Liquid holdup is one of the most critical factors for the formation of pipe effusion, which is closely related to the efficiency of pipe transportation. Nowadays, liquid holdup is mainly estimated according to empirical or semiempirical correlation. Besides, little has been done concerning the accurate prediction of liquid holdup. Therefore, to obtain more precise forecast, this paper proposed a prediction method concerning liquid holdup in horizontal pipe with BP neural network algorithm. Meanwhile, a sensitivity analysis on the key factors impacting liquid holdup was conducted by the combination of the forecast calculation and orthogonal experiment design. The results showed that compared with the empirical calculation (the smallest standard deviation 8.65%), the BP neural network prediction model had achieved more accurate estimation (the average relative error is 7.38%). In addition, the sensitivity analysis indicated that the main indexes including pipe diameter, gas‐ and liquid‐phase superficial velocities, and temperature have significant influence on the liquid holdup. Pipe diameter, liquid‐phase superficial velocity, temperature, and viscosity are positively correlated with the liquid holdup, while pressure and gas‐phase superficial velocity are negatively correlated with it.

No abstract

A model for predicting wax deposition rate in pipeline transportation is constructed to predict wax deposition in actual pipeline, which can provide decision support for the flow guarantee of waxy crude oil in pipeline transportation. This paper analyzes the working principle of Back Propagation Neural Networks (BPNN). Aiming at the problems of BPNN model, such as over learning, long training time, low generalization ability and easy to fall into local minimum, the paper proposes an improved scheme of using Whale Optimization Algorithm (WOA) to optimize BPNN model(WOA-BPNN).Taking 38 groups of crude oil wax deposition experimental data in Huachi operation area as an example, the simulation calculation is carried out in MATLAB, and the Genetic Algorithm optimized BPNN(GA-BPNN) and the non Optimized BP neural network are used as comparative models for comparative analysis. The results show that the Mean Relative Error (MRE) of WOA-BPNN model in predicting wax deposition rate is 2.72% and the coefficient of determination(R 2 ) is 0.9966, which are better than those of BPNN and GA-BPNN models. It is proved that WOA-BPNN model has higher accuracy and robustness in predicting wax deposition rate.

Abstract. Natural gas is the third largest energy pillar in the world, the best energy that all countries are scrambling to develop. Five main influencing factors of natural gas consumption are analyzed by collecting relevant information, including GDP, the gross industrial output value, the increased value of the third industrial production, the urban population, and the proportion of natural gas in primary energy. Then based on data from 2001 to 2011, factor analysis is taken by using the SPSS software. Then a linear regression model is obtained to predict the natural gas consumption. At last, the natural gas consumption in 2011-2013 is predicted by the proposed model, and the result is analyzed which shows that the model based on SPSS is reasonable and efficient.

The loop experiment device plays an important role in the study of wax deposition, and the calculation of the temperature distribution of the test section is the key to establish the wax deposition model. In the conditions of the wax deposition was not formed and constant wall temperature of the tube, the energy balance equation is solved by using separation of variables and combining the Kummer equation (S-K method), the distribution law of temperature in the test section is obtained, and the solution results was compared with Svendsen method, the difference between the results obtained by the two methods and the experimental results is also analyzed. The results showed that, the temperature distribution of the test section is consistent with the two methods, and the computing result of Svendsen method is generally higher than the S-K method. Under different axial distances for the take value, the maximum difference of computing results between the two methods is large when the position is farther away from the entrance, and the maximum difference is 0.27℃. Under different radial distances for the take value, with the increase of the axial distance, the difference between the results obtained by the two methods increases gradually in general, and the greater the radial distance, the greater the difference, the maximum difference is 0.27 ℃, thus the calculation results of these two kinds of methods have a higher coincide degree. The results obtained by the two methods are higher than the experimental results, but the difference is small, the results obtained by the S-K method are closer to the experimental results, and this method can avoid solve the numerical integration (Svendsen method) and the inconvenience of Bessel function, so it has a certain advantages.