METHOD OF CONTROLLING CONDITIONS TELEMECHANISED OIL-FIELD FACILITIES USING NEURAL NETWORK ANALYSIS Russian patent published in 2016 - IPC G06N3/02 G06N3/08 G05B13/04 E21B47/26 

FIELD: oil industry.

SUBSTANCE: invention relates to methods of monitoring state of telemechanised wells, submersible equipment at an oil field. Method of controlling conditions of telemechanised oil-field facilities using neural network analysis comprises preparation of data from an archive in form of n-dimension vectors of conditions of wells, forming a Kohonen map, sampling data from archive base in form of n-dimension vectors of conditions of wells. Algorithm of neural network analysis uses a dependent parameter, prediction values of dependent parameter are calculated, difference between calculated and measured values of dependent parameter is calculated. Results of algorithm are presented in form of a composite graph of two variables: average distance between vectors of input parameters and vector of model for each well and difference between values of calculated and measured dependent parameter for each well.

EFFECT: technical result is a specific method of controlling operation of oil-field facilities and submersible equipment and telemetry data at oil fields.

1 cl, 3 dwg