遗传算法结合神经网络在油气产量预测中的应用

基于遗传算法的全局搜索能力和BP算法的局部精确搜索特性,通过采用遗传算法优化神经网络的方法,将遗传算法和BP算法有机结合,做到优势互补,在提高油气产量预测精度的研究中得到了很好的应用.在对国内某中小型气田油气产量的预测中,以历史产量资料进行检验,其结果表明,提出的预测方法,预测精度明显优于BP算法,证明了这种方法的有效性和可靠性.

The Combination of Artificial Neural Network and Genetic Algorithm Applied to Forecast of Oil and Gas Yield

It is known that the genetic algorithm(GA)is good at global searching,and the artificial neural network(ANN)is effective on accurate local searching,On this basis,we proposed a method to combine GA with BP algorithm and through GA optimizing BP network to forecast oil and gas yield,and it does well in the research of improving the precision of forecast,On the forecast of an internal gas field' yield,we test the method by historical data,the result indicates that the precision of the method which is proposed obviously overmatches BP algorithm,and the effectiveness and reliability of this method have been proved.