Since the gradient descent method is prone to local extremes,and ordinary swarm intelligence optimi-zation algorithms are prone to premature convergence,a lithology identification method based on the quantum vortex search algorithm(QVSA)and T-S fuzzy reasoning model is proposed.QVSA has the advantages of simple operation,fast convergence speed,and strong optimization ability,which helps the T-S fuzzy reasoning model obtain the optimal parameter configuration and achieve accurate identification of reservoir lithology.Firstly,QVSA with global search capability is used to optimize various parameters of the T-S fuzzy reasoning model.Then,the principal component analysis method is used to reduce the dimensionality of the acquired seis-mic attributes,and the optimized T-S fuzzy reasoning model is utilized to identify the reservoir lithology.The experimental results show that when the eight seismic attributes reflecting the reservoir characteristics are used to identify the reservoir lithology,the identification accuracy of the proposed method reaches 92％,which is 5.1％higher than that of the ordinary BP network method.At the same time,the precision,recall,F1 score,and other indicators are improved significantly compared with those of the BP network method.
万方数据