Huagui Huang

Maritime object detection is essential for port-based surveillance, ship tracking, and maritime security. However, practical implementation encounters two primary challenges: significant class imbalance (IMO identification numbers represent only 1.2% of labelled objects) and spatial inconsistency (predicted IMO numbers often appear beyond ship boundaries). Standard detectors and conventional class-balancing strategies fail to adequately address these difficulties, resulting in a persistent mismatch between research validation and practical performance. We present a hybrid autoencoder–YOLO framework with variable spatial regularisation. To the best of our understanding, this is the first methodology to simultaneously address class imbalance and spatial inconsistency in maritime IMO detection via reconstruction-guided learning and differentiable spatial regularisation. The model uses a YOLOv8 encoder shared by both a detection head (designed for ships and IMO numbers), and an auxiliary reconstruction decoder (a SkipDecoder with U-Net-style skip connections). A unique spatial limitation loss provides the physical restriction that each IMO number must be within a ship’s bounding box, using only anticipated boxes. Training occurs in two phases: autoencoder pretraining on the marine dataset, followed by phased joint optimisation with a curriculum schedule for the spatial weighting. In a dataset of 297 annotated images (utilising five-fold cross-validation with a 47-image preserved test set), our comprehensive model achieved 50.1% IMO AP50-95, 97.8% IMO precision, and 94.6% IMO F1-score on the test set, beating the baseline YOLOv8s by +7.8 percentage points, +6.5 percentage points, and +5.2 percentage points, respectively. Ablation studies indicate that reconstruction instruction improves IMO AP50-95 by +4.5 percentage points, while spatial regularisation adds +3.3 percentage points. Although ship detection results in a small compromise (ship AP50-95 decreases from 77.0% to 55.6%), this appears to be practically acceptable given the essential role of IMO numbers as unique ship IDs. Significantly, inference speed improves by 20% (8.0 ms per image on an NVIDIA A100 GPU) relative to YOLOv8s (10.0 ms). Comparisons with leading detectors (RetinaNet, Faster R-CNN, DETR, EfficientDet), all initialised with standard COCO-pretrained backbones and fine-tuned on our dataset, reveal that none achieve an IMO AP50-95 exceeding 42.3%, highlighting the task’s challenge and the accuracy of our design. The proposed framework shows potential to address the gap in practical implementation through reconstruction-based feature learning accompanied by a specified geometric baseline. It is precise, accurate, and fast, aligns with specific physics, and shows promise for real-time maritime surveillance applications, though we acknowledge the need for additional thorough verification across many operational environments.

Aluminum alloy hot rolling features diverse varieties, large variations in incoming strip thickness, and strong process nonlinearity. Traditional rolling force prediction models rely on simplified physical assumptions and poor adaptability, making it hard to satisfy high-precision production requirements. This paper presents a mechanism–data dual-driven PSO-BP neural network method for rolling force prediction which is applicable to the rolling temperature range of 320 °C to 520 °C. The SIMS mechanism model is employed as a physical constraint, and a hybrid PSO-GD algorithm optimizes the initial weights and thresholds of the BP network, avoiding the local optimum issue of conventional BP. The rolling mechanism model is embedded into the loss function to deeply integrate physical laws and data-driven learning. Validation using 508 sets of field data from 5083 aluminum alloy hot rolling shows that the model achieves a M_APE of 5.0794% and R² of 0.9254, significantly outperforming the traditional mechanism model (8.91%) and standard BP (8.77%). The proposed model preserves physical interpretability while utilizing data-driven adaptability, offering an effective approach for high-precision rolling force prediction and improving the dimensional accuracy of hot-rolled aluminum alloy sheets.

To address the challenge of transverse thickness consistency in wide-width electrode calendering, this study developed a flexible roll profile regulation technology based on electromagnetic induction heating. An axisymmetric electromagnetic–thermal–structural coupling finite element model is established and validated on a self-built experimental platform. Systematic simulations were conducted to investigate the influence of equivalent current density J_s, current frequency f, and coil turn n on the roll temperature and roll profile. The maximum temperature of the roll’s inner bore and the roll crown exhibit a positive correlation with J_s, f, and n. A cyclic heating strategy was developed to control and stabilize the roll profile. The stable crown C_W shows linear correlation with heating durations t₁ and a nonlinear trend with J_s. Under fixed J_s and t₁, further optimization of duty cycle and cooling conditions enables long-term stabilization of the roll profile.

This study focuses on the effect of an induction heating device on the entry of a thin strip continuous casting and rolling line. A finite element model for the electromagnetic–thermal coupling of transverse magnetic flux induction heating was developed by adopting COMSOL software 6.1 to systematically investigate the effects of process parameters on the magnetic field, eddy current field, and the transverse temperature distribution of the strip. The results show that when the gap is between 20 mm and 40 mm, the maximum value of magnetic induction in the overheating region at the edges of the strip increases from 0.28 T to 0.35 T and 0.38. When the strip width is 1000 mm, there is an approximately 29% increase in magnetic induction in comparison to a strip with a width of 800 mm, and both eddy current density and temperature exhibit abnormal fluctuations. The maximum temperature difference in the temperature uniformity region at the center of the strip is only 3 °C at different frequencies, and the temperature-rise curves almost completely overlap. With increasing current, the temperature difference between the weak temperature region and the temperature uniformity region at the center widens, indicating a deterioration in temperature uniformity. Meanwhile, the field conditions are simulated using a simplified model of continuous heating. The results indicate that the maximum temperature deviation in the overheating region at the edges of the strip is 6 °C, while the deviation in the temperature uniformity region is 2 °C. Furthermore, the simulation data reveal an average temperature rise of 1156 °C across the width of the strip, with a deviation of 1.4 °C compared to the measured results, which verifies the validity of the proposed model. The analysis results provide a reference basis for designing transverse magnetic flux induction heating devices and optimizing process parameters.