Search

Aiming to solve the problems of high cost and large error, a prediction model of oil and gas pipeline corrosion rate was established by using a knowledge graph and neural network. The knowledge map of oil and gas pipeline corrosion was constructed by the seven-step method and the fusion of Bidirectional Encoder Representations from Transformers, Bidirectional Long Short-Term Memory, and Conditional Random Fields models (BERT-Bi LSTM-CRF) combined extraction, and the triplet information was stored by the Neo4j graph database. With eight factors, such as carbon dioxide content, as input signals, three kinds of neural networks were used to screen the basic prediction model, and the genetic algorithm (GA) and particle swarm optimization algorithm (PSO) were used to optimize and compare. The results show that the extraction accuracy of BERT-Bi LSTM-CRF is 94.46%, the recall rate is 90.39%, and the F1 value is 92.38%. The optimized PSO-BP model has the best effect, and the coefficient of determination in the training stage and the test stage is as high as 0.9954 and 0.9935, and the total mean square error of the sample is reduced by 92.8% compared with that before optimization. The corrosion rate model proposed in this paper ensures the safe operation of oil and gas pipelines and offers a theoretical foundation for corrosion prediction. [ABSTRACT FROM AUTHOR]

Objective: To predict recurring atrial fibrillation (AF) following radiofrequency catheter ablation by assessing the attributes of the left atrium and the left atrial (LA) appendage (LAA) using transesophageal echocardiography (TEE) and speckle tracking imaging. Methods: The structural and functional indices of the LA and LAA of 80 patients with AF who underwent preoperative transthoracic echocardiography and TEE were measured. Recurrence was recorded postoperatively at 3, 6, and 12 months. The independent determinants of recurring AF were identified by logistic regression, and their optimum cutoff values, sensitivity, and specificity were estimated from the receiver operating characteristic (ROC) curves. Results: The recurrent and nonrecurrent groups comprised 17 and 63 patients, respectively. The LA internal diameter, LA end‐diastolic and end‐systolic volumes, LAA length, diameter and area of the opening of the LAA, and LAA end‐diastolic volume were higher in the recurrent group. The LA strain in the reservoir phase, the ejection fraction and filling velocity of the LAA, the LAA emptying velocity (LAAeV), and the LAA strain (LAAS) reduced considerably. Multifactorial regression analyses demonstrated that the LAAeV and LAAS were independent determinants of recurring AF. ROC curve analysis revealed that the LAAeV and LAAS predicted postoperative recurrence at 34.5 cm/s (area under the curve [AUC]: 0.954, sensitivity: 94.1%, and specificity: 92.1%) and 11.61% (AUC: 0.925, sensitivity: 82.4%, and specificity: 95.2%), respectively, while the AUC, sensitivity, and specificity of the combined predictors (LAAeV + LAAS) were 0.978, 94.1%, and 93.7%, respectively. Conclusion: The LAAeV and LAAS independently influenced the postoperative recurrence of AF. [ABSTRACT FROM AUTHOR]

Zinc stearate (Znst) was physically blended with the sodium 4-[(4 chlorobenzoyl) amino] benzoate (SCAB) to obtain the SCAB-Znst composite nucleating agent. Znst was used to improve the dispersion property of SCAB and exert a lubricating effect on the PP matrix. The scanning electron microscopy and the fracture surface morphology of the PP/SCAB composite illustrated that the addition of Znst greatly reduced the aggregation phenomenon of SCAB in the PP matrix. The result of the rotary rheometer indicated that Znst exhibits internal lubrication in PP. The DSC result illustrated that the crystallization properties of PP were improved. Compared with pure PP, the Tc of the PP/SCAB composite increased by 1.44 °C (PP/Znst), 13.48 °C (PP/SCAB), and 14.96 °C (PP/SCAB-Znst), respectively. The flexural strength of pure PP, PP/SCAB, and PP/SCAB-Znst were 35.8 MPa, 38.8 MPa, and 40.6 MPa, respectively. The tensile strength of the PP/SCAB and PP/SCAB-Znst reached the values of 39.8 MPa and 42.9 MPa, respectively, compared with pure PP (34.1 MPa). The results demonstrated that Znst can promote the dispersion of SCAB in the PP matrix while exerting a lubricating effect, which enabled the enhancement of the crystalline and mechanical properties of PP. [ABSTRACT FROM AUTHOR]