Search

Your search keyword '"Chloride"' showing total 119,061 results
Start Over Descriptor "Chloride"
119,061 results on '"Chloride"'

47. Measuring Chloride-Induced Structure Corrosion in Marine Environment: A Characterization Study of Fluorescence-Based Optical Sensor

Author

Chen, Xuande, Conciatori, David, Chen, Zhao, Thomas, Sanchez, Dhouib, Meriem, di Prisco, Marco, Series Editor, Chen, Sheng-Hong, Series Editor, Vayas, Ioannis, Series Editor, Kumar Shukla, Sanjay, Series Editor, Sharma, Anuj, Series Editor, Kumar, Nagesh, Series Editor, Wang, Chien Ming, Series Editor, Cui, Zhen-Dong, Series Editor, Lu, Xinzheng, Series Editor, and Weng, Chih-Huang, editor

Published
2025
Full Text
View/download PDF

50. Probabilistic prediction model for critical chloride concentration of reinforcement corrosion based on improved Gaussian process regression.

Author

Zhou, Huanyu, Wang, Zizhen, Chen, Xiaojie, and Yu, Bo

Subjects
*MACHINE learning, *KRIGING, *KERNEL functions, *CONCRETE corrosion, *PROBABILITY density function
Abstract

To describe the probabilistic characteristics of critical chloride concentration (CCC) and calibrate the computational accuracy of traditional prediction models, a probabilistic prediction model of CCC for reinforcement corrosion in concrete was developed based on an improved Gaussian process regression (GPR) model. Firstly, a new hybrid kernel function for the GPR model was developed by combining the radial basis function with the rational quartic kernel according to the sum of single kernel functions and automatic relevance determination function. The hyperparameters of the improved GPR model were determined based on Bayesian theory and the maximum likelihood estimation. Subsequently, a probabilistic prediction model of CCC for reinforcement corrosion in concrete was developed based on the improved GPR model and a total of 591 sets of experimental data. The accuracy and applicability of the proposed probabilistic prediction (PPP) model was validated by comparing with traditional kernel functions, machine learning models and empirical theoretical models. The results showed that the PPP model based on the new hybrid kernel function has high accuracy and generalisation capability. The PPP model provides an efficient way to describe the probabilistic characteristics of CCC for reinforcement corrosion in concrete and to calibrate the computational accuracy of traditional prediction models based on the probability density function and confidence intervals. [ABSTRACT FROM AUTHOR]

Published
2025
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results