Search Results (112)

This paper uses a systematic approach to constructing a mathematical description of the technological process of aluminum production, aimed at addressing control challenges and improving energy sustainability through a comprehensive analysis of technological parameters. Using expert assessment and correlation–regression analysis methods, the most significant technological parameters were identified, and quantitative relationships among them were established. Based on available statistical data from the current supply subsystem, a regression model was constructed that describes the influence of subsystem parameters on the voltage drop across the straight section of the bus and confirms the key role of transition resistances in welded joints in energy loss formation. Using the obtained dependencies, a conceptual model of the electrolysis process and its mathematical representation describing interactions among the electrical, thermal, and physicochemical subsystems of the electrolyzer was developed. The developed model is applicable to the analysis and prediction of technological modes, the construction of digital twins, and the development of automated control systems. In future work, the model is planned to be experimentally verified using a laboratory aluminum electrolysis setup in order to refine model parameters and assess applicability under industrial electrolyzer conditions. Full article

To address challenges in weld recognition during vacuum electron beam welding caused by dark environments and metal reflections, this study proposes an improved hybrid algorithm combining YOLOv11-seg with adaptive Canny edge detection. By incorporating the UFO-ViT attention mechanism and optimizing the network architecture with the EIoU loss function, along with adaptive threshold setting for the Canny operator using the Otsu method, the recognition performance under complex conditions is significantly enhanced. Experimental results demonstrate that the optimized model achieves an average precision (mAP) of 77.4%, representing a 9-percentage-point improvement over the baseline YOLOv11-seg. The system operates at 20 frames per second (FPS), meeting real-time requirements, with the generated welding trajectories showing an average length deviation of less than 3 mm from actual welds. This approach provides an effective pre-weld visual guidance solution, which is a critical step towards the automation of electron beam welding. Full article

Empirical approaches alone have significant limitations for accurate estimation of the fracture toughness of welds in gas line pipes being considered for repurposing to hydrogen service. These problems arise because most samples machined from ex-service welds contain a range of microstructures. The different microstructural zones have different properties and even when compact tension samples with side grooves are utilized, it is unlikely that plane strain conditions are achieved during laboratory testing. Thus, the measured toughness may not be directly relevant to assessing in-service performance. The present research has been undertaken as part of an integrated series of projects seeking to define a robust protocol for assessing the damage tolerance of piping used for the transmission of hydrogen, especially when considering repurposing existing infrastructure. The key work described in this paper involved establishing heat treatments which produced microstructures relevant to the constituents found in ex-service welds of X46 type steel. Following comprehensive microstructural characterization, these heat treatments were applied to steel sections which allowed for the fabrication of standard compact tension specimens, which were subsequently tested in hydrogen to measure fracture toughness. The results obtained showed that the fracture behavior varied for different microstructures. To identify the influence that hydrogen gas has on the performance of pipeline steels, it is important to assess microstructures relevant to the welds present, as testing only on base metal may not provide conservative information. However, the results from well-planned and carefully executed programs can be used to identify the relative performance in hydrogen. The data can also be used as critical input to models which form part of an integrated approach to structural integrity assessment. Full article

Inspecting the inner walls of large pressure vessels requires accurate weld seam recognition, complete coverage, and precise path tracking, particularly in low-feature environments. This paper presents a fully autonomous mobile robotic system that integrates weld seam detection, localization, and tracking to support ultrasonic testing. An improved Differentiable Binarization Network (DBNet) combined with the Spatially Variant Transformer (SVTR) model enhances digital stamp recognition, while weld paths are reconstructed from three-dimensional position data acquired via binocular stereo vision. To ensure complete traversal and accurate tracking, a global–local hierarchical planning strategy is implemented: the A-star (A*) algorithm performs global path planning, the Rapidly Exploring Random Tree Connect (RRT-Connect) algorithm handles local path generation, and point cloud normal–based spherical interpolation produces smooth tracking trajectories for robotic arm motion control. Experimental validation demonstrates a 94.7% digital stamp recognition rate, 95.8% localization success, 1.65 mm average weld tracking error, 2.12° normal fitting error, 98.2% seam coverage, and a tracking speed of 96 mm/s. These results confirm the system’s capability to automate weld seam inspection and provide a reliable foundation for subsequent ultrasonic testing in pressure vessel applications. Full article

Perforated cylindrical shaped metal plates are used with high efficiency in the manufacture of deflectors, components of cooling systems, wind tunnels, climatic chambers, filters, and cylindrical implants. This is particularly important for lightweight cylindrical structures, where even minor changes in stiffness can affect structural strength. One of the most important parameters determining the mechanical behavior of such structures is the effective elastic modulus of the perforated element which characterizes its resistance to deformation. The research involves plates made of stainless steel 304 alloy, where perforations were created using the laser-cutting method. The cylindrical shape of the samples with height 50 mm, thickness 1 mm, and diameter 48 mm of each specimen was obtained using metal rolling and welding techniques. To determine the effective elastic modulus, a non-destructive material property evaluation method was applied by solving an inverse problem. In this research, resonance frequencies were determined using a laser vibrometer and a full factorial experimental plan was developed. Physical samples were digitized into 3D models using 3D scanning technology. To evaluate the accuracy of the applied finite element numerical model, its convergence analysis was performed. Numerical results were approximated using the least-squares method, while the effective elastic modulus was calculated by formulating and minimizing the error functional between experimental and numerical eigenfrequencies. The results indicate that increasing the relative perforation area from 0% to 50.24% leads to a decrease in the effective elastic modulus from 184.76 GPa to 50.69 GPa, confirming that increasing the perforation area in a stainless steel 304 cylinder reduces its elastic properties. The observed reduction in resonance frequencies and elastic properties is primarily due to the stiffness decrease caused by the higher perforation volume. Full article

This paper pioneers the use of the symmetrical Hybrid-RAG strategy in the ship welding process domain, addressing the problems of fragmented, unstructured knowledge storage, as well as the limitations of traditional Retrieval-Augmented Generation (RAG), particularly high retrieval noise and low accuracy when answering complex procedural queries. This study proposes an intelligent three-stage symmetric “Generate–Retrieve–Generate” framework for the ship welding process (SWP-Chat), supported by dual retrieval engines: a Neo4j knowledge graph for symbolic reasoning and a vector database for semantic retrieval. Unlike approaches that rely solely on LLM-based process planning, SWP-Chat uses the LLM to generate a logical form, then executes Cypher queries on Neo4j, enabling transparent traceability, precise entity–relation constraints, and deterministic retrieval. Meanwhile, the vector channel supplements unstructured or contextual welding information to enhance semantic coverage. To further improve efficiency, principal component analysis (PCA) was employed for vector dimensionality reduction, reducing average retrieval latency by 31% while retaining more than 95% variance. In addition, an explainable structural–confidence fusion formula integrates evidence from both engines to produce auditable and trustworthy industrial responses. Experimental evaluation demonstrates that the framework achieves an F1 score of 79.35%, greatly surpassing typical RAG systems. Full article

This study implemented a Lean Six Sigma (LSS) methodology to enhance the productivity of the mechanical and industrial engineering technology workshops of an international higher education institution. The efficiency and effectiveness of the engineering workshops were often compromised by poor housekeeping and operational practices, which resulted in incomplete tasks, long operational and activity times, disorganized tools, cluttered workspaces, and a lack of systematic processes for managing materials. These issues led to waste in the form of lost time, unnecessary movement, and safety risks. This eventually affected the overall productivity of the workshops. Following the combination of the Define, Measure, Analyze, Improve, and Control (DMAIC) methodology of Six Sigma with Lean manufacturing, the investigation was conducted in two parts. The first part of this research mainly consisted of measuring the existing state of the three workshops to map the process and frame issues and origins of variations. During the second part of this study, the focus shifted towards Lean thinking while applying the chosen Lean Six Sigma (LSS) tools. Implementation revealed several benefits in the workshops during each phase of DMAIC. A Plan–Do–Check–Act (PDCA) continuous improvement board was installed in the main workshop to promote continuous improvement and sustainability. The process capability increased for the main workshop and welding laboratory, which shows an increase in service and performance standards after LSS implementation. For the main workshop, the process capability ‘Cp’ increased from 0.33 to 1.24 and the process capability index (Cpk) increased from 0.26 to 0.99. The process capability index (Cpk) for the main workshop increased; however, it did not reach the value of 1.33 due to the computer workstation installation not being completed during the study. The welding laboratory showed an increased ‘Cp’ from 0.67 to 2.13, and the process capability index (Cpk) increased from 0.18 to 1.34. The layout of the workshop office was improved to support efficient workflow by providing easy access to frequently used resources while keeping movement paths clear, thereby minimizing interruptions and promoting productivity. As a result, machines and tools were used more productively and operation times decreased. The mechanical workshops can continue increasing their process capability by following the outcomes and findings of the current study, leading to sustainable quality, efficiency, and operational reliability improvements. Full article

At present, traditional X-ray inspection is used to inspect the welds of the bottom, barrel section and short shell parts of the launch vehicle, which has the disadvantages of low automation, complicated process and low efficiency, and cannot meet the fast-paced development needs of multiple models at present. Moreover, the degree of digitization is low, the test results are recorded in the form of negatives, data statistics, storage and access are difficult, and the circulation efficiency is low, which is not conducive to product quality control and traceability; At the same time, it cannot adapt to and meet the needs of digital and intelligent transformation and development. In this paper, a dual-robot collaborative digital radiographic inspection system for rocket tank welds is developed by combining dual-robot control technology and digital radiographic inspection technology. The system can be directly applied to digital radiographic inspection of tank bottom, barrel section and short shell welds of multiple types of launch vehicles; meanwhile, the dual-robot path planning technology based on the dual-mode is studied. Finally, the imaging software platform based on VS and Twincat3.0 VS2015 software combined with QT upper computer is designed. Experiments show that compared with the existing traditional ray detection methods, the detection efficiency of the system is improved by 5 times, the image sensitivity reaches W14, the resolution reaches D10, and the standardized signal-to-noise ratio reaches 128, which far exceeds the requirements of process technology A, and meets the current non-destructive detection work of multi-model rocket tank welds. Full article

This paper reports on the applicability of fatigue crack detection with an infrared thermography camera, the T-gap method, to a steel bridge in Denmark. The T-gap method is a non-destructive test developed in Japan and does not require approaching close to the bridge members, unlike visual inspections. The principle of the T-gap method is to measure the thermal profile of the welding point. One of the crucial factors generating the temperature gap is the solar altitude, and there is a smaller solar altitude in high-latitude areas, so it is unclear whether the T-gap method is more applicable in higher-latitude areas than Japan. Thus, the trial of the T-gap method in Denmark, which is located at a higher latitude than Japan, was planned to grasp the method’s applicability. As the results of trials, the T-gap method successfully detected both locations and the length of cracks even in Denmark. Full article

The study examines in detail the possibility of using well casing as a means for power transmission downhole to high-power equipment, such as pumps. The ultimate goal is to transmit single-phase AC to the well bottom and then convert it into three-phase power to operate the downhole equipment, which is a major challenge for such applications. The focus is set on the particular problem of the contact between the packer slips and the casing, and the study aims to examine it in detail. An analysis of high-voltage effects (arcing, etching, contact welding, and heating) and possible mechanical and chemical failures (fatigue, corrosion, surface treatment, contact pressure, and stresses) is performed. These effects are evaluated using common physics laws, and the mechanical structural behavior of the contact is analyzed through Finite Element Method simulation. The performed calculations and analyses show that this is a viable and innovative solution that eliminates the use of cables (umbilicals), especially for long distances and in deep wells. The main contribution is the validated conceptual design, with physical prototyping and tests planned for the next stage of this research. Full article

The emergence of mass personalized production has increased the adaptability and intelligence requirements of welding robots. To address the challenges associated with mass personalized production, this paper proposes a novel knowledge-driven framework for intelligent welding process planning in cloud robotics systems. This framework integrates cloud-edge-end collaborative computing with ontology-based knowledge representation to enable efficient welding process optimization. A hierarchical knowledge-based architecture was developed using the SQLite 3.38.0, Redis 5.0.4, and HBase 2.1.0 tools. The ontology models formally define the welding tasks, resources, processes, and results, thereby enabling semantic interoperability across heterogeneous systems. A hybrid knowledge evolution method that combines cloud-based welding simulation and transfer learning is presented as a means of achieving inexpensive, efficient, and intelligent evolution of welding process knowledge. Experiments demonstrated that, with respect to pure cloud-based solutions, edge-based knowledge bases can reduce the average response time by 86%. The WeldNet-152 model achieved a welding parameter prediction accuracy of 95.1%, while the knowledge evolution method exhibited a simulation-to-reality transfer accuracy of 78%. The proposed method serves as a foundation for significant enhancements in the adaptability of welding robots to Industry 5.0 manufacturing environments. Full article

This study explores the integration of circular design principles into automotive product development, focusing on the environmental implications of design decisions related to geometry, material selection, and assembly methods. A case study approach was used to iteratively redesign a plastic automotive component, incorporating structural reinforcements and glass fiber (GF) to enhance performance. While these changes improved mechanical properties, they negatively impacted recyclability due to increased material heterogeneity and irreversible assembly using ultrasonic welding. Circularity performance was evaluated using the Recycling Desirability Index (RDI), Material Circularity Indicator (MCI), and circular design guidelines (CDGs). Despite achieving 20% recycled content, recyclability remained limited. Alternative design strategies—such as eliminating GF, replacing welding with mechanical fasteners, and enabling take-back systems—led to significant improvements in circularity scores. Notably, MCI analysis indicated that energy recovery pathways offered better circularity outcomes than landfilling. The findings highlight the importance of early-stage material standardization and assembly planning to enhance end-of-life recovery. This study underscores the environmental trade-offs inherent in current automotive design practices and calls for stronger collaboration between engineers, designers, and sustainability experts to align product development with circular economy goals. Findings emphasize the need for systemic changes in product development processes and industrial mindsets, including overcoming resistance to design modifications and fostering cross-departmental collaboration, to effectively implement circular economy principles in the automotive sector. Full article

Feature tracking is essential for welding crawler robots’ trajectory planning. As welding often occurs in dark environments like pipelines or ship hulls, the system requires low-light image capture for laser tracking. However, such images typically have poor brightness and contrast, degrading both weld seam feature extraction and trajectory anomaly detection accuracy. To address this, we propose a Retinex-based low-light enhancement network tailored for cladding scenarios. The network features an illumination curve estimation module and requires no paired or unpaired reference images during training, alleviating the need for cladding-specific datasets. It adaptively adjusts brightness, restores image details, and effectively suppresses noise. Extensive experiments on public (LOLv1 and LOLv2) and self-collected weld datasets show that our method outperformed existing approaches in PSNR, SSIM, and LPIPS. Additionally, weld seam segmentation under low-light conditions achieved 95.1% IoU and 98.9% accuracy, confirming the method’s effectiveness for downstream tasks in robotic welding. Full article

Multi-layer multi-pass welding plays an important role in manufacturing industries such as nuclear power plants, pressure vessel manufacturing, and ship building. However, distortion or welding defects are still challenges; therefore, welding monitoring and quality control are essential tasks for the dynamic adjustment of execution during welding. The aim was to propose a machine vision system for monitoring and surface quality evaluation during multi-pass welding using a line scanner and infrared camera sensors. The cross-section modelling based on the line scanner data enabled the measurement of distortion and dynamic control of the welding plan. Lack of fusion, porosity, and burn-through defects were intentionally generated by controlling welding parameters to construct a defect inspection dataset. To reduce the influence of material surface colour, the proposed normal map approach combined with a deep learning approach was applied for inspecting the surface defects on each layer, achieving a mean average precision of 0.88. In addition to monitoring the temperature of the weld pool, a burn-through defect detection algorithm was introduced to track welding status. The whole system was integrated into a graphical user interface to visualize the welding progress. This work provides a solid foundation for monitoring and potential for the further development of the automatic adaptive welding system in multi-layer multi-pass welding. Full article

Accurate weld seam recognition is essential in automated welding systems, as it directly affects path planning and welding quality. With the rapid advancement of industrial vision, weld seam instance segmentation has emerged as a prominent research focus in both academia and industry. However, existing approaches still face significant challenges in boundary perception and structural representation. Due to the inherently elongated shapes, complex geometries, and blurred edges of weld seams, current segmentation models often struggle to maintain high accuracy in practical applications. To address this issue, a novel structure-aware and boundary-enhanced YOLO (SABE-YOLO) is proposed for weld seam instance segmentation. First, a Structure-Aware Fusion Module (SAFM) is designed to enhance structural feature representation through strip pooling attention and element-wise multiplicative fusion, targeting the difficulty in extracting elongated and complex features. Second, a C2f-based Boundary-Enhanced Aggregation Module (C2f-BEAM) is constructed to improve edge feature sensitivity by integrating multi-scale boundary detail extraction, feature aggregation, and attention mechanisms. Finally, the inner minimum point distance-based intersection over union (Inner-MPDIoU) is introduced to improve localization accuracy for weld seam regions. Experimental results on the self-built weld seam image dataset show that SABE-YOLO outperforms YOLOv8n-Seg by 3 percentage points in the AP(50–95) metric, reaching 46.3%. Meanwhile, it maintains a low computational cost (18.3 GFLOPs) and a small number of parameters (6.6M), while achieving an inference speed of 127 FPS, demonstrating a favorable trade-off between segmentation accuracy and computational efficiency. The proposed method provides an effective solution for high-precision visual perception of complex weld seam structures and demonstrates strong potential for industrial application. Full article