The connection structure in the convolutional layers of most deep learning-based algorithms used for the classification of hyperspectral images (HSIs) has typically been in the forward direction. In this study, an end-to-end alternately updated spectral–spatial convolutional network (AUSSC) with a recurrent feedback structure is used to learn refined spectral and spatial features for HSI classification. The proposed AUSSC includes alternating updated blocks in which each layer serves as both an input and an output for the other layers. The AUSSC can refine spectral and spatial features many times under fixed parameters. A center loss function is introduced as an auxiliary objective function to improve the discrimination of features acquired by the model. Additionally, the AUSSC utilizes smaller convolutional kernels than other convolutional neural network (CNN)-based methods to reduce the number of parameters and alleviate overfitting. The proposed method was implemented on four HSI data sets, as follows: Indian Pines, Kennedy Space Center, Salinas Scene, and Houston. Experimental results demonstrated that the proposed AUSSC outperformed the HSI classification accuracy obtained by state-of-the-art deep learning-based methods with a small number of training samples.

Steelmaking continuous casting (SCC)—hot rolling (HR) is a key process in the production of steel products. It is also a process with large energy consumption. Energy saving has always been an important goal of production scheduling of this process. In this paper, aiming at integrated scheduling optimization for SCC-HR processes, energy saving objective is converted to minimize waiting time of slabs in slab yard, so as to reduce slab temperature loss and achieve the goal of saving energy. An integrated two-stage mathematical programming model is established for the above problems, and a hybrid algorithm of genetic algorithm and linear programming is designed for the integrated model. The correctness of the model and the validity of the algorithm are verified by computational experiments using simulated instances.

Layout design of the production line is a difficult problem directly affecting the productivity. This paper researches on a rapid method of dynamic layout for the production line in manufacturing industry. Based on virtual simulation technology, a visualization system of production line layout is developed using virtual simulation software called Unreal Engine. The developed layout design system is applied for a steel production line. Moreover, the production process simulation function of layout design system is used to simulate the production process of this production line. The reasonableness of production line layout is verified so that it can be modified and optimized easily.

Existing unsupervised anomaly detection methods suffer from insufficient parameter precision, poor robustness to noise, and limited generalization capability. To address these issues, this paper proposes an Adaptive Diffusion Adversarial Evolutionary Network (ADAEN) for unsupervised anomaly detection in tabular data. The proposed network employs an adaptive hierarchical feature evolution generator that captures multi-scale feature representations at different abstraction levels through learnable attribute encoding and a three-layer Transformer encoder, effectively mitigating the gradient vanishing problem and the difficulty of modeling complex feature relationships that are commonly observed in conventional generators. ADAEN incorporates a multi-scale adaptive diffusion-augmented discriminator, which preserves scale-specific features across different diffusion stages via cosine-scheduled adaptive noise injection, thereby endowing the discriminator with diffusion-stage awareness. Furthermore, ADAEN introduces a multi-scale robust adversarial gradient loss function that ensures training stability through a diffusion-step-conditional Wasserstein loss combined with gradient penalty. The method has been evaluated on 14 UCI benchmark datasets and achieves state-of-the-art performance in anomaly detection compared to existing advanced algorithms, with an average improvement of 8.3% in AUC, an 11.2% increase in F1-Score, and a 15.7% reduction in false positive rate.