Downhole Pressure Estimation Using Committee Machines and Neural Networks

Abstract

In gas-lifted oil wells the monitoring of downhole pressure plays an important role. However, the permanent downhole gauge (PDG) sensor often fails. Because maintenance or replacement of PDGs is usually unfeasible, soft-sensors are promising alternatives to monitor the downhole pressure in the case of sensor failure. In this paper, a data-driven soft-sensor is implemented to estimate the downhole pressure using committee machines composed by finite impulse response (FIR) neural networks. Experimental results in three real datasets of the same oil well indicate that the identified soft-sensor is able to predict the downhole pressure with satisfactory accuracy. The model input variables were selected by statistical tests which increased insight concerning such variables. Committee machines outperformed single-model soft-sensors on experimental data.

Including steady-state information in nonlinear models: an application to the development of soft-sensors

“…A strategy used to avoid the lack of information caused by the failure of the downhole pressure gauge in deep water oil production plants is the use of soft-sensor techniques. To this end, grey-box modeling procedures were applied as described in [46,14,8].…”

Desenvolvimento de soft sensor para poços de petróleo usando MGGP

“…Há anos, monitorar processos é uma atividade realizada em diversos setores da indústria e trata-se de uma etapa muito importante para a garantia de um funcionamento correto, seja para reduzir custos de manutenc ¸ão, evitar perdas de produc ¸ão, identificar melhorias no processo, possibilitar ac ¸ões de prevenc ¸ão de acidentes e falhas. Quando um processo envolve ambiente hostil, esse monitoramento passa a ser indispensável, como é o caso de poc ¸os de extrac ¸ão de petróleo [1]- [3].…”