基于等时距处理和IOWHA算子的路基沉降预测

Subgrade Settlement Prediction Based on Equidistance Processing and IOWHA Operator

为避免随机因素对单一预测模型影响,建立更符合软土路基沉降规律的模型和方法以提高预测模型的精度和可靠性,分别以原始沉降数据、经三次样条插值和经分段三次Hermite插值处理的数据为样本值建立Gompertz模型、Logistic模型和灰色Verhulst模型3种预测模型,将每种模型的3种情况的预测值同实测值进行对比分析,选出每种模型对样本处理的优势方法。以每种模型的优势方法为单一模型,建立基于诱导有序加权调和平均(induced ordered weighted harmonic averaging, IOWHA)算子的组合模型,该组合模型按照每个时刻单一模型的预测精度的高低对最优权系数进行求解。结果表明:在沉降速率发生明显变化时刻的数据作为最后一组样本值进行预测时,Gompertz模型和Logistic模型以分段三次Hermite插值等时距处理的数据为样本值预测效果更好,灰色Verhulst模型以原始沉降数据为样本值预测结果精度更高。求解基于IOWHA算子的组合预测模型的赋权系数时,遗传算法(genetic algorithm, GA)比使用MATLAB的非线性优化的工具箱的求解方法更为可靠,得到的组合模型预测精度更高。

In order to avoid the influence of random factors on the single prediction model,a model and method which were more in line with the settlement law of soft soil roadbed were established to improve the accuracy and reliability of the prediction model.Three prediction models,Gompertz model,Logistic model and grey Verhulst model were established with the original settlement data,cubic spline interpolation and piecewise cubic Hermite interpolation data as sample values,the prediction value of 3 cases of each model was compared with the measured value,and the superior method of sample processing for each model was selected.Taking the dominant method of each model as a single model,a combined model based on IOWHA operator was established.The combined model solved the optimal weight coefficient according to the forecast precision of the single model at each time.The results show that the Gompertz model and Logistic model are more effective when the data at the time when the sedimentation rate changes obviously as the last set of samples,the grey Verhulst model is more accurate when the original settlement data is taken as the sample value.Genetic algorithm(GA)is more reliable in solving the weight coefficient of the combined forecasting model based on induced ordered weighted harmonic averaging(IOWHA)operator than the nonlinear optimization toolbox of MATLAB,and the forecasting precision of the combined forecasting model is higher.