Abstract: In order to improve the convergence speed and reduce the bit error rate of adaptive bidirectional turbo equalizer,a weighted feedback bidirectional turbo equalization algorithm is proposed.Firstly,a hybrid feedback scheme of posterior mean and prior mean is used in a single equalizer feedback input to improve the accuracy of equalizer output in each iteration;secondly,the weighted combination of a posteriori mean and a priori mean is used as the non-causal input of another equalizer feedback,which improves the accuracy of feedback input and the utilization of data;finally,the optimized normalized least mean square algorithm is used in weight iteration to improve the convergence speed of equalizer in training phase.In the Qiandaohu experiment,the bit error rate of the proposed method is only 1/3 of that of the traditional bidirectional turbo equalizer at the same 3.75 kbps communication rate.The simulation and experimental data show that this method needs less iterations to achieve the same bit error rate,and has higher stability in time-varying channel,and can achieve lower bit error rate.