Qi Zhuang, Dong Liu, Bo Liu, Mei Liu

Frontiers in Heat and Mass Transfer (FHMT) 20 - 13 (2023)

In the actual operation of wet gas pipeline, liquid accumulation is easy to form in the low-lying and uphill sections of the pipeline, which leads to a series of problems such as reduced pipeline transportation efficiency, increased pipeline pressure drop, hydrate formation, slug flow and intensified corrosion in the pipeline. Therefore, it is very important to accurately predict the liquid holdup of wet gas pipeline. Based on seeker optimization algorithm, the liquid holdup prediction model of BP neural network optimized by seeker optimization algorithm is established and compared with the prediction models of traditional BPNN algorithm, GA-BPNN and PSO-BPNN. The results show that the Mean Absolute Percentage Error of SOA-BPNN model is 3.7351%, and the Root Mean Square Error is 0.0113. This model has high prediction accuracy and wide application range, which is obviously superior to other algorithms, and provides a new method for accurate prediction of liquid holdup of wet gas pipeline.