Search Results (101)

Accurate weld defect detection is critical for ensuring structural safety and evaluating welding quality in industrial applications. Manual inspection methods have inherent limitations, including inefficiency and inadequate sensitivity to subtle defects. Existing detection models, primarily designed for natural images, struggle to adapt to the characteristic challenges of weld X-ray images, such as high noise, low contrast, and inter-defect similarity, particularly leading to missed detections and false positives for small defects. To address these challenges, a multi-dimensional feature fusion model (MADet), which is a multi-branch deep fusion network for weld defect detection, was proposed. The framework incorporates two key innovations: (1) A multi-scale feature fusion network integrated with lightweight attention residual modules to enhance the perception of fine-grained defect features by leveraging low-level texture information. (2) An anchor-based feature-selective detection head was used to improve the discrimination and localization accuracy for five typical defect categories. Extensive experiments on both public and proprietary weld defect datasets demonstrated that MADet achieved significant improvements over the state-of-the-art YOLO variants. Specifically, it surpassed the suboptimal model by 7.41% in mAP@0.5, indicating strong industrial applicability. Full article

In the integration of structured light systems (SLSs) into automotive manufacturing pipelines, achieving reliable 3D reconstruction under industrial conditions remains a critical challenge. Factors such as environmental variability, surface reflectivity, and optical configuration often compromise dimensional accuracy and point cloud quality, limiting the deployment of SLSs for inspection tasks. This paper presents a practical metric-based methodology for evaluating the dimensional accuracy and point cloud quality of SLSs targeted at automotive inspection applications. Unlike existing approaches focused primarily on theoretical or hardware-specific parameters, the proposed methodology considers all phases of the acquisition–reconstruction pipeline, including calibration, environmental variability, and image enhancement strategies, to practically guide engineers step-by-step in adapting SLSs to real-world operational constraints. The methodology was experimentally validated through a case study in an automotive production setting, where it enabled the detection of reconstruction biases caused by surface reflectivity and viewing angle. It also demonstrated the ability to quantify improvements obtained through image enhancement algorithms. These results confirm the methodology’s capacity to expose critical performance trade-offs and guide optimization choices in practical inspection scenarios. By offering a repeatable and application-oriented evaluation framework, the methodology supports the robust integration of digital vision systems in industrial workflows, facilitating more informed decisions for system designers, process engineers, and quality control professionals. Full article

Structural timber is an important building material, but surface defects such as cracks and knots seriously affect its load-bearing capacity, dimensional stability, and long-term durability, posing a significant risk to structural safety. Conventional inspection methods are unable to address the issues of multi-scale defect characterization, inter-class confusion, and morphological diversity, thus limiting reliable construction quality assurance. To overcome these challenges, this study proposes WDNET-YOLO: an enhanced deep learning model based on YOLOv8n for high-precision defect detection in structural wood. First, the RepVGG reparameterized backbone utilizes multi-branch training to capture critical defect features (e.g., distributed cracks and dense clusters of knots) across scales. Second, the ECA attention mechanism dynamically suppresses complex wood grain interference and enhances the discriminative feature representation between high-risk defect classes (e.g., cracks vs. knots). Finally, CARAFE up-sampling with adaptive contextual reorganization improves the sensitivity to morphologically variable defects (e.g., fine cracks and resin irregularities). The analysis results show that the mAP50 and mAP50-95 of WDNET-YOLO are improved by 3.7% and 3.5%, respectively, compared to YOLOv8n, while the parameters are increased by only 4.4%. The model provides a powerful solution for automated structural timber inspection, which directly improves building safety and reliability by preventing failures caused by defects, optimizing material utilization, and supporting compliance with building quality standards. Full article

Pine nuts hold significant economic value due to their rich plant protein and healthy fats, yet precise variety classification has long been hindered by limitations of traditional techniques such as chemical analysis and machine vision. This study proposes a novel near-infrared (NIR) spectral feature selection algorithm, termed the improved binary equilibrium optimizer with selection probability (IBiEO-SP), which incorporates a dynamic probability adjustment mechanism to achieve efficient feature dimensionality reduction. Experimental validation on a dataset comprising seven pine nut varieties demonstrated that, compared to particle swarm optimization (PSO) and the genetic algorithm (GA), the IBiEO-SP algorithm improved average classification accuracy by 5.7% (p < 0.01, Student’s t-test) under four spectral preprocessing methods (MSC, SNV, SG1, and SG2). Remarkably, only 2–3 features were required to achieve optimal performance (MSC + random forest: 99.05% accuracy, 100% F1/precision; SNV + KNN: 97.14% accuracy, 100% F1/precision). Furthermore, a multimodal data synergy strategy integrating NIR spectroscopy with morphological features was proposed, and a classification model was constructed using a soft voting ensemble. The final classification accuracy reached 99.95%, representing a 2.9% improvement over single-spectral-mode analysis. The results indicate that the IBiEO-SP algorithm effectively balances feature discriminative power and model generalization needs, overcoming the contradiction between high-dimensional data redundancy and low-dimensional information loss. This work provides a high-precision, low-complexity solution for rapid quality detection of pine nuts, with broad implications for agricultural product inspection and food safety. Full article

In order to rationally utilize wood materials, increase wood quality, and mitigate drawbacks, research on industrial techniques for timber protection and preservation is essential on a European and global scale. When high-quality timber enters the market, it offers structures and objects that have considerable added value. This study examines the performance of thermally treated (6 h at 170 °C and 200 °C) softwood species (fir wood) when exposed outdoors and applied on wooden building structures as cladding timber, among other structures. International standards were applied for the characterization of the untreated and thermally treated wooden boards after the treatments in terms of physical, hygroscopic, and surface properties. In contrast, all the boards (of dimensions 390 × 75 × 20 mm in length, width, thickness respectively) were exposed outdoors to direct sunlight and a combination of biotic and abiotic factors for a six-month period to mainly investigate the thermal properties (heat transfer analysis/insulation properties) using a real-time test in situ, as well as to investigate their potential resistance to natural weathering (color, surface roughness, visual inspection, etc.). Heat transfer in the thermally treated wood specimens was found to be much slower than that in the untreated specimens, which, combined with lower hygroscopicity and higher dimensional stability, reveals the high potential of thermally treated wood utilization in outdoor applications, such as cladding, facades, frames, and other outdoor elements. Full article

This study introduces a machine vision system (MVS) developed for the inspection and removal of defective gears to enhance the efficiency of mass production processes. The system employs a rotary table that transports gears through the inspection stage at a controlled speed. Various defects, including missing teeth, surface irregularities, and dimensional deviations, are reliably identified through this method. Faulty gears are automatically separated from the production line using a pneumatic actuator. Experimental evaluations confirm the system’s high accuracy and consistency, with a defect detection standard deviation of less than 1%. This level of deviation corresponds to a defect detection accuracy exceeding 98%, with both precision and recall consistently surpassing 96%. By reducing manual intervention and accelerating quality control procedures, the proposed system contributes to improved production efficiency and product quality, offering a practical and effective solution for manufacturing environments. Full article

The main function of triangulation-based laser profile sensors—also referred to as laser profilometers or profilers—is the three-dimensional scanning of moving objects using laser triangulation. In addition to capturing 3D data, these profilometers simultaneously generate grayscale images of the scanned objects. However, the quality of these images is often degraded due to interference of the laser light, manifesting as speckle noise. In profilometer images, this noise typically appears as vertical stripes. Unlike the column fixed pattern noise commonly observed in TDI CMOS cameras, the positions of these stripes are not stationary. Consequently, conventional algorithms for removing fixed pattern noise yield unsatisfactory results when applied to profilometer images. In this article, we propose an effective method for suppressing speckle noise in profilometer images of flat surfaces, based on local column median vectors. The method was evaluated across a variety of surface types and compared against existing approaches using several metrics, including the standard deviation of the column mean vector (SDCMV), frequency spectrum analysis, and standard image quality assessment measures. Our results demonstrate a substantial improvement in reducing column speckle noise: the SDCMV value achieved with our method is 2.5 to 5 times lower than that obtained using global column median values, and the root mean square (RMS) of the frequency spectrum in the noise-relevant region is reduced by nearly an order of magnitude. General image quality metrics also indicate moderate enhancement: peak signal-to-noise ratio (PSNR) increased by 2.12 dB, and the structural similarity index (SSIM) improved from 0.929 to 0.953. The primary limitation of the proposed method is its applicability only to flat surfaces. Nonetheless, we successfully implemented it in an optical inspection system for the furniture industry, where the post-processed image quality was sufficient to detect surface defects as small as 0.1 mm. Full article

In this paper, we are looking for the answer to the following question: what geometric deviations do polymer gears made by 3D printing have from the theoretical geometry? From a practical point of view, the question is whether the currently installed injection-molded gear can be replaced by a 3D-printed gear. Thus, the measurements are also carried out on the sample gear and the comparison is made with this data as well. Knowing the data of the existing gear wheel, the CAD model was created, and based on this, samples of the gear were printed using various 3D printing machines. The printed gears were then subjected to geometrical analysis. During the inspection, we performed the measurement of the chordal thickness of the gear wheel using a gear tool caliper, instead of pin measurement and span measurement using a special micrometer, and 3D scanning and analysis. A surface roughness measurement was carried out as well. By conducting measurements on the injection-molded and 3D-printed samples, this research seeks to evaluate the reliability and limitations of the 3D-printed gears, providing insights into their industrial use. This study aims to determine whether 3D printing technologies can produce gears with sufficient accuracy and surface quality for practical applications. Based on the conducted analysis, general conclusions were drawn regarding the potential applicability of the 3D-printed gears. The experimental results indicate notable differences in dimensional accuracy between gears manufactured using Fused Deposition Modeling (FDM) and Selective Laser Sintering (SLS). In terms of chordal thickness measurements, FDM gears exhibited a mean relative error of 1.96 mm, whereas SLS gears showed a significantly higher average deviation of 5.64 mm. For the pin measurement, the relative error averaged 0.193 mm in the case of FDM gears, compared to 0.616 mm for SLS gears. Similarly, the span over four teeth measurements resulted in an average deviation of 0.153 mm for FDM gears, while SLS gears demonstrated a markedly higher mean error of 0.773 mm. With regard to surface roughness, it can be concluded that SLS-manufactured gears exhibit superior performance compared to FDM gears, with an average Ra value of 2.65 µm versus 9.28 µm, although their surface quality remains inferior to that of the injection-molded gear. In light of the higher relative errors observed in SLS gears compared to FDM gears, the dimensions of the theoretical model should be refined to improve the manufacturing accuracy of SLS-produced gears. Full article

In order to solve the problems of stress concentration in the roadway peripheral rock and poor support effect in a wide range of high-stress areas under the high-stress environment of MaKeng Iron Mine, this study is based on the theory of loose circle support, combined with the calculation of the anchor suspension theory to determine the reasonable length of pipe slit anchors and other key parameters. Through the two methods of punching and bonding, we examined the destructive effect to determine the thickness of the spray concrete and, finally, put forward the pipe slit anchor mesh spraying support technology program. The numerical model was constructed by using three-dimensional numerical simulation software (FLAC3D 5.0), and the support effect analysis of the support scheme was carried out systematically. The research results show the following: under the high-stress environment dominated by external horizontal tectonic stress, the use of pipe slit anchor net spray support technology can significantly improve the distribution characteristics of the plastic zone, stress field and displacement around the roadway; after the support, the deformation and displacement of the surrounding rock around the empty zone are significantly reduced, effectively preventing the destruction of the surrounding rock under the high-stress environment. The program not only unifies the mine support form and support parameters but also specifies the support construction method and construction quality inspection standard, which provides a scientific technical guarantee for mine shaft support and has an important reference value for the support design and construction of a mine roadway under a similar high-stress environment. Full article

Tablet surface defects are typically controlled by visual inspection in the pharmaceutical industry. This is an insufficient response variable for knowledge-based formulation and process development, and it results in rather limited robustness of the control strategy. In this article, we present an analytical method for the quantitative characterization of visual tablet surface defects. The method involves analysis of the tablet surface by a digital microscope to obtain optical images and three-dimensional surface scans. Pre-processing procedures are applied for the simplification of the data to allow the detection of the imprint characters and tablet surface structures by a Faster R-CNN object detection model. Geometrical variables like perimeter and area were derived from the results of the object detection model and statistically analyzed for a selected number of tablets. The analysis allowed the development of product-specific acceptance criteria by a small reference dataset, and the quantitative evaluation of sticking, picking, chipping, and abrasion defects. The method showed high precision and sensitivity and demonstrated robust detection of visual tablet surface defects without false negative results. The image analysis was automated, and the developed algorithm can be operated by a simple routine on a standard computer in a few minutes. The method is suitable for industrial use and enables advancements in industrial formulation and process development while providing a novel opportunity for the quality control of visual tablet surface defects. Full article

This paper presents a discrete Fourier transform (DFT)-based signal processing framework for eddy current non-destructive testing (NDT), aiming to enhance signal quality for precise defect characterization in critical nuclear components. By enforcing strict periodicity matching between sampling points and signal frequencies, the proposed approach mitigates DFT spectrum leakage, validated via phase linearity analysis with errors of ≤0.07° across the 20 Hz–1 MHz frequency range. A high-resolution 24-bit analog-to-digital converter (ADC) hardware architecture eliminates complex analog balancing circuits, reducing system-wide noise by overcoming the limitations of traditional 16-bit ADCs. A 6 × 6 mm application-specific integrated circuit (ASIC) for array sensors enables three-dimensional (3D) defect visualization, complemented by Gaussian filtering to suppress vibration-induced noise. Our experimental results demonstrate that the digital method yields smoother signal waveforms and superior 3D defect imaging for nuclear power plant tubes, enhancing result interpretability. Field tests confirm stable performance, showcasing clear 3D defect distributions and improved inspection performance compared to conventional techniques. By integrating DFT signal processing, hardware optimization, and array sensing, this study introduces a robust framework for precise defect localization and characterization in nuclear components, addressing key challenges in eddy current NDT through systematic signal integrity enhancement and hardware innovation. Full article

In recent years, the semiconductor industry has embraced advanced artificial intelligence (AI) techniques to facilitate intelligent manufacturing throughout their organizations, with particular emphasis on virtual metrology (VM) systems. Nonetheless, the practical application of data-driven virtual metrology for product quality inspection encounters notable hurdles, such as annotating inspections in highly dynamic industrial environments. This leads to complexities and significant expenses in data acquisition and VM model training. To address the challenges, we delved into transfer learning (TL). TL offers a valuable avenue for knowledge sharing and scaling AI models across various processes and factories. At the same time, research on transfer learning in VM systems remains limited. We propose a novel parameter transfer learning (PTL) architecture for VM systems and examine its application in industrial process automation. We implemented cross-factory and cross-recipe transfer learning to enhance VM performance and offer practical advice on adapting TL to meet individual needs and use cases. By leveraging extensive data from Seagate wafer factories, known for their large-scale and high-dimensional nature, we achieved significant PTL performance improvements across multiple performance metrics, with the true positive rate (TPR) increasing by 29% and false positive rate (FPR) decreasing by 43% in the cross-factory study. In contrast, in the cross-recipe study, TPR increased by 27.3% and FPR decreased by 6.5%. With our proposed PTL architecture and its performance achievements, insufficient data from the new manufacturing sites, new production lines and new products are addressed with shorter VM model training time and smaller computational power with strong final quality prediction confidence. Full article

To improve the accuracy and completeness of three-dimensional sculpture reconstruction, this study proposes a global–local two-step scanning method for industrial robot-based scanning. First, a global model is generated through stepped rotary scanning based on the object’s dimensions. Subsequently, local viewpoint planning is conducted to refine regions that were incompletely captured in the initial step, with a genetic algorithm optimizing the scanning paths to enhance efficiency. The local models are then aligned and fused with the global model to produce the final 3D reconstruction. Comparative experiments on sculptures made of different materials were conducted to validate the effectiveness of the proposed method. Compared with CAD-slicing and surface-partitioning methods, the proposed approach achieved superior model completeness, a scanning accuracy of 0.26 mm, a standard deviation of 0.31 mm, and a total scanning time of 152 s. The results indicate that the proposed method enhances reconstruction integrity and overall quality while maintaining high efficiency, making it a viable approach for high-precision 3D surface inspection tasks. Full article

Dimensional quality inspection of prefabricated components is crucial for ensuring building quality and safety. Currently, manual measurement methods are predominantly used in dimensional quality inspection of prefabricated components, which are both time-consuming and labor-intensive, constraining production efficiency. This study thus developed a non-contact image measurement system using an innovative three-dimensional (3D) matrix camera, which automatically performed dimensional quality inspection, utilizing technologies such as a parallel optical axis four-camera matrix imaging and machine learning algorithms. Compared to traditional techniques, this system exhibited enhanced adaptability to the manufacturing process of prefabricated components, along with desirable accuracy and efficiency. Building upon a comprehensive literature review, the hardware constituents of the 3D matrix camera image measurement system were meticulously introduced, followed by the underlying principles and implementations of data acquisition, processing and comparison methods, including parallel optical axis four-camera matrix imaging, automatic stitching algorithms for 3D point clouds, feature recognition algorithms, and matching principles. The feasibility of the proposed system was validated through a case study analysis. The application results indicated that the system was capable of automatically performing non-contact measurements of dimensional deviations in prefabricated components with an accuracy of ±3 mm, thereby enhancing production quality. Full article

Modern vision-based inspection systems are inherently limited by their two-dimensional nature, particularly when inspecting complex product geometries. These systems are often unable to capture critical depth information, leading to challenges in accurately measuring features such as holes, edges, and surfaces with irregular curvature. To address these shortcomings, this study introduces an approach that leverages computer-aided design-oriented three-dimensional point clouds, captured via a laser line triangulation sensor mounted onto a motorized linear guide. This setup facilitates precise surface scanning, extracting complex geometrical features, which are subsequently processed through an AI-based analytical component. Dimensional properties, such as radii and inter-feature distances, are computed using a combination of K-nearest neighbors and least-squares circle fitting algorithms. This approach is validated in the context of steel part manufacturing, where traditional 2D vision-based systems often struggle due to the material’s reflectivity and complex geometries. This system achieves an average accuracy of 95.78% across three different product types, demonstrating robustness and adaptability to varying geometrical configurations. An uncertainty analysis confirms that the measurement deviations remain within acceptable limits, supporting the system’s potential for improving quality control in industrial environments. Thus, the proposed approach may offer a reliable, non-destructive inline testing solution, with the potential to enhance manufacturing efficiency. Full article