Search

With the development of data collection and storage capabilities in recent decades, abundant data have been accumulated in geotechnical engineering fields, providing opportunities for the usage of machine learning approaches. Thus, a rising number of scholars are adopting machine learning techniques to settle geotechnical issues. In this paper, the application of three popular machine learning algorithms, support vector machine (SVM), artificial neural network (ANN), and decision tree (DT), as well as other representative algorithms in geotechnical engineering, is reviewed. Meanwhile, the applicability of diverse machine learning algorithms in settling specific geotechnical engineering issues is compared. The main findings are as follows: ANN, SVM, and DT have been widely adopted to solve a variety of geotechnical engineering issues, such as the classification of soil and rock types, predicting the properties of geotechnical materials, etc. Based on the collected relevant research, the performance of random forest (RF) in sorting soil types and assessing landslide susceptibility is satisfying; SVM has high precision in classifying rock types and forecasting rock deformation; and backpropagation ANNs and Hopfield ANNs are recommended to forecast rock compressive strength and soil settlement, respectively. [ABSTRACT FROM AUTHOR]

To widely apply coral sand aggregate (CSA) concrete in practical ocean engineering, it requires to have a precious evaluation of its compressive strength in marine environment. In the study, 1280 triaxial shear tests on concrete containing different content and properties of CSA in marine environment was conducted. Based on the test results, a database was established, and a unique machine learning method was developed via combining the Logic Development Algorithm (LDA) with the ensemble technique of Adaptive Boosting Algorithm (AdaBoost) and Artificial Neural Network (ANN). This novel approach represents the first attempt to utilize this model for estimating the compressive strength of CSA concrete. To validate the applicability of the proposed approach, five conventional machine learning algorithms were also built as a reference, including LDA optimized ANN and Support Vector Machine, Particle Swarm Optimization Algorithm and Genetic Algorithm optimized AdaBoost-ANN. The research findings indicate: Firstly, the AdaBoost-ANN model optimized by LDA outperforms than the conventional models in terms of predictive accuracy and efficiency; For example, for the LDA-AdaBoost-ANN, LDA-SVM, LDA-ANN, GA-AdaBoost-ANN and PSO-AdaBoost-ANN model, their Root Mean Square Error (RMSE) is 2.73, 5.82, 6.97, 7.47 and 3.85 on testing datasets respectively; for the LDA-AdaBoost-ANN, LDA-SVM, LDA-ANN, GA-AdaBoost-ANN and PSO-AdaBoost-ANN model, their Mean Absolute Error (MAE) is 4.8, 11.34, 12.5, 9.86 and 8.45 on testing datasets respectively; for the LDA-AdaBoost-ANN, LDA-SVM, LDA-ANN, GA-AdaBoost-ANN and PSO-AdaBoost-ANN model, their Mean Absolute Percentage Error (MAPE) is 6.26%, 23.36%, 24.35%, 10.19% and 13.79% on testing datasets respectively. Secondly, the sensitivity analysis by using the novel model reveals that confining pressure, CSA content and immersion period in seawater have relatively high impact on the compressive strength. Thirdly, an analytical formula was established based on the novel algorithm. • 1280 triaxial shear tests were performed on coral sand aggregate concrete. • A unique machine learning model was developed based on the experimental database. • The compressive strength of the concrete was assessed by using the model. [ABSTRACT FROM AUTHOR]

The selection of printing parameters for 3D printing can dramatically affect the dynamic performance of components such as polymer spur gears. In this paper, the performance of 3D printed gears has been optimised using a machine learning process. A genetic algorithm (GA)–based artificial neural network (ANN) multi-parameter regression model was created. There were four print parameters considered in 3D printing process, i.e. printing temperature, printing speed, printing bed temperature and infill percentage. The parameter setting was generated by the Sobol sequence. Moreover, sensitivity analysis was carried out in this paper, and leave-one cross validation was applied to the genetic algorithm-based ANN which showed a relatively accurate performance in predictions and performance optimisation of 3D printed gears. Wear performance of 3D printed gears increased by 3 times after optimised parameter setting was applied during their manufacture. [ABSTRACT FROM AUTHOR]