An effective detection method based on IPSO-WNN for acoustic telemetry signal of well logging while drilling

Abstract

Acoustic telemetry technology for Well Logging While Drilling(LWD) is one promising kind of LWD data transmission technologies. It takes the elastic wave propagating along the drill string as carrier to transmit downhole measurement data up to the ground. However, polluted by the acoustic noises which are produced by drilling rigs and mud circulation, as well as attenuated during the process of propagation, the surface signal is so completely buried in a variety of noises that it is very difficult to be detected. To solve the problem, firstly an efficient wavelet neural network classifier trained by improved particle swarm optimizer algorithm is presented in this paper. Secondly, the classifier is used to find the mapping relation between downhole original data and surface noisy data. Then the surface noisy telemetry signal can be detected intelligently through the relation. Finally, this method has been proved to be good effect through practical application.