基于改进Transformer网络的测井曲线生成方法OA

To address issues of diminished accuracy and prolonged training periods in well logging curve generation mod-els,a method based on an improved Transformer neural network,termed WLP-T(well log prediction Transform-er),has been proposed.Firstly,the model enhances the input embedding module of Transformer,so that the net-work can capture the local features in the input sequence,and improves the local spatial awareness ability of the model.Secondly,we employ a learnable position coding to rectify the inadequacy of the Transformer's position coding in capturing the temporal characteristics of time series data.Finally,a more streamlined and efficient decod-er module is introduced to replace the original Transformer decoder,significantly boosting the model's training speed while upholding performance standards.Experiments on predicting curves in un-drilled formations,comple-ting missing curves,and correcting curves are conducted on real logging data.The results show that compared to LSTM(long short-term memory),GRU(gated recurrent unit),and the original Transformer network models,the WLP-T model achieved better results,offering a new approach to generate logging curves.