Título: The Improvement of Neural Network Cascade-Correlation Algorithm and Its Application in Picking Seismic First Break
Autores: Zhe, LI; College of information and control engineering, China University of Petroleum (East China), China.
Rong, SHENG; Xinjiang Oilfield Karamay Power Plant, Xinjiang.
Weixiu, XU; Sinopec Oil Engineering Geophysical Limited Company Shengli Branch, Dongying, China.
Jing, YANG; Sinopec Oil Engineering Geophysical Limited Company Shengli Branch, Dongying, China.
Fecha: 2013-06-30
Publicador: Advances in Petroleum Exploration and Development
Fuente:
Tipo: info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
Peer-reviewed Article

Tema:
Neural network; Cascade-correlation algorithm; Picking seismic first break

Descripción: Neural Network is a kind of widely used seismic wave travel time auto-picking method. Most commercial software such as Promax often uses Back Propagation (BP) neural network. Here we introduce a cascade-correlation algorithm for constructing neural network. The algorithm’s convergence is faster than BP algorithm and can determine its own network architecture according to training samples, in addition, it can be able to expand network topology to learn new samples. The cascaded-correlation algorithm is improved. Different from the standard cascade-correlation algorithm, improved algorithm starts at an appropriate BP network architecture (exits hidden units), but the standard one’s initial network only includes input layer and output layer. In addition, in order to prevent weight-illgrowth, adding regularization term to the objective function when training candidate hidden units can decay weights. The simulation experiment demonstrates that improved cascade-correlation algorithm is faster convergence speed and stronger generalization ability. Analytically study five attributes, including instantaneous intensity ratio, amplitude, frequency, curve length ratio, adjacent seismic channel correlation. Intersection figure shows that these five attributes have distinctiveness of first break and stability. The neural network first break picking method of this paper has achieved good effect in testing actual seismic data.Key words: Neural network; Cascade-correlation algorithm; Picking seismic first break
Idioma: Inglés

Artículos similares:

Economic Analysis of Liquefied Natural Gas Floating Production Storage and Offloading Plant (LNG FPSO) Using Probabilistic Approach por N. Edwin, Lazson; Department of Petroleum and Gas Engineering, University of Port Harcourt,S. Sunday, Ikiensikimama; Department of Petroleum and Gas Engineering, University of Port Harcourt
Design and Operational Procedures for a Locally Made Steam Distillation Apparatus por Hosein, Raffie; Chemical Engineering Department, The University of the West Indies, St Augustine,Lewis-Hosein, Rhonda; Chemical Engineering Department, The University of the West Indies, St Augustine
The Effects of Pore Pressure and Temperature Difference Variation on Borehole Stability por Chi, AI; Key Laboratory of Education Ministry for Enhanced Oil Recovery, Northeast Petroleum University, Daqing, Hei Longjiang Province, China.,Yuwei, LI; Key Laboratory of Education Ministry for Enhanced Oil Recovery, Northeast Petroleum University, Daqing, Hei Longjiang Province, China.,Yu, LIU; Key Laboratory of Education Ministry for Enhanced Oil Recovery, Northeast Petroleum University, Daqing, Hei Longjiang Province, China.
Contents por Chao, Jamie
Finite Volume Method for Solving a Modified 3-D 3-Phase Black-Oil Hydrocarbon Secondary Migration Model, and Its Application to the Kuqa Depression of the Tarim Basin in Western China por Guangren, SHI; Research Institute of Petroleum Exploration and Development, PetroChina,Jinshan, MA; Research Institute of Petroleum Exploration and Development, PetroChina,Xinshe, YANG; Mathematics and Scientiic Computing, National Physical Laboratory,Junhua, CHANG; Research Institute of Petroleum Exploration and Development, PetroChina,Jun, WAN; Research Institute of Petroleum Exploration and Development, PetroChina
Determination of Non-Darcy Porous Flow Boundary Value in Formation Type III por Yikun, LIU; EOR key lab in the Ministry Of Education in Northeast Petroleum University.,Shuang, LIANG; EOR key lab in the Ministry Of Education in Northeast Petroleum University.,Lingyun, CHEN; EOR key lab in the Ministry Of Education in Northeast Petroleum University.,Fengjiao, WANG; EOR key lab in the Ministry Of Education in Northeast Petroleum University.,Yang, XUAN; Production Engineering Research Institute in Daqing Oil Field Co.,Qian, LIU; The second factory in Daqing Oil Field Co.
Cotton Oil and Sunflower Oil Fuel Mixtures por Arapatsakos, Charalampos; Department of Production and Management Engineering, Democritus University of Thrace, V. Sofias Street, 67100, Xanthi , GREECE,Karkanis, Anastasios; Department of Production and Management Engineering, Democritus University of Thrace, V. Sofias Street, 67100, Xanthi , GREECE,Christoforidis, Dimitrios; Department of Production and Management Engineering, Democritus University of Thrace, V. Sofias Street, 67100, Xanthi , GREECE,Moschou, Marianthi; Department of Production and Management Engineering, Democritus University of Thrace, V. Sofias Street, 67100, Xanthi , GREECE,Pantokratoras, Ioannis; Department of Production and Management Engineering, Democritus University of Thrace, V. Sofias Street, 67100, Xanthi , GREECE
10 
Principal Points in Cementing Geothermal Wells por Salim, Prisca; Texas A&M University at Qatar,Amani, Mahmood; Texas A&M University at Qatar