A Big Data Method Based on Random BP Neural Network and Its Application for Analyzing Influencing Factors on Productivity of Shale Gas Wells

In recent years, big data and artificial intelligence technology have developed rapidly are now widely used in fields of geophysics, well logging, test analysis the exploration development oil gas. The shale gas requires a large number production wells, so inherent advantages for evaluating productivity wells analyzing influencing factors whole block. To this end, paper combines BP neural network algorithm with random probability to establish method on using in-depth extraction relevant information reduce unstable results from single-factor statistical network. We modeled analyzed our model amount data. Under standard conditions, influences geological engineering can be converted same scale comparison. This more intuitively quantitatively reflect different productivity. Taking 100 Changning block as case, shows that maximum EUR obtained when horizontal has fracture coefficient 1.6, Type I reservoir 18 m thick, optimal section 1600 long, 20 fractured sections.