Ingenieurwissenschaften und zugeordnete Tätigkeiten
Filtern
Erscheinungsjahr
Dokumenttyp
- Zeitschriftenartikel (168) (entfernen)
Sprache
- Englisch (141)
- Deutsch (20)
- Russisch (5)
- Italienisch (1)
- Mehrsprachig (1)
Schlagworte
- Laser beam welding (41)
- Additive manufacturing (14)
- Laser metal deposition (14)
- Microstructure (11)
- Laser welding (9)
- Mechanical properties (9)
- Solidification cracking (9)
- Resistance spot welding (7)
- Hybrid laser-arc welding (6)
- Numerical simulation (6)
- Thick-walled steel (6)
- Widerstandspunktschweißen (6)
- Artificial neural network (5)
- DED (5)
- Hybrid laser arc welding (5)
- Laserstrahlschweißen (5)
- Liquid metal embrittlement (5)
- Additive Fertigung (4)
- Crack (4)
- Critical strain (4)
- Numerical modeling (4)
- Porosity (4)
- Solidification (4)
- Weld pool shape (4)
- 9%Ni steel (3)
- Deep penetration (3)
- Design of experiments (3)
- Directed energy deposition (3)
- Electromagnetic weld pool support (3)
- Element transport (3)
- High power laser beam welding (3)
- Inconel 718 (3)
- Laser hybrid welding (3)
- Liquid Metal Embrittlement (3)
- Magnetic field (3)
- Magnetohydrodynamics (3)
- Mathematical modeling (3)
- Mechanical mismatching (3)
- Multi-physical modelling (3)
- Quality assurance (3)
- Simulation (3)
- Welding simulation (3)
- Advanced high strength steels (2)
- Aluminium (2)
- Auftragschweißen (2)
- Austenitic stainless steels (2)
- Bulge effect (2)
- Circumferential weld (2)
- Clad steels (2)
- Cladding parameter (2)
- Coarse-grained heat-affected zone (2)
- Data preparation (2)
- Dimensional accuracy (2)
- Directed Energy Deposition (2)
- Dissimilar metal weld overlays (2)
- Dual phase steel (2)
- Duplex AISI 2205 (2)
- Duplex stainless steel (2)
- Electromagnetic weld pool control (2)
- Electron beam welding (2)
- End crater (2)
- Equivalent heat source (2)
- FEA (2)
- Festigkeit (2)
- Finite element simulation (2)
- Friction stir welding (2)
- Full penetration (2)
- Gap bridgeability (2)
- Grain refinement (2)
- Grain size (2)
- Hardness (2)
- Heat conduction (2)
- Heat treatment (2)
- High-power laser beam welding (2)
- High-strength low-alloy steel (2)
- Hochfester Stahl (2)
- Hot crack (2)
- Hot cracking (2)
- Hybrid welding (2)
- Künstliche Intelligenz (2)
- L-PBF (2)
- Laser (2)
- Laser cladding (2)
- Laser energy distribution (2)
- Laser-Pulver-Auftragschweißen (2)
- Laserhybridschweißen (2)
- Local critical strain (2)
- Matching ferritic welding electrode (2)
- Melt pool dynamics (2)
- Metal mixing (2)
- Nickel (2)
- Nickel alloys (2)
- Numerical modelling (2)
- Numerical process simulation (2)
- Optical flow (2)
- Partial penetration (2)
- Pipe manufacturing (2)
- Pipeline (2)
- Preheating (2)
- Process monitoring (2)
- Process simulation (2)
- Qualitätssicherung (2)
- Ray tracing (2)
- Refill friction stir spot welding (2)
- Residual stress (2)
- Seam geometry (2)
- Single pass welding (2)
- Submerged arc welding (2)
- Superellipse (2)
- Thermal cycles (2)
- Ti-6Al-4V (2)
- Transformable steels (2)
- Weld defects (2)
- Weld pool dynamics (2)
- Weldability (2)
- Wire arc additive manufacturing (2)
- laser welding (2)
- resistance spot welding (2)
- AC magnetic field (1)
- AGIL (1)
- AHSS (1)
- AM (1)
- AM feature integration (1)
- Adaptive control (1)
- Adaptive welding beam oscillation (1)
- Additive Manufacturing (1)
- Advanced High-Strength Steel (AHSS) (1)
- Advanced high strength steel (1)
- Advanced high-strength steel (1)
- Advanced high-strength steels (1)
- AlMg0.7SiTiB filler wire (1)
- Aluminum alloy 2024-T3 (1)
- Aluminum alloys (1)
- Aluminum bronze (1)
- Artificial Intelligence (1)
- As-shielded arc welding (1)
- Austenitic welding electrode (1)
- Automated manufacturing (1)
- Automatisierte Fertigung (1)
- Automobilindustrie (1)
- Automotive application (1)
- Bead-on-plate welds (1)
- Bending test (1)
- Boundary element method (1)
- Build-up strategy (1)
- Bulge formation (1)
- Bulging (1)
- Bulging effect (1)
- Bulging effects (1)
- CFD model (1)
- CO2 lasers (1)
- Carbon dioxide footprint (1)
- Charpy impact toughness (1)
- Cimensional Accuracy (1)
- Clustering (1)
- Coarse grained heat affected zone (1)
- Columnar crystal growth (1)
- Computer vision (1)
- Condition monitoring (1)
- Convolutional neural network (1)
- Corrosion (1)
- Cracking (1)
- Crater (1)
- Critical strain rate (1)
- Cryogenic steel (1)
- Crystal branch development (1)
- DED-EB (1)
- DED-LB (1)
- DIC (1)
- DIP transfer (1)
- Damage prediction (1)
- Deep learning (1)
- Deep penetration laser beam welding (1)
- Deformed geometry (1)
- Dendrite growth (1)
- Density measurement (1)
- Deposition rate (1)
- Deposition welding (1)
- Die-cast aluminum (1)
- Die-casted aluminum (1)
- Digital Image Correlation (1)
- Digitalisierung (1)
- Digitalization (1)
- Digitization (1)
- Direct energy deposition (1)
- Directed Energy Depositio (1)
- Dissimilar joints (1)
- Dissimilar welding (1)
- Distortion (1)
- Duplex (1)
- Duplex stainless steels (1)
- Duplex steels (1)
- EBAM (1)
- EBSD (1)
- Economic wide technology replacement (1)
- Edge quality (1)
- Electro-thermomechnical model (1)
- Electrode geometry (1)
- Electromagnetic (1)
- Electromagnetic backing (1)
- Electromagnetic influence (1)
- Electromagnetic stirring (1)
- Electromagnetic support (1)
- Electromagnetic supported degassing (1)
- Electromagnetic weld pool support system (1)
- Elektromagnetische Badstütze (1)
- Elektromagnetische Schmelzbadunterstützung (1)
- Embedded electronics (1)
- Energy efficiency (1)
- Energy input (1)
- Energy parameters of the arc (1)
- Environment (1)
- Environmental impact categories (1)
- Equivalent stress concentration factors (1)
- FEM (1)
- Fatigue tests (1)
- Ferromagnetic steel (1)
- Ferromagnetic steels (1)
- Fiber laser (1)
- Filler wire (1)
- Filler wire mixing (1)
- Fine-grained Steel (1)
- Finite Element Method (1)
- Finite element analysis (1)
- Finite element method (1)
- Finite element method (FEM) (1)
- Flange width (1)
- Flüssigmetallinduzierte Rissbildung (1)
- Fresnel reflection (1)
- Full penetration welding (1)
- Fusion zone (1)
- Fusion zone profile (1)
- Fusion zone size (1)
- Fusion zone, nickel alloys (1)
- GMA surfacing (1)
- GMA welding (1)
- GTAW (1)
- Galvanized steel (1)
- Gap bridging (1)
- Gas shielded arc welding (1)
- General analytical solutions (1)
- Gleeble experiments (1)
- Gleeble testing (1)
- Grade S960QL steel (1)
- Grain structure (1)
- Greenhouse gas mitigation (1)
- Greens function method (1)
- HSLA (1)
- Hardly separable problem (1)
- Hartmann effect (1)
- Heat Input (1)
- Heat Treatment (1)
- Heat flow (1)
- Heat input (1)
- High brightness (1)
- High power (1)
- High power welding (1)
- High process speeds (1)
- High strength steel (1)
- High strength steels (1)
- High-Power Welding (1)
- High-power fibre laser (1)
- High-power laser beam (1)
- High-strength fine-grained steels (1)
- High-strength steel sheets (1)
- Highspeed-plasma-laser-cladding (1)
- Hohlprofilknoten (1)
- Hold time (1)
- Hot Cracks (1)
- Hot cracking test (1)
- Hybrid Laser Arc Welding (1)
- Hybrid Laser-Arc Welding (1)
- Hybridschweißen (1)
- Imaging (1)
- Impact absorbed energy (1)
- In situ strain (1)
- Inconel 625 (1)
- Inconel 939 (1)
- Industrial and Manufacturing Engineering (1)
- Instumented indentation test (1)
- Integrated alignment features (1)
- Kaltzähe Stähle (1)
- Kerbspannungskonzept (1)
- Keyhole collapse (1)
- Keyhole mode welding (1)
- Keyhole stability (1)
- Kl (1)
- Körperschall (1)
- LMD (1)
- LME (1)
- Lamé curves (1)
- Lamé curves approximation (1)
- Laser Beam Welding (1)
- Laser Metal Deposition (1)
- Laser Metal Deposition (LMD) (1)
- Laser Powder Bed Fusion (1)
- Laser Welding (1)
- Laser beam Welding (1)
- Laser beam weliding (1)
- Laser cutting (1)
- Laser implantation (1)
- Laser keyhole welding (1)
- Laser melting (1)
- Laser metal fusion (1)
- Laser powder bed fusion (1)
- Laser powder-based directed energy deposition (1)
- Laser surfacing (1)
- Laser-Pulver-Auftragsschweißen (1)
- Laser-hybrid welding (1)
- Laser-metal-deposition (1)
- Laserschweißen (1)
- Life cycle assessment (1)
- Life cycle assessment (LCA) (1)
- Life-cycle assessment (1)
- Lifetime (1)
- Liquid Metal Embrittlement (LME) (1)
- Local fatigue spproaches (1)
- Lokale Effekte (1)
- Longitudinal weld (1)
- Lorentz force (1)
- Low alloy steels (1)
- Low feed rates (1)
- Low heat input GMA welding (1)
- Low heat input Gma welding (1)
- Lötrissigkeit (1)
- MAG welding (1)
- MHD (1)
- Magnesium Alloy (1)
- Magnesium alloy (1)
- Magnetic bath support (1)
- Manganese (1)
- Marangoni flow (1)
- Matching ferritic filler metal (1)
- Material modeling (1)
- Mechanical Properties (1)
- Mechanical properties of the joints (1)
- Mechanical property (1)
- Mechanical-technological properties (1)
- Metallic vapour plume (1)
- Microstructure Tensile strength (1)
- Misalignment of edges (1)
- Model calibration (1)
- Model order reduction (1)
- Modellierung (1)
- Modified spray arc (1)
- Molten pool dynamics (1)
- Multi-materials joining (1)
- Multi-regional inputeoutput data (1)
- Multiple reflections (1)
- Narrow gap welding (1)
- Natural convection (1)
- Neural networks (1)
- Neuronales Netz (1)
- Ni-based austenitic filler metal (1)
- Ni-based austenitic welding electrode (1)
- Ni-based superalloy (1)
- NiCrBSi (1)
- Notch stress approach (1)
- Novel metrology (1)
- Novel optical measurement (1)
- Numerical Simulation (1)
- Numerical analysis (1)
- Numerical simulations (1)
- Numerical welding simulation (1)
- Numerical welding simulations (1)
- Numerische Simulation (1)
- Open science (1)
- Open source (1)
- Optical measurement (1)
- Optical measurment technique (1)
- Oscillating magnetic field (1)
- Oscillating vapor plume (1)
- PBF-LB/M (1)
- Partial penetration welding (1)
- Path planning (1)
- Periodic solidification pattern (1)
- Phase field method (1)
- Phase transformation (1)
- Pipe Welding (1)
- Pipe weld preparation (1)
- Pipeline steel of grade X120 (1)
- Plane crystalization (1)
- Plasma cutting (1)
- Plasma-cut samples (1)
- Plastic deformation (1)
- Plume heating (1)
- Porosity reduction (1)
- Post-weld heat treatment (1)
- Precipitation hardening aluminum alloys (1)
- Process chain (1)
- Process innovations (1)
- Proper generalized decomposition (1)
- Prozessüberwachung (1)
- Pufferschichten (1)
- Pulsed laser beam welding (1)
- Qualität (1)
- RSW (1)
- Ray teacing (1)
- Ray-tracing methods (1)
- Repair welding (1)
- Research data management (1)
- Resistance Spot Welding (RSW) (1)
- Rissanfälligkeit (1)
- Rissbildung (1)
- SMAW (1)
- Schutzgas (1)
- Schutzgasschweißen (1)
- Schweißeignung (1)
- Schweißnahtgeometrie (1)
- Schweißsimulation (1)
- Schweißunregelmäßigkeiten (1)
- Secondary heat source (1)
- Selective Laser Melting (1)
- Selektive-laser-melting (1)
- Sensor (1)
- Shielding gases (1)
- Ship building (1)
- Shipbuilding steel (1)
- Single-pass welding (1)
- Software (1)
- Stainless Steel (1)
- Stainless steels (1)
- Steady-state weld pool (1)
- Steel and Al (1)
- Strain fields prediction (1)
- Strain measurement (1)
- Strain rate (1)
- Strain-rate (1)
- Stress-strain behavior (1)
- Super martensitic filler material (1)
- Superalloy (1)
- Surface cracks (1)
- Surface structuring (1)
- Sustainability assessment (1)
- TIG welding (1)
- TRIP - transformation induced plasticity (1)
- Tandem gas metal arc welding (1)
- Tandem welding (1)
- Technical crack detection (1)
- Temperature distribution (1)
- Tensile properties (1)
- Tensile resistance spot welding experiment (1)
- Testing method (1)
- Texture (1)
- Thermal softening (1)
- Thermo physical simulation (1)
- Thermo-fluid dynamics (1)
- Thermo-fluid flow (1)
- Thick materials (1)
- Thick plate welding (1)
- Thick plates (1)
- Thick steel plates (1)
- Thick-Walled Steel (1)
- Thick-plate welding (1)
- Thick-walled Structures (1)
- Thin steel plates (1)
- Three-dimensional crystallization (1)
- Titanium alloy (1)
- Toughness (1)
- Transformation induced plasticity (TRIP) (1)
- Transient heat transfer (1)
- Tubular X-joints (1)
- Tubular joints (1)
- Tungsten carbide (1)
- Turbine blade (1)
- Turbine components (1)
- Two-dimensional solidification (1)
- Two-run welding technique (1)
- Ultrasonic vibration (1)
- Unterpulverschweißen (1)
- V-notch impact toughness (1)
- Vakuum (1)
- Vapor recondensation (1)
- Vaporization (1)
- Verzug (1)
- Viscoplasticity (1)
- Wear resistance (1)
- Weld end crater (1)
- Weld imperfections (1)
- Weld pool (1)
- Weld pool behavior (1)
- Weld pool modeling (1)
- Weld pool support (1)
- Weld root (1)
- Weld seam geometry (1)
- Welding (1)
- Welding Current (1)
- Welding Simulation (1)
- Welding parameter (1)
- Welding process simulation (1)
- Welding residual stresses (1)
- Welding thermal cycle (1)
- Weldx (1)
- Werkstofffragen (1)
- Werkstoffranking (1)
- Widerstandspressschweißen (1)
- Windkraftanlagen (1)
- Wineglass shape (1)
- Wire electron beam additive manufacturing (1)
- Wire feed laser beam welding (1)
- Wire-based additive manufacturing (1)
- YAG lasers (1)
- Zinc (1)
- Zinc coated steel (1)
- Zink (1)
- Zinkbeschichtung (1)
- cryogenic steel (1)
- digital image correlation (1)
- dual phase steel (1)
- hardness (1)
- hochfeste Stähle (1)
- local effects (1)
- microstructure (1)
- quality assurance (1)
- sensitivity analysis (1)
- strength (1)
- tensile strength (1)
- vacuum (1)
- welding residual stresses (1)
- Äquivalente Spannungskonzentrationsfaktoren (1)
- Ökonomische und ökologische Vorteile (1)
- ГИДРОДИНАМИКА (1)
- КОНВЕКЦИЯ (1)
- ЛАЗЕРНАЯ СВАРКА (1)
- МЕТОД КОНЕЧНЫХ ЭЛЕМЕНТОВ (1)
- СВАРОЧНАЯ ВАННА (1)
- ТЕМПЕРАТУРНОЕ ПОЛЕ (1)
- ТЕПЛОПРОВОДНОСТЬ (1)
- ЧИСЛЕННОЕ МОДЕЛИРОВАНИЕ (1)
Organisationseinheit der BAM
- 9 Komponentensicherheit (137)
- 9.3 Schweißtechnische Fertigungsverfahren (135)
- 5 Werkstofftechnik (2)
- 5.2 Metallische Hochtemperaturwerkstoffe (2)
- 5.5 Materialmodellierung (1)
- 7 Bauwerkssicherheit (1)
- 7.7 Modellierung und Simulation (1)
- 9.0 Abteilungsleitung und andere (1)
- 9.6 Additive Fertigung metallischer Komponenten (1)
Electromagnetic stirring is known to promote material flow, reduce porosity, uniform elements distribution, and refine grain in laser beam welding (LBW), which enhances the applicability of LBW in various industries. In this study, a phase-field model of dendrite growth in AA5754 Al alloy electromagnetic stirring laser beam welding was established. The model considered the thermal electromagnetic Lorentz force resulting from the interaction between the electric field generated by the Seebeck effect and the magnetic field, as well as the temperature gradient and solidification rate of the solidification interface obtained from the computational fluid dynamics electromagnetic stirring LBW model. The variation rules of dendrite growth with different magnetic parameters and effects are analyzed. Comprehensively, the magnetic field promotes the solidification rate, thus promoting interfacial instability and a large magnetic flux density leads to a faster interface instability. The solidification rate as well as the temperature gradient affect the growth rate, and the accelerated growth caused by the so lidification rate with a high frequency and a large magnetic flux density effectively inhibits the slow growth caused by the temperature gradient. The thermal electromagnetic Lorentz force is the main factor for the branch increment at low frequencies, while both thermal electromagnetic Lorentz force and temperature gradient in crease the number of branches at high frequencies. The calculated average branch numbers considering various factors in the stable stage under different magnetic parameters were consistent with the results of the scanning electron microscope tests.
Despite the advances in hardware and software techniques, standard numerical methods fail in providing real-time simulations, especially for complex processes such as additive manufacturing applications. A real-time simulation enables process control through the combination of process monitoring and automated feedback, which increases the flexibility and quality of a process. Typically, before producing a whole additive manufacturing structure, a simplified experiment in the form of a beadon-plate experiment is performed to get a first insight into the process and to set parameters suitably. In this work, a reduced order model for the transient thermal problem of the bead-on-plate weld simulation is developed, allowing an efficient model calibration and control of the process. The proposed approach applies the proper generalized decomposition (PGD) method, a popular model order reduction technique, to decrease the computational effort of each model evaluation required multiple times in parameter estimation, control, and optimization. The welding torch is modeled by a moving heat source, which leads to difficulties separating space and time, a key ingredient in PGD simulations. A novel approach for separating space and time is applied and extended to 3D problems allowing the derivation of an efficient separated representation of the temperature.
The results are verified against a standard finite element model showing excellent agreement. The reduced order model is also leveraged in a Bayesian model parameter estimation setup, speeding up calibrations and ultimately leading to an optimized real-time simulation approach for welding experiment using synthetic as well as real measurement data.
A method of solving the thermo-fluid dynamics problem is presented, enabling the prediction of the shape and dimensions of the weld pool during keyhole laser welding of thick plates. It is shown that the rear weld pool boundary can be satisfactorily approximated by a set of superellipses (Lamé curves). The presence of a convex rear weld pool boundary in the mid-plane has been observed experimentally and reproduced numerically. It was shown that in this zone the concentration of liquating impurities increases and the local solidification temperature decreases, contributing to the susceptibility to hot cracking.
Numerical and experimental assessment of liquid metal embrittlement in externally loaded spot welds
(2024)
Zinc-based surface coatings are widely applied with high-strength steels in automotive industry. Some of these base materials show an increased brittle cracking risk during loading. It is necessary to examine electrogalvanized and uncoated samples of a high strength steel susceptible to liquid metal embrittlement during spot welding with applied external load. Therefore, a newly developed tensile test method with a simultaneously applied spot weld is conducted. A fully coupled 3D electrical, thermal, metallurgical and mechanical finite element model depicting the resistant spot welding process combined with the tensile test conducted is mandatory to correct geometric influences of the sample geometry and provides insights into the sample’s time dependent local loading. With increasing external loads, the morphology of the brittle cracks formed is affected more than the crack depth. The validated finite element model applies newly developed damage indicators to predict and explain the liquid metal embrittlement cracking onset and development as well as even ductile failure.
A fundamental study of physical mechanisms of wineglass-shaped fusion zone profile in laser melting
(2024)
The fusion zone geometry in laser melting processes e.g., laser welding and laser-based additive manufacturing, of metallic materials has commonly a wineglass-shaped profile which is critical to the grain orientation and stress distribution. Hereby, we adopt for the first time a decoupling work through a combination of multi-physics modelling and experiments to reveal the fundamental mechanisms of this special morphology. Two physicsbased easy-to-use metal vapour models are proposed to consider the vapour’s momentum and thermal effects separately. It is found that the direct laser energy absorption and Marangoni shear stress which are widely hypothesised to dominate the wineglass-shape formation show only a minor influence. The additional heating from the metallic vapour plume rather than its momentum impact contributes predominantly to the enlarging of the molten pool top region, resulting directly in the formation of the wineglass-shaped fusion zone. The generality of the plume heating effect is also validated in two types of materials (steel and Al) in a wide range of parameters.
Beim Unterpulverschweißen sind die Prozessgeräusche ein Indikator für eine gute Fügequalität. Diese Beurteilung kann i.d.R. nur von einer erfahrenen Fachkraft durchgeführt werden. Eine kürzlich entwickelte künstliche Intelligenz kann automatisch das akustische Prozesssignal anhand vortrainierter Merkmale klassifizieren und die Fügequalität anhand des Geräuschs beurteilen. Der Algorithmus, einmal richtig trainiert, kann den Prüfaufwand beim Unterpulverschweißen deutlich reduzieren.
The effect of the oscillating metal vapor plume on the keyhole and molten pool behavior during the laser beam welding of AlMg3 aluminum alloys is investigated by experimental and numerical methods. The real-time height of the metal vapor plume is measured by high-speed camera observation. The obtained experimental results are used to evaluate the additional heating source and laser beam attenuation caused by the scattering and absorption based on the Beer–Lambert theory. Furthermore, the dynamic behavior of the metal vapor plume is incorporated into a 3D transient heat transfer and fluid flow model, coupled with the ray tracing method, for the laser beam welding of the AlMg3 alloy. It is found that additional heating resulting from the scattered and absorbed laser beam energy by the metal vapor plume significantly expands the shape of the molten pool on the top region. Moreover, the oscillating metal vapor plume caused the fluctuation of the high-temperature region in the molten pool. The probability of keyhole collapse at the bottom increases 17% due to the oscillating laser power induced by the laser beam attenuation. The internal interplay between the metal vapor plume, molten pool shape, and keyhole collapse is obtained. The developed model has been validated by experiments, which shows a good agreement.
The strain field can reflect the initiation time of solidification cracks during the welding process. The traditional strain measurement is to first obtain the displacement field through digital image correlation (DIC) or optical flow and then calculate the strain field. The main disadvantage is that the calculation takes a long time, limiting its suitability to real-time applications. Recently, convolutional neural networks (CNNs) have made impressive achievements in computer vision.
To build a good prediction model, the network structure and dataset are two key factors. In this paper, we first create the training and test sets containing welding cracks using the controlled tensile weldability (CTW) test and obtain the real strain fields through the Lucas–Kanade algorithm. Then, two new networks using ResNet and DenseNet as encoders are developed for strain prediction, called StrainNetR and StrainNetD. The results show that the average endpoint error (AEE) of the two networks on our test set is about 0.04, close to the real strain value. The computation time could be reduced to the millisecond level, which would greatly improve efficiency.
A technique for calculating the main solidification parameters for a two-dimensional columnar crystal growth during complete penetration laser beam welding of thin steel sheets was developed. Given that the weld pool interface is described by Lamé curves (superellipses) within the horizontal plane of growth, general analytical solutions were derived for the geometry of the crystal axis and the corresponding growth rate and cross-sectional area of the crystal. A dimensionless analysis was performed to provide insights on the dependence of the solidification parameters on the shape and dimensions of the rear part of the weld pool boundary. The derived solutions were applied for the case of complete penetration laser beam keyhole welding of 2 mm thick 316L austenitic chromium-nickel steel sheets. It was shown that the reconstruction of the weld pool boundary with Lamé curves provides higher accuracy and flexibility compared to results obtained with elliptical functions. The validity of the proposed technique and the derived analytical solutions was backed up by a comparison of the obtained solutions to known analytical solutions and experimentally determined shapes and sizes of the crystals on the top surface of the sheet. The dimensions of the calculated crystal axis correlated well with the experimentally obtained results.
AbstractLaser beam welding has become widely applied in many industrial fields in recent years. Solidification cracks remain one of the most common welding faults that can prevent a safe welded joint. In civil engineering, convolutional neural networks (CNNs) have been successfully used to detect cracks in roads and buildings by analysing images of the constructed objects. These cracks are found in static objects, whereas the generation of a welding crack is a dynamic process. Detecting the formation of cracks as early as possible is greatly important to ensure high welding quality. In this study, two end-to-end models based on long short-term memory and three-dimensional convolutional networks (3D-CNN) are proposed for automatic crack formation detection. To achieve maximum accuracy with minimal computational complexity, we progressively modify the model to find the optimal structure. The controlled tensile weldability test is conducted to generate long videos used for training and testing. The performance of the proposed models is compared with the classical neural network ResNet-18, which has been proven to be a good transfer learning model for crack detection. The results show that our models can detect the start time of crack formation earlier, while ResNet-18 only detects cracks during the propagation stage.