%0 Journal Article
%T 基于机器学习预测普通和高强混凝土弹性模量<br>Predicting the Elastic Modulus of Normal and High-Strength Concrete Based on Machine Learning
%A 邹志鹏
%J Modeling and Simulation
%P 2591-2601
%@ 2324-870X
%D 2024
%I Hans Publishing
%R 10.12677/mos.2024.133236
%X 高性能混凝土(High Performance Concrete, HPC)在增强建筑物及基础设施的可持续性与可靠性方面发挥着重要作用。机器学习技术已经广泛应用于预测混凝土的多项性能指标。本研究提出了应用高斯过程(Gaussian Process, GP)模型，预测普通和高强混凝土基于抗压强度的弹性模量。为优化GP模型的预测准确性，本研究采用Kalman滤波和平滑((Kalman Filtering and Smoothing, KF/KS)技术以降低数据离散性的影响。研究结果显示，GP模型能够有效利用物理模型，预测和泛化能力良好。通过应用KF/KS技术处理数据，模型的性能得到进一步提升。该模型具有较高的准确性和稳定性，有望成为弹性模量估算的快速、稳健和低成本的工具。<br />
High Performance Concrete (HPC) plays a crucial role in enhancing the sustainability and reliability of buildings and infrastructure. Machine learning techniques have been widely applied to predict various performance indices of concrete. This study introduces the use of Gaussian Process (GP) models to predict the elastic modulus of normal and high-strength concrete based on compressive strength. To optimize the predictive accuracy of the GP model, this research employs Kalman Filtering and Smoothing (KF/KS) techniques to reduce the impact of data dispersion. The results demonstrate that the GP model can effectively utilize physical models, showing good prediction and generalization capabilities. The performance of the model is further improved by processing data through KF/KS techniques. With high accuracy and stability, the model promises to be a fast, robust, and low-cost tool for estimating the elastic modulus.
%K 高性能混凝土，弹性模量，机器学习，高斯过程，Kalman滤波和平滑<br>High Performance Concrete
%K Elastic Modulus
%K Machine Learning
%K Gaussian Process
%K Kalman Filtering and Smoothing
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=87312