Use of Recurrent and Convolutional Neural Networks for the Problem of Long Term Condition Prediction for Equipment of an Oil-and-gas Production Enterprise
Abstract
At present a new complex approach to solution of problems of long term prediction of equipment condition on the base of telemetric data received from pump units of the complex of field gathering and oil treatment, is highly needed. Therefore we suggest data analysis based on use of recurrent neural networks. In comparison with feed-forward networks, recurrent neural networks are oriented to processing of sequences of vectors, not single vectors of parameters. Here, the output signal of the network is a vector of probabilities, which shows that the current condition of the controlled object belongs to one or another predefined class from the knowledge base.
Keywords
Recurrent neural network, Digital oilfield, Electrical submesible pumps
DOI
10.12783/dtetr/eeta2017/7713
10.12783/dtetr/eeta2017/7713
Refbacks
- There are currently no refbacks.