Image super-resolution (SR) models based on the generative adversarial network (GAN) face challenges such as unnatural facial detail restoration and local blurring. This paper proposes an improved GAN-based model to address these issues. First, a Multi-scale Hybrid Attention Residual Block (MHARB) is designed, which dynamically enhances feature representation in critical face regions through dual-branch convolution and channel-spatial attention. Second, an Edge-guided Enhancement Block (EEB) is introduced, generating adaptive detail residuals by combining edge masks and channel attention to accurately recover high-frequency textures. Furthermore, a multi-scale discriminator with a weighted sub-discriminator loss is developed to balance global structural and local detail generation quality. Additionally, a phase-wise training strategy with dynamic adjustment of learning rate (Lr) and loss function weights is implemented to improve the realism of super-resolved face images. Experiments on the CelebA-HQ dataset demonstrate that the proposed model achieves a PSNR of 23.35 dB, a SSIM of 0.7424, and a LPIPS of 24.86, outperforming classical models and delivering superior visual quality in high-frequency regions. Notably, this model also surpasses the SwinIR model (PSNR: 23.28 dB → 23.35 dB, SSIM: 0.7340 → 0.7424, and LPIPS: 30.48 → 24.86), validating the effectiveness of the improved model and the training strategy in preserving facial details.
In order to achieve the whole process control of crack formation of engineered cementitious composites (ECC) under loading and improve the mechanical properties of ECC, steel fibers are mixed into traditional ECC to get polyvinyl alcohol (PVA)-steel hybrid fiber reinforced cementitious composites (HyFRCC). And the key parameters to affect the HyFRCC performance are PVA fiber content, steel fiber content, and aspect ratio of steel fiber. In order to investigate the mechanical properties of PVA-steel HyFRCC such as the compressive toughness, 15 PVA-steel HyFRCC specimens with different volume fraction of steel fiber and PVA fiber, together with 1 non-fibrous cementitious composites specimen and 3 ECC specimens with PVA fibers only for comparison were designed and uniaxial compression tests were conducted. Furthermore, the effect of fiber content, fiber type and fiber geometrical characteristic on the compressive toughness of HyFRCC were analyzed. The results show that PVA fiber content, steel fiber content and aspect ratio of steel fiber have little impact on the uniaxial compressive strength of the PVA-steel HyFRCC, while the peak strain, compressive toughness and the post-peak ductility of PVA-steel HyFRCC are improved significantly due to fiber hybridization. The formation of large scale cracks of ECC specimens after post-peak loading is restrained effectively with the addition of steel fiber. The mixture of PVA and steel fiber has a remarkable effect on the improvement of ECC compression toughness and crack control. It indicates that the energy dissipation and damage control capacity of the structural component with PVA-steel HyFRCC under seismic loading will be enhanced.
针对回收电动汽车电池时必须拆卸和分类电池组件的问题,提出了一种实现电动汽车电池组件半自动化拆卸和分类的移动机器人系统.该系统利用行为树模型来执行认知和监控任务,以模块化的方式集成不同的机器人能力,如导航、目标跟踪、运动规划和抓取.在静态和动态环境下对该系统框架进行了仿真测试,并根据机器人完成任务的时间和成功率对其进行评估.结果表明:机器人在静态和动态环境下完成电池组件分类任务的平均时间分别为51.63min和83.09min,总体成功率分别为 95%和 82%,验证了所提机器人系统的有效性,具有高效率和高成功率的性能.
随着WSNs入侵方式的多样化,现有检测算法的准确性会显著下降,为此提出了基于混合特征学习数学模型的WSNs入侵检测方法.检测中先基于嗅探器定时获取传感器节点运行参数,并利用熵权法选取无线传感器网络节点混合特征因子,包括能耗率、丢包率、报文发送频率、报文接收频率,再从获取传感器节点运行参数中获得四个特征因子对应的数值.利用BP神经网络构建入侵检测数学模型,以混合特征因子数值为输入,确定WSNs入侵类型,以实现对WSNs入侵行为的精确检测.结果表明:基于强化学习的入侵检测模型,基于双向循环生成对抗网络的入侵检测模型相比,所研究模型应用下,F1-measure数值更大,由此说明该模型入侵检测更全面,检测结果更准确,模型的整体性能更好.
行政处罚法规定具有一定社会影响的处罚决定应当公开,有助于发挥对行政相对人的教育作用和对社会公众的警示作用.但目前,我国关于行政处罚决定公开中存在着对"具有一定社会影响"的判断标准尚不明确;公开机制有关规定尚不完善以及错误公开后行政相对人的救济渠道不畅通等问题.笔者提出根据行政处罚决定公开所针对的客体的分类界定"具有一定社会影响"的标准,从公开内容的限度、时限和程序方面对行政处罚决定公开的有关规定进行完善、畅通错误公开后行政相对人的救济途径等完善对策.
