Zhitong Liu

Convolutional neural networks(CNNs) show significant potential for bearing fault diagnosis. However, tra-ditional CNNs face challenges such as poor noise resistance, high computational complexity, reliance on extensive samples, and limited generalizability. As a result, this paper proposes WDSC-Net, a lightweight, multiscale feature fusion method, focusing on limited labeled fault samples. Initially, a wide kernel convo-lutional is employed, aiming to reduce parameters and computational complexity. Next, features are fed into a 1×1 convolutional layer reduces feature dimensionality. Subsequently, leveraging the benefits of depth-separable convolution (DSC) allows the separation of spatial and channel features, constructing four convolutional layers of varying scales to amplify the nonlinear fault representation. Finally, an improved feature soft-threshold denoising module is introduced for global feature denoising. Validation on CWRU and MCDS datasets shows that the WDSC-Net method exhibits superior generalizability and noise resistance compared to typical deep-learning fault methods

In aeroengine maintenance, endoscopic imaging serves as a crucial tool for detecting blade defects and evolves toward intelligence driven by computer vision technology. Currently, supervised-learning-based defect segmentation methods mainly rely on extensive pixel-level annotations, making it laborious and time consuming. This article shifts focus to the abundant unlabeled data in real-world scenarios and introduces an innovative semisupervised defect segmentation method termed SAIT. Within this framework, three parallel self-supervised mechanisms are adeptly integrated with a semisupervised framework, aiming to bolster defect semantic segmentation with limited labeled samples. In the initial phase, by leveraging the capability of the vision transformer to dissect images into patches, four stochastic distortions are seamlessly infused into the patch sequence. Subsequently, three self-supervised tasks from image level to pixel level are achieved through a customized joint objective function paired with a tailored backbone network. In the second phase, SAIT undergoes pixel-level fine-tuning via the proposed class-centric loss, mitigating class imbalances in limited sample sizes and enhancing initial training. Experiments on a proprietary dataset demonstrate that SAIT achieved 78.42% and 86.70% in mean intersection over union and mean pixel accuracy metrics, respectively, with 25% labeled data, significantly improving the performance of existing semisupervised defect segmentation techniques. Meanwhile, experiments on the open-source dataset further indicate that SAIT holds promise for application in other industrial sectors beyond aeroengine inspection.

Intercultural foreign language learning among K -12 students at international schools involves the cross-cultural discovery of the changing habits of people whose mother tongue might be different instructive languages at schools. Bilingual education is essential in bridging the gap between the mother tongue and instructive languages. However, it needs effective strategies that combine in-classroom language learning with new technology. Several language learning and teaching trends concerning the digital environment and innovative technologies such as machine translation or digitalization are currently challenging K-12 schools and families. This research investigates the role of machine translation in learning among K-12 students at international schools in the cities of Shenzhen, Guangzhou, and Zhuhai. It aims to identify these gaps in existing research and propose innovative strategies for boosting learning outcomes to recognize the learning habits they developed as young learners in the 21st century and their cultural motivations. Bilingual surveys are being handed out to K-12 families. These surveys are written in both English and Chinese. In total, 221 of them were collected. The data was analyzed to examine how helpful machine translation is for academic learning in both languages. The strengths and weaknesses were summarized among K-12 students using machine translation, highlighting strategies used with it at international K-12 schools.

With continuous advancements in sensor technology and computer vision, automated surface defect detection has become an important problem in the modern manufacturing industry. Although deep-learning-based defect detection methods have proven successful in various inspection tasks, they often require extensive high-quality pixel-level annotations for model training. Industrial defects, characterized by diverse shapes and intricate textures, require manual labelling by skilled inspectors. This study introduces a weakly supervised defect segmentation framework called the progressively learning dynamic level set (PLDL) to overcome these constraints. This framework incorporates two parallel learning modules and a differentiable level set module interconnected through a progressive learning strategy facilitated by an innovative loss function. Using only image-level labels as inputs, the PLDL framework iteratively refines object boundaries, dynamically optimizes the training process, and generates pixel-level outputs. Our method is efficient and consistent, requiring no manual supervision or post-processing steps. Experimental results on four benchmark datasets representing diverse industrial scenarios reveal that PLDL outperforms recent weakly supervised models. It achieved 76.52%, 85.23%, 85.71%, 84.43%, and 83.17% in mIoU, mPA, Precision, Recall, and F-measure, respectively, indicating its superior effectiveness in weakly supervised defect segmentation.