Application of foundation settlement prediction based on improved particle swarm algorithm and wavelet de-noising ground settlement prediction

In dealing with the problem of premature, the swarm was divided into different types and different update strategy was carried on each swarm. In order to improve the algorithm´s convergence precise we also introduced the chaos mutation operations to increase particles´ diversity. Meanwhile in order to remove the noise in the raw foundation settlement data, we introduced the wavelet algorithm. And we also made a compare with the standard particle swarm optimization to forecast the foundation settlement. The experiment indicated that this method had a better global and local searching ability and a high forecast precision.