Search Results (5)

Real-time and accurate identification of the blast furnace (BF) condition is essential for maintaining stability and improving energy efficiency in steelmaking. However, the harsh environment inside the BF makes direct acquisition of the BF condition extremely difficult. To address this challenge, this study proposes an online BF condition recognition method based on spatiotemporal texture feature coupling and diffusion networks (STFC-DN). The method employs a multi-domain Swin-Transformer module (MDSTM) combined with wavelet decomposition and channel attention to extract the gas flow region. A temporal feature pyramid network module (T-FPNM) is then used to capture both the global and local spatiotemporal characteristics of this region. Heuristic clustering and an idempotent generative network (IGN) are introduced to obtain standardized BF condition features, enabling intelligent classification through multi-metric similarity analysis. Experimental results show that the proposed STFC-DN achieves an average accuracy exceeding 98% when identifying four BF conditions: normal, hanging, oblique stockline, and collapsing, with an inference speed of approximately 28 FPS. This approach demonstrates both high accuracy and real-time capability, showing strong potential for advancing the intelligent and sustainable development of the steel industry. Full article

This study investigates the transverse loads acting on high-speed train bogie frames under actual service conditions. To enable direct identification, the locating arms were instrumented as bending sensors and calibrated under realistic lateral-stop constraints, ensuring robustness of the measurement channels. Field tests were conducted on a CR400BF high-speed EMU over a 226 km route at six speed levels (260–390 km/h), with gyroscope and GPS signals employed to recognize typical operating conditions, including straights, curves, and switches (straight movement and diverging movements). The results show that the proposed recognition method achieves high accuracy, enabling rapid and effective identification and localization of typical operating conditions. Under switch conditions, the bogie frame transverse loads are characterized by low-frequency, large-amplitude fluctuations, with overall RMS levels being higher in diverging switches and straight-through depot switches. Curve parameters and speed levels exert significant influence on the amplitude of the transverse-load trend component. On curves with identical parameters, the trend-component amplitude exhibits a quadratic nonlinear relationship with train speed, decreasing first and then increasing in the opposite direction as speed rises. In mainline curves and straight sections, the RMS values of transverse loads on Axles 1 and 2 scale proportionally with speed level, with the leading axle in the direction of travel consistently producing higher transverse loads than the trailing axle. When load samples are balanced across both running directions, the transverse load spectra of Axles 1 and 2 at the same speed level show negligible differences, while the spectrum shape index increases proportionally with speed level. Full article

The non-consumptive effects of past predator exposure on phytoplankton have gained recognition, but how these effects are modulated by resource availability requires further study. We examined the simultaneous effects of past predator exposure (direct, indirect, and no exposure) and nutrient regime (combinations of N- and P-repletion and limitation) on the paralytic shellfish toxin retention and cell growth rate of a toxic dinoflagellate, Alexandrium catenella (strain BF-5), under a laboratory-simulated bloom condition (exponential, stationary, and declining phases). Within a past predator exposure treatment, cell toxin retention was generally higher under N-replete than N-limited conditions. The cells of past direct predator exposure treatment retained or produced more toxin than those in the indirect-exposure or no-exposure treatments regardless of nutrient regime in the exponential and stationary phase. By contrast, cells directly exposed to predators showed lower growth rates than the other two treatments, and also showed a tradeoff between toxin retention rate and growth rate. Separate experiments also showed that the effect of past predator exposure on reducing cell growth is stronger under N repletion than N limitation. These results imply that the interactions of past predator exposure and resource availability impact bloom dynamics and toxin transfer in the food web. Full article

This paper presents a traffic sign recognition (TSR) system based on the deep convolutional neural network (CNN) architecture, which proves to be extremely accurate in recognizing traffic signs under challenging conditions such as bad weather, low-resolution images, and various environmental-impact factors. The proposed CNN is compared with other architectures, including GoogLeNet, AlexNet, DarkNet-53, ResNet-34, VGG-16, and MicronNet-BF. Experimental results confirm that the proposed CNN significantly improves recognition accuracy compared to existing models. In order to make our model interpretable, we utilize explainable AI (XAI) approaches, specifically Gradient-weighted Class Activation Mapping (Grad-CAM), that can give insight into how the system comes to its decision. The evaluation of the Tsinghua-Tencent 100K (TT100K) traffic sign dataset showed that the proposed method significantly outperformed existing state-of-the-art methods. Additionally, we evaluated our model on the German Traffic Sign Recognition Benchmark (GTSRB) dataset to ensure generalization, demonstrating its ability to perform well in diverse traffic sign conditions. Design issues such as noise, contrast, blurring, and zoom effects were added to enhance performance in real applications. These verified results indicate both the strength and reliability of the CNN architecture proposed for TSR tasks and that it is a good option for integration into intelligent transportation systems (ITSs). Full article

The accurate identification of the shape of the blast furnace (BF) burden surface is a crucial factor in the fault diagnosis of the BF condition and guides the charge operation. Based on the BF 3D point cloud data of phased array radar, this paper proposes a 3D burden surface feature definition system. Based on expert experience, the feature parameters of the burden surface are extracted. The voxel feature was extracted based on improved BNVGG. The optimized PointCNN extracts the point cloud features. The features of the burden surface were defined from three perspectives: the surface shape, voxel, and point cloud. The research of the 2D burden line is extended to the 3D burden surface, and the assumption of the symmetry of the BF is eliminated. Finally, the accuracy of the burden surface classification under each feature was evaluated, and the effectiveness of each feature extraction algorithm was verified. The experimental results show that the shape feature defined based on expert experience affects the recognition of the burden surface. However, it is defined from the data perspective and cannot accurately identify a similar burden surface shape. Therefore, the voxel features and point cloud features of the burden surface were extracted, improving the identification accuracy. Full article