Effects of Saturation Levels on the Ultrasonic Pulse Velocities and Mechanical Properties of Concrete

Prediction of Compressive Strength of Partially Saturated Concrete Using Machine Learning Methods

The aim of this research is to recommend a set of criteria for estimating the compressive strength of concrete under marine environment with various saturation and salinity conditions. Cylindrical specimens from three different design mixtures are used as concrete samples. The specimens are subjected to different saturation levels (oven-dry, saturated-surface dry and three partially dry conditions: 25%, 50% and 75%) on water and water–NaCl solutions. Three parameters (P- and S-wave velocities and electrical resistivity) of concrete are measured using two NDT equipment in the laboratory while two parameters (density and water-to-binder ratio) are obtained from the design documents of the concrete cylinders. Three different machine learning methods, which include, artificial neural network (ANN), support vector machine (SVM) and Gaussian process regression (GPR), are used to obtain multivariate prediction models for compressive strength from multiple parameters. Based on the R-squared value, ANN results in the highest accuracy of estimation while GPR gives the lowest root-mean-squared error (RMSE). Considering both the data analysis and practicality of the method, the prediction model based on two NDE parameters (P-wave velocity measurement and electrical resistivity) and one design parameter (water-to-binder ratio) is recommended for assessing compressive strength under marine environment.

Analysis and Prediction of Sulfate Erosion Damage of Concrete in Service Tunnel Based on ARIMA Model

Sulfate erosion is a major cause of concrete durability deteriorations, especially for the service tunnels that suffer sulfate erosion for a long time. Accurately predicting the concrete damage failure under sulfate erosion has been a challenging problem in the evaluation and maintenance of concrete structures. Here we design the dry-wet cycle test of service tunnel concrete under sulfate erosion and analyze the Elastic relative dynamic modulus (Erd) and mass under 35 times cycle periods. Then we develop an autoregressive integrated moving average (ARIMA) prediction model linking damage failure to Erd and mass. The results show that the deterioration of concrete first increased and then decreased with an extension of the dry-wet cycle period. Moreover, based on a finite set of training data, the proposed prediction approach shows high accuracy for the changes of concrete damage failure parameters in or out of the training dataset. The ARIMA method is proven to be feasible and efficient for predicting the concrete damage failure of service tunnels under sulfate erosion for a long time.