Yu-Ching Wu

Dr. Yu-Ching Wu

orcid

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 May 2018 in Construction and Building Materials
Verified
Journal Article
Closed access
Yu-Ching WuYu-Ching Wu
Yu-Ching Wu
Zhen-Hua DuanZhen-Hua Duan
Zhen-Hua Duan

7 July 2024 in Buildings
Verified
Journal Article
Open access
PDF file
Peng ZhuPeng Zhu
Peng Zhu
WCWenshuo Cao
Wenshuo Cao
LZLianzhen Zhang
Lianzhen Zhang
YZYongjun Zhou
Yongjun Zhou
Yu-Ching WuYu-Ching Wu
Yu-Ching Wu
ZMZhongguo John Ma
Zhongguo John Ma
The creep behavior of Ultra-High-Performance Concrete (UHPC) was investigated by machine learning (ML) and SHapley Additive exPlanations (SHAP). Important features were selected by feature importance analysis, including water-to-binder ratio, aggregate-to-cement ratio, compressive strength at loading age, elastic modulus at loading age, loading duration, steel fiber volume content, and curing temperature. Four typical ML models—Random Forest (RF), Artificial Neural Network (ANN), Extreme Gradient Boosting Machine (XGBoost), and Light Gradient Boosting Machine (LGBM)—were studied to predict the creep behavior of UHPC. Via Bayesian optimization and 5-fold cross-validation, the ML models were tuned to achieve high accuracy (R2 = 0.9847, 0.9627, 0.9898, and 0.9933 for RF, ANN, XGBoost, and LGBM, respectively). The contribution of different features to the creep behavior was ranked. Additionally, SHAP was utilized to interpret the predictions by the ML models, and four parameters stood out as the most influential for the creep coefficient: loading duration, curing temperature, compressive strength at loading age, and water-to-binder ratio. The SHAP results were consistent with theoretical understanding. Finally, the UHPC creep curves for three different cases were plotted based on the ML model developed, and the prediction by the ML model was more accurate than that by fib Model Code 2010.

26 September 2018 in Archives of Computational Methods in Engineering
Verified
Journal Article
Closed access
PDF file
Yu-Ching WuYu-Ching Wu
Yu-Ching Wu
BYBin Yang
Bin Yang

14 April 2023 in Buildings
Verified
Journal Article
Open access
PDF file
Peng ZhuPeng Zhu
Peng Zhu
ZLZongyang Li
Zongyang Li
YZYunming Zhu
Yunming Zhu
Yu-Ching WuYu-Ching Wu
Yu-Ching Wu
WQWenjun Qu
Wenjun Qu
The durability of two types of widely used glass fiber reinforced polymer (GFRP) bars, one without coating (G1) and one with slightly surface sand-coating (G2), were studied through accelerated aging. Concrete cylinders reinforced with GFRP bars were immersed in tap water in temperature-controlled tanks. The influence of different exposure temperatures, 20, 40, and 60 °C, and also different exposure times, 30, 60, 90, 120, and 180 days, on the degradation of the two types of GFRP bars was investigated. The tensile strengths of GFRP bars after different exposure times were evaluated with tensile tests, and the variation of the microstructure and elemental compositions of conditioned specimens was evaluated with scanning electron microscopy (SEM) images and energy dispersive X-ray spectroscopy (EDS), respectively. The degradation rate of the tensile strength retentions of two types of GFRP bars decreased with an increase in the exposure time at all exposure temperatures. The tensile strength retentions of the GFRP bars were studied by three commonly used prediction models. Based on the degradation mechanism of fiber-matrix debonding, a new model was proposed. These four models were evaluated with the test results and a new model proposed was suggested as the best model to predict the residual tensile strength of the GFRP bars. The durability parameters of the GFRP bars were discussed. The tensile strength retention tended to converge to a constant value (52%) with the increase of exposure time, which contributes to the determination of the environmental reduction factor in relevant design guides, and the fiber-matrix debonding was found to be the main degradation mechanism due to the surrounding concrete environment. The sand-coating had some effect on the activation energy of the GFRP bars.

15 June 2023 in Mathematics
Verified
Journal Article
Open access
PDF file
PZPeng Zhi
Peng Zhi
Yu-Ching WuYu-Ching Wu
Yu-Ching Wu
CQCheng Qi
Cheng Qi
TZTao Zhu
Tao Zhu
XWXiao Wu
Xiao Wu
HWHongyu Wu
Hongyu Wu
The purpose of this study is to investigate the role that a deep learning approach could play in computational mechanics. In this paper, a convolutional neural network technique based on modified loss function is proposed as a surrogate of the finite element method (FEM). Several surrogate-based physics-informed neural networks (PINNs) are developed to solve representative boundary value problems based on elliptic partial differential equations (PDEs). According to the authors’ knowledge, the proposed method has been applied for the first time to solve boundary value problems with elliptic partial differential equations as the governing equations. The results of the proposed surrogate-based approach are in good agreement with those of the conventional FEM. It is found that modification of the loss function could improve the prediction accuracy of the neural network. It is demonstrated that to some extent, the deep learning approach could replace the conventional numerical method as a significant surrogate model.

14 October 2023 in Heliyon
Verified
Journal Article
Open access
HWHongyu Wu
Hongyu Wu
Yu-Ching WuYu-Ching Wu
Yu-Ching Wu
PZPeng Zhi
Peng Zhi
XWXiao Wu
Xiao Wu
TZTao Zhu
Tao Zhu
This study aims at generation of a novel artificial bee colony algorithm using surrogate finite element method with neural network technique. In this paper, theory of surrogate finite element method with physics-informed neural networks (PINNs) are generated and applied to deal with the geometrically nonlinear optimization problem of size, shape and topology for single-layer domes. In the artificial bee colony algorithm, the feedforward neural network is used to surrogate finite element analyses. Three numerical examples of 10-bar truss, Lamella dome, and Kiewit dome are carried out to verify feasibility and accuracy of the proposed method. Results of the present study are in good agreement with ones from literature. It is indicated that optimization processes can be considerably accelerated using the modified algorithm. That is, using the neural network surrogate-based models could significantly increase computational efficiency of structural optimum design for single-layer domes.