Industrial Internet of Things (IIoT) empowers smart manufacturing by enabling real-time data collection, analysis, and optimization. Wire Arc Additive Manufacturing (WAAM), as a smart manufacturing method, is attracting considerable attention in industry and academia due to its ability to fabricate large com-ponents, whilst allowing material savings. Monitoring the geome-try of the bead is essential for ensuring the quality and consistency of the manufactured components, and even provide feedback to enhance the control of the manufacturing process. In recent years, deep learning-based geometry monitoring approaches have gained significant attention. However, several challenges remain. Existing methods often overlook the physical relationships among process signals, rely solely on data-driven graph constructions, and suffer from poor interpretability due to the black-box nature of neural networks. Additionally, fixed receptive fields in graph convolu-tional networks (GCNs) limit feature extraction and model perfor-mance. To address these issues, this study proposes a physics-aware graph network (PAGN). A sensor network is designed to construct graph data based on based on the physical relationships among signals. Leveraging the interpretability of wavelet trans-form, PAGN integrates a multi-scale filter (MSF) module and an adaptive multi-scale stacking (AMSS) module, enabling multi-res-olution analysis of graph signals. Lastly, the effectiveness of the proposed PAGN is evaluated on the copper and chrome zirconium copper dataset. Experimental results on both datasets demon-strate the effectiveness of the proposed PAGN framework, achiev-ing RMSE reductions of 10.37% and 12.02% and MAE reductions of 8.9% and 5.15%compared to the other methods.

The inspection of power transmission line has achieved notable achievements in the past few years, primarily due to the integration of deep learning technology. However, current inspection approaches continue to encounter difficulties in generalization and intelligence, which restricts their further applicability. In this paper, we introduce Power-LLaVA, the first large language and vision assistant designed to offer professional and reliable inspection services for power transmission line by engaging in dialogues with humans. Moreover, we also construct a large-scale and high-quality dataset specialized for the inspection task. By employing a two-stage training strategy on the constructed dataset, Power-LLaVA demonstrates exceptional performance at a comparatively low training cost. Extensive experiments further prove the great capabilities of Power-LLaVA within the realm of power transmission line inspection. Code shall be released.

Semiconductor gas sensors are important candidates with small size, low-power consumption, and low-cost characteristics for gas sensing in the Internet of Things (IoT), but the nonlinear response, unstable baseline, and the variability of the responses toward temperature and humidity fluctuation harm its performance. Here, we proposed a new technique called virtual alternating current (ac) measurements to enable semiconductor gas sensors to achieve high linear response ($R^{2}>0.99$), stable baseline, and easily calibrated temperature and humidity fluctuation. The most outstanding advantage of our technique is to achieve excellent performance simply by measuring resistance. The universality and feasibility of our technique were verified by a range of commercial and homemade sensing elements and a range of analyte. We also successfully generalized our technique to non-Debye relaxation systems, which further expands the scope of semiconductor gas sensor types available in our technique. We believe that our technique will enable gas sensing nodes built with semiconductor gas sensors in the IoT to achieve markedly superior performance.

Knowledge distillation aims to transfer representation ability from a teacher model to a student model. Previous approaches focus on either individual representation distillation or inter-sample similarity preservation. While we argue that the inter-sample relation conveys abundant information and needs to be distilled in a more effective way. In this paper, we propose a novel knowledge distillation method, namely Complementary Relation Contrastive Distillation (CRCD), to transfer the structural knowledge from the teacher to the student. Specifically, we estimate the mutual relation in an anchor-based way and distill the anchor-student relation under the supervision of its corresponding anchor-teacher relation. To make it more robust, mutual relations are modeled by two complementary elements: the feature and its gradient. Furthermore, the low bound of mutual information between the anchor-teacher relation distribution and the anchor-student relation distribution is maximized via relation contrastive loss, which can distill both the sample representation and the inter-sample relations. Experiments on different benchmarks demonstrate the effectiveness of our proposed CRCD.

Due to the cross-sensitivity to kinds of gases, traditional single sensor is impossible to selectively detect gases, which limits its application. In this paper, a sensor array with supervised and unsupervised algorithms was employed to selectively detect NO2, CO and their mixtures. To improve the recognition accuracy, average resistance over a period of time was introduced to acquire features, including response value, response time and recovery time. Firstly, principal component analysis (PCA) was utilized to reduce the dimensionality of samples. With the help of unsupervised fuzzy C-means clustering algorithm, samples have exhibited obvious clustering. Furthermore, artificial neural network (ANN) has reached a high accuracy of quantitative identification on six different detected gases varying from 0 to 50 ppm.