Natural gas hydrate depressurization exploitation productivity prediction method based on deep neural network

• Main Authors: LUAN HENGJIE, MA XIANZHUANG, LIU MINGKANG, YAN PENG, JIANG YUJING, LIU JIANKANG, DU XIAOYU, SHI YICHEN, CHEN YONGQIANG, LI XINPENG
• Format: Patent
• Language: Chinese; English
• Published: 06.02.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a natural gas hydrate depressurization exploitation productivity prediction method based on a deep neural network, and the method mainly comprises the steps: building a five-layer deep neural network model, and carrying out the training, optimization, testing and evaluation of the model through the existing multi-scale natural gas hydrate depressurization exploitation test data; a productivity prediction module is designed based on the model, so that accurate prediction of the productivity of the multi-scale natural gas hydrate depressurization exploitation test under different working conditions is realized, the exploitation strategy is adjusted, the exploitation process is optimized, the exploitation efficiency is improved, and a large amount of manpower and material resources required by the traditional natural gas hydrate depressurization exploitation test are reduced; and due to the automatic learning and mode recognition capabilities of the deep learning model, the burden of labo