Deep-learning-based pyramid-transformer for localized porosity analysis of hot-press sintered ceramic paste.

Scanning Electron Microscope (SEM) is a crucial tool for studying microstructures of ceramic materials. However, the current practice heavily relies on manual efforts to extract porosity from SEM images. To address this issue, we propose PSTNet (Pyramid Segmentation Transformer Net) for grain and pore segmentation in SEM images, which merges multi-scale feature maps through operations like recombination and upsampling to predict and generate segmentation maps. These maps are used to predict the corresponding porosity at ceramic grain boundaries. To increase segmentation accuracy and minimize loss, we employ several strategies. (1) We train the micro-pore detection and segmentation model using publicly available Al2O3 and custom Y2O3 ceramic SEM images. We calculate the pixel percentage of segmented pores in SEM images to determine the surface porosity at the corresponding locations. (2) Utilizing high-temperature hot pressing sintering, we prepared and captured scanning electron microscope images of Y2O3 ceramics, with which a Y2O3 ceramic dataset was constructed through preprocessing and annotation. (3) We employed segmentation penalty cross-entropy loss, smooth L1 loss, and structural similarity (SSIM) loss as the constituent terms of a joint loss function. The segmentation penalty cross-entropy loss helps suppress segmentation loss bias, smooth L1 loss is utilized to reduce noise in images, and incorporating structural similarity into the loss function computation guides the model to better learn structural features of images, significantly improving the accuracy and robustness of semantic segmentation. (4) In the decoder stage, we utilized an improved version of the multi-head attention mechanism (MHA) for feature fusion, leading to a significant enhancement in model performance. Our model training is based on publicly available laser-sintered Al2O3 ceramic datasets and self-made high-temperature hot-pressed sintered Y2O3 ceramic datasets, and validation has been completed. Our Pix Acc score improves over the baseline by 12.2%, 86.52 vs. 76.01, and the mIoU score improves from by 25.5%, 69.10 vs. 51.49. The average relative errors on datasets Y2O3 and Al2O3 were 6.9% and 6.36%, respectively.

Dense monocular depth estimation for stereoscopic vision based on pyramid transformer and multi-scale feature fusion.

Stereoscopic display technology plays a significant role in industries, such as film, television and autonomous driving. The accuracy of depth estimation is crucial for achieving high-quality and realistic stereoscopic display effects. In addressing the inherent challenges of applying Transformers to depth estimation, the Stereoscopic Pyramid Transformer-Depth (SPT-Depth) is introduced. This method utilizes stepwise downsampling to acquire both shallow and deep semantic information, which are subsequently fused. The training process is divided into fine and coarse convergence stages, employing distinct training strategies and hyperparameters, resulting in a substantial reduction in both training and validation losses. In the training strategy, a shift and scale-invariant mean square error function is employed to compensate for the lack of translational invariance in the Transformers. Additionally, an edge-smoothing function is applied to reduce noise in the depth map, enhancing the model's robustness. The SPT-Depth achieves a global receptive field while effectively reducing time complexity. In comparison with the baseline method, with the New York University Depth V2 (NYU Depth V2) dataset, there is a 10% reduction in Absolute Relative Error (Abs Rel) and a 36% decrease in Root Mean Square Error (RMSE). When compared with the state-of-the-art methods, there is a 17% reduction in RMSE.

Efficient Photodegradation of Rhodamine B by Fiber-like Nitrogen-Doped TiO2/Ni(OH)2 Nanocomposite under Visible Light Irradiation.

N-TiO2/Ni(OH)2 nanofiber was successfully prepared by combining the electrospinning and solvothermal method. It has been found that under visible light irradiation, the as-obtained nanofiber exhibits excellent activity for the photodegradation of rhodamine B, and the average degradation rate reaches 3.1%/min-1. Further insight investigations reveal that such a high activity was mainly due to the heterostructure-induced increase in the charge transfer rate and separation efficiency.

Hierarchical Design of CuO/Nickel-Cobalt-Sulfide Electrode by a Facile Two-Step Potentiostatic Deposition.

Herein, a scalable electrodeposition strategy is proposed to achieve hierarchical CuO/nickel-cobalt-sulfide (NCS) electrodes using two-step potentiostatic deposition followed by high-temperature calcination. The introduction of CuO provides support for the further deposition of NSC to ensure a high load of active electrode materials, thus generating more abundant active electrochemical sites. Meanwhile, dense deposited NSC nanosheets are connected to each other to form many chambers. Such a hierarchical electrode prompts a smooth and orderly transmission channel for electron transport, and reserves space for possible volume expansion during the electrochemical test process. As a result, the CuO/NCS electrode exhibits superior specific capacitance (Cs) of 4.26 F cm-2 at 20 mA cm-2 and remarkable coulombic efficiency of 96.37%. Furthermore, the cycle stability of the CuO/NCS electrode remains at 83.05% within 5000 cycles. The multistep electrodeposition strategy provides a basis and reference for the rational design of hierarchical electrodes to be applied in the field of energy storage.

Achieving Self-Supported Hierarchical Cu(OH)2/Nickel-Cobalt Sulfide Electrode for Electrochemical Energy Storage.

Herein, nickel-cobalt sulfide (NCS) nanoflakes covering the surface of Cu(OH)2 nanorods were achieved by a facile two-step electrodeposition strategy. The effect of CH4N2S concentration on formation mechanism and electrochemical behavior is investigated and optimized. Thanks to the synergistic effect of the selected composite components, the Cu(OH)2/NCS composite electrode can deliver a high areal specific capacitance (Cs) of 7.80 F cm-2 at 2 mA cm-2 and sustain 5.74 F cm-2 at 40 mA cm-2. In addition, coulombic efficiency was up to 84.30% and cyclic stability remained 82.93% within 5000 cycles at 40 mA cm-2. This innovative work provides an effective strategy for the design and construction of hierarchical composite electrodes for the development of energy storage devices.

Facile Route to Achieve a Hierarchical CuO/Nickel-Cobalt-Sulfide Electrode for Energy Storage.

Herein, a novel self-supporting CuO/nickel-cobalt-sulfide (NCS) electrode was designed in a two-step electrodeposition technique followed by a calcination process. Three-dimensional copper foam (CF) was exploited as the current collector and spontaneous source for the in situ preparation of the CuO nanostructures, which ensured sufficient deposition space for the subsequent NCS layer, thus forming abundant electrochemical active sites. Such a hierarchical structure is conducive to providing a smooth path for promoting electronic transmission. Therefore, the optimized CuO/NCS electrode exhibits outstanding energy storage capability with extremely superior specific capacitance (Cs) of 7.08 F cm-2 at 4 mA cm-2 and coulombic efficiency of up to 94.83%, as well as excellent cycling stability with capacitance retention of 83.33% after 5000 cycles. The results presented in this work extend our horizons to fabricate novel hierarchical structured electrodes applied to energy storage devices.