Fault diagnosis is vital in manufacturing system, since early detections on the emerging problem can save invaluable time and cost. With the development of smart manufacturing, the data-driven fault ...diagnosis becomes a hot topic. However, the traditional data-driven fault diagnosis methods rely on the features extracted by experts. The feature extraction process is an exhausted work and greatly impacts the final result. Deep learning (DL) provides an effective way to extract the features of raw data automatically. Convolutional neural network (CNN) is an effective DL method. In this study, a new CNN based on LeNet-5 is proposed for fault diagnosis. Through a conversion method converting signals into two-dimensional (2-D) images, the proposed method can extract the features of the converted 2-D images and eliminate the effect of handcrafted features. The proposed method which is tested on three famous datasets, including motor bearing dataset, self-priming centrifugal pump dataset, and axial piston hydraulic pump dataset, has achieved prediction accuracy of 99.79%, 99.481%, and 100%, respectively. The results have been compared with other DL and traditional methods, including adaptive deep CNN, sparse filter, deep belief network, and support vector machine. The comparisons show that the proposed CNN-based data-driven fault diagnosis method has achieved significant improvements.
Arranging ionic liquids (ILs) with long‐range order can not only enhance their performance in a desired application, but can also help elucidate the vital between structure and properties. However, ...this is still a challenge and no example has been reported to date. Herein, we report a feasible strategy to achieve a crystalline IL via coordination self‐assembly based reticular chemistry. IL1MOF, was prepared by designing an IL bridging ligand and then connecting them with metal clusters. IL1MOF has a unique structure, where the IL ligands are arranged on a long‐range ordered framework but have a labile ionic center. This structure enables IL1MOF to break through the typical limitation where the solid ILs have lower proton conductivity than their counterpart bulk ILs. IL1MOF shows 2–4 orders of magnitude higher proton conductivity than its counterpart IL monomer across a wide temperature range. Moreover, by confining the IL within ultramicropores (<1 nm), IL1MOF suppresses the liquid–solid phase transition temperatures to lower than −150 °C, allowing it to function with high conductivity in a subzero temperature range.
A reticular chemistry based strategy opens a facile toolbox for designing liquid molecules with long‐rang‐ordered framework of MOF. IL1MOF is the first crystalline ionic liquid (IL) combining a balance of good mechanical properties and high conductivity. It expands the use of IL electrolytes to an low temperature region.
Gastric cancer (GC) is one of the most common malignancies worldwide. Most patients are diagnosed at advanced stages due to the subtle symptoms of earlier disease and the low rate of regular ...screening. Systemic therapies for GC, including chemotherapy, targeted therapy and immunotherapy, have evolved significantly in the past few years. For resectable GC, perioperative chemotherapy has become the standard treatment. Ongoing investigations are exploring the potential benefits of targeted therapy or immunotherapy in the perioperative or adjuvant setting. For metastatic disease, there have been notable advancements in immunotherapy and biomarker-directed therapies recently. Classification based on molecular biomarkers, such as programmed cell death ligand 1 (PD-L1), microsatellite instability (MSI), and human epidermal growth factor receptor 2 (HER2), provides an opportunity to differentiate patients who may benefit from immunotherapy or targeted therapy. Molecular diagnostic techniques have facilitated the characterization of GC genetic profiles and the identification of new potential molecular targets. This review systematically summarizes the main research progress in systemic treatment for GC, discusses current individualized strategies and presents future perspectives.
The performance of Li‐ion batteries (LIBs) is highly dependent on their interfacial chemistry, which is regulated by electrolytes. Conventional electrolyte typically contains polar solvents to ...dissociate Li salts. Herein we report a weakly solvating electrolyte (WSE) that consists of a pure non‐polar solvent, which leads to a peculiar solvation structure where ion pairs and aggregates prevail under a low salt concentration of 1.0 M. Importantly, WSE forms unique anion‐derived interphases on graphite electrodes that exhibit fast‐charging and long‐term cycling characteristics. First‐principles calculations unravel a general principle that the competitive coordination between anions and solvents to Li ions is the origin of different interfacial chemistries. By bridging the gap between solution thermodynamics and interfacial chemistry in batteries, this work opens a brand‐new way towards precise electrolyte engineering for energy storage devices with desired properties.
A weakly solvating electrolyte affords a new path towards anion‐derived interfacial chemistry in lithium‐ion batteries. By formulating electrolyte with a non‐polar solvent, ion pairs and aggregates prevail under normal concentrations and give rise to anion‐derived interphases on graphite electrodes with superior electrochemical performances.
Fault diagnosis plays an important role in modern industry. With the development of smart manufacturing, the data-driven fault diagnosis becomes hot. However, traditional methods have two ...shortcomings: 1) their performances depend on the good design of handcrafted features of data, but it is difficult to predesign these features and 2) they work well under a general assumption: the training data and testing data should be drawn from the same distribution, but this assumption fails in many engineering applications. Since deep learning (DL) can extract the hierarchical representation features of raw data, and transfer learning provides a good way to perform a learning task on the different but related distribution datasets, deep transfer learning (DTL) has been developed for fault diagnosis. In this paper, a new DTL method is proposed. It uses a three-layer sparse auto-encoder to extract the features of raw data, and applies the maximum mean discrepancy term to minimizing the discrepancy penalty between the features from training data and testing data. The proposed DTL is tested on the famous motor bearing dataset from the Case Western Reserve University. The results show a good improvement, and DTL achieves higher prediction accuracies on most experiments than DL. The prediction accuracy of DTL, which is as high as 99.82%, is better than the results of other algorithms, including deep belief network, sparse filter, artificial neural network, support vector machine and some other traditional methods. What is more, two additional analytical experiments are conducted. The results show that a good unlabeled third dataset may be helpful to DTL, and a good linear relationship between the final prediction accuracies and their standard deviations have been observed.
Convolutional neural network (CNN) has gained increasing attention in fault classification. However, the performance of CNN is sensitive to its learning rate. Some previous works have been done to ...tune the learning rate, including the "trial and error" and manual search, which heavily depend on the experts' experiences and should be conducted repeatedly on every dataset. Because of the variety of the fault data, it is time-consuming and labor intensive to use these traditional tuning methods for fault classification. To overcome this problem, in this article, we develop a novel learning rate scheduler based on the reinforcement learning (RL) for convolutional neural network (RL-CNN) in fault classification, which can schedule the learning rate efficiently and automatically. First, a new RL agent is designed to learn the policies about the learning rate adjustment during the training process. Second, a new structure of RL-CNN is developed to balance the exploration and exploitation of the agent. Third, the bagging ensemble version of RL-CNN (RL-CNN-Ens) is presented. Three bearing datasets are used to test the performance of RL-CNN-Ens. The results show that RL-CNN-Ens outperforms the traditional DLs and machine learning methods. Meanwhile, RL-CNN-Ens can find the state-of-the-art learning rate schedulers as human designed, showing its potential in fault classification.
With the rapid development of smart manufacturing, data-driven fault diagnosis has attracted increasing attentions. As one of the most popular methods applied in fault diagnosis, deep learning (DL) ...has achieved remarkable results. However, due to the fact that the volume of labeled samples is small in fault diagnosis, the depths of DL models for fault diagnosis are shallow compared with convolutional neural network in other areas (including ImageNet), which limits their final prediction accuracies. In this research, a new TCNN(ResNet-50) with the depth of 51 convolutional layers is proposed for fault diagnosis. By combining with transfer learning, TCNN(ResNet-50) applies ResNet-50 trained on ImageNet as feature extractor for fault diagnosis. Firstly, a signal-to-image method is developed to convert time-domain fault signals to RGB images format as the input datatype of ResNet-50. Then, a new structure of TCNN(ResNet-50) is proposed. Finally, the proposed TCNN(ResNet-50) has been tested on three datasets, including bearing damage dataset provided by KAT datacenter, motor bearing dataset provided by Case Western Reserve University (CWRU) and self-priming centrifugal pump dataset. It achieved state-of-the-art results. The prediction accuracies of TCNN(ResNet-50) are as high as 98.95% ± 0.0074, 99.99% ± 0 and 99.20% ± 0, which demonstrates that TCNN(ResNet-50) outperforms other DL models and traditional methods.
Exosomes are well-known key mediators of intercellular communication and contribute to various physiological and pathological processes. Their biogenesis involves four key steps, including cargo ...sorting, MVB formation and maturation, transport of MVBs, and MVB fusion with the plasma membrane. Each process is modulated through the competition or coordination of multiple mechanisms, whereby diverse repertoires of molecular cargos are sorted into distinct subpopulations of exosomes, resulting in the high heterogeneity of exosomes. Intriguingly, cancer cells exploit various strategies, such as aberrant gene expression, posttranslational modifications, and altered signaling pathways, to regulate the biogenesis, composition, and eventually functions of exosomes to promote cancer progression. Therefore, exosome biogenesis-targeted therapy is being actively explored. In this review, we systematically summarize recent progress in understanding the machinery of exosome biogenesis and how it is regulated in the context of cancer. In particular, we highlight pharmacological targeting of exosome biogenesis as a promising cancer therapeutic strategy.
Regulating the tumor microenvironment (TME) has been a promising strategy to improve antitumor therapy. Here, a red blood cell membrane (mRBC)‐camouflaged hollow MnO2 (HMnO2) catalytic nanosystem ...embedded with lactate oxidase (LOX) and a glycolysis inhibitor (denoted as PMLR) is constructed for intra/extracellular lactic acid exhaustion as well as synergistic metabolic therapy and immunotherapy of tumor. Benefiting from the long‐circulation property of the mRBC, the nanosystem can gradually accumulate in a tumor site through the enhanced permeability and retention (EPR) effect. The extracellular nanosystem consumes lactic acid in the TME by catalyzing its oxidation reaction via LOX. Meanwhile, the intracellular nanosystem releases the glycolysis inhibitor to cut off the source of lactic acid, as well as achieve antitumor metabolic therapy through the blockade of the adenosine triphosphate (ATP) supply. Both the extracellular and intracellular processes can be sensitized by O2, which can be produced during the decomposition of endogenous H2O2 catalyzed by the PMLR nanosystem. The results show that the PMLR nanosystem can ceaselessly remove lactic acid, and then lead to an immunocompetent TME. Moreover, this TME regulation strategy can effectively improve the antitumor effect of anti‐PDL1 therapy without the employment of any immune agonists to avoid the autoimmunity.
A strategy based on intra/extracellular lactic acid exhaustion is reported to achieve synergistic metabolic therapy and immunotherapy of tumors. This strategy is performed by a cascade catalytic nanosystem (PMLR) that integrates a hollow MnO2 nanocarrier with lactate oxidase and a glycolysis inhibitor.
Most cancer vaccines are unsuccessful in eliciting clinically relevant effects. Without using exogenous antigens and adoptive cells, we show a concept of utilizing biologically reprogrammed ...cytomembranes of the fused cells (FCs) derived from dendritic cells (DCs) and cancer cells as tumor vaccines. The fusion of immunologically interrelated two types of cells results in strong expression of the whole tumor antigen complexes and the immunological co-stimulatory molecules on cytomembranes (FMs), allowing the nanoparticle-supported FM (NP@FM) to function like antigen presenting cells (APCs) for T cell immunoactivation. Moreover, tumor-antigen bearing NP@FM can be bio-recognized by DCs to induce DC-mediated T cell immunoactivation. The combination of these two immunoactivation pathways offers powerful antitumor immunoresponse. Through mimicking both APCs and cancer cells, this cytomembrane vaccine strategy can develop various vaccines toward multiple tumor types and provide chances for accommodating diverse functions originating from the supporters.