Qian Meng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Qian Meng has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Jingwen He
Samfox School of Architecture, Washington University in St. Louis, USA
4 shared publications - Zhang Feng
School of Civil Engineering Southeast University 210096 NANJING CHINA
3 shared publications - Haoran Xu
Columbia University
2 shared publications - Chongying Ling
School of Physics and Telecommunication Engineering, Yulin Normal University, Yulin 537000, China
1 shared publication - Guyue Gui
University of Chicago, USA
1 shared publication - Hanwen Cui
School of Engineering and Built Environment, Griffith University, Southport, QLD 4222, Australia
1 shared publication
Latest Publications
- Open Access
Knowledge-Driven Interval Multi-Objective Scheduling for Green Construction Under Time-Varying Carbon Emission Factors
Reducing carbon emissions during construction is essential for meeting dual carbon targets. Current green scheduling methods assume fixed emission factors, overlooking time-dependent variations driven by grid peak-valley patterns. Under interval duration uncertainty coupled with tight dynamic carbon budgets, conventional algorithms struggle with sparse feasible solutions and slow Pareto front convergence. We formulate a bi-objective interval RCPSP model with time-varying carbon emission factors that minimizes both interval makespan and total carbon emissions. A possibility degree measure converts scalar carbon budgets into linearized hard constraints. To solve this NP-hard problem, we propose the Knowledge-Driven Interval Multi-Objective Evolutionary Algorithm (KD-IMOEA), which integrates four components: Knowledge-Driven Initialization (KDI), Adaptive Time-window Carbon-aware Decoding (TCD), Carbon Budget-aware Repair Mutation (CBM), and Interval Pareto Elite Archive (IPA), forming an end-to-end carbon-aware optimization pipeline. We validate KD-IMOEA on J30 through J120 benchmark instances; results show it outperforms four established algorithms, including NSGA-II, in both convergence and distribution, with hypervolume (HV) gains up to 6.3%. A green building case study confirms that KD-IMOEA exploits spatiotemporal decoupling to identify float time and assign energy-intensive machinery to lower-carbon operating profiles. At the optimal compromise makespan of 169.5 days, this strategy cuts carbon emissions by 3.07% over traditional baselines, enabling management-driven emission savings without extending project duration.
Open AccessKnowledge-Driven Interval Multi-Objective Scheduling for Green Construction Under Time-Varying Carbon Emission Factors
Reducing carbon emissions during construction is essential for meeting dual carbon targets. Current green scheduling methods assume fixed emission factors, overlooking time-dependent variations driven by grid peak-valley patterns. Under interval duration uncertainty coupled with tight dynamic carbon budgets, conventional algorithms struggle with sparse feasible solutions and slow Pareto front convergence. We formulate a bi-objective interval RCPSP model with time-varying carbon emission factors that minimizes both interval makespan and total carbon emissions. A possibility degree measure converts scalar carbon budgets into linearized hard constraints. To solve this NP-hard problem, we propose the Knowledge-Driven Interval Multi-Objective Evolutionary Algorithm (KD-IMOEA), which integrates four components: Knowledge-Driven Initialization (KDI), Adaptive Time-window Carbon-aware Decoding (TCD), Carbon Budget-aware Repair Mutation (CBM), and Interval Pareto Elite Archive (IPA), forming an end-to-end carbon-aware optimization pipeline. We validate KD-IMOEA on J30 through J120 benchmark instances; results show it outperforms four established algorithms, including NSGA-II, in both convergence and distribution, with hypervolume (HV) gains up to 6.3%. A green building case study confirms that KD-IMOEA exploits spatiotemporal decoupling to identify float time and assign energy-intensive machinery to lower-carbon operating profiles. At the optimal compromise makespan of 169.5 days, this strategy cuts carbon emissions by 3.07% over traditional baselines, enabling management-driven emission savings without extending project duration.
- Open Access
- 21 July 2025
- Published by MDPI AG in Preprints.org
User Portrait-Driven Smart Home Device Deployment Optimization and Spatial Interaction Design
This study proposes a deployment optimization model tailored to personalized smart home environments, guided by user profile data. The model integrates multi-dimensional inputs, including static attributes (n=15), behavioral sequences (length L=96, embedding dimension d=128), and preference tags (vector size k=64). It aims to enhance both device placement efficiency and spatial interaction effectiveness.The approach leverages dual-stream feature encoding, a reinforcement learning policy network, and a synergistic mechanism combining Gaussian Process Regression (GPR) and Q-learning. Experimental results indicate that the optimization reduces average communication latency from 61.2 ms to 38.5 ms and decreases energy consumption by 22.4%, demonstrating significant improvements in system responsiveness and energy efficiency.Based on the behavioral data of 500 users, the experimental results demonstrate that the proposed method significantly improves interaction accuracy (up to 93.1%) and resource scheduling efficiency (hit rate increased to 91.2%), compared to baseline strategies.
- 21 July 2025
- Published by MDPI AG in Preprints.org
Open AccessUser Portrait-Driven Smart Home Device Deployment Optimization and Spatial Interaction Design
This study proposes a deployment optimization model tailored to personalized smart home environments, guided by user profile data. The model integrates multi-dimensional inputs, including static attributes (n=15), behavioral sequences (length L=96, embedding dimension d=128), and preference tags (vector size k=64). It aims to enhance both device placement efficiency and spatial interaction effectiveness.The approach leverages dual-stream feature encoding, a reinforcement learning policy network, and a synergistic mechanism combining Gaussian Process Regression (GPR) and Q-learning. Experimental results indicate that the optimization reduces average communication latency from 61.2 ms to 38.5 ms and decreases energy consumption by 22.4%, demonstrating significant improvements in system responsiveness and energy efficiency.Based on the behavioral data of 500 users, the experimental results demonstrate that the proposed method significantly improves interaction accuracy (up to 93.1%) and resource scheduling efficiency (hit rate increased to 91.2%), compared to baseline strategies.
- Open Access
Circular Economy Innovation in Built Environments: Mapping Policy Thresholds and Resonant Resilience via DEMATEL–TAISM
Under China’s dual-carbon strategy, the construction sector still lacks a systematic quantitative view of what drives its shift to a circular economy. This study couples the Decision-Making Trial and Evaluation Laboratory (DEMATEL) with Total Adversarial Interpretive Structural Modeling (TAISM) to build a weighted, multi-layer model of the policy–market–organization–technology chain. DEMATEL measures causal strengths, and TAISM arranges the variables into five levels without subjective thresholds, revealing a five-stage activation pathway. Fiscal incentives and regulations start the cascade; market demand amplifies their effect into a “resonant resilience” mechanism that improves cost performance. Robustness tests show 87% hierarchy stability and causal variation within ±0.6%. Sensitivity checks indicate that policy support must supply at least 30% of total network weight, because market capital alone cannot meet circular-construction costs. A three-tier intervention—policy incentives, financial amplification, and digital decomposition via green finance, BIM, and material passports—is therefore recommended.
Open AccessCircular Economy Innovation in Built Environments: Mapping Policy Thresholds and Resonant Resilience via DEMATEL–TAISM
Under China’s dual-carbon strategy, the construction sector still lacks a systematic quantitative view of what drives its shift to a circular economy. This study couples the Decision-Making Trial and Evaluation Laboratory (DEMATEL) with Total Adversarial Interpretive Structural Modeling (TAISM) to build a weighted, multi-layer model of the policy–market–organization–technology chain. DEMATEL measures causal strengths, and TAISM arranges the variables into five levels without subjective thresholds, revealing a five-stage activation pathway. Fiscal incentives and regulations start the cascade; market demand amplifies their effect into a “resonant resilience” mechanism that improves cost performance. Robustness tests show 87% hierarchy stability and causal variation within ±0.6%. Sensitivity checks indicate that policy support must supply at least 30% of total network weight, because market capital alone cannot meet circular-construction costs. A three-tier intervention—policy incentives, financial amplification, and digital decomposition via green finance, BIM, and material passports—is therefore recommended.
- Open Access
- 13 June 2025
- Published by Atlantis Press SARL
- p. 402-408
Research on Innovative Applications of AI in Sustainable Architecture: Blueprint for Future Building Technology
- 13 June 2025
- Published by Atlantis Press SARL
- p. 402-408
Open AccessResearch on Innovative Applications of AI in Sustainable Architecture: Blueprint for Future Building Technology
- Open Access
- 8 April 2025
- Published by MDPI AG in Preprints.org
Drone-3D Printing Linkage for Rapid Construction of Sustainable Post-Disaster Temporary Shelters
In order to improve the response speed and structural stability of post-disaster temporary shelter construction, a rapid construction technology based on UAV-3D printing linkage is proposed. An air-ground collaborative architecture is constructed to achieve precise construction through SLAM modeling, BIM optimization engine and dynamic path planning, and highly rheological bio-based composites are used to optimize deposition precision and interlayer bond strength. We analyze the intelligent scheduling, real-time path optimization and environmental adaptability of the UAV swarm, and verify the construction accuracy, construction efficiency and material performance under different working conditions. The results show that the technology can efficiently construct a low-energy, high-strength temporary shelter structure in complex terrain environments, with a 45% reduction in carbon emission compared with traditional methods, and the energy consumption per unit area of construction is controlled within 0.8kWh/m², and the construction of 200m² shelter is completed within 72 hours. Combined with multimodal sensing monitoring and intelligent control algorithms, it can further enhance the autonomy and sustainability of disaster emergency construction.
- 8 April 2025
- Published by MDPI AG in Preprints.org
Open AccessDrone-3D Printing Linkage for Rapid Construction of Sustainable Post-Disaster Temporary Shelters
In order to improve the response speed and structural stability of post-disaster temporary shelter construction, a rapid construction technology based on UAV-3D printing linkage is proposed. An air-ground collaborative architecture is constructed to achieve precise construction through SLAM modeling, BIM optimization engine and dynamic path planning, and highly rheological bio-based composites are used to optimize deposition precision and interlayer bond strength. We analyze the intelligent scheduling, real-time path optimization and environmental adaptability of the UAV swarm, and verify the construction accuracy, construction efficiency and material performance under different working conditions. The results show that the technology can efficiently construct a low-energy, high-strength temporary shelter structure in complex terrain environments, with a 45% reduction in carbon emission compared with traditional methods, and the energy consumption per unit area of construction is controlled within 0.8kWh/m², and the construction of 200m² shelter is completed within 72 hours. Combined with multimodal sensing monitoring and intelligent control algorithms, it can further enhance the autonomy and sustainability of disaster emergency construction.
- Open Access
- 7 February 2025
- Published by MDPI AG in Preprints.org
Research on Green Warehousing Logistics Site Selection Optimization and Path Planning based on Deep Learning
When it comes to e-commerce and logistics industry developing rapidly, the location and path planning of green warehousing and logistics have attracted more and more attention, and how to improve efficiency and reduce environmental impact has become the focus of research. This paper presents a new optimization approach based on Deep Neural Network (DNN), which is used to solve the multi-objective optimization problem in the warehouse location and path planning. We propose to use a deep neural network model to optimize the weights and parameters of the network as a whole through the combined PSO method, so that the dynamic and diverse needs of the logistics environment can be better adapted to changes. Unlike traditional methods based on heuristics or simple machine learning models, this paper adopts the principle of minimizing the transportation cost, while achieving the minimization of energy consumption and the limited carbon emissions in path planning, i.e. optimizing the particle swarm of DNN. Empirical results indicate that, when compared to classical optimization techniques, our approach enhances transportation cost and environmental sustainability by 18% and 12%.
- 7 February 2025
- Published by MDPI AG in Preprints.org
Open AccessResearch on Green Warehousing Logistics Site Selection Optimization and Path Planning based on Deep Learning
When it comes to e-commerce and logistics industry developing rapidly, the location and path planning of green warehousing and logistics have attracted more and more attention, and how to improve efficiency and reduce environmental impact has become the focus of research. This paper presents a new optimization approach based on Deep Neural Network (DNN), which is used to solve the multi-objective optimization problem in the warehouse location and path planning. We propose to use a deep neural network model to optimize the weights and parameters of the network as a whole through the combined PSO method, so that the dynamic and diverse needs of the logistics environment can be better adapted to changes. Unlike traditional methods based on heuristics or simple machine learning models, this paper adopts the principle of minimizing the transportation cost, while achieving the minimization of energy consumption and the limited carbon emissions in path planning, i.e. optimizing the particle swarm of DNN. Empirical results indicate that, when compared to classical optimization techniques, our approach enhances transportation cost and environmental sustainability by 18% and 12%.
- Open Access
- 1 January 2025
- Published by Southern United Academy of Sciences Limited in Journal of Computer Technology and Applied Mathematics
- Vol. 2 (1) , 8-14
Using Machine Learning for Sustainable Concrete Material Selection and Optimization in Building Design
This paper explores the application of machine learning (ML) in the selection and optimization of concrete materials for sustainable building design. It discusses how AI-driven platforms, such as Concrete Copilot and SmartMix, are revolutionizing concrete mix design by improving performance, reducing costs, and minimizing environmental impact. By leveraging ML techniques, these platforms enable real-time optimization of concrete ingredients, enhancing both resource efficiency and sustainability. The paper highlights the potential of machine learning to drive innovation in the concrete industry, contributing to the development of greener, more efficient building materials for future construction projects.
- 1 January 2025
- Published by Southern United Academy of Sciences Limited in Journal of Computer Technology and Applied Mathematics
- Vol. 2 (1) , 8-14
Open AccessUsing Machine Learning for Sustainable Concrete Material Selection and Optimization in Building Design
This paper explores the application of machine learning (ML) in the selection and optimization of concrete materials for sustainable building design. It discusses how AI-driven platforms, such as Concrete Copilot and SmartMix, are revolutionizing concrete mix design by improving performance, reducing costs, and minimizing environmental impact. By leveraging ML techniques, these platforms enable real-time optimization of concrete ingredients, enhancing both resource efficiency and sustainability. The paper highlights the potential of machine learning to drive innovation in the concrete industry, contributing to the development of greener, more efficient building materials for future construction projects.
- Open Access
- 25 December 2024
- Published by MDPI AG in Preprints.org
Research on Innovative Applications of AI in Sustainable Architecture: Blueprint for Future Building Technology
With increasing concerns over climate change and resource scarcity, sustainable construction has become a key priority. The proposed model integrates a multi-layer AI structure with three modules: data collection, intelligent prediction, and dynamic control. IoT sensors first gather real-time environmental data, which the AI system uses to operate effectively. A deep learning network then predicts building energy demand, enabling dynamic energy adjustments using LSTM neural networks. Finally, reinforcement learning algorithms adaptively control energy and environmental systems, incorporating climate predictions, building thermal properties, and energy prices to maximize efficiency. The model dynamically adjusts energy consumption based on predicted demand and factors such as climate forecasts, building thermal properties, and energy prices. Experimental simulations confirm the model’s effectiveness in reducing energy use and emissions across various building scenarios.
- 25 December 2024
- Published by MDPI AG in Preprints.org
Open AccessResearch on Innovative Applications of AI in Sustainable Architecture: Blueprint for Future Building Technology
With increasing concerns over climate change and resource scarcity, sustainable construction has become a key priority. The proposed model integrates a multi-layer AI structure with three modules: data collection, intelligent prediction, and dynamic control. IoT sensors first gather real-time environmental data, which the AI system uses to operate effectively. A deep learning network then predicts building energy demand, enabling dynamic energy adjustments using LSTM neural networks. Finally, reinforcement learning algorithms adaptively control energy and environmental systems, incorporating climate predictions, building thermal properties, and energy prices to maximize efficiency. The model dynamically adjusts energy consumption based on predicted demand and factors such as climate forecasts, building thermal properties, and energy prices. Experimental simulations confirm the model’s effectiveness in reducing energy use and emissions across various building scenarios.
- Open Access
- 9 September 2024
- Published by MDPI AG in Preprints.org
Research on Old Building Renovation Strategies by using Green Building Technologies
In light of the accelerated pace of economic growth and urbanisation, the transformation of green buildings has emerged as a prominent area of re-search. A considerable number of existing buildings have been constructed and are still in use. However, the energy consumption and environmental impact throughout the entire life cycle of these buildings are not adequately considered in the renovation design. This results in high energy consumption and poor indoor comfort. In this work, we include improving the thermal insulation of buildings, such as thickening the insulation of external walls and replacing energy-efficient windows to reduce energy losses caused by temperature differences between in-door and outdoor buildings; Adopt energy-efficient HVAC systems to reduce en-ergy consumption and improve indoor air quality by upgrading equipment effi-ciency, optimizing duct design, and intelligent control systems; At the same time, we will introduce renewable energy sources such as solar energy, and we will not only install solar photovoltaic panels to generate electricity, but also use solar thermal collector systems to provide hot water and heating, so as to achieve di-versified and sustainable use of energy. Combined, these measures can effec-tively reduce the overall energy consumption of the building, reduce carbon emissions, and improve the comfort and health of the indoor environment. During the experimental analysis, the energy consumption and indoor comfort before and after the renovation were evaluated, and the results showed that the energy consumption was significantly reduced and living comfort was improved.
- 9 September 2024
- Published by MDPI AG in Preprints.org
Open AccessResearch on Old Building Renovation Strategies by using Green Building Technologies
In light of the accelerated pace of economic growth and urbanisation, the transformation of green buildings has emerged as a prominent area of re-search. A considerable number of existing buildings have been constructed and are still in use. However, the energy consumption and environmental impact throughout the entire life cycle of these buildings are not adequately considered in the renovation design. This results in high energy consumption and poor indoor comfort. In this work, we include improving the thermal insulation of buildings, such as thickening the insulation of external walls and replacing energy-efficient windows to reduce energy losses caused by temperature differences between in-door and outdoor buildings; Adopt energy-efficient HVAC systems to reduce en-ergy consumption and improve indoor air quality by upgrading equipment effi-ciency, optimizing duct design, and intelligent control systems; At the same time, we will introduce renewable energy sources such as solar energy, and we will not only install solar photovoltaic panels to generate electricity, but also use solar thermal collector systems to provide hot water and heating, so as to achieve di-versified and sustainable use of energy. Combined, these measures can effec-tively reduce the overall energy consumption of the building, reduce carbon emissions, and improve the comfort and health of the indoor environment. During the experimental analysis, the energy consumption and indoor comfort before and after the renovation were evaluated, and the results showed that the energy consumption was significantly reduced and living comfort was improved.
- Open Access
- 23 August 2024
- Published by Darcy & Roy Press Co. Ltd. in Academic Journal of Science and Technology
- Vol. 12 (2) , 7-12
The Integration of Artificial Intelligence in Architectural Visualization Enhances Augmented Realism and Interactivity
The construction industry is an important part of the national economic market of various countries; since 2013, the construction industry's added value in the gross domestic product has been more than 6%, reaching 6.89% in 2022, and is a pillar industry of the national economy. Intelligent construction is the realistic demand to promote the high-quality development of China's construction industry. It is the key focus of transforming and upgrading the traditional construction industry to information, digital, and intelligent. As a new production factor, construction robots have become the key to promoting intelligent construction. Under the guidance of various national and industry policies, thanks to China's huge construction market volume and rich application scenarios, many innovative and entrepreneurial entities have entered the field of construction robots. Architectural visualization is a crucial aspect of architectural design and communication. With the development of science and technology, artificial intelligence (AI) technology is increasingly becoming an essential tool for architectural visualization and communication. The emergence of AI technology has provided architects with more flexible and creative ways to present design ideas. All along, designers who love architecture have been passionate about exploring better solutions for architecture, but there is never an optimal solution for architectural design; AI is the fire of the future era; it brings us more opportunities but also forces us to face new challenges from the future.
- 23 August 2024
- Published by Darcy & Roy Press Co. Ltd. in Academic Journal of Science and Technology
- Vol. 12 (2) , 7-12
Open AccessThe Integration of Artificial Intelligence in Architectural Visualization Enhances Augmented Realism and Interactivity
The construction industry is an important part of the national economic market of various countries; since 2013, the construction industry's added value in the gross domestic product has been more than 6%, reaching 6.89% in 2022, and is a pillar industry of the national economy. Intelligent construction is the realistic demand to promote the high-quality development of China's construction industry. It is the key focus of transforming and upgrading the traditional construction industry to information, digital, and intelligent. As a new production factor, construction robots have become the key to promoting intelligent construction. Under the guidance of various national and industry policies, thanks to China's huge construction market volume and rich application scenarios, many innovative and entrepreneurial entities have entered the field of construction robots. Architectural visualization is a crucial aspect of architectural design and communication. With the development of science and technology, artificial intelligence (AI) technology is increasingly becoming an essential tool for architectural visualization and communication. The emergence of AI technology has provided architects with more flexible and creative ways to present design ideas. All along, designers who love architecture have been passionate about exploring better solutions for architecture, but there is never an optimal solution for architectural design; AI is the fire of the future era; it brings us more opportunities but also forces us to face new challenges from the future.