reconstruction performance was compared between the greedy theory-based orthogonal matching pursuit (OMP) algorithm and the convex optimization theory-based basis pursuit (BP). Also, an empirical mode decomposition (EMD)-based intrinsic mode function (IMF) circular matrix was constructed to provide another idea for the construction of the sensing matrix. Although the experimental results were not able to reach the ideal effect in the simulation, the image was restored accurately with a small number of measured values, and flaw identification could be guaranteed, indicating that the CS algorithm can effectively improve the defect detection efficiency of the phased array.

Ultrasound radiomics nomogram for predicting large-number cervical lymph node metastasis in papillary thyroid carcinoma.

To evaluate the value of preoperative ultrasound (US) radiomics nomogram of primary papillary thyroid carcinoma (PTC) for predicting large-number cervical lymph node metastasis (CLNM). A retrospective study was conducted to collect the clinical and ultrasonic data of primary PTC. 645 patients were randomly divided into training and testing datasets according to the proportion of 7:3. Minimum redundancy-maximum relevance (mRMR) and least absolution shrinkage and selection operator (LASSO) were used to select features and establish radiomics signature. Multivariate logistic regression was used to establish a US radiomics nomogram containing radiomics signature and selected clinical characteristics. The efficiency of the nomogram was evaluated by the receiver operating characteristic (ROC) curve and calibration curve, and the clinical application value was assessed by decision curve analysis (DCA). Testing dataset was used to validate the model. TG level, tumor size, aspect ratio, and radiomics signature were significantly correlated with large-number CLNM (all P< 0.05). The ROC curve and calibration curve of the US radiomics nomogram showed good predictive efficiency. In the training dataset, the AUC, accuracy, sensitivity, and specificity were 0.935, 0.897, 0.956, and 0.837, respectively, and in the testing dataset, the AUC, accuracy, sensitivity, and specificity were 0.782, 0.910, 0.533 and 0.943 respectively. DCA showed that the nomogram had some clinical benefits in predicting large-number CLNM. We have developed an easy-to-use and non-invasive US radiomics nomogram for predicting large-number CLNM with PTC, which combines radiomics signature and clinical risk factors. The nomogram has good predictive efficiency and potential clinical application value.

Characteristics of the low‐level jets observed over Dunkerque (North Sea French coast) using 4 years of wind lidar data

AbstractThis study investigates the occurrence and characteristics of low‐level jets (LLJs) up to 200 m above sea level in the North Sea area, specifically in the southernmost part of the basin, at the entrance of the English Channel. Using a short‐range Doppler lidar installed in Dunkerque Port, on the northern coast of France, wind profiles were recorded for 4 years and analyzed statistically. LLJs were detected on more than 11,000 of the 10‐min average wind profiles (5% of time), with similar jet core height and core speed distributions as in other sites in the southern North Sea area, and a similar annual cycle. However, there were differences in the core directions and the daily cycle, with afternoon northeastly jets being the most frequent in Dunkerque, whereas southwesterly nocturnal jets were dominant in the other North Sea sites. This suggests that wind channeling in the Dover Strait is likely a major factor for LLJ formation in Dunkerque region. The study also examined the conditions of LLJ occurrence using European Centre for Medium‐Range Weather Forecast (ECMWF) reanalysis v5 and ultrasonic anemometer data, but the different types of LLJs sharing the same core direction and occurrence conditions made it difficult to quantify specific jet formation mechanisms. This is the first experimental study on the North Sea shore, and at the entrance of the English Channel, providing valuable insights into the LLJ behavior in the region.