Predictive Analysis Of Bridge Condition By Improved Grey Markov Model

With the growing prosperity and development of China's transportation and bridge industry,the problems of “aging” and “disease” for a large number of bridges are caused by the development of the transportation industry.Thus it is important to find a fast and effective method to tackle with the problems in bridge state prediction.On the one hand,using the prediction model that fits the scientific logic best can effectively study the internal laws of things,and on the other hand,it can also play an irreplaceable role in the corresponding decision making by the relevant departments.After referring to various methods and shortcomings of bridge state prediction since modern times,the grey Markov model is first to be introduced for the historical data of the bridge.The health status of the bridge is expressed in the form of a matrix,and the state transition matrix of the bridge data is solved to further predict the health status of the bridge.This thesis uses the data of a type of bridge in a certain section of Hebei Province as the experimental data of the prediction model.The shortcomings of the Grey Markov prediction model is taken into account to obtain a more accurate prediction model,this thesis combines the metabolic model with the residual optimized gray Markov model for the first time and applies it to the prediction of the bridge health status.The improved Grey Markov model is used to predict the data of a type of bridge in a certain section of Hebei Province.The prediction results show that the Gray Markov prediction model improved by the metabolic model predicts the average relative error of the bridge data up to 0.04%.The rate of average relative error of the grey Markov model prediction is 3.39%,and the rate of the bridge predicted by the Gray Markov model after residual optimization is-0.06%.By comparison,it is not difficult to find that the model optimized by using metabolism is close to the original data from the data curve.Compared with the previous data,the prediction results and accuracy are greatly improved,and the prediction effect is relatively more in accordance with the actual law.This study provides a new idea and method for bridge operation state prediction,improves prediction accuracy,and provides technical support for relevant resolution.