Parameter prediction method of shield slurry separation system by neural network based on wavelet denoising
When the slurry shield passes through the composite formation,the parameters of shield tunneling control and slurry separation system generally fluctuate greatly,influencing construction safety and tunnelling efficiency.In order to improve the safety and stability of the construction process and prevent abnormal working condition prediction,based on the Wangjing Tunnel,the coordinated control technique,including solid-liquid separation screening,two-stage cyclone,and centrifugal/pressure filtration are adopted according to the stratum conditions.Shield tunneling parameters(tunnelling speed,cutter head speed,total propulsion force,etc.)and slurry separation parameters(feed quantity,feed gravity,feed viscosity,etc)are collected.Data quality can be improved through Cook distance outlier detection,wavelet threshold denoising.12 parameters are selected as inputs,such as specific gravity ratio and viscosity ratio of two-stage cyclone separation,and the output parameters are discharge volume,discharge specific gravity and discharge viscosity,A BP neural network was established to predict parameters of the slurry separation system,three different formation annulus were selected for prediction.Results show that the average prediction errors are all within 5％,while predictions have high accuracy under the composite formation.
万方数据
维普
