Search

This study rigorously examines the impact of various data preprocessing techniques on the accuracy of machine learning models in predicting concrete's compressive strength. It develops ten regression models under nine distinct preprocessing scenarios, including normalization, standardization, principal component analysis (PCA), and polynomial features, utilizing a comprehensive dataset featuring normal and high-strength performances. The results reveal that using polynomial features and kernel PCA significantly enhanced model performance, with R values soaring to 93.27 and 94.65% during training and 88.51 and 88.77% during testing, respectively. This indicates their strong ability to capture the hidden nonlinear relationships within data. Conversely, discretization exhibited the least effectiveness, with the highest normalized root mean square error values of 14.2 (training) and 16.8 (testing) and normalized mean absolute error values of 11.6 (training) and 13.6 (testing), suggesting a potential loss of essential data granularity. Additionally, the study found that machine learning techniques generally surpassed traditional regression models, with higher R values being a consistent trend. These findings offer a nuanced understanding of the importance of preprocessing choice in concrete strength prediction and provide valuable insights for the concrete industry and data scientists, emphasizing the critical role of data preprocessing in achieving optimal model accuracy in materials science. [ABSTRACT FROM AUTHOR]

The predictions of porosity and permeability from well logging data are important in oil and gas field development. Currently, many scholars use machine learning algorithms to predict reservoir properties. However, few scholars have researched the prediction of reservoir porosity and permeability while drilling. This approach requires not only a high prediction accuracy but also short model processing and calculation times as new logging data are incorporated while drilling. In this paper, four machine learning algorithms were evaluated: the one-versus-rest support vector machine (OVR SVM), one-versus-one support vector machine (OVO SVM), random forest (RF) and gradient boosting decision tree (GBDT) algorithms. First, samples of wireline logging data from the Yan969 wellblock of the Yan'an gas field were chosen for model training. To improve the accuracy and reduce the input parameter dimensions and model training time as much as possible, data correlation analysis was performed. Second, we used the grid search method to approximate ranges of reasonable parameter values and then used k-fold cross-validation to optimize the final parameters and avoid overfitting. Third, we used the four classification models to predict porosity and permeability while drilling with data from logging while drilling (LWD) logs. Finally, we indicate the best porosity and permeability prediction models to use while drilling. To ensure that the prediction accuracy is as high as possible and that the model training time is as short as possible, the OVO SVM algorithm was suggested for porosity and permeability prediction. Therefore, appropriate machine learning algorithms can be used to predict porosity and permeability while drilling. [ABSTRACT FROM AUTHOR]