Prediction of urban rail settlement based on wavelet denoising and optimization of extreme learning machine
The deformation of the subway track structure is an important factor affecting the safe operation of subways,especially the settlement deformation. Therefore,monitoring the deformation of subway track settlement and accurately judging the trend of track settlement deformation based on the monitoring results are of great significance. This article took the monitoring data of subway line 2 in a city as an example and leveraged the advantages of wavelet analysis and extreme learning machine (ELM) models in data processing and prediction. The particle swarm optimization (PSO) algorithm was applied to optimize the ELM model parameters,and a PSO-ELM combined prediction model based on wavelet denoising was constructed to predict subway track settlement deformation. By using wavelet analysis to denoise monitoring data,the interference problem of prediction results caused by unstable monitoring data was solved. By constructing a PSO-ELM combined prediction model,the problem of limited prediction accuracy caused by the randomness of model parameter selection was solved. The settlement prediction results of the proposed PSO-ELM model considering wavelet denoising were compared with those of a single ELM model and ELM model considering wavelet denoising. The results show that the proposed combined prediction model has the highest prediction accuracy,and the prediction error does not change significantly with the increase in prediction periods,demonstrating high robustness and adaptability.
万方数据
维普
