Search

To diagnose multiple faults (blockage and leakage) of a district heating system (MFDHS) in a timely and accurate manner, a new multi-fault diagnosis method is proposed that considers fault diagnosis as a classification problem based on principal component analysis (PCA) and a Back Propagation (BP) neural network. Using this method, a simulation model of heating-network faults is constructed and fault experiments are conducted. Based on the simulation model and experiments, the experimental (ED) and model (MD) datasets are effectively constructed followed by the construction of substitute datasets(SD) that replaces the experimental data with model data. PCA and data standardization are then adopted to process all the datasets. Finally, three BP neural network classification models are trained and tested using the three datasets. To demonstrate the effectiveness of this method, four experimental heating networks, namely a single heat source and branch (SHB), single heat source and single loop (SHSL), double heat source and branch (DHB), and double heat source and double loop (DHDL), are discussed as case studies. The results show that the relative errors of the experimental and simulation data for the pressures and flow rates are less than 5%. The highest prediction accuracy is obtained when the fault to the normal data are 95–5% under training sets to testing sets of 70–30%, while for the four heating networks, the prediction accuracy of the method built with ED is 99.93%, 99.99%, 99.84%, and 99.66% respectively, whereas it reaches 99.99% for MD. The accuracies are 99.99%, 98.13%, 97.4%, and 99.99%, respectively, with MD serving as the training set while another 11400 sets of experimental data serve as the testing set. Accordingly, the accuracy ranges from 95.56% to 88.03%, 97.85–93.29%, 95.65–85.71%, and 100–84.82%, with SD serving as the training set and another 11400 sets of experimental data serving as the testing set.

Background: Difficult biliary cannulation and unintended pancreatic cannulation exist in biliary interventions during endoscopic retrograde cholangiopancreatography. Wire-guided cannulation over a pancreatic stent (PS-WGC) and needle-knife precut over a pancreatic stent (PS-NKP) may facilitate biliary cannulation. This study aimed to compare the outcomes of PS-NKP and PS-WGC following guidewire passage into the pancreatic duct. Methods: A total of 304 patients who inserted a pancreatic stent and continued cannulation using wire-guided (PS-WGC) or needle-knife precut (PS-NKP) from October 2018 to November 2021 in three centers were ultimately enrolled in this study. The success rate of cannulation and incidence of complications were compared between the two groups. Results: Results of the success rate of cannulation in the PS-NKP (n= 98) group were significantly higher compared with the PS-WGC (n= 206) group (96.9% vs. 89.8%; P< 0.05). The overall adverse events were 10.2% (31/304), and PS-NKP had lower (PEP) rates compared with the PS-WGC (3.1% vs. 10.7%, P< 0.05). Conclusion: The PS-NKP group is superior to the PS-WGC group in terms of the effectiveness and safety of continued cannulation. Using needle-knife precut, especially early use, over the pancreatic stent to continue cannulation reduced PEP compared with PS-WGC.

Wastewater often contains humic acid (HA) and inorganic anions together. We studied the oxidation properties of high concentration HA in an ozone system and effects of different mass concentrations of CO32-, HCO3-, SO42-, Cl-, NO2-and NO3-on the ozonation of HA were investigated. After 30 min, the color number, HA, chemical oxygen demand (COD) and total organic carbon were considerably eliminated, the ozone use decreased significantly and the biodegradability ratio of biochemical oxygen demand (BOD5)/COD increased from an influent 0.23 to 0.52. Also, the UV-visible spectrum and three-dimensional excitation and emission matrix fluorescence spectrum tests demonstrated that the HA was significantly decomposed into small molecular matters. Also, common inorganic anions had significant influences during the ozonation process. For a 30 min reaction, and water samples with mass concentrations of CO32-, HCO3-, Cl-and NO2-of 0.5–3.0, 5.0–20.0, 5.0–20.0 and 0.1–0.8 g L–1, respectively, the removal rates of HA were reduced by 8.36%–16.40%, 2.95%–8.85%, 0.66%–3.28% and 10.16%–16.06% respectively, compared with water samples without these anions, and the apparent kinetic constants kobswere 13.88–9.51, 14.59–11.31 and 16.67–14.20 min–1; for water samples with SO42-and NO3-mass concentrations of 0.5–2.0 and 2.0–8.0 g L–1, the removal rates of HA increased by 2.30%–10.16% and 2.30%–7.54%, and kobswere 17.71–23.85 and 17.9–21.19 min–1. Ozonation could be inhibited by CO32-, HCO3-, Cl-and NO2-, and the depressions increased as the input increased, however, there is some facilitation when SO42-and NO3-exist, and the degradation could be accelerated as theinput increased.

Semantic segmentation based on deep learning has been gradually applied to digital rocks, but the amount of training sets and the fineness of data labelling affect the accuracy of the final segmentation, as well as the pixel-level annotation would cost a lot of human effort and be accompanied by certain errors. To address the problem of high data labelling cost of sandstone cast thin section images and segmentation accuracy affected by manual bias, this paper proposes a new method combining Smoothed Score Class Activation Mapping (SSCAM) and Restricted Similarity Dual Contrast Learning (RSimDCL), and we named it CSSRS. Using an image-level annotated dataset, the study applied CSSRS to the images with pore segments (pore images) presented and those without (background images). CSSRS utilized SSCAM to obtain the general location of the pores from the cast thin section map, adopted RSimDCL to obtain the fine boundaries of the pore area, and combined these two methods to generate more accurate pore segmentation of sandstone cast thin section images. Finally, pore segmentation was performed on the same test dataset using CSSRS and RSimDCL, and the segmentation results were compared with various Class Activation Mapping (CAM) algorithms based on weakly supervised learning and various Generative Adversarial Networks (GAN) algorithms. Results showed that CSSRS demonstrated the highest Precision of 79.35% (18.65% higher than the second best method RSimDCL). In addition, the study applied Mean Intersection over Union (MIoU), Dice, Pixel Accuracy (PA), False Positive Rate (FPR) comparison metrics and found that CSSRS consistently demonstrated a better performance of 5%–6% improvement than the second best method in each metric. In conclusion, the CSSRS method based on weakly supervised learning can be applied to pore segmentation of sandstone cast thin section images, which significantly reduces the data annotation workload, avoids the manual bias, and also increases the segmentation effect to a greater extent.

Oil-based cuttings (OBCs) produced during shale gas exploration are classified as hazardous waste, and are difficult and expensive to dispose of. Appropriate disposal of such OBCs has become a key issue requiring urgent attention. Here, we have applied surfactant-free microemulsions (SFMEs) to deoil OBCs. The deoiled OBCs, the recovered SFMEs, and the base oil have been characterized. Studies have shown that gentle stirring and mixing of n-hexane/tert-butanol/water (30:65:5 wt%) can form a cleaning agent that serves as an SFME. The oil content of the OBCs after deoiling by SFMEs was less than 1%, and the remaining solid phase showed no hazardous characteristics. The optimum conditions for cleaning OBCs with the SFME have been identified as 30–35 °C, a duration of 20 min, a solid–liquid mass/volume ratio of 1:4, and a stirring speed of 200 rpm. Thereafter, samples are optimally dried at 100 °C for 50 min. The recovered cleaning agent can be reused efficiently. The recovered base oil was essentially unchanged, except for some contamination with organic additives from the oil-based mud. The deoiling mechanism of OBCs with an SFME mainly depends on the strong solubilization ability of the SFME.