A novel competitive learning neural network based acoustic transmission system for oil-well monitoring

The optimal operation of an oil-well requires the periodic measurement of temperature and pressure conditions at the downhole. In this work, acoustic waves are used to transmit data to the surface through the pipeline column of the well, making up a wireless transmission system. Binary data is transmitted in two frequencies, using FSK modulation. Such transmission faces problems with noise, attenuation and, at pipeline joints, multiple reflections and nonlinear distortion. Hence, conventional demodulation techniques do not work well in this case. The neural network presented here classifies signals received by the receiver to estimate the transmitted data, using a linear-vector-quantization (LVQ) network, with the help of a preprocessing procedure that transforms time-domain incoming signals in three-dimensional images. The results have been successfully verified. The neural network estimation principles presented on this paper can be easily applied in other pattern and time-domain recognition applications.