AUTOMATED SYSTEM FOR IDENTIFICATION AND PREDICTION OF COMPLICATIONS IN THE PROCESS OF CONSTRUCTION OF OIL AND GAS WELLS Russian patent published in 2021 - IPC E21B44/00 G06N3/02 G05B13/04 

FIELD: oil and gas industry.

SUBSTANCE: invention relates to the field of the oil and gas industry, namely to systems for monitoring the construction of oil and gas wells and control of drilling operations, and is intended to identify and predict complications of the main types, such as absorption of drilling fluid, sticking (tightening) of drilling tools, gas, oil and water showings during the construction of oil and gas wells. The technical problem to be solved by the proposed invention is to reduce the accident rate during the construction of oil and gas wells by increasing the accuracy and reliability of identifying and predicting the occurrence of complications during the construction of new oil and gas wells under conditions of a priori uncertainty associated with incomplete and / or inaccurate knowledge of geological-geophysical conditions. This problem is solved by the fact that the automated system for identifying and predicting complications during the construction of oil and gas wells contains a module for collecting real-time data of geological and technological research from the construction site with an archived database of geological and technological research connected to it, a module for preliminary processing of geological and technological data. technological research, a module for marking up geological and technological research data, a marked-up database of geological and technological research, a module for the formation, training and validation of generalized neural network models, a module for predicting the parameters of geological and technological research, a module for recognizing technological operations, a module for assessing the likelihood of complications by predictive and real-time data, a module for evaluating the mismatch of the output values ​​of neural network models using predicted and real-time data, a data generation module for adapting neural network models, module for operational data markup for adaptation of neural network models, module for adaptation of neural network models, module for checking and replacing generalized neural network models.

EFFECT: achieved technical result consists in providing feedback based on the assessment of the mismatch of the outputs of neural network models based on predicted and real-time data, adaptation (recalculation), verification and replacement of current generalized neural network models and, thus, the implementation of step-by-step adaptation to specific geological and geophysical conditions.

1 cl, 1 dwg