Ultrasonic-guided lamb wave approach is an effective non-destructive testing (NDT) method used for detecting localized mechanical damage, corrosion, and welding defects experienced in metallic pipelines. Signal processing of the guided waves is often challenged due to the complexity of operational conditions and environments in the pipelines. Machine learning approaches in recent years, including convolutional neural networks (CNN) and long short-term memory (LSTM), have exhibited their advantages to overcome these challenges for signal process and data classification of complex systems, thus great potential for damage detection of critical oil/gas pipeline structures. In this study, a CNN-LSTM hybrid model is utilized for decoding ultrasonic guided waves for damage detection of metallic pipelines, and twenty-nine features are extracted as input to classify different types of defects from metallic pipes. The prediction capacity of the CNN-LSTM model is assessed by comparing it to the CNN and LSTM. The results demonstrate that the CNN-LSTM hybrid model exhibits much higher accuracy, with 94.8%, as compared to those of CNN and LSTM. Interestingly, the results also reveal that predetermined features, including time-, frequency-, and time-frequency domains, could significantly improve the robustness of the deep learning approaches, even though the deep learning approaches are often believed they include automated feature extraction, without the hand-crafted steps as the shallow learning do. Furthermore, the CNN-LSTM model displays higher performance when the noise level is relatively low (e.g., SNR=9 or higher), as compared to the other two models, but its prediction drops gradually with the increase of the noise.

Porcine epidemic diarrhea virus (PEDV) has caused great damage to the global pig industry. The innate immunity plays a significant role in resisting viral infection, however, the exact role of innate immunity in the anti-PEDV response has not been fully elucidated. In this study, we observed that various porcine innate immune signaling adaptors are involved in the anti-PEDV activity. Among these, TRIF and MAVS showed the strongest anti-PEDV activity. The endogenous TRIF, MAVS and STING were selected for further examination of anti-PEDV activity. Agonist stimulation experiments showed that TRIF, MAVS and STING signaling all have obvious anti-PEDV activity. The siRNA knockdown assay showed that TRIF, MAVS and STING are also all involved in anti-PEDV response, and their remarkable effects on PEDV replication were confirmed in TRIF-/-, MAVS-/- and STING-/- Vero cells. For further verification, the anti-PEDV activity of TRIF, MAVS and STING could be reproduced in porcine IPEC-DQ cells. In summary, this study reveals that multiple pattern recognition receptor (PRR) signaling pathways of porcine innate immunity play an important role in the anti-PEDV infection, providing new and useful antiviral knowledge for prevention and control of PEDV spreading.

The innate immune system is the first line of host defense sensing viral infection. Manganese (Mn) has recently been found to be involved in the activation of innate immune DNA sensing cGAS-STING pathway and subsequent anti-DNA virus function. However, whether Mn2+ mediates host defense against RNA viruses is still unclear. In the current study, we demonstrated that Mn2+ exhibited antiviral effects against various animal and human viruses including RNA viruses such as PRRSVs and the VSV as well as a DNA virus such as the HSV1 in a dose-dependent manner. Moreover, cGAS and STING were both investigated in the Mn2+ mediated antiviral roles using the knockout cells made by CRISPR-Cas9 approach. Unexpectedly, the results revealed that neither cGAS knockout nor STING knockout had any effect on Mn2+ mediated antiviral functions. Nevertheless, we verified that Mn2+ promoted the activation of cGAS-STING signaling pathway. These findings suggest that Mn2+ has broad spectrum antiviral activities in a cGAS-STING pathway independent manner. This study also provides significant insights into redundant mechanisms participating in the Mn2+ antiviral functions and also indicates new target for Mn2+ antiviral therapeutics.