Discrete Wavelet Transform: Architectures, Design and Performance Issues
Journal of VLSI Signal Processing Systems
Neural Networks for Applied Sciences and Engineering
Neural Networks for Applied Sciences and Engineering
Neural Networks in a Softcomputing Framework
Neural Networks in a Softcomputing Framework
| Hi-index | 0.00 |
One of the significant issues in each petrophysical evaluation is the determination of reservoir fluid contacts. Since each fluid with an exclusive disturbance contributes to the intensity of the recorded well-log signals, it is expectant to conceive disturbance imparted by each fluid would be endowed with a specific span of energy. Therefore, disturbance variations in recorded signals can be considered as a significant criterion in determining the boundary between reservoir fluids. In this context, the wavelet transform (WT) has been employed on new well logs generated by principle component analysis (PCA) method to decompose them into a series of components revealing reservoir features by which the intensity and variable characteristics of reservoir fluid energy can be closely scrutinized. In this study, the principle component analysis has been used to tackle unraveling the correlation of selected well logs. The results obtained in this investigation are indicative of using the combination of wavelet analysis and principle component analysis as an efficient method in the determination of reservoir fluid contacts.