Recognition and Predicting Lava Underground Based on High Speed and Precise Genetic Algorithm Neural Network
Deep lava maybe contain petroleum and natural gas or CO2 gas, it is very important to find lava but the lava is in deep stratum and has complex structure, so it is difficult to find lava stratum. There are some methods to predict where the lava is but some problem also is in them such as the precision of recognition and forecasting is not high. A generic algorithm with adaptive and floating-point code is proposed to overcome disadvantages of the genetic algorithm and BP algorithm. This algorithm is combined with BP to give GA-BP mixed algorithm which has higher accuracy and faster convergence speed. The new algorithm also provides improved predict accuracy of lava reservoir. An example shows the validity and feasibility of this algorithm.
Genetic algorithms Neural networks Lava reservoir Recognition and predicting Characteristic parameter
Meijuan Gao Jingwen Tian Jin Li
Beijing Union University, Beijing, china;Beijing University of Chemical Technology Beijing, china Beijing University of Chemical Technology Beijing, china
国际会议
2006 IEEE International Conference on Information Acquisition
山东威海
英文
1091-1095
2006-08-20（万方平台首次上网日期，不代表论文的发表时间）