Search

Real-time and accurate predictive maintenance of industrial equipment is fundamental for ensuring the safety and stability of advanced manufacturing processes. Current fault diagnosis methods based on data mining rely on a large number of labeled samples, and obtaining sufficient labeled data for diagnosing industrial equipment faults is challenging. Meta-learning can achieve the diagnosis of few-shot samples to a certain extent, but the effect is not ideal. Semi-supervision can effectively leverage a large number of unlabeled samples, which is of great practical significance for handling scenarios involving limited labeled samples. However, noise interference can occur when unlabeled samples appear that do not belong to known categories. Therefore, this study proposes adaptive semi-supervised meta-learning networks (ASMNs) for noisy few-shot gearbox fault diagnosis. Firstly, a residual network with a Morlet Wavelet layer is used to extract signal features. Next, sample-level attention is defined to select unlabeled samples that are more similar to labeled sample prototypes, thereby reducing the influence of noisy samples. The adaptive metric is used to obtain the relational distance functions of labeled samples and unlabeled samples. Adaptive semi-supervised ASMNs uses unlabeled data to refine prototypes for better fault diagnosis. The effectiveness and anti-noise performance of the proposed method are verified by using two gearbox datasets with various few-shot noise scenarios. [ABSTRACT FROM AUTHOR]

Reconstructive phase transitions involving breaking and reconstruction of primary chemical bonds are ubiquitous and important for many technological applications. In contrast to displacive phase transitions, the dynamics of reconstructive phase transitions are usually slow due to the large energy barrier. Nevertheless, the reconstructive phase transformation from β- to λ-Ti3O5 exhibits an ultrafast and reversible behavior. Despite extensive studies, the underlying microscopic mechanism remains unclear. Here, we discover a kinetically favorable in-plane nucleated layer-by-layer transformation mechanism through metadynamics and large-scale molecular dynamics simulations. This is enabled by developing an efficient machine learning potential with near first-principles accuracy through an on-the-fly active learning method and an advanced sampling technique. Our results reveal that the β−λ phase transformation initiates with the formation of two-dimensional nuclei in the ab-plane and then proceeds layer-by-layer through a multistep barrier-lowering kinetic process via intermediate metastable phases. Our work not only provides important insight into the ultrafast and reversible nature of the β−λ transition, but also presents useful strategies and methods for tackling other complex structural phase transitions. Reconstructive phase transitions in materials are usually slow due to large activation energy barriers. Here, the authors show a kinetically favorable layer-by-layer mechanism in Ti3O5 transformations using machine-learning molecular dynamics simulations. [ABSTRACT FROM AUTHOR]

The effectiveness of anti‐metastasis therapy is hampered by the highly immunosuppressive microenvironment found in both tumor tissues and lymph nodes. In this work, a therapeutic nanovaccine, CaGlu NPs, is introduced composed of calcium carbonate nanoparticles (CaCO3 NPs) and β‐glucan. Through the synergistic effect of CaCO3 NPs and β‐glucan, CaGlu NPs can induce immunogenic cell death in tumor tissues, repolarize tumor macrophages, reverse the immunosuppressive tumor microenvironment, effectively activate antigen‐specific cytotoxic T lymphocytes, promote dendritic cells maturation, and eventually elicit an effective anti‐tumor immune response in both primary tumors and metastatic lymph nodes. Meanwhile, CaGlu NPs can remodel the metabolic microenvironment in tumors and lymph nodes by decreasing the expression of lactate dehydrogenase A and hypoxia‐inducible factor‐1α, further enhancing the anti‐tumor immune response. CaGlu NPs also inhibit tumor angiogenesis and lymphangiogenesis and induce long‐term immune memory effects. This therapeutic nanovaccine strategy, which simultaneously remodels the metabolic and immunosuppressive microenvironments in tumors and metastatic lymph nodes, showed strong anti‐metastatic effects in vivo. This study presents a promising approach to effectively treat lymph node metastatic tumors using nanomaterial‐assisted immunotherapies and underscores its broad potential for clinical applications. [ABSTRACT FROM AUTHOR]

With climate change expected to intensify the occurrence and severity of droughts, the control of groundwater table (GWT) depth and capillary rise on topsoil moisture may render a critical driver of biological activity. Consequently, GWT depth could influence topsoil carbon mineralization. In this study, undisturbed 200 cm long soil columns of three different textures (loamy sand, sandy loam and silt loam) were subjected to two artificial GWT depths (–165 cm and –115 cm) in the laboratory. We examined (1) moisture supply by capillary rise along the soil profile and specifically into the top 20 cm soil, and (2) consequently the effect of GWT on decomposition of an added 13C-enriched substrate (ryegrass) over a period of ten weeks, with limited water applications representing a dry summer. A 50 cm difference in GWT depth (–165 cm vs. –115 cm) resulted in different topsoil moisture for the sandy loam (31 % vs. 38 % Water-filled pore space (WFPS)) and silt loam (33 % vs. 43 % WFPS) soils. In the loamy sand soil, GWT-induced moisture differences appeared only up to 85 cm above the GWT. The expected acceleration of mineralization of the added ryegrass under a shallower GWT was not confirmed. In contrast, C mineralization pulses after the wetting events were even higher for the drier –165 cm GWT soils. For the silt loam soil, where capillary rise supply had the largest contribution to topsoil moisture, a lower mineralization rate of the stable Cryegrass pool was also found with shallower GWT. These findings suggest that a potential capillary rise effect of increased topsoil moisture on ryegrass mineralization might have been counteracted by other processes. We postulate that the Birch effect might have been magnified following the rewetting of drier topsoils under deeper GWT levels, ultimately enhancing mineralization compared to where the soil remains consistently wetter under shallower GWT levels. Based on our findings, including the process of texture-specific capillary supply from the GWT can be required to adequately simulate moisture in the topsoil during droughts as they occurred over the past summers in North-West Europe, depending on GWT and texture combination. However, the net effect on topsoil C mineralization is complex and correct simulation of C mineralization may require further integration of specific processes connected to fluctuating soil moisture state, such as the Birch effect. [ABSTRACT FROM AUTHOR]