Remained work time forecasting of oil and gas extraction equipment with application of artificial neural networks technology
Abstract
Remained work time forecasting of oil and gas extraction equipment with application of artificial neural networks technology
Incoming article date: 27.10.2014In the article method based on application of artificial neural networks for forecasting of the remained work time on the basis of equipment operational condition analysis is considered. Transformation of telemetric data with application of a generalized Veibull distribution function had reduced influence of noise factors. Validation mechanism is introduced for increase of forecasting accuracy and definition of conditions of neural network training end. A comparative study is performed between the proposed method and known one. The results demonstrate the advantage of the proposed method in achieving more accurate remained work time prediction.
Keywords: artificial neural network, forecasting, remaining work time, Veibull's distribution, oil and gas extraction equipment