No abstract

With the development of machine learning in recent years, the application of machine learning to machine fault diagnosis has become increasingly popular. Applying traditional feature extraction methods for complex systems will weaken the characterization capacity of features, which are not conducive to subsequent classification work. A reciprocating compressor is a complex system. In order to improve the fault diagnosis accuracy of complex systems, this paper does not use traditional fault diagnosis methods and applies deep convolutional neural networks (CNNs) to process this nonlinear and non-stationary fault signal. The valve fault data is obtained from the reciprocating compressor test bench of the Daqing Natural Gas Company. Firstly, the single-channel vibration signal is collected on the reciprocating compressor and the one-dimensional CNN (1-D CNN) is used for fault diagnosis and compared with the traditional model to verify the effectiveness of the 1-D CNN. Next, the collected eight channels signals (three channels of vibration signals, four channels of pressure signals, one channel key phase signal) are applied by 1-D CNN and 2-D CNN for fault diagnosis to verify the CNN that it is still suitable for multi-channel signal processing. Finally, further study on the influence of the input of different channel signal combinations on the model diagnosis accuracy is carried out. Experiments show that the seven-channel signal (three-channel vibration signal, four-channel pressure signal) with the key phase signal removed has the highest diagnostic accuracy in the 2-D CNN. Therefore, proper deletion of useless channels can not only speed up network operations but also improve diagnosis accuracy.

Non-infectious prenatal mortality severely affects the porcine industry, with pathological placentation as a likely key reason. Previous studies have demonstrated that peroxisome proliferator-activated receptor gamma (PPARγ) deficiency causes defects in the uteroplacental vasculature and induces embryonic losses in mice. However, its role in porcine placental angiogenesis remains unclear. In the present study, PPARγ expression was investigated in porcine uteroplacental tissues at gestational day (GD) 25, GD40 and GD70 via quantitative polymerase chain reaction (qPCR), Western blot and immunohistochemistry (IHC). Moreover, the roles of PPARγ in porcine placental angiogenesis were investigated using a cell model of porcine umbilical vein endothelial cells (PUVECs) to conduct proliferation, migration and tube formation assays in vitro and a mouse xenograft model to assess capillary formation in vivo. The results showed that PPARγ was mainly located in the glandular epithelium, trophoblast, amniotic chorion epithelium and vascular endothelium, as indicated by the higher expression levels at GD25 and GD40 than at GD70 in endometrium and by higher expression levels at GD40 and GD70 than at GD25 in placenta. Moreover, PPARγ expression was significantly downregulated in placenta with dead foetus. In PUVECs, knocking out PPARγ significantly inhibited proliferation, migration and tube formation in vitro and inhibited capillary formation in mouse xenografts in vivo by blocking S-phase, promoting apoptosis and downregulating the angiogenic factors of VEGF and its receptors. Overall, the spatiotemporal heterogeneity of PPARγ expression in porcine uteroplacental tissue suggests its vital role in endometrial remodelling and placental angiogenesis, and PPARγ regulates placental angiogenesis through VEGFmediated signalling.

The clearance faults on joint of moving mechanism are most common in a reciprocating compressor. In order to investigate the relationship between the clearance faults and the dynamic behavior of the moving mechanism, a dynamic model with clearances of a reciprocating compressor is built via software ADAMS. We take into the clearance size and clearance number into consideration and set clearance fault on the joint between the crank and connecting rod, the joint between connecting rod and crosshead and both joints of connecting rod, exploring the effect of these factor on the dynamic response. Then we make a non-linear analysis to estimate the chaos behavior. In the end, we conclude that the clearance size and the number of clearance both strongly influence the dynamic behaviors of the moving mechanism, so do the position where clearance fault happens. As the clearance size increases or the number of clearance fault increase, the acceleration will oscillate more violent and have higher amplitude, furthermore, it is more possible to show chaotic behaviors.