Search Results (47)

Welding robots are essential in modern manufacturing, providing high precision and efficiency in welding processes. To optimize their performance and minimize errors, accurate simulation of their behavior is crucial. This paper presents a novel approach to enhance the simulation of welding robots using the Virtual, Augmented, and Mixed Reality (VAM) simulation platform. The VAM platform offers a dynamic and versatile environment that enables a detailed and realistic representation of welding robot actions, interactions, and responses. By integrating VAM with existing simulation techniques, we aim to improve the fidelity and realism of the simulations. Furthermore, to accelerate the learning and optimization of the welding robot’s behavior, we incorporate deep reinforcement learning (DRL) techniques. Specifically, DRL is utilized for task offloading and trajectory planning, allowing the robot to make intelligent decisions in real-time. This integration not only enhances the simulation’s accuracy but also improves the robot’s operational efficiency in smart manufacturing environments. Our approach demonstrates the potential of combining advanced simulation platforms with machine learning to advance the capabilities of industrial robots. In addition, experimental results show that ANFIS achieves higher accuracy and faster convergence compared to traditional control strategies such as PID and FLC. Full article

One of the prospective methods of robotic welding with a consumable electrode in shield gas metal arc welding is the GMAW Rapid HF process (GRHF, HF-high frequency), in which welded joints with deep penetration welds are obtained thanks to the specially programmed welding characteristics of the arc. A pulsed frequency equalized to 5000 Hz was used to achieve consumable electrode arc stabilization and improve penetration. This work consists of two main sections, including the research and analysis of wire electrode melting and weld pool formation in the innovative GRHF process and its influences on joint strength and the economic advantages of welding. As a result of our research and strength tests, as well as an image analysis of phenomena occurring in the welding arc and weld pool, assumptions were developed about the use of the GRHF process, which is characterized by deep penetration welds without welding imperfections that reduce the quality of the welded joints and their strength. Welding conditions and parameters leading to welded joints characterized by high relative strength related to the weight of the used filler material were proposed. As a result of our research, it was found that the use of welding processes with deep penetration leads to material savings related to the reduced consumption of filler materials while maintaining the required high strength of welded joints. Savings of filler materials reaching 80% were achieved compared with hitherto used methods. At the same time, the maximum load-carrying capacity of welding joints was maintained. Full article

In the industry, the robotic gas metal arc welding (GMAW) process has a huge range of applications, including in the automotive sector, construction companies, the shipping industry, and many more. Automatic quality inspection in robotic welding is crucial because it ensures the uniformity, strength, and safety of welded joints without the need for constant human intervention. Detecting defects in real time prevents defective products from reaching advanced production stages, reducing reprocessing costs. In addition, the use of materials is optimized by avoiding defective welds that require rework, contributing to cleaner production. This paper presents a novel dataset of robot GMAW images for experimental purposes, including human-expert segmentation and human knowledge labeling regarding the different errors that may appear in welding. In addition, it tests an automatic segmentation approach for robot GMAW quality assessment. The results presented confirm that automatic segmentation is comparable to human segmentation, guaranteeing a correct welding quality assessment to provide feedback on the robot welding process. Full article

Layout design is the process in which industrial robots and other manufacturing components are positioned within a manufacturing system so that the intended operations can be handled appropriately. The traditional layout design process presents several challenges. It involves numerous iterations of testing different manually generated manufacturing layouts, requiring extensive trial and error to achieve an optimal solution. This process is highly time-consuming and demands significant expertise and cognitive effort from the designer. Within this publication, a flexible, scalable, and efficient function-block-based solution is presented for the optimization of manufacturing system layouts, especially in the field of multi-robot cells in two different use cases: one in additive manufacturing and one in jig-less welding. The findings showcase that the methodology followed enabled the efficient allocation of industrial robots in a workspace, minimizing the cognitive effort required in comparison to the traditional manual trial-and-error layout design procedure. Full article

Plasma arc welding can achieve high-quality welding joints in high-strength manufacturing fields, such as aviation and automotive, and improve production efficiency. It is important to observe the weld pool state in real-time in robot automatic welding. However, the electrodes of the plasma welding torch cannot be observed from the outside. Teaching the weld line to torch in real-time to be observable to humans will be difficult. Also, it is difficult to process the image to obtain the position of the weld line in K-PAW. In this study, a camera was utilized to observe the weld pool. The authors estimate the weld line position in real time by image processing based on U-Net prediction. The U-Net model demonstrates sufficient prediction where the accuracy reached 99.5% for the training data and 96.5% for the test data recognition. Moreover, a control method utilized weld line position estimated from the boundary area to verify the effectiveness of this prediction model from 3 mm within the deviation of 1 mm, which is within the range of permissible welding errors. It could reduce image processing errors in the weld pool image and provide higher recognition accuracy than image processing. Combining vision sensing technologies and deep learning methods will provide new technologies to enable higher welding precision and improve welding quality. It could also accelerate the development of welding technology in the intelligent manufacturing field. Full article

Effective thermal management is essential in welding processes to maintain structural integrity and material quality, especially in high-precision industrial applications. This study examines the thermal behavior of an AISI 1080 steel plate containing 100 blind holes filled using robotic electric arc welding. Temperature measurements, recorded with eight strategically positioned thermocouples, monitored the thermal evolution throughout the robotic welding process. The experimental results validated a computational heat transfer model developed with ANSYS Fluent software to simulate and predict temperature distribution achieving a mean absolute percentage error (MAPE) below 4.53%. A feedforward neural network was trained with simulation-generated data to optimize welding sequences. The optimization focuses on minimizing the area under the thermal history curves, reducing temperature gradients, and mitigating overheating risks. Integrating CFD simulations and neural networks introduces a hybrid methodology combining precise numerical modeling with advanced predictive capabilities. The hybrid CFD-FNN results reached a determination coefficient ($R^2$) of 0.93 and an MAPE of 3.5% highlighting the potential of this approach to predict the thermal behavior in multipoint welding processes. This model generated optimized welding trajectories improving the uniformity of the temperature field, reducing thermal gradients and minimizing temperature peaks, thus aiding in preventing overheating. This framework represents a significant advancement in welding technologies, demonstrating the effective application of deep learning techniques in optimizing complex industrial processes. Full article

Laser vision seam tracking enhances robotic welding by enabling external information acquisition, thus improving the overall intelligence of the welding process. However, camera images captured during welding often suffer from distortion due to strong noises, including arcs, splashes, and smoke, which adversely affect the accuracy and robustness of feature point detection. To mitigate these issues, we propose a feature point extraction algorithm tailored for weld images, utilizing an improved Deeplabv3+ semantic segmentation network combined with EfficientDet. By replacing Deeplabv3+’s backbone with MobileNetV2, we enhance prediction efficiency. The DenseASPP structure and attention mechanism are implemented to focus on laser stripe edge extraction, resulting in cleaner laser stripe images and minimizing noise interference. Subsequently, EfficientDet extracts feature point positions from these cleaned images. Experimental results demonstrate that, across four typical weld types, the average feature point extraction error is maintained below 1 pixel, with over 99% of errors falling below 3 pixels, indicating both high detection accuracy and reliability. Full article

Laser beam welding is the most modern and promising process for the automatic or robotized welding of structures of the highest Execution Class, EXC3-4, which are made of a variety of weldable structural materials, mainly steel, titanium, and nickel alloys, but also a limited range of aluminum, magnesium, and copper alloys, reactive materials, and even thermoplastics. This paper presents a systematic review and analysis of the author’s research results, research articles, industrial catalogs, technical notes, etc., regarding laser beam welding (LBW) and laser hybrid welding (LHW) processes. Examples of industrial applications of the melt-in-mode and keyhole-mode laser welding techniques for low-alloy and high-alloy steel joints are analyzed. The influence of basic LBW and LHW parameters on the quality of welded joints proves that the laser beam power, welding speed, and Gas Metal Arc (GMA) welding current firmly decide the quality of welded joints. A brief review of the artificial intelligence (AI)-supported online quality-monitoring systems for LBW and LHW processes indicates the decisive influence on the quality control of welded joints. Full article

In this study, we analyzed the arc magnetic field to assess the stability of the arc welding process, particularly in robotic welding where direct measurement of welding current is challenging, such as under water. The characteristics of the magnetic field were evaluated based on low-frequency fluctuations and the symmetry of the signals. We used double-wire pulsed MIG welding for our experiments, employing Q235 steel with an 8.0 mm thickness as the material. Key parameters included an average voltage of 19.8 V, current of 120 A, and a wire feeding speed of 3.3 m/min. Our spectral analysis revealed significant correlations between welding stability and factors such as the direct current (DC) component and the peak power spectral density (PSD) frequency. To quantify this relationship, we introduced a novel approach using sample entropy and mix sample entropy (MSE) as new evaluation metrics. This method achieved a notable accuracy of 88%, demonstrating its effectiveness in assessing the stability of the robotic welding process. Full article

The aim of this study was to determine the microstructural evolution, tensile characteristics, and strain-hardening response of AZ31B magnesium alloy welds as influenced by post-weld heat treatment (PWHT). Thus, the AZ31B alloy was welded by using a low-power pulsed Nd:YAG laser-arc hybrid welding equipped on the six-axis welding robot in the present study. Microstructure, mechanical properties and strain-hardening behaviors of the AZ31B joints under various post-weld heat treatment (PWHT) temperatures were characterized. As the heat treatment temperature increases, the grain size of the welded joint gradually increases, and the amount of β-Mg₁₇AI₁₂ phase noticeably decreases. The mechanical properties of the welded joint specimens showed a significant enhancement when subjected to heat treatment at 300 °C and 350 °C for 20 min. Especially, after 350 °C heat treatment for 20 min, the ultimate tensile strength (UTS) and elongation (EL) of specimen were 339.6 MPa and 20.1%, respectively, which were up to 99.5% and 98.5% of the AZ31B base material (BM). The strain-hardening capacity of specimens is significantly influenced by the grain size. Due to having the largest grain size, the 400–20 min specimen exhibited the highest hardening capacity and strain hardening exponent. In Kocks-Mecking type curves, both stage III and stage IV were observed in BM and joint specimens. At higher net flow stresses, the strain hardening rate in the 400–20 min joint specimen was higher due to the larger grains, which allowed for more dislocation accommodation and improved the capacity for dislocation storage. Full article

This paper presents the novel enhanced Wagner–Hagras interval type-3 Takagi–Sugeno–Kang fuzzy logic system with type-1 non-singleton inputs (EWH IT3 TSK NSFLS-1) that uses the backpropagation (BP) algorithm to train the antecedent and consequent parameters. The proposed methodology dynamically changes the parameters of only the alpha-0 level, minimizing some criterion functions as the current information becomes available for each alpha-k level. The novel fuzzy system was applied in two industrial processes and several fuzzy models were used to make comparisons. The experiments demonstrated that the proposed fuzzy system has a superior ability to predict the critical variables of the tested processes with lower prediction errors than those produced by the benchmark fuzzy systems. Full article

In the shipbuilding industry, welding automation using welding robots often relies on arc-sensing techniques due to spatial limitations. However, the reliability of the feedback current value, core sensing data, is reduced when welding target workpieces have significant curvature or gaps between curved workpieces due to the control of short-circuit transition, leading to seam tracking failure and subsequent damage to the workpieces. To address these problems, this study proposes a new algorithm, MBSC (median-based spatial clustering), based on the DBSCAN (density-based spatial clustering of applications with noise) clustering algorithm. By performing clustering based on the median value of data in each weaving area and considering the characteristics of the feedback current data, the proposed technique utilizes detected outliers to enhance seam tracking accuracy and responsiveness in unstructured and challenging welding environments. The effectiveness of the proposed technique was verified through actual welding experiments in a yard environment. Full article

Within the drilling, petrochemical, construction, and related industries, coatings are used to recover components that failed during service or to prevent potential failures. Due to high stresses, such as wear and corrosion, which the materials are subjected to, industries require the application of coating between dissimilar materials, such as carbon steels and stainless steels, through arc welding processes. In this work, an austenitic stainless steel (ER308) coating was applied to an H13 tool steel substrate using the gas metal arc welding (GMAW) robotic process. The heat input during the process was calculated to establish a relationship between the geometry obtained in the coating and its dilution percentage. Furthermore, the evolution of the microstructure of the coating, interface, and substrate was evaluated using XRD and SEM techniques. Notably, the presence of martensite at the interface was observed. The mechanical behavior of the welded assembly was analyzed through Vickers microhardness, and a pin-on-disk wear test was employed to assess its wear resistance. It was found that the dilution percentage is around 18% at high heat input (0.813 kJ/mm) but decreases to about 14% with reduced heat input. Microhardness tests revealed that at the interface, the maximum value is reached at about 625 HV due to the presence of quenched martensite. Moreover, increasing the heat input favors wear resistance. Full article

The arc sound signal is one of the most important aspects of information related to pattern identification regarding the penetration state of ship robotic GMAW; however, arc sound is inevitably affected by noise interference during the signal acquisition process. In this paper, an improved wavelet threshold denoising method is proposed to eliminate interference and purify the arc sound signal. The non-stationary random distribution characteristics of GMAW noise interference are also estimated by using the high-frequency detail coefficients in different domains after wavelet transformation, and a mode of measuring scale that is logarithmically negatively correlated with the wavelet decomposition scale is created to update the threshold. The gradient convergent threshold function is established using the natural logarithmic function structure and concave–convex gradient to enable the nonlinear adjustment of the asymptotic rate. Further, some property theorems related to the optimized threshold function are proposed and theoretically proven, and the effectiveness and adaptability of the improved method are verified via the denoising simulation of speech synthesis signals. The four traditional denoising methods and our improved version are applied in the pretreatment of the GMAW arc sound signal, respectively. Statistical analysis and short-time Fourier transform are used to extract eight-dimensional time and frequency domain feature parameters from the denoised signals with randomly time-varying characteristics, and the extracted joint feature parameters are used to establish a nonlinear mapping model of penetration state identification for ship robotic GMAW using the pattern classifiers of RBFNN, PNN and PSO-SVM. The simulation results yielded by visual penetration classification and the multi-dimensional evaluation index of the confusion matrix indicate that the improved denoising method proposed in this paper achieves a higher accuracy in the extraction of penetration state features and greater precision in the identification of pattern classification. Full article

The welding and construction processes for H-type thick-plate bridge steel involve complex multi-pass welding processes, which make it difficult to ensure its welding performance. Accordingly, it is crucial to explore the inherent correlations between the welding process parameters and welding quality, and apply them to welding robots, eliminating the instability in manual welding. In order to improve welding quality, the GMAW (gas metal arc welding) welding process parameters are simulated, using the Q345qD bridge steel flat joint model. Four welds with X-shaped grooves are designed to optimize the parameters of the welding current, welding voltage, and welding speed. The optimal welding process parameters are investigated through thermal–elastic–plastic simulation analysis and experimental verification. The results indicate that, when the welding current is set to 230 A, the welding voltage to 32 V, and the welding speed to 0.003 m/s, the maximum deformation of the welded plate is 0.52 mm, with a maximum welding residual stress of 345 MPa. Both the simulation results of multi-pass welding, and the experimental tests meet the welding requirements, as they show no excessive stress or strain. These parameters can be applied to building large steel-frame bridges using welding robots, improving the quality of welded joints. Full article