Life prediction of underground structure by sulfate corrosion using Harris hawks optimizing genetic programming

Abstract

A corrosive sulfate environment can cause strong deterioration and destruction of reinforced concrete (RC) underground structures and seriously reduce their service life. Thus, it is very important to predict the service life of RC underground structures in corrosive sulfate environments. However, the service life of underground structures is affected by numerous complicated engineering and environmental factors and cannot be determined by traditional theoretical and experimental investigations. Therefore, to solve this problem, a new data-driven method based on Harris hawks optimizing genetic programming (HHO-GP) is proposed. In this new method, to improve the traditional genetic programming (GP), a new global optimization algorithm called Harris hawks optimization (HHO) is adopted to optimize its main controlling parameters. Based on 25 groups of real engineering data, the life prediction model of underground structures in corrosive sulfate environments with 12 main engineering and environmental influence factors is established by the HHO-GP method. The results show that the average relative training error (5.5%) and predicting error (6.3%) of the new prediction model are small. Therefore, the proposed HHO-GP method can construct a suitable life prediction model based on only real engineering data, regardless of how many complicated influencing factors are considered. Moreover, our data-driven life prediction model is described by one explicit polynomial function based on 12 influencing factors. Thus, it can be applied in real engineering simply and easily. Finally, the influence of the main controlling parameters of the HHO-GP on its accuracy and efficiency is analyzed. The results reveal that considering the computing accuracy and efficiency and the model completeness, the small population size and maximum iterations of HHO are suitable, whose recommended values are all 15. The population size and maximum number of iterations of GP have little influence on the prediction accuracy. Their recommended values all can be 50.