A NOVEL COMPETITIVE LEARNING NEURAL NETW ACOUSTIC TRANSMISSION SYSTEM FOR OIL-WELL

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 surface through the pipeline column of the well, malung 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 timedomain incoming signals in three-dimensional images. The results have been successfully verified. The neural network estimation principles presented on th~s paper can be easily applied in other pattern and timedomain recognition applications.