Well leakage working condition prediction method and system based on non-uniform data and intelligent optimization algorithm

• Main Authors: DENG SONG, YIN WEN, PAN HAOYU, CAI MENG, ZHANG YIXIN, PEI CHUNYU, CAI CHUCHU, SHI YADONG
• Format: Patent
• Language: Chinese; English
• Published: 10.11.2023
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a well leakage working condition prediction method and system based on non-uniform data and an intelligent optimization algorithm, and the method comprises the steps: carrying out the analysis of various types of well drilling data, selecting well logging data, and carrying out the processing of the well logging data; improving the logging data by using an SMOTE interpolation algorithm, and establishing a sample set; a sparrow search algorithm is improved and optimized by using double-chaos mapping and an elite reverse strategy, BP neural network parameters are optimized by using the improved sparrow search algorithm, and a prediction model is constructed; and performing modeling verification by using field data. The well leakage complex prediction model based on the improved hybrid sparrow search algorithm-BP neural network is constructed, modeling verification is carried out by using field data in order to better verify the effectiveness of the model, the result shows that the proble