Precast deck joints using a new straight lap splice continuous method Woo-Young Go, Han-Joo Lee, Young-Jin Kim and Myoung-Sung Choi
Abstract; Full Text (2703K) .	pages 1-12.	DOI: 10.12989/acc.2024.17.1.001

Abstract
Precast deck joints have problems due to the occurrence of additional processes at construction sites, the complexity of construction, and the lack of design and construction standards for precast deck joints. To solve these, this study proposes a new precast deck joint that uses an Ultra-High-Performance Fiber-reinforced Cement Composite (UHPFRCC) filling material containing steel fibers and a straight rebar joint. In addition, the structural performance of the proposed joint, based on various parameters, was compared to that of existing precast deck joints, and the proposed joint showed equivalent strength and ductility. Therefore, the proposed joint can solve construction site problems by replacing the existing ones. The influence of various variables is expected to provide basic data on the design and construction guidelines for the precast deck joints.

Key Words
design and construction guidelines; ductility; precast deck joint methods; strength; structural performance

Address
(1) Woo-Young Go, Myoung-Sung Choi:
Department of Civil and Environmental Engineering, Dankook University, Yongin, Republic of Korea;
(2) Han-Joo Lee, Young-Jin Kim:
Korea Concrete Research Center Institute, Seoul, Republic of Korea.

open access
Engineering properties of pervious concretes produced with recycled aggregate at different aggregate-to-cement ratio Briar K. Esmail, Najmadeen M. Saeed, Soran R. Manguri and Mustafa Günal
Abstract; Full Text (7868K) .	pages 13-26.	DOI: 10.12989/acc.2024.17.1.013

Abstract
Due to its capacity to address urgent environmental challenges connected to urbanization and stormwater management, pervious concrete, a sustainable and innovative material, has attracted a lot of attention recently. The aim of this study was to find the engineering characteristics of pervious concrete made from recycled aggregate (RA) at various aggregateto-cement ratios (A/C) and the addition of 5% (by weight of total aggregate) of both natural and recycled fine aggregate to produce a very sustainable concrete product for a variety of applications. The three distinct aggregate-to-cement ratios, 6, 5, and 4, were used to produce pervious concrete using recycled aggregate in the research approach. The ratio of water to cement (w/c) was maintained at 0.3. Pervious concrete was created using single-sized recycled aggregate that passed through a 12.5 mm sieve and was held on a 9.5 mm sieve, as well as natural and recycled sand that passed through a 4 mm sieve. The production of twelve distinct concrete mixtures resulted in the testing of each concrete sample for dry density, abrasion resistance, compressive and splitting tensile strengths, porosity, and water permeability. A statistical method called GLM-ANOVA was also used to assess the characteristics of pervious concrete made using recycled aggregate. According to the experimental results, lowering the aggregate-to-cement ratio enhances the pervious concrete's overall performance. Additionally, a modest amount of fine aggregate boosts mechanical strength while lowering void content and water permeability. However, it was noted that such concretes' mechanical qualities were adversely affected to some extent. The results of this study offer insight into the viability of using recycled aggregates in order to achieve both structural integrity and environmental friendliness, which helps to optimize pervious concrete compositions.

Key Words
abrasion resistance; compressive and splitting tensile strength; pervious concrete; porosity; recycled aggregate and sand; water permeability

Address
(1) Briar K. Esmail:
Department of Civil Engineering, Faculty of Engineering, Koya University, Koya, Iraq;
(2) Briar K. Esmail:
ISISE, Department of Civil engineering, University of Minho, Guimarães, Portugal;
(3) Najmadeen M. Saeed, Soran R. Manguri:
Civil Engineering Department, University of Raparin, Ranya, Iraq;
(4) Najmadeen M. Saeed:
Civil Engineering Department, Faculty of Engineering, Tishk International University, Erbil, Iraq;
(5) Mustafa Günal:
Civil Engineering Department, Gaziantep University, Gaziantep, Türkiye.

Optimized machine learning algorithms for predicting the punching shear capacity of RC flat slabs Huajun Yan, Nan Xie and Dandan Shen
Abstract; Full Text (1980K) .	pages 27-36.	DOI: 10.12989/acc.2024.17.1.027

Abstract
Reinforced concrete (RC) flat slabs should be designed based on punching shear strength. As part of this study, machine learning (ML) algorithms were developed to accurately predict the punching shear strength of RC flat slabs without shear reinforcement. It is based on Bayesian optimization (BO), combined with four standard algorithms (Support vector regression, Decision trees, Random forests, Extreme gradient boosting) on 446 datasets that contain six design parameters. Furthermore, an analysis of feature importance is carried out by Shapley additive explanation (SHAP), in order to quantify the effect of design parameters on punching shear strength. According to the results, the BO method produces high prediction accuracy by selecting the optimal hyperparameters for each model. With R² = 0.985, MAE = 0.0155 MN, RMSE = 0.0244 MN, the BO-XGBoost model performed better than the original XGBoost prediction, which had R² = 0.917, MAE = 0.064 MN, RMSE = 0.121 MN in total dataset. Additionally, recommendations are provided on how to select factors that will influence punching shear resistance of RC flat slabs without shear reinforcement.

Key Words
Bayesian optimization; flat slabs; machine learning; punching shear strength

Address
(1) Huajun Yan, Nan Xie:
School of Civil Engineering, Beijing Jiaotong University, Beijing, 100044, China;
(2) Dandan Shen:
SANY Heavy Industry Co., LTD, Beijing, 100044, China.