Haitao Wang

Deep learning-based image classification techniques have been widely utilized in low-voltage AC series-type fault arc detection. However, the transformation of signals into images frequently leads to significant loss of current signal characteristics, thereby compromising arc recognition accuracy. Additionally, uncharacterized signal content may be lost due to multiple factors, including sensor bandwidth limitations, sensor-event distance, and the topological configuration of the circuit where the fault originated. To address this challenge, a novel framework for identifying series-type low-voltage AC fault arcs is presented, which integrates the Markov transfer field (MTF) with multi-feature fusion and an improved residual neural network (ResNet18). This approach employs fast Fourier transform (FFT) to compute magnitude and phase data and then converts the original current signals, magnitude spectrograms, and phase spectrograms into MTF images. An adaptive weighted averaging strategy is subsequently applied to fuse these MTF images, generating composite discriminative features that preserve both amplitude and phase information from the original signals. The proposed system incorporates a convolutional block-based attention mechanism (CBAM) into the ResNet18 architecture to enhance feature representation while reducing training complexity. Extensive experimental evaluations on a diverse dataset demonstrate that the developed method achieves an impressive recognition accuracy of 99.88% for series fault arcs. This result validates the effectiveness of the proposed framework in maintaining critical signal characteristics and improving detection precision compared to existing approaches.

At the microscale, the three-dimensional morphological features of contact surfaces have a significant impact on the performance of electrical contacts. This paper aims to reconstruct the microscopic contact state of contact groups and to deeply study the effect of contact morphological features on electrical contact performance. To fully obtain multimodal data such as the three-dimensional micro-morphological features and chemical composition distribution of contact surfaces, this paper proposes a contact surface feature-matching method based on entropy rate superpixel seed point adaptive morphological reconstruction. This method can adaptively retain meaningful seed points while filtering out invalid seed points, effectively solving the problem of over-segmentation in traditional superpixel segmentation method. Experimental results show that the proposed method achieves a segmentation accuracy of 92% and reduces over-segmentation by 30% compared to traditional methods. Subsequently, on the basis of the moving and static contact group difference plane model and the W-M model, this paper constructs a three-dimensional surface fractal contact model with an irregular base. This model has the ability to layer simulate multi-parameter elastic and plastic and to extract fractal parameter point cloud height, which can more accurately reflect the actual contact state of the contact group. The model demonstrates a 15% improvement in contact area prediction accuracy and a 20% reduction in contact resistance estimation error compared to existing models. Finally, this paper compares and verifies the theoretical feasibility of the model, providing a new theoretical contact model for the study of the impact of three-dimensional micro-morphology on the electrical contact reliability.

Non-intrusive load monitoring is a significant advancement in energy conservation and smart electricity usage as it enables the identification of load status and equipment type without the need for extensive sensing instruments. As one of the important steps of non-intrusive load monitoring, non-intrusive load identification plays a crucial role in the correct identification of electrical appliances. In this paper, a novel approach is presented to amalgamate multiple appliance features into a new identification feature, which is then used for appliance recognition through an improved lightweight deep learning model. This addresses the issue of low accuracy when using a single feature for appliance identification. The core concept involves initially capturing the current data of an appliance during steady state operation and fusing the image features of the appliance encoded by Gramian summation angular field, Gramian difference angular field, and Markov transition field into new recognition features for each appliance using average weighting. Subsequently, a shufflenetv2 lightweight deep learning model based on the squeeze -and-excitation module is used to mine the constructed load feature information for the load classification task. The method is then experimentally validated on the Self-test Dataset, PLAID, and WHITED dataset, resulting in recognition accuracies of 100%, 98.214%, and 99.745%, respectively. These results demonstrate the effectiveness of the proposed method in significantly improving recognition performance compared to the original approach.

To investigate the stability and electrical and physical properties of undoped CuO and CuO doped with rare earth elements, electronic structures and elastic constants were calculated using first-principles density functional theory. Additionally, experimental verification was carried out on AgCuO and AgCuO-X (La, Ce, Y) electrical contacts, which were prepared using sol–gel and powder metallurgy methods. The contacts were tested under an 18 V/15 A DC resistive load using the JF04D contact material testing system. Arc parameters were analyzed, and three-dimensional surface profilometry and scanning electron microscopy were used to study the altered erosion morphology of the electrically contacted materials; moreover, the potential mechanisms behind their arc erosion behavior were investigated in depth. The results demonstrate that the doping of rare earth elements can improve the electrical conductivity and physical properties of the contacts, optimize the arc parameters, and enhance their resistance to arc erosion. Notably, AgCuO-Ce exhibited the highest electrical conductivity and the least amount of material transfer; moreover, it had excellent arc time and energy parameters, resulting in the best resistance to arc erosion. This study provides a theoretical basis for the screening of doping elements to enhance the performance of AgCuO contact materials and offers new ideas and scientific references for this field.

Because of the different ways in which contact materials work, the basic requirements for silver metal oxide contact materials are different. They are anti-welded and anti-erosion when closed, anti-erosion when broken, and arc easily moved and have smaller contact resistance. In this paper, La₂O₃ is used as a stable oxide in contact material to replace CdO. A new type of Ag/SnO₂-La₂O₃-Bi₂O₃ contact material is first obtained through using powder metallurgical method. Then electrical contact material parameter tester is used to test the electrical contact performance of the contact material. Through experiments, the arcing voltage and current curves, arcing energy curves, fusion power curves while broken and contact resistance while closed were obtained. Analysis of the results showed that the addition of La₂O₃ makes the contact material have the following advantages: smaller electrical wear, smaller arc energy, smaller contact resistance and arc is more easily extinguished.