Laser Welding Of Sheet Metals Research Articles

Industrial Laser Welding Defect Detection and Image Defect Recognition Based on Deep Learning Model Developed

Aiming at the problem of the poor robustness of existing methods to deal with diverse industrial weld image data, we collected a series of asymmetric laser weld images in the largest laser equipment workshop in Asia, and studied these data based on an industrial image processing algorithm and deep learning algorithm. The median filter was used to remove the noises in weld images. The image enhancement technique was adopted to increase the image contrast in different areas. The deep convolutional neural network (CNN) was employed for feature extraction; the activation function and the adaptive pooling approach were improved. Transfer Learning (TL) was introduced for defect detection and image classification on the dataset. Finally, a deep learning-based model was constructed for weld defect detection and image recognition. Specific instance datasets verified the model’s performance. The results demonstrate that this model can accurately identify weld defects and eliminate the complexity of manually extracting features, reaching a recognition accuracy of 98.75%. Hence, the reliability and automation of detection and recognition are improved significantly. The research results can provide a theoretical and practical reference for the defect detection of sheet metal laser welding and the development of the industrial laser manufacturing industry.

The effect of laser welding modes on mechanical properties and microstructure of 304L stainless steel parts fabricated by laser-foil-printing additive manufacturing

The success of laser-foil-printing (LFP) additive manufacturing depends critically on the laser welding of sheet metals onto the substrate or the previous layer during the part fabrication process. The welding can be generally categorized into two modes: conduction mode and keyhole mode. In this study, 304L stainless steel parts fabricated by the LFP process using the two laser welding modes are compared. The porosity, microstructure, and tensile properties of the fabricated parts in these two modes are measured and compared in the laser scanning direction (X) and part building direction (Z). The parts fabricated in the conduction mode have a higher density than those fabricated in the keyhole mode. On the tensile properties, both yield strength (YS) and ultimate tensile strength (UTS) have insignificant differences statistically based on the ANOVA analysis between the tensile specimens fabricated with the two welding modes by the LFP process. However, the conduction-mode parts have higher elongation than the keyhole-mode parts in both the X and Z directions, and the difference is especially significant in the Z direction. By using the electron backscattered diffraction (EBSD), it was found that the much higher ductility for the conduction-mode parts in the Z-axis direction is mainly due to the distinct grain boundary interface density in the Z-axis direction between the two welding modes.

A Multi-Sensor Data Fusion System for Laser Welding Process Monitoring

Most existing laser welding process monitoring (LWPM) technologies focus on detecting post-process defects. However, in sheet metal laser welding applications such as welding of electronic consumer products during mass production, in-process defect detection is more important. In this article, a compact LWPM system using multi-sensor data fusion to detect in-process defects has been built. This system can collect the time series of plasma intensity, light intensity and temperature data for feature analysis. To verify the system's effectiveness, a plasma-light-temperature dataset has been compiled, which consists of 5,836 samples of nine classes, including one positive class and eight negative classes of typical in-process defects. A multi-sensor data fusion network based on a convolution neural network for in-process defect detection, called IDDNet, has also been proposed. Experimental results have demonstrated that IDDNet can achieve better multi-classification results than the support vector machine, with an overall accuracy of 97.57%. In particular, considering this monitoring process as a binary classification problem, IDDNet can achieve a 99.42% accuracy. Moreover, IDDNet can reach an average speed of 0.79ms per sample on a single GTX 1080ti graphics card, which meets the real-time requirement for industrial production. The proposed LWPM system has been successfully verified in real applications of sheet metal laser welding.

Small Batch Laser Welding Using Light Fasteners and Laser Tack Welding

Laser welding is known for its low heat input compared to arc welding methods. This could enable laser welding of sheet metals with lighter fastening solutions and less time-consuming tack welding alternatives. A feasibility study was carried out to study four different corner joint types for 2 mm thick cold rolledcold-rolled steel sheet by using filler-free laser welding. The aim of the research was to get more experimental knowledge about the laser welding of corner joints. Also possible benefits concerning faster manufacturing times and smaller costs by developing fastening applications for small batch laser welding was to be studied in practice. The 170 mm long joints were welded without air gap or pressing. All corner joint types proved to be weldable with a continuous wave Yb:YAG diode-pumped disk laser. It was also found during the With the experiment it was also found out that laser welding enables the use of light and inexpensive fasteners such as magnetic holders in steadinstead of traditional clamps and fixturing. With some joint types, the insufficient fastening power of magnetic fasteners against distortions was compensated by making a spot-like laser tack weld toat the end of the weld before welding the actual seam. This showed that it is possible to make precise and small tack welds with a laser and to use laser -tacking in sheet metal assembly.

Developments and Trends in Laser Welding of Sheet Metal

There is some remarkable progress in laser beam welding of sheet metal which is driven by the advent of improved laser systems and process technologies. Here, potentials for reducing distortion and avoiding hot cracking are highlighted, and examples of current developments are given in the field of thin and thick sheet metal welding including spot welding of difficult-to-weld materials and material combinations.

Robust Fixture Configuration Design for Sheet Metal Assembly With Laser Welding

Fixturing plays an important role in the quality of metal fit-up for sheet metal assembly with laser welding. To reduce the sensitivity of the designed fixture configuration to location fluctuation, this paper provides a quality design of the fixture configuration for sheet metal laser welding. A generic robust design methodology, labeled the two-stage response surface methodology, is developed in the robust design model. The first stage is to find the Robust Design Space (RDS), in which robust solutions with higher degrees of insensitivity reside. Within the RDS, a second-order response surface model can be fitted by a 3k fractional factorial design in the second stage. Based on the resultant response model, the robust fixturing scheme and the influential design locators can be obtained by an optimization and a statistical screening techniques. The degree of metal fit-up is taken as the performance characteristic of the robust design. An example illustrates how the robust design method effectively meets the quality requirements of the fixturing design.

Penetration control in laser welding of sheet metal

For economical reasons it is desirable to apply the highest possible speed during laser welding. Increasing the welding speed at a certain laser power might result in insufficient penetration of the weld. This work describes the design of a feedback controller, which is able to maintain full penetration in mild steel sheets. An optical detector, which is placed inside the Nd:Yttrium–aluminium–garnet laser source, measures the intensity of the weld-pool radiation through the optical fiber. This sensor signal is used as input of a feedback control system. A model, which describes the dynamic response of the welding process including the sensor and laser source dynamics, has been obtained, using system identification techniques. The input of this model is the laser power and the output is the modeled sensor signal. Based on this dynamic model a feedback controller is designed and implemented. The laser power is used as an actuator. The controller maintains full penetration during welding of tracks with disturbances like sudden artificial power fluctuations and sudden speed changes. This feedback controller opens the possibility to optimize the welding speed without risking lack of penetration.

Weld Pattern Design for Sheet Metal Laser Welding Considering Fixturing Quality

In sheet metal assembly by laser welding, metal fit-up is an important specification for achieving welding quality. The fixture plays an important role in satisfying the intimate metal fit-up that laser weld requires. The fixturing quality for sheet metal laser welding is directly related to the assembly weld patterns used (weld location, weld length, etc.). The design of assembly weld patterns is a critical phase in the fixture design cycle. Traditionally, the determination of the weld pattern is based on the designer's experience. Because of this it is quite easy to cause unexpected deviations from the assembly weld quality requirements. In this study, a new computer-aided design approach for the assembly weld pattern is developed, where the sources of variation in the weld areas of the parts are considered in detail. Using this approach, the weld location and the weld length obtained are much more reasonable and cost-ju.itified. A simple example and a case study show that the approach presented for assembly weld pattern design can reasonably meet the fixturing quality requirements.

Phase change problem and effects of geometrical constants on weld pool geometry in sheet metal laser welding

A three-dimensional quasi-state heat conduction model is presented for the solid/liquid interface in laser welding of thin sheet metals. The vapour plasma plume effect is incorporated into the model by considering the electromagnetic field equation to determine the laser power reaching the substrate surface after passing through the plume region. Optical properties, such as the dielectric constant and electrical conductivity of plume, and the thermal conductivity of the vapour of stainless steel 316 in the plume region are estimated. Elliptic-paraboloid weld pool geometry is considered and analytic expressions for temperature distributions are obtained in the solidand liquidregions based on theweld pool geometry. Experimental and theoretical results for the weld depths and widths areillustratedfor process parameters such as the laser power, welding speed, and weld pool shape factors in x and y directions.

Effects of absorptivity, shielding gas speed, and contact media on sheet metal laser welding

A three-dimensional quasi-steady state heat conduction model is developed for laser welding of sheet metals. The heat flux at the surface of the workpiece is considered to be due to a moving Gaussian laser beam. An analytical expression is obtained for the temperature distribution by solving the conduction problem using the Fourier integral transform technique. This expression is used to locate the melting temperature isotherm, and thereby determine the weld depth and width. Experimental and theoretical results for the weld depths and widths are illustrated for different welding parameters such as the laser power, absorptivity, welding speed, and shielding gas speed. The theory and experiment are found to agree reasonably well. The effects of absorptivity, shielding gas speed, and heat loss due to different contact media at the bottom surface of the workpiece are also investigated, and are found to be significant for thin metal laser welding.

Determination of weld pool shape and temperature distribution by solving three-dimensional phase change heat conduction problem

A quasi-steady state heat conduction model considering phase change for laser welding of sheet metals is presented. The method of least squares was used to solve the governing equation in the liquid phase. The solution provides the weld pool shape and the temperature distribution in the weld pool. Results for stainless steel were compared with experimental data and fairly good agreement was obtained between the theoretical predictions and the experimental data.

Weld geometry and tensile strength in laser welded thin sheet metals

Weld geometries and their effects on the ultimate tensile strength (UTS) of welded specimens were studied experimentally for type 316 stainless steel sheets. Bead on plate welding with 0.1 and 0.2 mm thick workpieces and lap welding with 0.1 mm thick workpieces were carried out. The results showed that the strength of lap welds is influenced by the weld geometry to a large extent. A three-dimensional quasi-steady state heat conduction model was developed to understand the heat flow mechanism during laser welding of sheet metals of finite thickness. The temperature distribution and weld geometry were calculated using the mathematical model and the theoretical results were found to compare well with experimental data. More energy is used to produce melt pools in thinner workpieces than in thicker ones. The model can be used to select suitable process parameters to achieve a predetermined UTS by controlling the weld geometry.