Explore the vast range of titles available.

In order to relieve the problem of a false and missed detection of casting defects in X-ray detection, a robust detection method based on vision attention mechanism and deep learning of feature map is proposed. The ray images are used as input sequence, the false detection is eliminated by the intra-frame attention strategy, and the missed detection is excluded by the inter-frame deep convolution neural network (DCNN) strategy. In the intra-frame detection stage, the center-peripheral difference method is proposed to simulate the difference operation of biological vision; the suspicious defect area is directly detected according to the gradient threshold in this stage. In the inter-frame learning stage, the convolution neural network is established based on deep learning strategy to extract defect feature from a suspicious defect area; a deep learning feature vector is obtained in this stage. The similarity degree of the suspicious defect area is computed by a feature vector; a casting defect is tracked by the similarity matching of the suspicious defect in continuous frames; then, the false defects (such as noise) is excluded after defect tracking. The experimental results show that the false rate and missed rate for detection of casting defects are less than 4%, and the accuracy of the defect detection is more than 96%, which proves the robustness of the proposed method.

The current casting surface defect detection algorithms suffer from poor small target defect recognition and imbalance between detection performance and detection time. An improved algorithmic framework for casting defect detection was proposed based on the DEtection TRansformer (DETR) algorithm. The algorithm takes ResNet with an efficient channel attention (ECA)-Net module as the backbone network. In addition, based on the original algorithm architecture, dynamic anchor boxes, improved multi-scale deformable attention module, and SIoU loss function are introduced to improve the sensitivity of transformer structure to input location information and scale size, and the small target defect detection performance is effectively improved. The recognition performance of the algorithm in a self-built casting defect dataset was studied. The improved DETR algorithm has 97.561% accuracy in recognizing two defects, namely sandinclusion and notch, with the detection rate being improved by 65.854% and 17.073% compared with the original DETR and you only look once (Yolo)-V5, respectively. This algorithm verifies the applicability of the transformer architecture target detection algorithm for casting defect detection tasks and provides new ideas for detecting other similar application scenarios.

Fe-Mn-Al-C high-manganese and high-aluminum (high-Mn and high-Al) steel has the characteristics of high strength at room temperature and low temperature, good fatigue performance, high elongation, and good energy absorption in collisions. It is a lightweight advanced steel material with great potential for structural parts in automobile, transportation, military, and other fields. At present, there are serious surface quality defects and drastic slag–metal reactions during the continuous casting production, which hinder the efficient production of high-Mn and high-Al steel. The paper focuses on the development and challenges of continuous casting of high-Mn and high-Al steel. Firstly, the current development status of high-Mn and high-Al steel is reviewed. Then, combined with the production practice of continuous casting, difficulties and key points of control of high-Mn and high-Al steel are introduced from three aspects of non-metallic inclusion control, casting superheat control, and cooling process control. Finally, the challenges currently encountered in the production different types of mold fluxes are summarized and analyzed, and the key points for the development and application of a new type of titanium-containing continuous casting mold flux for high-Mn and high-Al steel are discussed. It is expected to provide a useful reference for improving the quality of Fe-Mn-Al-C high-Mn and high-Al steel for automotive and realizing its efficient and large-scale continuous casting production as soon as possible.

Manual inspection of onba earing casting defects is not realistic and unreliable, particularly in the case of some micro-level anomalies which lead to major defects on a large scale. To address these challenges, we propose BearFusionNet, an attention-based deep learning architecture with multi-stream, which merges both DenseNet201 and MobileNetV2 for feature extraction with a classification head inspired by VGG19. This hybrid design, figuratively beaming from one layer to another, extracts the enormity of representations on different scales, backed by a pre-preprocessing pipeline that brings defect saliency to the fore through contrast adjustment, denoising, and edge detection. The use of multi-head self-attention enhances feature fusion, enabling the model to capture both large and small spatial features. BearFusionNet achieves an accuracy of 99.66% and Cohen’s kappa score of 0.9929 in Kaggle’s Real-life Industrial Casting Defects dataset. Both McNemar’s and Wilcoxon signed-rank statistical tests, as well as five-fold cross-validation, are employed to assess the robustness of our proposed model. To interpret the model, we adopt Grad-Cam visualizations, which are the state of the art standard. Furthermore, we deploy BearFusionNet as a web-based system for near real-time inference (5–6 s per prediction), which enables the quickest yet accurate detection with visual explanations. Overall, BearFusionNet is an interpretable, accurate, and deployable solution that can automatically detect casting defects, leading to significant advances in the innovative industrial environment.

This article presents the findings of a study focusing on the gas generation of 3D-printed cores fabricated using binder-jetting technology with furfuryl resin. The research aimed to compare gas emission levels, where the volume generated during the thermal degradation of the binder significantly impacts the propensity for gaseous defects in foundries. The study also investigated the influence of the binder type (conventional vs. 3D-printed dedicated binder) and core construction (shell core) on the quantity of gaseous products from the BTEX group formed during the pouring of liquid foundry metal into the cores. The results revealed that the emitted gas volume during the thermal decomposition of the organic binder depended on the core sand components and binder type. Cores produced using conventional methods emitted the least gases due to lower binder content. Increasing Kaltharz U404 resin to 1.5 parts by weight resulted in a 37% rise in gas volume and 27% higher benzene emission. Adopting shell cores reduced gas volume by over 20% (retaining sand with hardener) and 30% (removing sand with hardener), presenting an eco-friendly solution with reduced benzene emissions and core production costs. Shell cores facilitated the quicker removal of gaseous binder decomposition products, reducing the likelihood of casting defects. The disparity in benzene emissions between 3D-printed and vibratory-mixed solid cores is attributed to the sample preparation process, wherein 3D printing ensured greater uniformity.

Industrial X-ray analysis is common in aerospace, automotive or nuclear industries where structural integrity of some parts needs to be guaranteed. However, the interpretation of radiographic images is sometimes difficult and may lead to two experts disagree on defect classification. The automated defect recognition (ADR) system presented herein will reduce the analysis time and will also help reducing the subjective interpretation of the defects while increasing the reliability of the human inspector. Our convolutional neural network (CNN) model achieves 0.942 mAP@IoU = 0.50, which is considered as similar to expected human performance, when applied to an automotive aluminium castings dataset (GDXray). On an industrial environment, its inference time is less than 400 ms per 16 GB DICOM image (16 bits), so it can be installed on production facilities with no impact on delivery time. In addition, an ablation study of the main hyper-parameters to optimise model accuracy from the initial baseline result of 0.75 mAP up to 0.942 mAP, was also conducted.

In light of fuel consumption reduction and environmental regulations, the automotive industry favors lightweight components. Aluminum is chosen for its superior corrosion resistance and high strength-to-weight ratio in complex vehicle parts which are manufactured using high pressure die-casting (HPDC) process. However, this process suffers from significant mechanical property variations and unreliable stress cycles due to defects like porosity, shrinkage, misrun, and hot tears, leading to fatigue failures. Despite the detrimental impact of casting defects, the underlying reasons for the high variability in the HPDC process remain unclear. Numerical tools provide insights into parameters that are challenging to measure experimentally. This research presents a thorough analysis of the design, development, fabrication, and testing of an aluminum die-cast swing arm utilizing Magma 5 software. The study focuses on the solidification characteristics of the swing arm, examining factors such as pore length, solidification duration, hot spot distribution, and shrinkage porosity severity. To support design improvements aimed at addressing identified failures, the commercial simulation software Magma 5 was employed. These enhancements resulted in a substantial reduction in solidification time and effectively shifted hot spots away from previously identified cracked areas. Additionally, there were significant decreases in both the percentage and intensity of porosity, confirmed by X-ray and CT scan analyses. Durability tests conducted with a dynamometer indicated a remarkable 50% increase in fatigue life compared to the original design. The research highlights the significance of early simulation-based design modifications in reducing fatigue failures in HPDC aluminum components. It was noted that excessive porosity levels exceeding 8% are a major factor contributing to this issue. Recommendations include avoiding thicker designs and complex part configurations to reduce porosity, as well as assessing defect locations in relation to surface proximity and stress regions.

The paper presents an example of Instance-Based Learning using a supervised classification method of predicting selected ductile cast iron castings defects. The test used the algorithm of k-nearest neighbours, which was implemented in the authors’ computer application. To ensure its proper work it is necessary to have historical data of casting parameter values registered during casting processes in a foundry (mould sand, pouring process, chemical composition) as well as the percentage share of defective castings (unrepairable casting defects). The result of an algorithm is a report with five most possible scenarios in terms of occurrence of a cast iron casting defects and their quantity and occurrence percentage in the casts series. During the algorithm testing, weights were adjusted for independent variables involved in the dependent variables learning process. The algorithms used to process numerous data sets should be characterized by high efficiency, which should be a priority when designing applications to be implemented in industry. As it turns out in the presented mathematical instance-based learning, the best quality of fit occurs for specific values of accepted weights (set #5) for number k = 5 nearest neighbours and taking into account the search criterion according to “product index”.

This article proposes a progressive frequency domain-guided depth model with adaptive preprocessing to solve the problem of defect detection with weak features based on X-ray images. In distinct intuitive surface defect detection tasks, non-destructive testing of castings using X-rays presents more complex and weak defect features, leading to lower accuracy and insufficient robustness on the part of current casting defect detection methods. To address these challenges, the proposed method establishes four specialized mechanisms to improve model accuracy. First, an adaptive image contrast enhancement method is proposed to enhance the features of defects in casting images to promote subsequent feature extraction and prediction. Second, a subtle clue mining module based on frequency domain attention is proposed to fully extract the discriminative features of casting defects. Third, a feature refinement module based on progressive learning is proposed to achieve a balance between feature resolution and semantic information. Finally, a refined deep regression supervision mechanism is designed to improve defect detection accuracy under strict intersection-to-union ratio standards. We established extensive ablation studies using casting defect images in GDXray, conducted detailed comparative experiments with other methods, and performed experiments to analyze the robustness of the resulting models. Compared with other X-ray defect detection methods, our framework achieves an average +4.6 AP. Compared to the baseline, our proposed refined deep regression supervision mechanism results in an improvement of 5.3 AP.

In this study, the time-temperature behaviour of selected process parameters is established. The paper describes a new approach to understanding the defect generation phenomena in castings by considering the uniqueness of individual green sand moulds. It also explains the changing values of process parameters by experimental investigation. Foundry is the science of experiments. The aim is to achieve the right quality, quantity, and cost with minimum rejections. The casting quality results from several interconnected, dynamic, and complicated processes that are part of a foundry operation. Quality castings are produced by exercising proper control over several process parameters involved in the casting process. Despite taking several control measures regarding proper casting design, methoding and processing, casting defects are still observed. Defect reduction continues to be the primary goal in sand casting foundries due to the same. This paper investigates the essential parameters of the Green Sand casting process for understanding the influence over the generation of the casting defect in green sand moulding grey cast iron components. This study also adopts the time series method of recording the process parameters and finding the values of process parameter sets for individual moulds. The results showed a systematic predictive behaviour of the selected process parameters. By recording the process parameters under given conditions, it is found that they are time and temperature-dependent. Values can be obtained by building regression equations. It has been found that values of per cent moisture and green compressive strength reduce, whereas permeability and mould hardness increase.