A Novel Hierarchical Vision Transformer and Wavelet Time-Frequency Based on Multi-Source Information Fusion for Intelligent Fault Diagnosis.

Deep learning (DL) has been widely used to promote the development of intelligent fault diagnosis, bringing significant performance improvement. However, most of the existing methods cannot capture the temporal information and global features of mechanical equipment to collect sufficient fault information, resulting in performance collapse. Meanwhile, due to the complex and harsh operating environment, it is difficult to extract fault features stably and extensively using single-source fault diagnosis methods. Therefore, a novel hierarchical vision transformer (NHVT) and wavelet time-frequency architecture combined with a multi-source information fusion (MSIF) strategy has been suggested in this paper to boost stable performance by extracting and integrating rich features. The goal is to improve the end-to-end fault diagnosis performance of mechanical components. First, multi-source signals are transformed into two-dimensional time and frequency diagrams. Then, a novel hierarchical vision transformer is introduced to improve the nonlinear representation of feature maps to enrich fault features. Next, multi-source information diagrams are fused into the proposed NHVT to produce more comprehensive presentations. Finally, we employed two different multi-source datasets to verify the superiority of the proposed NHVT. Then, NHVT outperformed the state-of-the-art approach (SOTA) on the multi-source dataset of mechanical components, and the experimental results show that it is able to extract useful features from multi-source information.

Bearing Fault Diagnosis of Hot-Rolling Mill Utilizing Intelligent Optimized Self-Adaptive Deep Belief Network with Limited Samples.

Given the complexity of the operating conditions of rolling bearings in the actual rolling process of a hot mill and the difficulty in collecting data pertinent to fault bearings comprehensively, this paper proposes an approach that diagnoses the faults of a rolling mill bearing by employing the improved sparrow search algorithm deep belief network (ISAA-DBN) with limited data samples. First, the fast spectral kurtosis approach is adopted to convert the non-stationary original vibration signals collected by the acceleration sensors installed at the axial and radial ends of the rolling mill bearings into two-dimensional (2D) spectral kurtosis time-frequency images with higher feature recognition, and the principal component analysis (PCA) technique is used to decrease the dimension of the data in order to achieve a high diagnosis rate with a limited number of samples. Subsequently, the sparrow search algorithm (SSA) is used to realize the intelligent optimized self-adaptive function of a deep belief network (DBN). Furthermore, the firefly disturbance algorithm is employed to improve the spatial search capability and robustness of SSA-DBN in order to achieve better performance of the ISSA-DBN method. Finally, the proposed approach is experimentally compared to other approaches used for diagnosis. The results show that the proposed approach not only retains the useful features of the data through dimension reduction but also improves the efficiency of the diagnosis and achieves the highest diagnosis accuracy with limited data samples. In addition, the optimal position of the sensor for diagnosing rolling mill roll faults is identified.

Multi-Representation Domain Adaptation Network with Duplex Adversarial Learning for Hot-Rolling Mill Fault Diagnosis.

The multi-process manufacturing of steel rolling products requires the cooperation of complicated and variable rolling conditions. Such conditions pose challenges to the fault diagnosis of the key equipment of the rolling mill. The development of transfer learning has alleviated the problem of fault diagnosis under variable working conditions to a certain extent. However, existing diagnosis methods based on transfer learning only consider the distribution alignment from a single representation, which may only transfer part of the state knowledge and generate fuzzy decision boundaries. Therefore, this paper proposes a multi-representation domain adaptation network with duplex adversarial learning for hot rolling mill fault diagnosis. First, a multi-representation network structure is designed to extract rolling mill equipment status information from multiple perspectives. Then, the domain adversarial strategy is adopted to match the source and target domains of each pair of representations for learning domain-invariant features from multiple representation networks. In addition, the maximum classifier discrepancy adversarial algorithm is adopted to generate target features that are close to the source support, thereby forming a robust decision boundary. Finally, the average value of the predicted probabilities of the two classifiers is used as the final diagnostic result. Extensive experiments are conducted on an experimental platform of a four-high hot rolling mill to collect the fault state data of the reduction gearbox and roll bearing. The experimental results reveal that the method can effectively realize the fault diagnosis of rolling mill equipment under variable working conditions and can achieve average diagnostic rates of up to 99.15% and 99.40% on the data sets of the rolling mill gearbox and bearing, which are respectively 2.19% and 1.93% higher than the rates achieved by the most competitive method.

Integrated prodrug micelles with two-photon bioimaging and pH-triggered drug delivery for cancer theranostics.

Nanodrug carriers with fluorescence radiation are widely used in cancer diagnosis and therapy due to their real-time imaging, less side effect, better drug utilization as well as the good bioimaging ability. However, traditional nanocarriers still suffer from unexpectable drug leakage, unsatisfactory tumor-targeted drug delivery and shallow imaging depth, which limit their further application in cancer theranostics. In this study, an integrated nanoplatform is constructed by polymeric prodrug micelles with two-photon and aggregation-induced emission bioimaging, charge reversal and drug delivery triggered by acidic pH. The prodrug micelles can be self-assembled by the TP-PEI (DA/DOX)-PEG prodrug polymer, which consists of the two-photon fluorophore (TP), dimethylmaleic anhydride (DA) grafted polyethyleneimine (PEI) and polyethylene glycol (PEG). The PEG segment, DOX and DA are bridged to polymer by acid cleavable bonds, which provides the micelles a 'stealth' property and a satisfactory stability during blood circulation, while the outside PEG segment is abandoned along with the DA protection in the tumor acidic microenvironment, thus leading to charge reversal-mediated accelerated endocytosis and tumor-targeted drug delivery. The great antitumor efficacy and reduced side effect of these pH-sensitive prodrug micelles are confirmed by antitumor assays in vitro and in vivo. Meanwhile, these micelles exhibited great deep-tissue two-photon bioimaging ability up to 150 µm in depth. The great antitumor efficacy, reduced side effect and deep two-photon tissue imaging make the TP-PEI (DA/DOX)-PEG prodrug micelles would be an efficient strategy for theranostic nanoplatform in cancer treatment.

Oxidation-Responsive and Aggregation-Induced Emission Polymeric Micelles with Two-Photon Excitation for Cancer Therapy and Bioimaging.

Polymeric micelles with stimuli-triggered drug release and AIE active bioimaging have emerged as potential candidates for theranostics. Herein, a curcumin (Cur) loaded oxidation-responsive mPEG-b-PLG (Se)-TP polymeric micelle system with great aggregation-induced emission (AIE) active and two-photon imaging property has been developed for simultaneous antitumor treatment and bioimaging. Cur-loaded polymeric micelles with a core-shell structure and a homogeneous size of 136 nm show great physiological stability while rapidly disassemble under oxidation environment with accelerated drug release. The excellent biocompatibility and great AIE property and two-photon excitation endow these functional mPEG-b-PLG (Se)-TP micelles as bioprobes for the two-photon imaging of cells and deeper tissues. Furthermore, the biodistribution of nanocarriers and intracellular drug delivery can also be traced. Moreover, the Cur-loaded micelles also show great tumor inhibition ability and minimal side effects in vivo compared with free drug. These novel polymeric micelles are expected to be potential candidates for cancer theranostics.

Long non-coding RNA RUNXOR accelerates MDSC-mediated immunosuppression in lung cancer.

BACKGROUND: RUNX1 overlapping RNA (RUNXOR) is a long non-coding RNA that has been indicated as a key regulator in the development of myeloid cells by targeting runt-related transcription factor 1 (RUNX1). Myeloid-derived suppressor cells (MDSCs) are a heterogeneous population of cells consisting of immature granulocytes and monocytes with immunosuppression. However, the impact of lncRNA RUNXOR on the development of MDSCs remains unknown. METHODS: Both the expressions of RUNXOR and RUNX1 in the peripheral blood were measured by qRT-PCR. Human MDSCs used in this study were isolated from tumor tissue of patients with lung cancer by FCM or induced from PBMCs of healthy donors with IL-1ß + GM-CSF. Specific siRNA was used to knockdown the expression of RUNXOR in MDSCs. RESULTS: In this study, we found that the lncRNA RUNXOR was upregulated in the peripheral blood of lung cancer patients. In addition, as a target gene of RUNXOR, the expression of RUNX1 was downregulated in lung cancer patients. Finally, the expression of RUNXOR was higher in MDSCs isolated from the tumor tissues of lung cancer patients compared with cells from adjacent tissue. In addition, RUNXOR knockdown decreased Arg1 expression in MDSCs. CONCLUSIONS: Based on our findings, it is illustrated that RUNXOR is significantly associated with the immunosuppression induced by MDSCs in lung cancer patients and may be a target of anti-tumor therapy.