Article
Materials Science, Multidisciplinary
Peng Hao, Dachuan Liu, Kunpeng Zhang, Ye Yuan, Bo Wang, Gang Li, Xi Zhang
Summary: This study proposes a novel layout optimization method for curvilinearly stiffened panels based on deep learning-based models, which significantly improves structural efficiency. The research demonstrates the extraordinary promise of deep learning-based methods in the field of engineering optimization.
MATERIALS & DESIGN
(2021)
Article
Computer Science, Artificial Intelligence
Pengju Zhao, Wenjie Liao, Yuli Huang, Xinzheng Lu
Summary: The structural scheme design of shear wall structures is of great importance as it guides the whole structural design process and has a significant impact on subsequent design stages. Current design methods based on deep generative algorithms using pixel images have certain flaws and limitations, such as excessive model parameters and difficulty in reflecting topological characteristics of structures. This study proposes the use of graph neural networks (GNNs) to represent shear wall structures in graph data form and develops an intelligent design method based on GNNs, addressing the existing problems and limitations in shear wall layout design.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Construction & Building Technology
Pengju Zhao, Wenjie Liao, Yuli Huang, Xinzheng Lu
Summary: This study proposes an intelligent plan layout design method for frame beams based on a graph neural network. By training a neural network with a large-scale dataset of frame structure layouts, a novel graph neural network model for beam layout design is introduced. The test results demonstrate the high accuracy of the proposed method, comparable to the designs by engineers.
JOURNAL OF BUILDING ENGINEERING
(2023)
Article
Construction & Building Technology
Yangluxi Li, Lei Chen, Guangyao Li
Summary: A variable design method based on K-means clustering is proposed for the optimization of building layout. The optimization was implemented on Matlab using numerical simulation, genetic algorithm, and universal thermal climate index (UTCI). The building layouts with centralized type, decentralized type, and edge flow type water configuration were optimized. The results show a reduction of 0.1 to 0.6 degrees C in UTCI after the optimization. It is concluded that increasing wind velocity is crucial for improving thermal comfort under moderate heat stress.
INDOOR AND BUILT ENVIRONMENT
(2023)
Article
Agriculture, Multidisciplinary
Chun-Hsian Huang, Po-Jung Chen, Yi-Jie Lin, Bo-Wei Chen, Jia-Xuan Zheng
Summary: This research introduces a robot-based intelligent management design using FPGA device and BNN hardware module to intelligently manage crop growth environments. Through cryptographic hardware functions and dynamic adjustment, the robot can enhance the efficiency of crop growth environment control and ensure data transmission security.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Article
Computer Science, Interdisciplinary Applications
Wenliang Qian, Yang Xu, Hui Li
Summary: This study presents an autonomous architectural shape sketch design method using a self-sparse generative adversarial network, reducing reliance on aesthetic knowledge and time consumption in traditional design. By constructing a new architectural shape dataset, designing a self-adaptive sparse transform module, and evaluating sketch quality using FID, the proposed method outperformed other image generation approaches.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2022)
Article
Computer Science, Information Systems
Yan Pei, Genshu Lu
Summary: This paper introduces the design of an intelligent educational evaluation system using deep learning and utilizes the low-complexity offset minimal sum algorithm as the front-end processor to reduce computational complexity. Experimental results show that the proposal further improves the performance of unbalanced data classification in this problem scenario.
Article
Chemistry, Multidisciplinary
Katarzyna Grzesiak-Kopec, Barbara Strug, Grazyna Slusarczyk
Summary: This paper proposes an evolutionary technique for generating new design solutions for the floor layout problem, presenting a case study of one-story houses and discussing the evaluation method. The obtained results, advantages and issues related to this approach are also discussed.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Interdisciplinary Applications
Xiaopei Cai, Xueyang Tang, Shuo Pan, Yi Wang, Hai Yan, Yuheng Ren, Ning Chen, Yue Hou
Summary: This article introduces an intelligent recognition method for defects in concrete slabs of high-speed railway (HSR) based on a few-shot learning model. By training an artificial intelligence model with limited data, it can accurately identify different service conditions of HSR. The experimental results show satisfactory accuracy, low parameter quantity, and testing time.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2023)
Article
Chemistry, Multidisciplinary
Yihui Wang, Wei Sha, Mi Xiao, Cheng-Wei Qiu, Liang Gao
Summary: This study presents an intelligent design framework for thermal metamaterials using a pre-trained deep learning model. It can achieve the desired functional structures of thermal metamaterials with exceptional speed and efficiency, regardless of arbitrary geometry. This research sets up a novel paradigm for the automatic and real-time design of thermal metamaterials.
ADVANCED MATERIALS
(2023)
Article
Engineering, Aerospace
Tianhe Gao, Ziyu Xu, Zengcong Li, Pei Liu, Kuo Tian
Summary: A two-stage intelligent method for the layout design of the curved cabin door is proposed, which combines topology optimization and evolutionary algorithm to achieve an innovative and optimal design. The experimental results demonstrate the effectiveness of the proposed method in reducing mass while satisfying constraints, indicating its potential in improving the carrying capacity and efficiency of spacecraft.
Article
Engineering, Electrical & Electronic
Xueyong Yu, Heng Yu, Chunjing Liu
Summary: In this paper, we realize the environment design smart sensor network based on advanced extensive data analysis. We establish an innovative sensor network node MAC layer analysis model based on the Markov chain. The mathematical calculation method of node MAC layer delay is obtained through analyzing the nodes' Markov state transfer process. An automatic layout algorithm is proposed, considering applicability, aesthetics, and comfort.
JOURNAL OF SENSORS
(2022)
Article
Computer Science, Information Systems
K. U. Jaseena, Binsu C. Kovoor
Summary: Weather forecasting is the practice of predicting the state of the atmosphere based on different weather parameters. Accurate weather forecasts are crucial in various fields. With the advancement of atmospheric observing systems and the increasing volume of weather data, deep learning techniques are being used to improve weather prediction. This paper provides a comprehensive review of weather forecasting approaches and discusses potential future research directions.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Engineering, Marine
Lifu Wang, Dongyan Shi, Boyang Zhang, Guangliang Li, Wasim M. K. Helal
Summary: This paper establishes a quantifiable optimization mathematical model for the layout of umbilical components and proposes the use of the DE-GLM method to solve the model. To overcome the time and artificial costs of traditional layout algorithms, a novel convolutional neural network model is proposed to achieve real-time accurate prediction of umbilical component layout results. The method not only automatically obtains a layout design that satisfies the performance requirements, but also achieves an accuracy rate of 93.28% compared to other convolutional neural networks.
Article
Nanoscience & Nanotechnology
Zhuo Wang, Hongrui Zhang, Hanting Zhao, Tie Jun Cui, Lianlin Li
Summary: Electromagnetic sensing has wide applications in science, engineering, and military, but faces challenges in energy consumption, cost, efficiency, and portability. To address these challenges, the concept of intelligent EM metasurface camera is proposed, which combines inexpensive programmable metasurfaces with modern machine learning techniques. Experimental results show that this camera can observe human behaviors clearly with a high frame rate in highly noisy environments.
Article
Computer Science, Artificial Intelligence
Pengju Zhao, Wenjie Liao, Yuli Huang, Xinzheng Lu
Summary: The structural scheme design of shear wall structures is of great importance as it guides the whole structural design process and has a significant impact on subsequent design stages. Current design methods based on deep generative algorithms using pixel images have certain flaws and limitations, such as excessive model parameters and difficulty in reflecting topological characteristics of structures. This study proposes the use of graph neural networks (GNNs) to represent shear wall structures in graph data form and develops an intelligent design method based on GNNs, addressing the existing problems and limitations in shear wall layout design.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Engineering, Geological
Kaiqi Lin, You-Lin Xu, Xinzheng Lu, Zhongguo Guan, Jianzhong Li
Summary: This study proposes a digital twin-based life-cycle seismic performance assessment method for long-span cable-stayed bridges, which provides a more accurate estimation of the service life by considering the digital twin-based structural response prediction method considering lifetime earthquake occurrence and sequence.
BULLETIN OF EARTHQUAKE ENGINEERING
(2023)
Article
Engineering, Civil
Pengju Zhao, Wenjie Liao, Yuli Huang, Xinzheng Lu
Summary: This study proposes an attention-enhanced generative adversarial network model named StructGAN-AE for the intelligent design of shear wall structures. A pre-training method is used to overcome the limitation of data shortage. Case studies show that StructGAN-AE can generate a more reasonable local layout of shear walls in critical zones and improve the overall performance of shear wall design.
ENGINEERING STRUCTURES
(2023)
Article
Immunology
Eleonora Daini, Eleonora Vandini, Martina Bodria, Wenjie Liao, Carlo Baraldi, Valentina Secco, Alessandra Ottani, Michele Zoli, Daniela Giuliani, Antonietta Vilella
Summary: Alzheimer's disease (AD) is the most frequent cause of dementia and lacks effective therapy. Previous studies have shown that treatment with melanocortin analogs can induce neuroprotection in the early stages of AD. In this study, the neuroprotective role of melanocortins was investigated in two transgenic mouse models of severe AD. After 50 days of treatment, it was found that chronic stimulation of melanocortin receptors improved cognitive abilities of AD mice and decreased levels of hyperphosphorylated Tau, but had no effect on Aβ burden.
FRONTIERS IN IMMUNOLOGY
(2023)
Article
Construction & Building Technology
Pengju Zhao, Wenjie Liao, Yuli Huang, Xinzheng Lu
Summary: This study proposes an intelligent plan layout design method for frame beams based on a graph neural network. By training a neural network with a large-scale dataset of frame structure layouts, a novel graph neural network model for beam layout design is introduced. The test results demonstrate the high accuracy of the proposed method, comparable to the designs by engineers.
JOURNAL OF BUILDING ENGINEERING
(2023)
Article
Engineering, Civil
Wenjie Liao, Xinyu Wang, Yifan Fei, Yuli Huang, Linlin Xie, Xinzheng Lu
Summary: Seismic isolation improves building resilience, and intelligent design enhances efficiency, but existing designs are constrained by data. Therefore, a method that can learn physical mechanisms and design rules without data constraints is needed. This study proposes a physics-rule-co-guided self-supervised generative adversarial network to generate seismic isolation design based on layout drawings.
EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS
(2023)
Editorial Material
Engineering, Civil
Xinzheng Lu, Henry Burton
EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS
(2023)
Article
Engineering, Civil
Donglian Gu, Ahsan Kareem, Xinzheng Lu, Qingle Cheng
Summary: This study proposes a computational framework for the city-scale evaluation of wind effects on buildings in dense central business districts. It features GIS-based topology generation, large eddy simulation (LES) for time-varying wind loads, city-scale time history analysis, high-fidelity visualization of results, and city-scale performance assessment. By utilizing a portion of downtown San Francisco, the framework demonstrates its potential to revolutionize the computational design and assessment of buildings. It serves as a system-level computation-based analysis and design platform for building clusters.
JOURNAL OF WIND ENGINEERING AND INDUSTRIAL AERODYNAMICS
(2023)
Article
Construction & Building Technology
Yitian Feng, Yifan Fei, Yuanqing Lin, Wenjie Liao, Xinzheng Lu
Summary: This study developed a rule-embedded intelligent generative design method based on deep learning and generative adversarial networks (GANs) for rapid and accurate cross-sectional design of shear wall components. By embedding a differentiable rule evaluator in the GAN, the design efficiency was significantly improved and highly consistent with the design of engineers.
JOURNAL OF STRUCTURAL ENGINEERING
(2023)
Article
Engineering, Geological
Yuan Tian, Siying Chen, Simeng Liu, Xinzheng Lu
Summary: Tall buildings have a significant impact on the seismic safety of shorter buildings in their surroundings. Previous studies have mainly focused on analyzing the structure-soil-structure interactions in the local vicinity. However, considering the mass and period of tall buildings, their influence during earthquakes can extend over a wide area. Therefore, it is crucial to investigate the influence of tall buildings from a city-scale perspective.
SOIL DYNAMICS AND EARTHQUAKE ENGINEERING
(2023)
Article
Green & Sustainable Science & Technology
Donglian Gu, Yixing Wang, Xinzheng Lu, Zhen Xu
Summary: A probability-based city-scale method for assessing the earthquake-induced risk of passenger entrapment in elevators is proposed. City-scale time history analysis is performed to simulate the seismic response of building clusters, and the Monte Carlo simulation is conducted to consider the uncertainty of multiple factors. A case study of the Tsinghua University campus demonstrates the practicability of the method.
Article
Automation & Control Systems
Zhe Zheng, Yu-Cheng Zhou, Ke-Yin Chen, Xin-Zheng Lu, Zhong-Tian She, Jia-Rui Lin
Summary: This research aims to propose a novel approach to automatically evaluate and enhance the machine interpretability of single clauses and building codes. By introducing classification categories and developing a text classification model, the machine interpretability of building codes is improved, and a quantitative evaluation method is proposed. Experimental results show that the proposed method outperforms existing methods, and it is suggested that there is still room for improvement in the interpretability of building codes.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2024)
Article
Construction & Building Technology
Jawad Ahmad, Zhiguang Zhou
Summary: The addition of steel fibers and marble waste has a positive impact on the performance of self-compacting concrete (SCC) in aggressive environments, improving its mechanical properties, durability, and microstructure.
JOURNAL OF BUILDING ENGINEERING
(2024)
Article
Construction & Building Technology
Kyungjae Lee, Hyunwoo Lim
Summary: Building energy code updates induce correlations among building parameters, which can affect data analysis. This study investigates the impact of these correlations through sensitivity analysis and Principal Component Analysis (PCA).
JOURNAL OF BUILDING ENGINEERING
(2024)
Article
Construction & Building Technology
M. I. Nizovtsev, A. N. Sterlyagov
Summary: The effect of adding a layer of phase change material on the thermal inertia properties of the outer wall in lightweight building was numerically studied. It was found that in the regime of indoor air conditioning, adding a layer of paraffin in a foamed polyurethane wall can significantly reduce heat flux fluctuations on the inner wall surface. Additionally, locating the phase change material on the inner surface of the wall in the regime of daily in-phase fluctuations in the indoor and outdoor air temperatures produces the best effect.
JOURNAL OF BUILDING ENGINEERING
(2024)
Article
Construction & Building Technology
Mingzhen Wang, Eric Hu, Lei Chen
Summary: This study proposes an innovative and sustainable condenser-cooling approach called Radiation-enhanced Thermal Diode Tank (RTDT) to assist in energy-saving for Refrigeration and Air-conditioning (RAC) systems. The research finds that the RTDT-RAC system can save up to 40% energy compared to the reference RAC system, with a higher Coefficient of Performance (COP) of 5.34. Additionally, the parametric analysis shows that regions with larger day and night ambient temperature differences, higher room temperature setpoints, and increased RHP radiative surface areas can effectively increase energy savings.
JOURNAL OF BUILDING ENGINEERING
(2024)
Article
Construction & Building Technology
Hua Zhang, Xinyue Liu, Linjian Ma, Zeng Li
Summary: This study aims to investigate the impact of polypropylene (PP) fibers and aggregate contents on the mechanical performance of coral aggregate concrete (CASC). The results revealed that increasing the PP fiber contents and gravel replacement ratio significantly improved the dynamic compressive strength and toughness of CASC, while excessive fiber can have a detrimental effect. The study also developed a dynamic constitutive model that accurately predicted the stress-strain curve and mechanical properties of CASC.
JOURNAL OF BUILDING ENGINEERING
(2024)
Article
Construction & Building Technology
Navid Moghaddas-Zadeh, Mahmood Farzaneh-Gord, William P. Bahnfleth
Summary: This study presents a general procedure for designing a hybrid chiller network using a Particle Swarm Optimization algorithm to determine the optimal configuration and chiller loading distribution. Life cycle cost analysis is used to select the optimal configuration. Simulations show that the best energy and economic choices depend on the natural gas and electricity price ratio.
JOURNAL OF BUILDING ENGINEERING
(2024)
Article
Construction & Building Technology
Carolina Briceno, Miguel Azenha, Graca Vasconcelos, Paulo B. Lourenco
Summary: The conditioning of the brick units has an influence on the shear bond behavior of the unit-mortar interface. Longer immersion time improves the shear bond properties, while the cohesion values of premixed mortars are affected by the conditioning time.
JOURNAL OF BUILDING ENGINEERING
(2024)
Article
Construction & Building Technology
Seong-Yong Cheon, Hye-Jin Cho, Jae-Weon Jeong
Summary: A dedicated outdoor air system (DOAS) assisted by an isothermal dehumidifier and an indirect evaporative cooler is proposed, and its energy-saving potential is evaluated based on detailed simulations. The results indicate that despite the free cooling operation by the indirect evaporative cooler, the proposed system consumes 10% more operating energy due to the low coefficient of performance (COP) of the isothermal dehumidifier. Improvements in the COP of the isothermal dehumidifier are required for comparable energy performance.
JOURNAL OF BUILDING ENGINEERING
(2024)
Article
Construction & Building Technology
Xiaochen Ma, Wenchao Shi, Hongxing Yang
Summary: The actual wetting factor of the plate surface and the movement of spray droplets are important factors in the performance of indirect evaporative cooling (IEC) systems. A 3D computational fluid dynamics (CFD) model that considers these factors is proposed in this study. The model accurately predicts the performance of IEC systems and provides insights for further improvement.
JOURNAL OF BUILDING ENGINEERING
(2024)
Article
Construction & Building Technology
Panagiota Theodoropoulou, Eleonora Brembilla, Roel Schipper, Christian Louter
Summary: This study develops an optimized glare-based control strategy for Venetian blinds in real-life buildings, aiming to improve visual conditions while saving energy. The results show that the optimized algorithm can significantly improve visual conditions for different activities in the building, although it may increase the use of electric lighting in certain cases.
JOURNAL OF BUILDING ENGINEERING
(2024)
Article
Construction & Building Technology
Nari Yoon, Leslie Norford, Michael Wetter, Ali Malkawi
Summary: This study developed an analytical model for window operation schedules that leverages natural ventilation for different airflow rates, thermal masses, and climate variations. The research demonstrated that proper window scheduling can significantly reduce indoor temperature and save energy.
JOURNAL OF BUILDING ENGINEERING
(2024)
Article
Construction & Building Technology
Haoran Cheng, Denghu Jing
Summary: This study investigated the reinforcement and compressive behavior of rat-trap bond walls using steel plate frames. The results showed that the steel plate frame effectively enhanced the compressive peak load of the wall, and increasing the steel plate thickness improved compressive strength and confinement effect. Nonlinear relations were observed between the preload ratio and the peak load, and local buckling of the steel plate frame was affected by the preload ratio. Finite element models were used to verify the experimental results, and calculation formulas for predicting the compressive peak load were developed and found to be accurate.
JOURNAL OF BUILDING ENGINEERING
(2024)
Article
Construction & Building Technology
Bangyu Cheng, Jinlong Yang, Yucheng Fan, Zhi Ni, Ziyan Hang, Bowen Zeng, Huanxun Liu, Chuang Feng
Summary: This study investigates the property-microstructure relationships in graphene nanoplatelet (GNP) reinforced cement composites (GNPRCCs) using three-dimensional finite element modeling and experiments. The results reveal that GNPs aligned at 45 degrees have the most significant impact on enhancing load-bearing capacity and damage resistance of the composites. A larger GNP diameter-to-thickness ratio is beneficial for crack bridging and propagation control. The orientation and porosity of pores have significant effects on the damage behaviors of the composites, while pore shape shows negligible effects. These findings provide key guidelines for optimizing microstructural features and improving the performance and durability of construction materials.
JOURNAL OF BUILDING ENGINEERING
(2024)
Article
Construction & Building Technology
Patrick N. Lemougna, Arnold Ismailov, Erkki Levanen, Pekka Tanskanen, Juho Yliniemi, Katja Kilpimaa, Mirja Illikainen
Summary: This study investigates the effect of glass wool waste on the sintering properties of kaolinitic and illitic clays in the ceramic industry. It was found that the addition of glass wool increased compressive strength at lower temperatures, while the addition of spodumene tailings mitigated firing shrinkage at higher temperatures.
JOURNAL OF BUILDING ENGINEERING
(2024)
Article
Construction & Building Technology
Duidi Wu, Shuangdui Wu, Qianyou Zhao, Shuo Zhang, Jin Qi, Jie Hu, Borong Lin
Summary: This study proposes an intelligent elevator information system (IEIS) based on computer vision technology, which monitors elevator occupancy and guides demand-driven operation optimization to achieve energy-efficient management and efficient operation.
JOURNAL OF BUILDING ENGINEERING
(2024)