Machine Learning-Based Model for Prediction of Elastic Modulus of Calcium Hydroxide in Oil Well Cement Under High-Temperature High-Pressure Conditions

The purpose of this study is to analyze the relationship between the key factors and the output results, and to determine the feasible prediction method of the elastic modulus of calcium hydroxide in oil well cement. Combining the first-principles calculation method with machine learning, Material Studio (MS) was used to simulate calcium hydroxide at different temperatures and pressures, obtain the microstructure parameters of the mechanical properties of calcium hydroxide, and construct the initial data set. At the same time, the random forest feature importance analysis method is used to screen the input parameters, remove the weak correlation variables, and reduce the complexity of the prediction model. On this basis, three prediction models, the BP neural network (BP), radial product function neural network (RBF), and random forest model (RF), are constructed. The hidden layer of the prediction model was adjusted by orthogonal test. The results of different performance evaluation methods are compared, the regression ability of each model is evaluated comprehensively, and the optimal algorithm model is selected. The results show that the determination coefficient of the RBF model is 0.9988, the root mean square error is 0.04331, the average absolute error is 0.02995, the mean square error is 0.01876, and the prediction ability is the best. This method can be used to predict the elastic modulus of calcium hydroxide and provide a reliable method for predicting the elastic modulus of each phase of oil well cement.