Welding System Research Articles

Study of optimization for material processing parameters by means of probabilistic methodology for multi-objective optimization

Optimization for material processing parameters is a typical problem of multi-objective optimization, therefore selection and use of proper multi-objective optimization approach is indispensible. The inherent characteristic of newly proposed probabilistic methodology for multi-objective optimization is that it is with the feature of optimization of multiple objectives at the same time in viewpoint of system theory and in spirit of probability theory. In the present paper, the probabilistic methodology is employed to perform the designs of materials processing for improving quality and cost saving at the same time. The laser welding process of ANSI 304 austenitic stainless steel by using a pulsed Nd: YAG laser welding system and thin-wall machining of milling aluminum alloy 2024-T351 are taken as two examples. The quantitative optimum design of materials processing is performed equitably by conducting the assessment of preferable probability of each alternative. The studies indicate that: (1). the optimized parametric combination for the laser welding process of 2 mm thickness ANSI 304 austenitic stainless steel by using a pulsed Nd: YAG laser welding system is at laser parameters of 2.7 kW peak power, welding speed of 2 cm/min and pulse duration of 4 ms; (2). the optimized combination parameter for the thin-wall machining of milling aluminum alloy 2024-T351 is at tool diameter of 8 mm, feed per tooth of 0.06 mm/z, axial cut depth of 24 mm and radial cut depth of 0.625 mm. The optimal configurations guarantee the comprehensive quality of product and reducing energy consumption.

A guidance system for robotic welding based on an improved YOLOv5 algorithm with a RealSense depth camera

Vision-based automatic welding guidance technology plays an essential role in robotic welding. A laser vision sensor (LVS) relies on manual intervention to guide the robot when near the workpiece, which reduces the autonomy of the welding robot and productivity. To solve this problem, a robot welding guidance system based on an improved YOLOv5 algorithm with a RealSense Depth Camera was proposed. A coordinate attention (CA) module was embedded in the original YOLOv5 algorithm to improve the accuracy of weld groove detection. The center of the predicted frame of the weld groove in the pixel plane was combined with the depth information acquired by a RealSense depth camera to calculate the actual position of the weld groove. Subsequently, the robot was guided to approach and move over the workpiece. Then, the LVS was used to guide the welding torch installed at the end of the robot to move along the centerline of the weld groove and complete welding tasks. The feasibility of the proposed method was verified by experiments. The maximum error was 2.9 mm in guiding experiments conducted with a distance of 300 mm between the depth camera and the workpiece. The percentage error was within 2% in guidance experiments conducted with distances from 0.3 to 2 m. The system combines the advantages of the depth camera for accurate positioning within a large field and the LVS for high accuracy. Once the position of the weld groove of the workpiece to be welded has been determined, the LVS combined with the robot can easily track the weld groove and realize the welding operation without manual intervention.

Laser welding monitoring with multisensory data fusion: A brief review

As digital manufacturing is being implemented across industries, the automation of the laser welding process is a crucial step to enhance production efficiency. To monitor the in-situ welding process, there are several approaches to detect the electromagnetic and mechanical waves on various frequencies for comprehending laser beam-material interaction. Five sensing techniques, namely the optical microphone, welding camera, inline coherent imaging, infrared camera, and heat flux sensor, can be employed to identify distinct features in the laser welding process. These features include pore formation, melt pool geometry, weld bead topography, keyhole depth, and thermal distribution. The discussion of a proposed welding system designed with compatibility for multisensory data fusion is included, both on its capabilities and potential challenges, to offer guidance of welding monitoring.

Strategies for a scalable multi-robot large scale wire arc additive manufacturing system

Conventional robotic wire arc additive manufacturing technologies enable the rapid production of moderate-sized components using low-cost wire feedstocks and robotic welding systems. Efforts to date have primarily focused on single robot solutions. However, new configurations are possible with coordination of multiple robots and multi-degree of freedom positioners. This paper describes a new multi-agent control paradigm that enables multiple robots to work collaboratively on manufacturing a single component on a rotating platform. The advantages of this approach are increased deposition rate and productivity. This paper demonstrates this control strategy on a 19 degrees-of-freedom platform based on three wire arc additive systems surrounding a single rotating platform.

Temperature monitoring system of friction stir welding based on digital twin

ABSTRACT Temperature field distribution of friction stir welding (FSW) influences weld quality directly, so real-time monitoring of the welding temperature is significant. However, it is difficult to monitor the temperature in the core zone due to mechanical obstructions, material plastic deformation and complex thermal-mechanical coupling. To tackle this issue, this study develops a digital twin-based temperature monitoring system of FSW. Initially, a five-dimensional integrated framework based on the digital twin concept is proposed, outlining the process of building a digital twin-based temperature monitoring system of FSW. Subsequently, a motion simulation model of FSW is established, and synchronous motion simulation of the welding process is achieved. Real-time temperature readings from the FSW workpiece surface are gathered via an infrared thermal imager and synchronously transmitted to the FSW temperature monitoring system using socket communication. Additionally, a predictive model utilizing Support Vector Regression (SVR) is incorporated, enabling real-time and precise prediction of extremum temperatures in the core zone and over-limit alarm functionality. Finally, the temperature monitoring system of FSW, grounded in the digital twin concept and integrating the outlined models and features, is developed and experimentally validated. The system enables operators to exercise timely control over the welding process to ensure weld quality.

3DWS: reliable segmentation on intelligent welding systems with 3D convolutions

AbstractAutomated industrial welding processes depend on a large number of factors interacting with high complexity resulting in some sporadic and random variability of the manufactured product that may affect its quality. It is therefore very important to have an accurate and stable quality control. In this work, a deep learning (DL) model is developed for semantic segmentation of weld seams using 3D stereo images of the seam. The objective is to correctly identify the shape and volume of the weld seam as this is the basic problem of quality control. To achieve this, a model called UNet$${\mathcal {L}}$$ L ++ has been developed, based on the UNet and UNet++ architectures, with a more complex topology and a simple encoder to achieve a good adaptation to the specific characteristics of the 3D data. The proposed model receives as input a voxelized 3D point cloud of the freshly welded part where noise is abundantly visible, and generates as output another 3D voxel grid where each voxel is semantically labeled. The experiments performed with parts built by a real weld line show a correct identification of the weld seams, obtaining values between 0.935 and 0.941 for the Dice Similarity Coefficient (DSC). As far as the authors are aware, this is the first 3D analysis proposal capable of generating shape and volume information of weld seams with almost perfect noise filtering.

Performance Evaluation of Underwater (UW) Welding System with Friction Stir Welding (FSW) Method on 316L Stainless Steel Exposed to Sea Water

Friction Stir Welding (FSW) is a solid-state welding technique that can produce high-quality joints without defects that commonly occur in liquid welding. However, FSW has limitations in underwater applications due to the friction between the tool and the material that causes a decrease in heat efficiency and shear force. To overcome this problem, this study proposes an underwater welding (UW) system with the FSW method on 316L stainless steel exposed to seawater. This UW-FSW system uses a high-speed rotating tool surrounded by an inert gas shroud to prevent direct contact between the tool and seawater. The aim of this study is to evaluate the performance of this UW-FSW system in terms of mechanical properties, microstructure, and corrosion resistance of 316L stainless steel joints. The results of this study show that the UW-FSW system can produce joints with better tensile strength, hardness, and corrosion resistance than conventional FSW. This is due to the rapid cooling, reduction of oxidation, and formation of a thicker passive layer on the joint surface. This study provides a contribution to the development of environmentally friendly and efficient underwater welding technology.

Short time resistance spot welding of 1.2Gpa ultra-high strength steel using high frequency power supply

The task of 1.2 GPa ultra-high strength steel sheet in short time’s high current spot welding has been clarified. High current and short time spot welding system and high frequency power supply has been developed. In order to prevent spatter, new dual-pulse welding method in which primary energization, cooling and secondary energization has been proposed. By using this novel welding method, nugget diameter and tensile shear strength satisfied the target and spatter did not occur. New method of 1.2 GPa ultra-high strength steel sheet in short time and high current spot welding has been established.

Versatile robotic welding system integrating laser positioning, trajectory fitting and real-time tracking

The three welding modes of laser positioning, trajectory fitting and real-time tracking are key links for flexible robotic welding, because they directly affect the adaptability of welding robots for complex structural parts. Nevertheless, there are few studies on the integration of laser positioning, trajectory fitting and real-time tracking welding. Aiming at the drawback of that the robot cannot efficiently match the corresponding welding process between different working conditions such as short seam, spatial curve seam and long seam welding, a control scheme that can integrate the above three welding modes is proposed in this paper. First, the welding requirements of laser positioning, trajectory fitting and real-time tracking are transformed into a unified 3D coordinate recognition task for integrated welding, so the identification of welding points under three different processes can be obtained through an identical inference. The next, given the fast inference speed of YOLOv5, a joint ROI extraction algorithm with YOLOv5 as the core is applied. To compensate for YOLOv5′s inability to directly locate seam centers, iterative centerline unbiased detector (ICUD) and adaptive feature extraction algorithm (AFEA) are proposed without the need for complex image pre-processing and with very strong immunity to strong exposure and strong arc spatter. Finally, teaching trajectory correction model, B-spline curve fitting model, and 3D coordinate real-time tracking model are presented to enhance the adaptability of the welding robot and to flexibly match the appropriate welding mode in various working conditions. Experimental results indicate that the welding trajectory is basically consistent with the seam centerline when laser positioning and trajectory fitting welding. In real-time tracking welding, the real-time deviation is mainly controlled within the range of ± 0.2 mm, and the average error is 0.1160 mm.

Experimental analysis of overlap fiber laser welding for aluminum alloys: Porosity recognition and quality inspection

In recent years, laser welding has become increasingly popular in the manufacturing industry due to its advantages, including a narrow heat affected zone, low levels of distortion, the possibility of remote processing, and high welding speeds compared to conventional electric arc welding techniques. In the automotive industry, the need for overlapped joint welding, particularly for chassis assembly, has become increasingly relevant. The internal porosity detection and control in laser welding of aluminum alloys has gained significant attention. To support laser users in optimizing the welding process, this paper presents an experimental methodology followed by a phenomenological analysis of the quality of overlapped welded joints. The study focuses on the laser welding of two different aluminum alloy configurations (1.6-mm-thick AA 6061-T6 and 2-mm-thick AA 6061-T6) using three welding strategies (ScanLab remote laser welding system, Trumpf D70 laser head, and Precitec YW52 wobbling head) to evaluate single and multiple laser variants for process parameter tuning. Additionally, the paper discusses the use of X-ray technology as an offline monitoring method for porosity recognition, and analyzes laser beam characterization and beam profile shape to calculate beam distribution. Then, statistical analysis of all methods is conducted and regression analysis is performed. These findings provide valuable insights into the integration of laser welding technology in the automotive and surface transportation industries. The analysis of results indicates that as the spot size decreases, the real spot size changes more abruptly with increasing Z position, whereas with a larger spot size, the beam size remains stable up to +/- 20–30 mm in Z position due to the large lens. Porosity is mainly caused by either a too small spot size (in the absence of wobbling; ≤0.4 mm) or low travel speed (≤4.0–4.5 m/min). On the other hand, if the spot size is too large, hot cracking can occur in autogenous laser welding.

Tubular cubic polynomial sonotrode for green and sustainable ultrasonic welding technology

Ultrasonic Welding has emerged as a sustainable, green, and efficient manufacturing technology. This technique joins unique and advanced materials quickly, with good welding quality through high-intensity vibrations. Ultrasonic welding uses relatively low energy and incurs lower costs compared to various conventional welding systems. One of the key aspects to ensure high welding quality and strength, along with the transmission of high forces, is the design of an efficient ultrasonic sonotrode. This research study is aimed at proposing, evaluating, and testing the design of a tubular cubic polynomial sonotrode using finite element analysis. This novel ultrasonic welding sonotrode operates with low stresses and high displacement amplification. The performance of the proposed ultrasonic welding sonotrode design was compared with the commercially popular sonotrode, as well as cubic Bezier, exponential, and conical designs. This comparison was done in terms of harmonic excitation response, stresses, axial stiffness, displacement amplification, and factor of safety. The performance characteristics were also evaluated along the sonotrode length. The proposed sonotrode was found to be superior in terms of high vibration amplification and axial stiffness within safe stress limits. The benefits of the flexible design as per requirement to attain a higher displacement amplitude at the output end; consequently, lower welding forces were also realized. The proposed design is an improvement towards an efficient and green manufacturing technology involving reduced cost, energy consumption, use of consumables, effort, waste generation, and harm to the environment.

In-situ observation of the bond formation process during ultrasonic metal welding of Al/Cu joints using Laser Doppler Vibrometry

In recent years, ultrasonic metal welding (USMW) has gained considerable research attention due to the increasing application of lithium-ion batteries in electric vehicles. Although USMW is widely used in battery manufacturing, the fundamental understanding and monitoring of the welding process needs to be investigated to ensure the process robustness. Therefore, this work aims to establish in-situ observation of the bond formation process by using Laser-Doppler Vibrometry (LDV). The acquired velocity data was analyzed in the time and time-frequency domains. Based on the relative motion, a five-stage model was developed to describe the welding process. The changes in system dynamics led to the formation of sidebands in the frequency domain. Additionally, the power consumption was recorded by the welding system, which had a good correlation with the system dynamics. The results provided the scientific understanding behind the bond formation process and suggested relevant signals for in-process monitoring.

Parameter estimation of Wiener-Hammerstein system based on multi-population self-adaptive differential evolution algorithm

PurposeThe Wiener-Hammerstein nonlinear system is made up of two dynamic linear subsystems in series with a static nonlinear subsystem, and it is widely used in electrical, mechanical, aerospace and other fields. This paper considers the parameter estimation of the Wiener-Hammerstein output error moving average (OEMA) system.Design/methodology/approachThe idea of multi-population and parameter self-adaptive identification is introduced, and a multi-population self-adaptive differential evolution (MPSADE) algorithm is proposed. In order to confirm the feasibility of the above method, the differential evolution (DE), the self-adaptive differential evolution (SADE), the MPSADE and the gradient iterative (GI) algorithms are derived to identify the Wiener-Hammerstein OEMA system, respectively.FindingsFrom the simulation results, the authors find that the estimation errors under the four algorithms stabilize after 120, 30, 20 and 300 iterations, respectively, and the estimation errors of the four algorithms converge to 5.0%, 3.6%, 2.7% and 7.3%, which show that all four algorithms can identify the Wiener-Hammerstein OEMA system.Originality/valueCompared with DE, SADE and GI algorithm, the MPSADE algorithm not only has higher parameter estimation accuracy but also has a faster convergence speed. Finally, the input–output relationship of laser welding system is described and identified by the MPSADE algorithm. The simulation results show that the MPSADE algorithm can effectively identify parameters of the laser welding system.

Development of 120 kV and 60 kW Three Phase LCC Resonant Converter for Electron Beam Welding System

Development of 120 kV and 60 kW Three Phase LCC Resonant Converter for Electron Beam Welding System

Target recognition and detection system based on sensor and nonlinear machine vision fusion

Abstract In order to realize the automatic detection system of electric sensor, a method based on sensor and nonlinear machine vision is proposed. Aiming at complex scenes and dynamic changes in target recognition and detection in large-scale industrial field, a target recognition and detection system based on the fusion of vision sensor and nonlinear machine vision is proposed. The system introduces nonlinear features and uses deep neural network to realize multi-scale analysis and recognition of image data on the basis of traditional machine vision. The system uses C++ language development and has a good user interface. The photoelectric sensor weld image is collected by machine vision technology, the target area of the image is detected by Gaussian model, the feature points of the target area are extracted by combining Hessian matrix, the extracted feature points are input into the quantum gate neural network model, and the recognition results are obtained. The simulation results show that the author’s method has the highest value among the three test indicators, with the highest accuracy rate of 97%, the highest recall rate of 98%, and the highest F1 value of 94. The time consumed by the author’s method for automatic identification of photoelectric sensor welding is within 6 s, the time spent on the film wall recognition method for automatic identification of photoelectric sensor welding is within 20 s, and the time spent by the feature extraction and identification method for automatic identification of photoelectric sensor weld is within 22 s. It has been proven that the method based on the fusion of sensors and nonlinear machine vision can achieve an automatic recognition and detection system for electrical sensor welds. The object detection and recognition method proposed in this article can be applied to dynamic changes and complex scenes in various complex backgrounds and has a good application prospect. The system proposed in this article has some limitations, such as the algorithm in the calculation accuracy, real-time, and other aspects that have room for improvement.

Comprehensive benchmarking of laser welding technologies including novel beam shapes and wavelengths for e-drive copper hairpins

Laser welding is the industrially accepted method for the joining of Cu hairpin windings in the production of electric drives. High brilliance laser beams are scanned over the bare ends of the Cu wires producing a rapid connection through deep penetration remote welding. Despite being an accepted manufacturing method, laser welding of Cu hairpins still requires detailed studies concerning manufacturing productivity and quality. As the availability of novel laser sources with higher power levels, new wavelengths, and beam shaping capabilities increase, the need for benchmarking studies emerges. In this work, six different laser welding systems were compared in terms of process productivity and quality during the welding of Cu hairpins used for automotive traction. The different solutions presented power levels from 3 to 6 kW, with wavelengths from near infrared (NIR) to visible, including in source dynamic beam shaping. The weld bead formation was observed through high-speed imaging. The welds were analyzed in terms of their geometry, internal defects, and most relevantly for their mechanical strength. The results showed advantages of each of the employed system while the laser systems providing the highest irradiance profile produced the fastest weld with more elevated mechanical strength independently from the wavelength.

Development of an Arc Image Classification Algorithm in Tip-Rotating Arc Welding using Camera Image Monitoring and Deep Learning

In this study, we developed a welding system and welding monitoring system for GMA (Gas Metal Arc) aluminum welding using a tip-rotation arc welding torch. Welding was performed under various conditions, including suitable, low-heat, and high-heat input conditions. For welding monitoring, current and voltage were measured, and arc images were obtained. After the experiments, arc images were analyzed and classified based on the bead quality and cross-sectional analysis data. To develop a welding quality prediction model using arc images, a CNN-based model was developed. A total of 5,203 images were trained, and the quality was predicted for 631 images. The prediction accuracy was 99.88% for training data, and the possibility of assessing the quality of welded joints based on arc images during welding was confirmed.

Study on infrared emissivity model based on perturbation method and Kirchhoff approximation and its application in aluminum alloy welding

Infrared temperature measurement ubiquitously finds applications across multifarious domains. The surface infrared emissivity constitutes the critical parameter influencing the precision of infrared temperature measurement. Therefore, investigating the surface infrared emissivity is of tremendous significance. This paper establishes an infrared emissivity analytical model for rough texture surfaces by considering the repercussions of roughness on the infrared emissivity of material surfaces. First, power spectrum analysis of random roughness is performed. The positive and negative power law components of the rough surface model are constructed using the Monte Carlo method and fractal theory, respectively. Second, based on the perturbation method and Kirchhoff approximation, the infrared emissivity model for rough textured surfaces is established. Third, the infrared emissivity of rough textured surfaces with different fractal dimensions (D), characteristic length scales (G), and surface textures is simulated using the FDTD optical simulation software to validate the efficacy of the infrared emissivity model. Finally, the infrared emissivity model is applied to the temperature measurement system of aluminum alloy friction stir welding. The infrared measurement precision before and after rectification is contrasted and scrutinized to validate the accuracy of this model.

Real-Time Defect Detection Scheme Based on Deep Learning for Laser Welding System

Laser welding, as an important material processing technology, has been widely used in various fields of industry. In most industrial welding production and processing, high precision is required for welding parameters and fixed work pieces. However, in the process of laser welding, serious heat transfer effect will bring unpredictable welding deviations, and even a small deviation will lead to serious welding defects, which will affect the quality of the welded products. Traditional non-destructive testing methods have been widely used, but they have been proved to have some limitations. Existing laser welding defect detection schemes are mainly focused on the detection of post-weld defects, which requires a large amount of data, and the real-time detection cannot be guaranteed. In this paper, we propose a data acquisition system for collecting changes in physical characteristics during laser welding with the aids of multiple sensors. Based on the data originating from sensors’ system, an efficient laser welding defect detection model has been designed and investigated based on the MSCNN (multi-scale convolutional neural network), BiLSTM (bidirectional long short-term memory), and AM (attention mechanism). The final proposed MSCNN-BiLSTM-AM fusion detection model can achieve 99.38% detection accuracy, which make the laser welding system more efficient and more suitable.

Development of automatic orbital pipe MIG welding system and process parameters’ optimization of AISI 1020 mild steel pipe using hybrid artificial neural network and genetic algorithm

Development of automatic orbital pipe MIG welding system and process parameters’ optimization of AISI 1020 mild steel pipe using hybrid artificial neural network and genetic algorithm