No abstract

No abstract

No abstract

Seismic attributes have been widely used in seismic object detection. While no unique attribute is expected to perfectly identify the targeted object, various attributes contributing to the same purpose should be utilized simultaneously when performing detection. Artificial neural network has been successfully applied in seismic object detection by combining multiple attributes into a single object-sensitive attribute. An optimized neural network fault detection approach was introduced by a case study from Stratton field, south Texas, United States. Results indicate that the new produced fault probability attribute could suppress the surrounding noises and highlight the faults. Application of ant-tracking to the fault-cube shows more convincible results than to individual attributes. In addition, several potential cross-strike fractures increase the structural complexity. The neural network-based fault detection contributes to better structural interpretation and is of great significance to hydrocarbon exploration, especially in area with complex fault system.

After summarizing the advantages and disadvantages of current integral methods, a novel vibration signal integral method based on feature information extraction was proposed. This method took full advantage of the self-adaptive filter characteristic and waveform correction feature of ensemble empirical mode decomposition in dealing with nonlinear and nonstationary signals. This research merged the superiorities of kurtosis, mean square error, energy, and singular value decomposition on signal feature extraction. The values of the four indexes aforementioned were combined into a feature vector. Then, the connotative characteristic components in vibration signal were accurately extracted by Euclidean distance search, and the desired integral signals were precisely reconstructed. With this method, the interference problem of invalid signal such as trend item and noise which plague traditional methods is commendably solved. The great cumulative error from the traditional time-domain integral is effectively overcome. Moreover, the large low-frequency error from the traditional frequency-domain integral is successfully avoided. Comparing with the traditional integral methods, this method is outstanding at removing noise and retaining useful feature information and shows higher accuracy and superiority.