Local Point Research Articles

Machine learning enabled identification of sheet metal localization

The Forming Limit Curve (FLC), which describes the maximum applicable strain before localization, depends on the particular material, but also on the applied load and history of the load. Recent investigations have shown that the non-proportional loading effect on the FLC can be predicted with data-driven or machine-learning-based methods. Here we compare different ML methods to their applicability in predicting localization points under multi-segmented non-proportional loading. Therefore, an FE-based metamodel is developed that allows imposing an arbitrary loading history on sheet metal to predict the point of localization. A series of virtual experiments are conducted with this metamodel to generate a database of bi-linear loading paths that are used for training. Different ML-based methods were used to predict the localization point based on the strain history data. The 1D-Convolutional Neural Network (1D-CNN), with the ability to learn dependency between input features, has the best accuracy in predicting the localization point.

A novel damage detection method for carbon fibre reinforced polymer structures based on distributed strain measurements with fibre optical sensor

This paper presents a novel approach for damage detection in carbon fibre reinforced polymer (CFRP) structures based on local strain feature matching. The proposed approach utilizes distributed in-plane strain measurements for plate structures under load (in-service application) to define a local point autocorrelation coefficient based on Delaunay triangulation and Hausdorff distance. This coefficient effectively identifies the discontinuities in distributed in-plate strain, enabling accurate capture of damage information through the damage index which is defined as the integral of this coefficient. Notably, the proposed approach requires no prior knowledge of the non-damaged strain distribution and yields excellent detection results for both Barely Visible Impact Damage (BVID) and Visible Impact Damage (VID). Leveraging the advantages of distributed strain sensing, coupled with image processing technology for the purpose of in-service damage detection of CFRP structures, the proposed novel method is a promising technology. The efficacy of this technology has been demonstrated in this paper through theoretical analysis and experimental investigations, offering valuable insights and reference for future research in this domain.

Inorganic–organic hybrid quantum dots for AOP-mediated photodegradation of ofloxacin and para-nitrophenol in diverse water matrices

Due to concerns about the accessibility of clean water and the quality of treated wastewater, developing a suitable solution to enhance the water quality is critical. Thus, the current study focused on the synthesis of cadmium-doped CdIn2S4 incorporated in chitosan, forming Cd/CdIn2S4@Ch quantum dots using a solvothermal technique for the efficient photodegradation of hazardous pollutants like ofloxacin and para-nitrophenol through H2O2-mediated AOP. Cd/CdIn2S4@Ch quantum dots were characterized by several advanced methods, including XRD, PL, UV-DRS, FTIR, SEM, HR-TEM, XPS, DSC, TGA, EDX, and Elemental mapping analysis. The influence of varying reaction parameters, such as the effect of organic compounds, inorganic ions, and water matrices, was also investigated. The prepared composite showed outstanding photodegradation efficiency of 85.51 ± 1.35% and 96.70 ± 1.31%, with a rate constant of 0.02334 and 0.15134 min−1, which is about 1.24 and 2.07 times higher than pristine CdIn2S4 for ofloxacin and para-nitrophenol, respectively. The COD values were reduced to 80.67 ± 1.67% for ofloxacin and 88.36 ± 1.43% for para-nitrophenol, whereas the TOC values reduced to 73.49% and 86.34%, respectively, from their initial values. The improved performance is ascribed to the encapsulation of CdIn2S4 by chitosan, leading to the self-doping of cadmium into the photocatalyst, as the incorporated cadmium doping site can generate a local electron accumulation point, improving the charge separation efficacy and surface charge mitigation capability of chitosan nanosheets even further. The scavenger experiments showed that hydroxyl and superoxide radicals played a significant part in the photodegradation of contaminants. Additionally, the quantum dots showed excellent constancy and were recyclable up to six times, suggesting exceptional stability and reusability of the manufactured photocatalyst. The fabricated Cd/CdIn2S4@Ch quantum dots could be an excellent photocatalyst for removing organic pollutants from wastewater in the near future.

Tracking of horizontal alignment of the long and large diameter uncharged hole in NATM tunnel

The long and large diameter uncharged hole boring (LLB) method is a cut blasting method that minimizes blast-induced vibrations by creating long and large diameter uncharged holes at the excavation face of tunnels prior to tunnel excavation. Drilling in this method typically uses a 50 m long with a 382 mm diameter hammer bit in the horizontal direction at the tunnel face. However, the significant weight and uni-directional rotation of the rod head, as well as variables such as geological characteristics, machine conditions, and inexperienced operators result in significant deviation from the target borehole alignment that hinders the vibration-dampening effect of the uncharged holes. Furthermore, since there is no method to verify the alignment of the boreholes until main tunnel construction, borehole misalignment is often not discovered until weeks after construction, which requires tunnel construction to cease until the equipment can be remobilized and an additional borehole be created, causing significant delays and increased costs for the entire tunnel project. In this study, the borehole alignment tracking and ground exploration system (BGS) is developed to predict and monitor the quality and alignment of boreholes for cut blasting methods such as the LLB methods immediately after boring. The BGS was subsequently tested at a subway construction site to evaluate its performance in the field. The measurements yielded by the BGS were compared with manually measured boring positions at every 5 m along the borehole. Although the BGS showed a maximum deviation of approximately 12% at a local point where the hole surface was relatively rough, the accuracy for the final boring position was approximately 97%, demonstrating excellent precision of the alignment tracking system. The BGS demonstrates excellent performance in predicting ground conditions and the boring quality of a cut hole immediately after drilling, and shows promise in various other applications for monitoring borehole alignment.

Symmetry analysis, optimal system, and invariant solutions for a (2+1)-dimensional two-phase mass flow model

The paper investigates a two-phase mass flow model governed by gravity, involving solid particles and a viscous fluid. By utilizing the Lie symmetries admitted by the system, similarity solutions for the (2+1)-dimensional two-phase mass flow model are obtained. A comprehensive set of local point symmetries is established, and a well-suited collection of two-dimensional subalgebras is constructed from the maximal Lie invariance algebra. The optimal system’s vector fields are then utilized to directly reduce the governing model to a system of ordinary differential equations. Through analytical solutions, we successfully solve the resulting systems and further analyze their physical behaviors numerically.

A Profound Multitask System for Gender Identification face recognition, Confront Discovery, Point of interest Localization, and Head Position Estimation Hyperface

Machine learning is a technology that has risen in its usage and popularity in the last few years. A huge number of people from around the world are learning this technology and putting the knowledge to various use. Machine learning algorithms are capable of learning from the provided data with high accuracy. Even though a significant amount of research has been conducted on face recognition, the integrated model of face recognition, landmark localization, head posture estimation, and gender identification that is capable of high accuracy and speed has not yet been investigated. As a result, we have developed a face recognition system that can make predictions about photos that are comparable to those made by humans. The principal component analysis PCA and the SVM were used here to accomplish facial recognition. In feature extraction, to reduce the dimensionality of large datasets, principal component analysis is performed. After the data have been preprocessed, they are entered into the SVM classifier to be used for image classification. The study of this is done via visualization, and it is used to measure the effectiveness of the model. This face recognition algorithm has an accuracy of at least 80% when it comes to classifying people's portraits. The findings of the experiments show that the suggested technique can successfully identify faces since it employs a feature-based algorithm that combines PCA classification and SVM detection.

Nonlocal symmetries, nonlocally related systems, similarity solutions and conservation laws of the Tzitzéica-Dodd-Bullogh equation

In this paper, a methodical procedure is utilized for the identification of nonlocal symmetries of the (1+1)-dimensional Tzitzéica-Dodd-Bullogh equation. Firstly, by introducing a set of canonical coordinates corresponding to the local Lie point symmetries, the considered partial differential eq. (PDE) is mapped to an invertibly equivalent PDE system. Furthermore, nonlocal symmetries are obtained from the inverse potential system of the invertibly equivalent PDE system. The exact solutions for the aforementioned PDE are acquired with the help of the extended generalized Kudryashov method corresponding to the admitted symmetries. In addition, the derivation of local conservation laws for the Tzitzéica-Dodd-Bullogh equation is obtained through the multiplier method. Moreover, using a symmetry-based technique and local conservation principles, a complete tree of nonlocally related PDE systems has been constructed.

From Local Initiatives to Coalitions for an Effective Agroecology Strategy: Lessons from South Africa

Agroecological food system transformation remains marginal in South Africa despite numerous policies, plans and programmes favouring sustainable agriculture. Problems of weak budgets, fragmented interventions and lack of coordination reflect the power dynamics in the prevailing food system, dominated by large-scale conventional agriculture and agribusiness. The paper provides an in-depth case study of the importance of promoting agroecological transitions. Following a qualitative research methodology based on a literature review for context, preparatory discussions with local contact points, and semi-structured interviews and focus group discussions with local actors in the field, the paper describes, analyses and characterises the agroecological transitions in the Overberg District in the Western Cape. It considers the broader policy, discursive and organisational landscape of agroecology followed by an in-depth analysis of the site drawing on key informant interviews and focus group discussions. The results demonstrate that local stakeholders are positioned to better connect food and nutrition issues with human health, biodiversity, climate change, natural resource management, and local development. As a result, transformative dynamics could emerge from local projects and programmes. Several lessons and recommendations are drawn to contribute to the policy debate. These highlight the potential of multi-actor coalitions which can develop from specific agroecological initiatives and activate positive dynamics, bringing in multiple interventions of municipalities.

A Local Point Method Based on DFS Expansion of Boundary Conditions for Eigenfrequencies Calculation of BoR Cavities

A Local Point Method Based on DFS Expansion of Boundary Conditions for Eigenfrequencies Calculation of BoR Cavities

Assessment of Groundwater Potential in a Mountainous Area Using Machine Learning and GIS, Rherhaya Basin, High Atlas, Morocco

Mountainous regions are vital for recharging aquifers in plain areas downstream, but understanding the geological, hydrogeological, and climatic factors is crucial to comprehend groundwater processes in these regions. Several parameters, including lithology, topography, secondary porosity, geological structures, and climatic conditions, affect the potential of groundwater in mountainous aquifers. Traditional groundwater modeling tools face several challenges in handling large amounts of real-time data, such as extracting useful features, quantifying uncertainty, and identifying links between different variables. Recent technological advances in artificial intelligence, particularly machine learning, provide solutions for hydrogeological research and applications. This paper focuses on modeling potential zones of groundwater sources using various methodologies based on GIS, spatial remote sensing, and machine learning. The study evaluated three models, Random Forest, Support Vector Machine, and Logistic Regression, in identifying potential groundwater zones in the Rherhaya watershed. More than 200 localized spring points were needed to ensure efficient model learning. The Support Vector Machine model demonstrated the highest performance during the 70/30% split, with a ROC-AUC of 84.4% for the test data. The study identified four critical conditioning factors of groundwater potentiality, including Topographic position index, River Distance, Valley Depth, and Plane Curvature. The models also highlighted the distance to rivers as a significant factor, particularly in the upstream portion of the watershed. The very low potentiality class occupied the largest area (over 32%), followed by low (between 24 and 29%), moderate (12–19%), high (10–14%), and very high (only 9–12%) classes. Only the Support Vector Machine model predicted that 12% of the catchment area had high potential for groundwater resources, indicating its superior performance in identifying high-potential zones. The results offer valuable insights that can aid decision-makers in effectively managing water resources in vulnerable areas.

An efficient autofocus method for microscope based on the improved first-order derivative Gaussian filtering operator

This paper introduces an improved filtering operator based on the first-order derivative Gaussian filtering operator. As the defocus distance decreases, the edges of an image transition from being smooth to sharp. Using the operator proposed in this study, a parameter can be obtained to quantify the degree of edge sharpness, where a smaller value indicates sharper edges. By using the characteristic, we can judge whether the object is near the focal plane. Combining this information, we proposed two focus method. Both of them can avoid the problem of the hill climbing algorithm locating at local extremum points and one of them can locate the watershed between “coarse search” and “fine search” before the sharpness value crosses the peak value, so as to realize the transition from “coarse search” to “fine search” before crossing the peak value and improve focusing efficiency. This is different from previous passive focusing strategies. The final experiment shows that the proposed solutions in this paper is effective. However, the methods proposed in this study are only applicable to incoherent optical microscopy imaging systems and are not suitable for coherent light source microscopy imaging systems. Besides, the prerequisite for the successful implementation of the two proposed focusing strategies in this study is that the target exhibits sharp edges when it is within the focal plane.

Concentration of nodal solutions for semiclassical quadratic Choquard equations

In this article concerns the semiclassical Choquard equation \(-\varepsilon^2 \Delta u +V(x)u = \varepsilon^{-2}( \frac{1}{|\cdot|}* u^2)u\) for \(x \in \mathbb{R}^3\) and small \(\varepsilon\). We establish the existence of a sequence of localized nodal solutions concentrating near a given local minimum point of the potential function \(V\), by means of the perturbation method and the method of invariant sets of descending flow. For more information see https://ejde.math.txstate.edu/Volumes/2023/75/abstr.html

Research on Fast Multi-Threshold Image Segmentation Technique Using Histogram Analysis

This paper investigates a method for the multi-threshold segmentation of grayscale imaging using the local minimum points of a histogram curve as the segmentation threshold. By smoothing the histogram curve and judging the conditions, the expected peaks and valleys are identified, and the corresponding minimum points are used as segmentation thresholds to achieve fast multi-threshold image segmentation. Compared to the OTSU method (maximum between-class variance) for multi-threshold segmentation and the region growing method, this method has less computational complexity. In the recognition and segmentation process of solder pads with adhesion of underfill in LED Chips, the segmentation time is less than one percent of that of the OTSU method and the region growing method. The segmentation effect is better than the OTSU method and the region growing method, and it can achieve fast multi-threshold segmentation of images. Moreover, it has strong adaptability to the differences in the overall grayscale of images, meeting the requirements for high UPH (Units Per Hour) in industrial production lines.

Study of the relationships between microstructure and local mechanical properties in the ductile-to-brittle transition of a bainitic steel containing local segregations

Although considered a 1st-class option to meet the drastic requirements of Reactor Pressure Vessels (RPV) environments, Mn-Mo-Ni bainitic alloys also have segregated microstructures that can lead to heterogeneous mechanical properties. The latter should explain the scatter and the brittle fracture sometimes observed along the ductile-to-brittle transition during qualification tests. The present study focuses on a highly segregated SA 508 Gr.3 (aka 20MND5) steel and investigates the evolutions of local mechanical properties with temperature. Microstructure analysis revealed positive and negative segregations mainly composed of lower and upper bainite, respectively. An experimental device was developed and combined with a systematic procedure to enable local microhardness measurements from room temperature to − 40 °C. Analysis of hardness maps revealed two critical parameters assumed to be involved in the macroscopic brittle fracture as the temperature decreases. The first one is a significant increase in the hardness of both phases, particularly a continuous increase in the lower bainite’s hardness, suggesting that this phase could preferentially lead to brittle fracture. A wide range of hardness values in selected positive segregation reinforced the idea of the possible existence of very local weak points that could explain the dispersion of the results of the macroscopic Charpy test. The second parameter is an extension in the brittle surfaces, leading to a greater probability of testing a brittle area due to an extension surface area of the weak points.

A deep learning method based on prior knowledge with dual training for solving FPK equation

The evolution of the probability density function of a stochastic dynamical system over time can be described by a Fokker–Planck–Kolmogorov (FPK) equation, the solution of which determines the distribution of macroscopic variables in the stochastic dynamic system. Traditional methods for solving these equations often struggle with computational efficiency and scalability, particularly in high-dimensional contexts. To address these challenges, this paper proposes a novel deep learning method based on prior knowledge with dual training to solve the stationary FPK equations. Initially, the neural network is pre-trained through the prior knowledge obtained by Monte Carlo simulation (MCS). Subsequently, the second training phase incorporates the FPK differential operator into the loss function, while a supervisory term consisting of local maximum points is specifically included to mitigate the generation of zero solutions. This dual-training strategy not only expedites convergence but also enhances computational efficiency, making the method well-suited for high-dimensional systems. Numerical examples, including two different two-dimensional (2D), six-dimensional (6D), and eight-dimensional (8D) systems, are conducted to assess the efficacy of the proposed method. The results demonstrate robust performance in terms of both computational speed and accuracy for solving FPK equations in the first three systems. While the method is also applicable to high-dimensional systems, such as 8D, it should be noted that computational efficiency may be marginally compromised due to data volume constraints.

3D point cloud global denoising algorithm based on different noise characteristics

When acquiring object point cloud data by three-dimensional scanning technology, noise is generated due to instrument accuracy and external factors. Existing algorithms rarely consider the characteristics of different noises and different regional noises when solving the point cloud denoising problem, this results in a limited effect on denoising. This paper presents an algorithm for denoising based on the characteristics of different types of noise and different regions in the point cloud. The algorithm includes large-scale noise removal and small-scale noise smoothing. Remove large-scale noise points by the relationship between the local point cloud and the global point cloud. For small-scale noise, the feature regions and non-feature regions are extracted according to the normal cosine information entropy. According to the characteristics of the small-scale noise in two regions, the noise distance distribution and the optimized bilateral filtering are used to deal with the small-scale noise in two regions respectively. Comparison experiments show that our algorithm can effectively remove the noise points mixed in the normal point cloud. The accuracy of large-scale noise removal reaches 99.1%. The proposed algorithm can protect the feature areas from being over-smoothed while smoothing the small-scale noise in non-featured areas.

Insights into Temperature Simulation and Validation of Fused Deposition Modeling Processes

In fused deposition modeling (FDM), the cooling history impacts the bonding between filaments and layers. The existence of thermal gradients can cause non-homogeneous properties and localized stress points that may affect the individual filaments, resulting in distortion and detachment. Thermal analysis can aid in understanding the manufacturing flaw, providing necessary tools for the optimization of the printing trajectory. The present work is intended to deepen understanding of the thermal phenomena occurring during the extrusion of polymeric materials, aiming at more efficient three-dimensional (3D) printing methods. A one-dimensional (1D) finite differential method was implemented using MATLAB to simulate the temperature evolution of an extruded filament, and the results were compared with two-dimensional (2D) COMSOL Multiphysics simulations, and experimentally validated using infrared thermography. Acrylonitrile–butadiene–styrene (ABS) was used as a test material. The energy dissipation includes forced convection and radiation heat losses to the surrounding medium.

A Robust and Integrated Visual Odometry Framework Exploiting the Optical Flow and Feature Point Method.

In this paper, we propose a robust and integrated visual odometry framework exploiting the optical flow and feature point method that achieves faster pose estimate and considerable accuracy and robustness during the odometry process. Our method utilizes optical flow tracking to accelerate the feature point matching process. In the odometry, two visual odometry methods are used: global feature point method and local feature point method. When there is good optical flow tracking and enough key points optical flow tracking matching is successful, the local feature point method utilizes prior information from the optical flow to estimate relative pose transformation information. In cases where there is poor optical flow tracking and only a small number of key points successfully match, the feature point method with a filtering mechanism is used for posing estimation. By coupling and correlating the two aforementioned methods, this visual odometry greatly accelerates the computation time for relative pose estimation. It reduces the computation time of relative pose estimation to 40% of that of the ORB_SLAM3 front-end odometry, while ensuring that it is not too different from the ORB_SLAM3 front-end odometry in terms of accuracy and robustness. The effectiveness of this method was validated and analyzed using the EUROC dataset within the ORB_SLAM3 open-source framework. The experimental results serve as supporting evidence for the efficacy of the proposed approach.

Improved Calibration of Eye-in-Hand Robotic Vision System Based on Binocular Sensor.

Eye-in-hand robotic binocular sensor systems are indispensable equipment in the modern manufacturing industry. However, because of the intrinsic deficiencies of the binocular sensor, such as the circle of confusion and observed error, the accuracy of the calibration matrix between the binocular sensor and the robot end is likely to decline. These deficiencies cause low accuracy of the matrix calibrated by the traditional method. In order to address this, an improved calibration method for the eye-in-hand robotic vision system based on the binocular sensor is proposed. First, to improve the accuracy of data used for solving the calibration matrix, a circle of confusion rectification method is proposed, which rectifies the position of the pixel in images in order to make the detected geometric feature close to the real situation. Subsequently, a transformation error correction method with the strong geometric constraint of a standard multi-target reference calibrator is developed, which introduces the observed error to the calibration matrix updating model. Finally, the effectiveness of the proposed method is validated by a series of experiments. The results show that the distance error is reduced to 0.080 mm from 0.192 mm compared with the traditional calibration method. Moreover, the measurement accuracy of local reference points with updated calibration results from the field is superior to 0.056 mm.

Local aggressive and physically realizable adversarial attacks on 3D point cloud

Deep learning models used to process 3D point cloud data exhibit a vulnerability to adversarial examples, which can result in potential misclassification. The research community has pivoted towards applying traditional optimization methods to generate adversarial examples specifically for the point cloud domain. However, these traditional optimization-based adversarial approaches come with their own set of limitations, including inconsistent point importance, non-optimal multi-label optimization, inflexible adversarial and perceptibility losses, and difficulty in constructing perceivable adversarial examples in physical environments. To surmount these challenges, we have introduced two novel techniques: a Local Aggressive Adversarial Attack (L3A) for simulated environments and a Normal Vector Metric Attack (NVMA) for physical environments. The L3A operates by enhancing the cost-effectiveness ratio between the attack and perceptibility aspects. This enhancement is realized through a combination of strategies, including local salient points, modeling example preference, and adjusting the goals for attack potency and indistinguishability. The NVMA generates physically printable adversarial point clouds by maintaining consistency in high-frequency regions between clean and adversarial examples. Our methods exhibit superior performance when tested against state-of-the-art point cloud deep learning models on benchmark datasets and physical models. This contribution enhances our understanding of adversarial attacks and defenses within the realm of 3D point cloud data. Our code is available at https://github.com/Chenfeng1271/L3A.