Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Acta Geophysica

2 2020

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Principal Slip Zone determination in the Wenchuan earthquake Fault Scientifc Drilling project hole 1: considering the Bayesian discriminant function

Fang Sinan, Zhang Zhansong, Wang Zhi, Pan Heping, Du Ting

Acta Geophysica

2020

Vol. 68, no. 6

1595--1607

Accurate determination of the Principal Slip Zone (PSZ) of earthquake fault zones is a key task of earthquake Fault Scientifc Drilling for future earthquake control. The fault zone structure of Wenchuan earthquake is complex, and there are many strong earthquakes recorded on the fault zone, which make determining the PSZ in the Wenchuan earthquake Fault Scientifc Drilling project-hole 1 (WFSD-1) difcult. At present, core analysis of whole coring is the decisive method for determining PSZ depth, and the fresh fault gouge at 589.2 m is the PSZ in WFSD-1. Abundant and comprehensive logging data can only be used as evidence to judge the PSZ. Based on the discrimination function and hyperplane equation in Bayes ian discriminant classifcation, we derive a new algorithm for computing the PSZ possibility using a Bayesian Discrimina tion function (PSZP-BDF) based on the simplifed model, and set up a mode to determine the PSZ directly using machine learning of well logging. For the verifcation of WFSD-1, the fault gouges are successfully identifed and the PSZ depth is accurately located. The algorithm objectively learns the sample data, which is naturally adaptive to the region. The calculation procedure is simple and does not require expensive coring data or heavy core tests in the well. The calculation speed is fast, using multiple physical data types. The PSZP-BDF algorithm is suitable for processing and interpreting earthquake fault scientifc drilling data.

3D crosswell electromagnetic inversion based on radial basis function neural network

Fang Sinan, Zhang Zhansong, Chen Wei, Pan Heping, Peng Jun

Acta Geophysica

2020

Vol. 68, no. 3

711--721

Crosswell electromagnetic (EM) method has fundamentally improved the horizontal detection ability of well logging and will become an increasingly promising approach for the secondary exploration of hydrocarbon reservoir. We applied orthogonal least squares (OLS) radial basis function neural network (RBFNN) based on improved Gram–Schmidt (G–S) procedure to three-dimensional (3D) crosswell EM inversion problems. In the inversion process of the simplifed crosswell model with single-grid conductivity anomalies and normal oil reservoir, compared the inversion results of other fve neural networks, OLS-RBFNN was proved to have the best global optimization ability and the fastest sample learning speed and the average inversion error of low conductivity anomalies model (4%) and oil reservoir model (9%) can meet the inversion requirements of crosswell EM method. Only the OLS-RBFNN could achieve ideal inversion results in the most concerned central area of crosswell model, and the inversion accuracy of this algorithm will be more outstanding when the model becomes more complex. Merely using the three-component time-domain crosswell EM data of two wells, the inversion of 3D medium conductivity in the crosswell dominant exploration area can be efectively realized through the nonlinear approximation of the OLS-RBFNN.