Neural radiance field enables highly realistic scene reconstruction, bridging physical and digital integration in intelligent manufacturing. 3D Gaussian Splatting (3DGS) stands out for its fast training and high reconstruction quality. However, applying 3DGS to industrial shape inspection presents two challenges: (1) The expression of bounded scenarios under mask supervision is inaccurate, leading to the degradation of geometric details and redundant Gaussian distribution. (2) Lacking of real-world scale, requiring sensor-based priors that introduce errors and complexity. To address over-reconstruction, two novel regularizations for Gaussian splatting are proposed. Local opacity regularization guides Gaussian partitioning at geometric edges and impose penalty terms of varying strengths to alleviate excessive edge reconstruction. Geometric regularization achieves global geometric consistency by enforcing the alignment of geometric parameters in a single or multiple views, thereby reducing outliers. To achieve shape inspection more efficiently, we introduce a robust and efficient Scale-ICP-based registration that aligns reconstructed scenes with CAD models. This method conducts global registration based on FPFH features, and adopts a robust strategy to automatically adjust the outlier sensitivity. Experiments on 3D reconstruction and registration datasets demonstrate that our method outperforms existing state-of-the-art approaches while completing digital modeling and shape inspection in minutes using only a consumer-grade monocular camera.

Electromagnetic powder warm compaction technology can further improve the forming quality of powder bodies. The warm compaction characteristics of copper powders were studied through experiments and simulations. Results showed that the spring back position of the stress wave was located at the radial quarter. The maximum values of equivalent stress and strain were located at the upper edge, while the minimum values occurred at the lower edge. The relative densities of the compacts at 150 °C and 200 °C were 98.49

Magnetic pulse welding is extensively employed for connecting power battery busbars, where the detection of defects in weld seam samples plays a critical role in quality assurance. Conventional approaches based on threshold segmentation, however, often suffer from high false positive rates. This study addresses the challenge of defect detection in aluminum–copper welded joints. We first perform microstructural analysis to elucidate fundamental differences in ultrasonic attenuation mechanisms between defective and defect-free samples. Based on these insights, we propose a novel deep learning architecture that integrates continuous wavelet transform with attention mechanisms—referred to as the continuous wavelet transform convolutional (CWTConv)-Transformer model. The proposed method exhibits two key innovations: first, it employs continuous wavelet transform to construct a localized time–frequency representation, overcoming limitations of traditional Fourier transforms in handling non-stationary signals; second, it adopts a parallel convolutional structure with differentiated receptive fields, forming a dual-branch feature extraction network capable of capturing multi-scale information. Finally, Transformer encoder layers are incorporated to establish global dependencies across frequency bands via self-attention. The experimental results indicate that the accuracy of weld defect detection using this model is 96.7%, with an F1 score of 96.26%. These metrics meet the detection requirements in actual industrial production settings.

Titanium bipolar plates (Ti-BBPs) typically corrode and form a high-resistivity passive film within the proton exchange membrane fuel cell (PEMFC) environment. Enhancing BPPs' corrosion resistance and electrical conductivity can effectively improve PEMFC performance. In this study, CrN and CrTiN coatings were deposited onto bare titanium (Ti) surfaces via cathodic arc physical vapor deposition, respectively. The effects of these coatings on the corrosion behavior, hydrophobicity, and surface conductivity in a simulated cathode environment were systematically investigated by electrochemical testing and surface analysis. After deposition of CrN and CrTiN coatings, the corrosion current density (icorr) of the Ti-BPPs decreased from 2.26 x 10-5 A center dot cm- 2 to 1.13 x 10- 8 A center dot cm- 2, and to 1.38 x 10- 7 A center dot cm- 2, respectively. This reduction is due to the superior chemical inertness and high density of the CrN and CrTiN coatings. Further, they effectively hinder electron transfer and consequently impede electrochemical corrosion. Mott-Schottky results revealed that the CrN coating behaved as a p-type semiconductor, while the CrTiN coating exhibited p-type semiconductor behavior at low potentials and n-type behavior at high potentials. Due to limited carrier transport caused by the dense passive film, the coating's carrier density decreased by one to two orders of magnitude. Following the potentiostatic polarization (PSP) test, the interfacial contact resistance (ICR) of bare Ti increased from 15.21 mS2 center dot cm2 to 51.96 mS2 center dot cm2. In contrast, the ICR of CrN and CrTiN coatings decreased from 51.96 mS2 center dot cm2 to 4.9 mS2 center dot cm2, and to 1.32 mS2 center dot cm2.

Field shapers concentrate electromagnetic forces on tubes during electromagnetic pulse tube forming and strongly influence deformation capability. This study investigates how the field shaper’s inner-to-outer diameter ratio limits tube compression. A Kirchhoff-law-based analytical model was combined with coupled electromagnetic-mechanical simulations and experiments. The model predicts that increasing the inner diameter reduces both inner-surface current and magnetic pressure. Meanwhile, the hoop-stress indicator first increases and then decreases because the tube radius and pressure exert competing effects. Under the investigated geometry and operating conditions, the favorable inner-to-outer diameter ratio ranges from 0.15 to 0.50. Under these conditions, current-path interference begins near 0.7 and becomes severe above 0.8, rapidly reducing inner-surface current. Experiments using 70 and 80 mm tubes validated the coupled simulation within the investigated range and supported the predicted trend. These findings guide design and indicate that larger tubes require greater field-shaper outer diameters, larger coils, and higher discharge energy.

To address cracking and rebound issues in aluminum alloy forming at room temperature, this study proposed a stamping-electrohydraulic hybrid forming (SEF) process to enhance the formability of deep concave components. A comparative analysis of the forming process and forming performance was conducted between the electrohydraulic forming (EHF) and SEF. An optimization of process parameters for SEF was completed. The results showed that the stamping stage of SEF made the shock wave energy uniformly act on more areas of the sheet and allowed enough material to flow into the forming area. These features improved the forming performance of the sheet. Compared with the EHF, the rebound of the center point for SEF was reduced by 30

Flat electromagnetic self-pierce riveting (FE-SPR) can connect carbon fiber-reinforced plastics (CFRP) and aluminum alloys with low damage and high efficiency in the automobile field. However, the lack of quantitative understanding of the fatigue performance of FE-SPR joints and the evolution of CFRP damage is hindering their engineering application. Therefore, the optimal process parameter, and the corresponding joint fatigue crack propagation, CFRP damage, and joint fatigue evolution are systematically investigated. The results showed that the optimal performance was achieved with the discharge voltage of 300 V, resulting in CFRP damage areas of 8.73 mm2 and a peak load of 6.28 kN. Three fatigue failure modes were achieved: complete fracture of the aluminum plate; local tearing of the aluminum plate; and tensile shear failure. The fracture of the aluminum plate for the low load level was attributed to fretting on the faying surface between the rivet and aluminum plate. This caused stress concentration, leading to crack initiation and propagation, resulting in eventual fracture. The ultrasonic nondestructive testing was conducted to evaluate the area of the CFRP damage under different fatigue life. It was found that, when the rivet leg was partially pulled out, the areas of CFRP damage increased slightly during the stage of stable cycle loading. Instead, it was more the initiation and propagation of cracks inside the aluminum plate. This result can provide a reference for practical applications.

Electrochemical characterization was employed to analyze the influence of F- on the performance of CrTiNcoated titanium bipolar plates (Ti-BPPs). The experiments were conducted in a simulated proton exchange membrane fuel cell (PEMFC) environment that used 0.5 M H2SO4 containing varying concentrations of F- at 70 degrees C. As F- concentration escalated from 0 to 10 ppm, electrochemical characterization revealed an increase in icorr from 9.95 & times; 10- 8 to 7.25 & times; 10- 7 A cm- 2. Electrochemical impedance spectroscopy (EIS) analysis demonstrated marked attenuation of both |Z| and phase angle within the low-frequency domain (0.01-1 Hz). MottSchottky result investigated that the carrier density within the passive film rose in the electrolyte. These collective observations consistently demonstrate accelerated corrosion kinetics and diminished protective capacity of the coating under elevated F- concentrations. A progressive increase in the severity of corrosion was observed on the coating surface with rising F- concentration, characterized by a transition from surface dissolution to the development of corrosion pits. Upon exposure to 10 ppm F-, the corrosive attack intensified, resulting in the formation of deeper pits and a slight thinning of the coating layer. Additionally, the underlying corrosion mechanisms were further elucidated using X-ray photoelectron spectroscopy (XPS) and inductively coupled plasma mass spectrometry (ICP-MS). Results suggest that the formation of soluble complexes between F- ions and the passivation layers (TiO2 and Cr2O3) on the coating surface significantly compromises the protective capability of the passivation layers.

Joining thin-walled Al/Cu tubes is challenging because of the large differences in material properties and the low structural rigidity of thin-walled tubes, which often result in severe deformation and poor weld quality during magnetic pulse welding (MPW). To overcome these limitations, this study proposes a novel magnetic pulse welding with granular support (MPW-GS), in which dynamically compacted granular media provide transient radial confinement to regulate tube deformation during high-velocity impact. Experiments demonstrate that AA1060/T2 joints can be produced under a discharge energy of 32kJ. Compared with conventional MPW, the proposed process suppresses the radial collapse of the inner tube by 65.67%, while achieving a maximum tensile load of 1.35 kN, exceeding the strength of the AA1060 base material. Typical wavy interfaces with the largest amplitude of 7 μm and a transition zone were observed, confirming an effective metallurgical bond at the welded interface. The FEM-DEM coupled simulations reveal that GS enhanced stress transfer and collision stability through dynamic densification, thereby improving the quality of the welded interface. Based on these findings, a stress-wave propagation model is established to explain the underlying welding mechanism. The analysis demonstrates that the dynamically compacted granular support enhances stress-wave reflection at the inner tube interface, thereby promoting interfacial wave formation and establishing a positive feedback mechanism between granular densification and stress-wave amplification. These works provide new insight into support material, deformation control and interface evolution in magnetic pulse welding of thin-walled dissimilar tubes.

Electromagnetic self-pierce upsetting riveting (ESP-UR) technology has advanced the development of ultra-high strength steel/aluminum alloy structures for automotive lightweight manufacturing. In this paper, ESP-UR process was used to join 22MnB5 steel and Al5052 alloys sheet. The effect of die depth on joint fatigue performance was comprehensively investigated. The study focused on joint characterization, microhardness, fatigue life under different confidence levels, and fatigue failure mechanism, with finite element simulations employed to analyze residual stress distribution in the joints. Results showed that using a concave die could improve the joint fatigue performance by affecting the profile the residual stress distribution and the stress concentration factor (Kt) compared to a flat die. Specifically, the joint with a die depth of 1.0 mm demonstrated the best fatigue performance, exhibiting the smallest Kt value in typical areas. It had a fatigue life that was 51.57

Electromagnetic high-speed nailing (E-HSN) presents a promising method for assembling carbon fiber reinforced plastic (CFRP) and aluminum alloy components in enclosed spaces applications, particularly side-panel-to-extruded-aluminum joints in new energy vehicle bodies. Although nail geometry critically governs joint quality, research integrating geometric optimization with the subsequent fatigue performance of E-HSN CFRP/Al joints remains scarce. This study systematically investigates the effects of three key geometric parameters—shank diameter (D), groove length (L), and tip radius (R)—on joint performance. Furthermore, the fatigue behavior, including failure mechanisms and life prediction, was comprehensively evaluated based on the optimized nail configurations. Results indicated that the L exerts the most significant influence on joint strength. Optimized configurations (Specimens 5, 6, and 8) successfully mitigate piercing-induced damage to the CFRP, thereby exhibiting superior quasi-static mechanical properties. Crucially, the fatigue failure modes demonstrate a distinct load dependency. In Specimens 5# and 8#, failure was dominated by nail detachment, systematically accompanied by fatigue cracking in the aluminum substrate. For Specimen 6, shank fracture occurs at the joint interface under a high load level (50% Fult) and shifts to the nail head at a moderate load level (40% Fult). At a low load level (30% Fult), the failure transitions to nail detachment accompanied by fatigue cracking around the nail holes in the aluminum plate. These findings provide critical insights for optimizing high-speed nail configurations and establish a solid foundation for implementing E-HSN technology in lightweight transportation equipment.

Pre-holed self-pierce riveting (PH-SPR) has excellent potential for application in joining ultra-high-strength steel (UHSS) and aluminum alloy thin-walled structures in new energy vehicles. However, protrusion or sheet penetration are always on the joints, severely affecting the vehicle's NVH (noise, vibration, harshness). To overcome these problems, a flat electromagnetic self-pierce riveting (FE-SPR) process was proposed using a semi-solid rivet to join 2.0 mm-thick 22MnB5 UHSS and 2.0 mm-thick 5052 aluminum alloys. Parallel studies were carried out to compare two processes in terms of joint quality, microhardness, microstructures, quasi-static mechanical performance, and failure behavior. The effect of process parameter on the FE-SPR joints was also discussed. The results indicated that the FE-SPR joints had better mechanical interlock and joint performance than the PH-SPR joints. Two failure modes were obtained: For PH-SPR joints, the rivet was extracted from the lower and upper sheets. For FE-SPR joints, the rivet was extracted from the lower sheet while remaining connected to the upper sheet because of interference-induced contact stress. The gap caused by insufficient filling of the rivet shank in the joint gradually decreased with the inclination angle (θ). The FE-SPR joint with the θ of 7° had the best peak load, which was 8.0

The fatigue life of magnetic pulse crimping (MPC) joints is crucial for the safe fatigue design of connection structures. Traditional fatigue life prediction methods primarily rely on loading condition analysis and fail to fully account for the impact of manufacturing variations (such as raw material dimensions, process parameters, and joint deformations), which presents challenges for accurate fatigue life prediction. To address this issue, this paper proposes a fatigue life prediction method for MPC joints that combines point cloud measurement and machine learning (ML) models. Random sample consensus (RANSAC) and point cloud segmentation are used to extract the joint deformation contour precisely. Compared to metallographic analysis, this method achieved non-destructive extraction of joint deformation features. Based on this, an integrated dataset covering the entire process from raw materials to fatigue testing is established. Five machine learning models are trained and tested, with results showing that the gradient boosting regression trees (GBRT) model performs the best. The visualization of a single decision tree in the GBRT model is analyzed, providing a transparent decision-making process. A comparison is made between the GBRT model and the traditional Basquin model. In the GBRT model, 100% of the training set and 90% of the testing set fall within the 1.5 times error band, while only 45% of the training set and 60% of the testing set in the Basquin model fall within this range. Additionally, the GBRT model achieves a higher coefficient of determination (R2) on the dataset compared to the Basquin model.

Electromagnetic forming (EMF) is applied to the hole flanging of aluminum alloys due to its significant advantages in improving forming limits and suppressing springback. However, a major challenge for this application lies in the conformal coil structure’s difficulty in achieving acceptable die gap conformity and deformation control. To address this, a loosely coupled finite element model was developed in Ansys to simulate the EMF hole flanging process. Utilizing this finite element model (FEM), the Plackett–Burman design (PBD) method identified 10 key variables (out of 18 structural coil parameters) that most significantly impact the distribution of electromagnetic force. Subsequently, the optimization process employed the Optimal Latin Hypercube Sampling (OLHS) technique, an Elliptic Basis Function (EBF) neural network model, and the Non-Dominated Sorting Genetic Algorithm II (NSGA-II) to obtain sensitivity analysis results, a Pareto solution set, and the optimal equilibrium solution. Sensitivity analysis revealed that the coil width parameter exerts the most substantial influence on thinning rate and die gap conformity. The optimized coil design generated electromagnetic forces that were strengthened at the flange edge and distributed more uniformly across the deformation zone during flanging. This resulted in increased acceleration magnitudes and enhanced deformation. For the formed parts, the maximum die gap decreased from 2.65 to 0.41 mm, and the axial height difference diminished from 1.30 to 0.26 mm. This optimized force and deformation control yielded flanged parts with significantly improved conformity to industrial product specifications. Moreover, the maximum thinning rate was reduced from 27.5 to 21.45

Continuous forming at high strain rates is an important research direction for future precision forming of light alloys. In this study, dynamic behavior of AA5052 aluminum alloy in two-step tensile testing at high strain rates were investigated. Special two-step tensile test piece at high strain rate was designed. The test piece of the special design contained a weak structural notch area and a dog-bone shaped area. The test piece was pre-stretched to a pre-determined strain so that the weak region broke. Then a secondary stretching was performed. The response surface equations of pre-strain and pre-strain rate were established separately to evaluate the functional relationship between the notch interval, tensile velocity and strain rate, and equivalent plastic strain. The effects of the parameters on the fracture strain were compared. The results showed that the test pieces could meet the requirements of the two-step tensile test at high strain rates. The pre-strain and pre-strain rate were affected by the size of the notch interval and the tensile velocity. The increase of tensile strength was related to pre-strain and secondary strain rate. The linear cumulative damage criterion can be used to interpret the two-step stretching at high strain rates. When the strain rate in single-step stretching is the same as the strain rate in each step of two-step stretching, the fracture strain in single-step stretching can be substituted for the fracture strain in two-step stretching. Research can help solve the problems of poor formability and early failure of lightweight alloys.

High-speed deformation fracture prediction of aluminum sheet, especially for biaxial tension state deformation, was a major problem in the development of electromagnetic bulging process. In this study, the biaxial tension failure limit of the AA5052 sheet was tested by the electromagnetic high-speed biaxial tensile testing equipment and quasi-static Nakazima experiment. A Digital Image Correlation (DIC) system was used to measure failure strain. Based on the tested data, a failure model considered stress state and strain rate coupling effect was established, which available for electromagnetic bulging failure prediction. Electromagnetic free bulging experiments were conducted to verify the failure criteria effectiveness. Results showed that the strain rate effects of the failure strain were influenced by the loading path. The strain rate effect of the sheet failure strain under plain strain state was higher than the loading stress triaxiality of uniaxial and biaxial tension state. Compared with the fracture prediction criterion ignored stress state effect on strain rate influence factor, the modified fracture model considered stress state and strain rate coupling effect could well predict the failure of electromagnetic bulging, which would exhibit different failure models at the rounded corner or the top under different discharge energies.

TC4 based composites were facing an urgent need to enhance physical performance. In this work, electromagnetic powder compaction (EMPC) technology was used to prepare carbon nanotubes reinforced TC4 based (CNTs/TC4) composites. The micro morphology and properties of the sintered bodies were studied through scanning/transmission electron microscopy (SEM/TEM) and a universal material testing machine at different sintering temperatures. Results showed that there was a significant turning point at 1100 degrees C, with a relative density of 98.01 %. The relationship between the relative length and density of sintered bodies was established through Gaussian fitting. The CNTs partially reacted with the TC4 matrix after 700 degrees C, generating equiaxed TiC particles. The compressive strength and strain reached the maximum values at 1300 degrees C and 600 degrees C, respectively, with values of 1884.64 MPa and 0.2336. The enhancement factors for compressive strength were only alloying and TiC particles at 1100 degrees C. There was not much difference in the fusion effect of particles at 1100 degrees C and 1300 degrees C. From the above analysis, it can be concluded that the CNTs/TC4 composites prepared by EMPC had relatively good comprehensive mechanical properties when sintered at 1100 degrees C.

The corrosion resistance of aluminum(Al)cable-copper(Cu)terminal joints fabricated by magnetic pulse crimping(MPC)and hydraulic clamp crimping(HCC)was compared.Performance degradation was evaluated by mechanical and electrical properties.Additionally,corrosion behavior was analyzed by electrochemical testing.Microscopic characterization was performed by scanning electron microscopy(SEM)and energy dispersive spectroscopy(EDS).Results show that the tensile strength of the corroded joints is reduced.However,due to the advantages of high-speed forming and contact tightness unique to MPC,the contact resistance of the corroded joints still maintains excellent.Electrochemical tests demonstrate that the MPC joints have higher corrosion potentials and smaller corrosion currents,providing better corrosion resistance.The formation of a primary battery between Al and Cu at the lap joint leads to the formation of severer corrosion pits.

Magnetic pulse crimping process has significant potential for high-voltage cable joint manufacturing due to its green, eco-friendly, efficient, and reliable advantages. In this paper, the fatigue characteristics and fracture behaviors of Cu-Al dissimilar cable joints prepared by magnetic pulse crimping (MPC) and hydraulic crimping (HC) were explored and compared. The fatigue life prediction models for the two cable joints at different reliability levels were developed. The contact resistance change features, crack propagation laws and fatigue failure mechanisms of cable joints were revealed. Results showed that the failure modes of cable joints at different stress levels could be divided into Al harness fracture (S-M >= 45.7 MPa), Cu terminal fracture (S-M < 34.3 MPa), and mixed fracture of the two (S-M = 34.3 MPa). As the stress level decreased, the fatigue life of cable joints gradually increased, and the failure mode gradually transitioned from Al harness fracture to Cu terminal fracture. The contact resistance of MPC and HC cable joints presented opposite changes during the fatigue process. Fretting wear at the Al-Cu contact generated Al2O3 particles. The initial fatigue cracks mainly initiated at the surface damage of Al harness in the crimping area and at the intersection of the tube end and the plate end on the upper surface of Cu terminal. Because there were significant stress concentrations at these two locations. The fatigue fractures all had typical crack initiation zones, crack propagation zones and instantaneous fracture zones.

Fatigue failure of joints is a critical factor affecting structural safety design. This study investigates the failure mechanism of aluminum (Al)-steel tubular joints fabricated via magnetic pulse crimping (MPC) using multiscale characterization techniques. Shear effects caused the thinning of the Al tube, which induced the formation of a notch on the inner surface. The mechanical interlocking of the material and the notch effect led to stress concentration, thereby promoting fatigue crack initiation (FCI) at the notch. Fracture morphology indicated that FCI was a mixture of intergranular and transgranular fracture. Interestingly, under higher stress conditions (58.5 MPa), the fatigue crack propagation (FCP) rate was extremely fast. The crack propagation process lacked a steady-state stage, with no distinct fatigue striations forming before fracture occurred. The features of the dimples were the main characteristic of final fracture (FF). Electron backscattered diffraction (EBSD) results showed that the differences in plastic deformation degree, dislocation density, and grain Schmid factor (SF) value were the main causes of intergranular and transgranular fracture in FCI.