基于改进的模拟退火人工神经网络的薄互储层参数预测
|
摘要
分析了模拟退火算法 (SA)与人工神经网络 BP算法 (简称 BP网 )各自的不足 ,设计了一种优化网络算法 ,将模拟退火和 Powell算法有机组合 ,代替 BP网中的梯度下降法 ,来训练网络权值 ,使网络具有较快的收敛速度和较高的逼近精度 .综合多种地震信息进行薄互储层参数 (砂岩厚度、孔隙度等 )的横向预测是当今世界石油勘探中的重要课题 ,薄互层沉积具有储层厚度薄且横向变化剧烈的特点 ,传统的 BP网络进行的参数预测达不到所需的精度和速度要求 .本文提出的优化网络算法较好地解决了薄互储层参数预测的精度和收敛速度问题 ,并通过实例验证了此方法的正确性和实用性
The disadvantage of the Simulated Annealing(SA) algorithm and BP algorithms was analyzed in this paper, design an optimization network algorithm, organic combine SA and Powell, insteaded of gradient falling algorithm of BP network to train network weight. it can get high accuracy and fast convergence speed. Today using multiple seismic information to predict thin interbeded reservoir parameter(thickness of grit,porosity)is an important research subject in the petroleum exploration. Thin interbeded reservoir have the features of reservoir thickness thin and change violently in horizontal, Traditional BP network can not get contentment result to predict thin interbeded reservoir parameters. Using the new algorithm in this paper can improve predict accuracy and convergence speed . The prediction results of an example proves this algorithm feasible and practicablity.
The disadvantage of the Simulated Annealing(SA) algorithm and BP algorithms was analyzed in this paper, design an optimization network algorithm, organic combine SA and Powell, insteaded of gradient falling algorithm of BP network to train network weight. it can get high accuracy and fast convergence speed. Today using multiple seismic information to predict thin interbeded reservoir parameter(thickness of grit,porosity)is an important research subject in the petroleum exploration. Thin interbeded reservoir have the features of reservoir thickness thin and change violently in horizontal, Traditional BP network can not get contentment result to predict thin interbeded reservoir parameters. Using the new algorithm in this paper can improve predict accuracy and convergence speed . The prediction results of an example proves this algorithm feasible and practicablity.
引文
1 赵振宇等.模糊理论和神经网络的基础与应用,清华大学出版社,1996
2 焦李成.神经网络系统理论,西安电子科技大学出版社,1995
3 Kirkpatrick S,etal.Optimiza tionbySimulatedAnnealing.Science,1983,(220):671～680
4 Harol dH,Szuand RalphLHartley.NonconvexOptimi zationbyFastSimulatedAnnealing.Proce ed ingsoftheIEEE,1987,75(11):1538～1540
5 赵玉清等.加速全局优化-鲍威尔法和模拟退火法的组合.电子学报,1998,(9)
6 王卓鹏等.一种改进的快速模拟退火组合优化法.系统工程理论与实践,1999,(2)
2 焦李成.神经网络系统理论,西安电子科技大学出版社,1995
3 Kirkpatrick S,etal.Optimiza tionbySimulatedAnnealing.Science,1983,(220):671～680
4 Harol dH,Szuand RalphLHartley.NonconvexOptimi zationbyFastSimulatedAnnealing.Proce ed ingsoftheIEEE,1987,75(11):1538～1540
5 赵玉清等.加速全局优化-鲍威尔法和模拟退火法的组合.电子学报,1998,(9)
6 王卓鹏等.一种改进的快速模拟退火组合优化法.系统工程理论与实践,1999,(2)
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心