Article
Engineering, Multidisciplinary
Mohammad Khorshidi Paji, Behrouz Gordan, Morteza Biklaryan, Danial Jahed Armaghani, Jian Zhou, Morteza Jamshidi
Summary: The study explores the impact of fresh and salty water on concrete compressive strength and proposes two hybrid artificial intelligence models to predict concrete compressive strength with high accuracy. Various parameters were found to significantly affect compressive strength, and the neuro-swarm intelligence model outperformed the neuro-imperialism model in predicting concrete compressive strength values.
Article
Mathematics
Danial Jahed Armaghani, Biao He, Edy Tonnizam Mohamad, Y. X. Zhang, Sai Hin Lai, Fei Ye
Summary: This study proposes two neuro-based metaheuristic models, neuro-imperialism and neuro-swarm, to estimate the peak particle velocity (PPV) caused by blasting. Through extensive observation and data collection, a detailed modeling procedure was conducted to estimate PPV values using both empirical methods and intelligence techniques. The neuro-swarm model outperforms the others in terms of accuracy.
Article
Environmental Sciences
Kevin Lawrence M. De Jesus, Delia B. Senoro, Jennifer C. Dela Cruz, Eduardo B. Chan
Summary: This study used physicochemical parameters to assess HM concentration in SW and GW in Marinduque Island Province, Philippines. The developed NN-PSO models showed superior prediction capability compared to other models.
Article
Computer Science, Artificial Intelligence
Xu Chen, Hugo Tianfield, Wenli Du
Summary: This paper introduces a novel bee-foraging learning PSO (BFL-PSO) algorithm with three different search phases, showing very competitive performance in terms of solution accuracy.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Information Systems
Kai Li, Hui Wang, Wenjun Wang, Feng Wang, Zhihua Cui
Summary: This paper proposes an artificial bee colony algorithm based on a modified nearest neighbor sequence to enhance optimization capability. Experimental results show that the algorithm performs competitively on various benchmark problems and complex problems.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Abidhan Bardhan, Pijush Samui, Kuntal Ghosh, Amir H. Gandomi, Siddhartha Bhattacharyya
Summary: This study proposes a novel integration of ELM and ANSI techniques for predicting the CBR of soils for railway tracks. Three ELM models, ELM-MPSO, ELM-TPSO, and ELM-IPSO, were developed and ELM-MPSO showed the most accurate prediction.
APPLIED SOFT COMPUTING
(2021)
Article
Engineering, Civil
Yuanqin Tao, Wei He, Honglei Sun, Yuanqiang Cai, Junqiang Chen
Summary: This paper proposes an inverse method to improve the prediction of tunnel displacements during adjacent excavation. Staged data assimilation and parameter identification are conducted using a multi-objective particle swarm optimization algorithm. An empirical formula and the Kriging method are applied to correct the time effect and reduce computational cost, respectively. The framework is verified using a typical staged excavation case.
Article
Thermodynamics
Chiazor Faustina Jisieike, Niyi Babatunde Ishola, Lekan M. Latinwo, Eriola Betiku
Summary: This study evaluated the modeling effectiveness of response surface methodology (RSM) and adaptive neuro-fuzzy inference system (ANFIS) in esterifying crude rubber seed oil (CRSO) with high free fatty acid (FFA). The ANFIS-PSO hybrid provided the best optimal conditions, resulting in the lowest FFA of 0.56%.
Article
Computer Science, Artificial Intelligence
Ryan Solgi, Hugo A. Loaiciga
Summary: This study evaluates the performance of seven bee-inspired metaheuristic algorithms in solving continuous optimization problems, ranks them based on convergence efficiency, and identifies ABC, BEGA, and MBO as the most efficient algorithms.
ARTIFICIAL INTELLIGENCE REVIEW
(2021)
Article
Computer Science, Interdisciplinary Applications
Jie Xing, Qinqin Zhao, Huiling Chen, Yili Zhang, Feng Zhou, Hanli Zhao
Summary: This paper proposes a bee foraging behavior-driven mutational salp swarm algorithm (BMSSA) based on an improved bee foraging strategy and an unscented mutation strategy. Experimental results validate the effectiveness of BMSSA in optimization problems and feature selection tasks.
JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Tingyu Ye, Wenjun Wang, Hui Wang, Zhihua Cui, Yun Wang, Jia Zhao, Min Hu
Summary: This article introduces a new artificial bee colony algorithm (RNSABC) based on random neighborhood structure to enhance the performance of the original ABC algorithm. The authors construct a random neighborhood structure and design an improved search strategy for optimization. Additionally, a depth-first search method is used to enhance the role of the onlooker bee phase. Experimental results demonstrate that RNSABC achieves competitive performance compared to nine other recent ABC variants.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Multidisciplinary Sciences
Zhixiang Fan, Chao Qian, Yuetian Jia, Zhedong Wang, Yinzhang Ding, Dengpan Wang, Longwei Tian, Erping Li, Tong Cai, Bin Zheng, Ido Kaminer, Hongsheng Chen
Summary: This study introduces the concept of homeostatic neuro-metasurfaces for automatic and monolithic management of dynamic wireless channels. Through the development of a flexible deep learning paradigm, the accuracy of global inverse design for large-scale metasurfaces exceeds 90%.
Article
Entomology
Francis A. Drummond, Jennifer Lund, Brian Eitzer
Summary: A two-year study in Maine wild blueberry fields monitored the health of migratory honey bee colonies in 2014 and 2015. Varroa mite infestations and pesticide residues on pollen were significant predictors of colony health, explaining 71% of the variance in colony health over the two years. Pathogen prevalence and incidence varied between the two years, with high levels of recently discovered pathogens and parasites detected.
Article
Computer Science, Artificial Intelligence
Chunfeng Wang, Pengpeng Shang, Peiping Shen
Summary: This paper presents a novel ABC algorithm based on Bayesian estimation (BEABC) to improve the performance of the original ABC algorithm. By replacing the selection probability with a probability calculated by Bayesian estimation and designing a directional guidance mechanism, BEABC achieves better results in single-objective, multi-objective, and real-world optimization problems.
COMPLEX & INTELLIGENT SYSTEMS
(2022)
Article
Construction & Building Technology
Nolan Concha, John Rei Aratan, Eloisa Marie Derigay, Joseph Manuel Martin, Rose Erika Taneo
Summary: A hybrid Neuro-Swarm model was developed to predict the shear strength capacity of steel fiber-reinforced concrete in deep beams. The model demonstrated remarkable performance indicators and superior prediction performance.
JOURNAL OF BUILDING ENGINEERING
(2023)
Article
Engineering, Civil
Shaohua Du, Diyuan Li, Bo Ruan, Genshui Wu, Bao Pan, Jinyin Ma
Summary: This paper investigates the boundary curve of the plastic zone and the principal stress distribution of the surrounding rock of a circular tunnel under non-tectonic stress. The effects of different factors on the shape of the plastic zone and the principal stress are analyzed. Support measures are proposed and the effectiveness of the support technology is validated.
EUROPEAN JOURNAL OF ENVIRONMENTAL AND CIVIL ENGINEERING
(2022)
Article
Energy & Fuels
Shaohua Du, Diyuan Li, Chunshun Zhang, Dawei Mao, Bo Ruan
Summary: This study focuses on the stability of the surrounding rock mass of the Wuyue Pumped Storage Power station in China, conducting experiments and theoretical analysis on the strength and deformation properties of the local granite. Experimental results show the influence of environmental variables on mechanical parameters, and a universal function law is proposed for practical application.
GEOMECHANICS AND GEOPHYSICS FOR GEO-ENERGY AND GEO-RESOURCES
(2021)
Article
Engineering, Geological
Diyuan Li, Bang Li, Zhenyu Han, Quanqi Zhu, Meng Liu
Summary: The study investigated the bi-modularity behavior of different rock materials in uniaxial compression and tension, validated the rationality of tensile elastic constants through experiments, and discussed the characteristics of different types of rocks.
ROCK MECHANICS AND ROCK ENGINEERING
(2021)
Article
Engineering, Geological
Quanqi Zhu, Diyuan Li, Zhenyu Han, Peng Xiao, Bang Li
Summary: This study utilized impact tests, compression tests, and digital image correlation to investigate the failure characteristics and mechanisms of rock specimens under different pre-stress conditions. The results revealed that pre-stress has dual effects on the dynamic mechanical behavior of rocks, with changes in crack patterns and strain localization observed as pre-stress levels increase.
Article
Engineering, Mechanical
Diyuan Li, Chenxi Zhang, Quanqi Zhu, Jinyin Ma, Feihong Gao
Summary: The deformation behavior, damage and fracture characteristics of granite specimens were tested and observed using 3D-DIC and SCC method. The study found that damage in the region of interest increases with axial stress, relative displacements indicate tensile-shear mixed mode fracture in SCC specimens, and new fracture initiates from the middle part of ESFB. Fracture energy of granite is estimated as 1760.4 J/m² based on energy conservation law.
FATIGUE & FRACTURE OF ENGINEERING MATERIALS & STRUCTURES
(2022)
Article
Chemistry, Analytical
Diyuan Li, Junjie Zhao, Zida Liu
Summary: This paper proposed a novel multitype hybrid rock lithology detection method based on convolutional neural network, effectively addressing the challenges in rock lithology recognition, and demonstrated the best performance in experimental evaluations.
Article
Geochemistry & Geophysics
Peng Xiao, Diyuan Li, Quanqi Zhu
Summary: In this study, a method to calculate the release of strain energy caused by excavation in pre-stressed rock is proposed. The influence of excavation height and width on strain energy release is inconsistent. The increase in lateral pressure coefficient leads to an exponential increase in strain energy release.
Article
Mathematics
Diyuan Li, Zida Liu, Danial Jahed Armaghani, Peng Xiao, Jian Zhou
Summary: This paper investigated the deficiencies of ensemble learning algorithms in rockburst prediction and proposed a novel machine learning model, deep forest, for predicting rockburst risk. By collecting a comprehensive database of 329 real rockburst cases and using Bayesian optimization to tune the hyperparameters, the deep forest model achieved high accuracy in both training and testing phases. The results of sensitivity analysis and validation with real cases demonstrated the outstanding capability of the deep forest model in rockburst prediction.
Article
Mathematics
Diyuan Li, Junjie Zhao, Jinyin Ma
Summary: This experimental study analyzes the impact of optimizers and learning rate on the performance of deep learning-based algorithms for rock thin-section image classification. The results show that deep learning-based approaches are highly effective and stable in rock thin-section image classification. The cosine learning-rate decay mode is a better option for learning-rate adjustment, and VGG16 and GoogLeNet models perform well, with Adam and RMSprop optimizers providing more robust capabilities.
Article
Energy & Fuels
Diyuan Li, Xiaoli Su, Feihong Gao, Zida Liu
Summary: The effects of temperature and cooling rate on the microstructural changes and mechanical properties of rocks in enhanced geothermal systems were investigated. The results showed that thermal-induced cracks destroy the rock microstructural integrity and cold water widens these cracks. The physical and mechanical properties of the rocks are weakened with increasing temperature. Rapid water cooling has a more significant effect on the rocks than slow cooling. Thermal-induced cracks alter the stress concentration and increase unstable crack propagation regions.
GEOMECHANICS AND GEOPHYSICS FOR GEO-ENERGY AND GEO-RESOURCES
(2022)
Article
Engineering, Geological
Zhenyu Han, Diyuan Li, Xibing Li
Summary: This study investigates the effects of axial pre-force and loading rate on the dynamic fracture behavior of rocks through coupled static-dynamic tests. The results show that both pre-force and loading rate have an impact on fracture parameters, with loading rate having a more significant effect. A new method based on the DIC technique is proposed to calculate crack opening distance (COD) and crack propagation velocity (CPV), improving efficiency and accuracy compared to traditional methods. The findings provide important insights into rock fracture dynamics and crack propagation.
INTERNATIONAL JOURNAL OF ROCK MECHANICS AND MINING SCIENCES
(2022)
Article
Geochemistry & Geophysics
Diyuan Li, Jingtai Jiang, Feihong Gao
Summary: This study conducted biaxial compression tests on granite samples with a combined fracture-hole structure, showing the impact of fracture dip angle and distance between fracture and hole on the strength and displacement of granite samples.
Article
Engineering, Mechanical
Xiaoli Su, Diyuan Li, Quanqi Zhu, Jinyin Ma
Summary: This study investigated the effects of fatigue loads on hydraulic fracturing in granite under different stress states. The results showed that the amplitudes of cyclic load had a significant impact on fracture initiation pressure and fracture morphology. Higher amplitude disturbance in the intermediate principal stress direction resulted in lower breakdown pressure and wider fractures. Increasing disturbance frequency led to the generation of complex fatigue cracks, which could weaken the rock strength.
FATIGUE & FRACTURE OF ENGINEERING MATERIALS & STRUCTURES
(2023)
Article
Engineering, Geological
Jinyin Ma, Diyuan Li, Pingkuang Luo, Chenxi Zhang, Feihong Gao
Summary: The influence of bedding angles and pre-static loads on dynamic mechanical properties and damage mechanisms of layered sandstone under cyclic impact loads was investigated through a series of cyclic impact tests. It was found that the number of resisting cyclic impacts and the total dissipated energy of the sandstone showed an initial decline followed by an increase with the rising of the bedding angles. The damage evolution of the sandstone under cyclic impacts was described using a damage factor and the impact time curves could be divided into three stages. The damage threshold decreased as the pre-static load increased.
ROCK MECHANICS AND ROCK ENGINEERING
(2023)
Article
Chemistry, Physical
Diyuan Li, Jinyin Ma, Quanqi Zhu, Bang Li
Summary: This study investigated the effects of three typical loading methods on the damage mechanism of rock specimens in dynamic Brazilian tests using five different rocks. The results showed that the loading modes significantly influenced the loading rate and dynamic tensile strength of the specimens, with mode-III loading exhibiting the highest values. The crack initiation position of the specimen in the dynamic Brazilian test was determined by the loading mode.