Summary
At present, mud pulse transmission is widely used in underground wireless transmission. To extract more accurately the original drilling fluid pulse signals while drilling, in this paper, we developed an algorithm for optimal denoising shaping based on particle-swarm-optimized time-varying filtering empirical mode decomposition (TVFEMD). The performance of TVFEMD heavily depends on its parameters (i.e., B-spline order and bandwidth threshold). In the traditional TVFEMD method, the parameters are given in advance and may not be optimized, so it is difficult to achieve satisfactory decomposition results. To tackle this issue, the correlation coefficient was used as the objective function, and the particle-swarm-optimization algorithm was used to optimize the parameters of TVFEMD in this paper. First, the particle swarm optimization was used to search for the best combination of parameters. Then, the TVFEMD was applied to obtain a series of intrinsic mode functions (IMFs). Subsequently, the optimal denoising and shaping algorithm was used to determine the best reconstructed signal by low-pass filtering. Permutation entropy was taken as the evaluation index to obtain a reconstruction signal. Finally, the reconstructed signal was processed by square wave shaping to obtain accurate drilling fluid pulse signals. The approximation of the algorithm is 0.7581, and relevance is as high as 0.8535. The simulation signal and drilling fluid pulse signal analysis results showed that the proposed approach can extract the original pulse signal accurately.
Forecasting outpatient visits using empirical mode decomposition coupled with back-propagation artificial neural networks optimized by particle swarm optimization
