In scenarios where global navigation satellite systems (GNSSs) and radio navigation systems are denied, vision-based autonomous landing (VAL) for fixed-wing unmanned aerial vehicles (UAVs) becomes essential. Accurate and real-time runway detection in VAL is vital for providing precise positional and orientational guidance. However, existing research faces significant challenges, including insufficient accuracy, inadequate real-time performance, poor robustness, and high susceptibility to disturbances. To address these challenges, this paper introduces a novel single-stage, anchor-free, and decoupled vision-based runway detection framework, referred to as YOLO-RWY. First, an enhanced data augmentation (EDA) module is incorporated to perform various augmentations, enriching image diversity, and introducing perturbations that improve generalization and safety. Second, a large separable kernel attention (LSKA) module is integrated into the backbone structure to provide a lightweight attention mechanism with a broad receptive field, enhancing feature representation. Third, the neck structure is reorganized as a bidirectional feature pyramid network (BiFPN) module with skip connections and attention allocation, enabling efficient multi-scale and across-stage feature fusion. Finally, the regression loss and task-aligned learning (TAL) assigner are optimized using efficient intersection over union (EIoU) to improve localization evaluation, resulting in faster and more accurate convergence. Comprehensive experiments demonstrate that YOLO-RWY achieves ${\mathrm{AP}}_{50:95}$ scores of 0.760, 0.611, and 0.413 on synthetic, real nominal, and real edge test sets of the landing approach runway detection (LARD) dataset, respectively. Deployment experiments on an edge device show that YOLO-RWY achieves an inference speed of 154.4 FPS under FP32 quantization with an image size of 640. The results indicate that the proposed YOLO-RWY model possesses strong generalization and real-time capabilities, enabling accurate runway detection in complex and challenging visual environments, and providing support for the onboard VAL systems of fixed-wing UAVs.

Crude oil price forecasting contributes to global economic development. This study proposes a hybrid deep learning model for crude oil price forecasting. First, empirical wavelet transform decomposes raw data into multiple. Then, three neural networks generate preliminary forecasts, which are subsequently refined by a reinforcement learning-based ensemble method. Finally, an error correction module handles residuals, further enhancing the forecasting outcomes. Three West Texas Intermediate datasets and additional emergency scenarios were used to validate the hybrid model. The findings indicate that the proposed model achieves superior predictive performance compared with sixteen benchmark methods and three advanced models.

Robot trajectory prediction is an essential part of building digital twin systems and ensuring the high-performance navigation of IoT mobile robots. In the study, a novel two-stage multi-objective multi-learner model is proposed for robot trajectory prediction. Five machine learning models are adopted as base learners, including autoregressive moving average, multi-layer perceptron, Elman neural network, deep echo state network, and long short-term memory. A non-dominated sorting genetic algorithm III is applied to automatically combine these base learners, generating an accurate and robust ensemble model. The proposed model is tested on several actual robot trajectory datasets and evaluated by several metrics. Moreover, different existing optimization algorithms are also applied to compare with the proposed model. The results demonstrate that the proposed model can achieve satisfactory accuracy and robustness for different datasets. It is suitable for the accurate prediction of robot trajectory.

Tool wear monitoring is crucial for optimizing cutting performance, reducing costs, and improving production efficiency. Existing tool wear prediction models usually design integrated models based on a convolutional neural network (CNN) and recurrent neural network (RNN) to extract spatial and temporal features separately. However, the topological structures between multi-sensor networks are ignored, and the ability to extract spatial features is limited. To overcome these limitations, a novel spatial–temporal adaptive graph convolutional network (STAGCN) is proposed to capture spatial–temporal dependencies with multi-sensor signals. First, a simple linear model is used to capture temporal patterns in individual time-series data. Second, a spatial–temporal layer composed of a bidirectional Mamba and an adaptive graph convolution is established to extract degradation features and reflect the dynamic degradation trend using an adaptive graph. Third, multi-scale triple linear attention (MTLA) is used to fuse the extracted multi-scale features across spatial, temporal, and channel dimensions, which can assign different weights adaptively to retain important information and weaken the influence of redundant features. Finally, the fused features are fed into a linear regression layer to estimate the tool wear. Experimental results conducted on the PHM2010 dataset demonstrate the effectiveness of the proposed STAGCN model, achieving a mean absolute error (MAE) of 3.40 μm and a root mean square error (RMSE) of 4.32 μm in the average results across three datasets.

The remaining useful life (RUL) prediction is essential for cost-effective production and reliable predictive maintenance in intelligent manufacturing. Existing deep learning-based approaches often struggle to capture complex degradation patterns across temporal, spatial, and frequency domains. To address this limitation, a dynamic spatial-temporal graph transformer with multi-frequency attention (DSTGT-MFA) is proposed in this paper for RUL prediction. The proposed DSTGT-MFA model consists of three key components: a multi-scale gated convolutional neural network for extracting hierarchical local features, a graph convolution transformer for modeling long-term spatial-temporal dependencies with dynamic and static adjacency matrices, and a multi-frequency spatial-temporal attention mechanism to enhance temporal and spatial attention in the frequency domain. This integrated architecture enables the model to comprehensively capture degradation trends and fuse multi-domain features. Extensive experiments conducted on the commercial modular aero-propulsion system simulation (CMAPSS) and new CMAPSS datasets demonstrate that the DSTGT-MFA model achieves superior prediction accuracy compared to twelve baseline methods.

In smart manufacturing, remaining useful life prediction is fundamental to condition-based maintenance for proactive decision-making. However, bearing vibration signals are often nonstationary and affected by impulsive noise, making it difficult to separate low-frequency degradation trends from high-frequency fault-sensitive details and to model their nonlinear and dynamic interactions. To address this issue, this paper proposes KGAMamba, a unified framework for structured trend-detail representation and efficient sequence modeling. By decomposing vibration signals into low-frequency degradation trends and high-frequency dynamic fluctuations, KGAMamba enables parallel processing of global degradation patterns and local fault dynamics. The model leverages Mamba for efficient long-range temporal modeling and introduces the Kolmogorov–Arnold network-driven global attention (KGA) module to enhance feature selectivity through joint channel and spatiotemporal nonlinear refinement. Cross-branch information is then adaptively fused via cross-attention. Comprehensive experiments on the XJTU-SY and FEMTO-ST benchmarks validate that KGAMamba consistently outperforms state-of-the-art methods across diverse operating conditions and fault modes.