Aqueduct pier advanced settlement forecasting method based on extreme learning machine

The invention discloses an aqueduct pier advanced settlement forecasting method based on an extreme learning machine. The aqueduct pier advanced settlement prediction method comprises: inputting dataobtained by aqueduct monitoring into a pre-constructed prediction model; performing operation through the prediction model to obtain a settlement amount change trend; analyzing the variation trend ofthe settling volume; performing forecasting according to the analysis results. According to the aqueduct pier advanced settlement prediction method based on an extreme learning machine, through historical data related to aqueduct piers, an extreme learning machine is combined to build and train a prediction model, the settlement amount of the aqueduct piers in a plurality of days in the future ispredicted, early warning of aqueduct pier settlement is achieved, and rich time is reserved for formulation of aqueduct emergency treatment measures. 本发明公开了一种基于极限学习机的渡槽槽墩超前沉降量的预报方法，步骤包括：将对渡槽监测得到的数据输入到预先构建的预测模型中；通过预测模型进行运算得到沉降量变