Autonomous construction framework for crane control with enhanced soft actor–critic algorithm and real‐time progress monitoring

Computer-Aided Civil and Infrastructure Engineering, Год журнала: 2025, Номер unknown

Опубликована: Янв. 30, 2025

Abstract With the shortage of skilled labors, there is an increasing demand for automation in construction industry. This study presents autonomous framework crane control with enhanced soft actor–critic (SAC‐E) algorithm and real‐time progress monitoring. SAC‐E a novel reinforcement learning superior speed training stability lifting path planning. In addition, robotic kinematics are implemented to ensure that can autonomously execute path. Last, hardware communication interfaces between robot operating system building information modeling (BIM) developed The performance proposed was demonstrated using robotized mobile stack concrete retaining blocks. results show be effectively used block update BIM platform.

Язык: Английский

---

A physics‐informed deep reinforcement learning framework for autonomous steel frame structure design

Computer-Aided Civil and Infrastructure Engineering, Год журнала: 2024, Номер unknown

Опубликована: Июнь 6, 2024

Abstract As artificial intelligence technology advances, automated structural design has emerged as a new research focus in recent years. This paper combines finite element method (FEM) and deep reinforcement learning (DRL) to establish physics‐informed framework, named FrameRL, for steel frame structure design. FrameRL models the process of frames (RL) process, enabling agent simulate engineer's role, interacting with environment learn methods policies Through computer experiments, it is demonstrated that can safe economical within 1 s, significantly faster than manual processes. Furthermore, performance compared traditional optimization algorithms three typical cases high‐rise case, demonstrating efficiently complete based on learned experiences policies.

Язык: Английский

---

Semi-active variable stiffness and damping control for adjacent structures using LSTM-based prediction algorithm

Journal of Building Engineering, Год журнала: 2025, Номер unknown, С. 112127 - 112127

Опубликована: Фев. 1, 2025

Язык: Английский

---

A hybrid machine learning framework for wind pressure prediction on buildings with constrained sensor networks

Computer-Aided Civil and Infrastructure Engineering, Год журнала: 2025, Номер unknown

Опубликована: Апрель 18, 2025

Abstract Accurate and efficient prediction of wind pressure distributions on high‐rise building façades is crucial for mitigating structural risks in urban environments. Conventional approaches rely extensive sensor networks, often hindered by cost, accessibility, architectural limitations. This study proposes a novel hybrid machine learning (ML) framework that reconstructs high‐fidelity (HFWP) coefficient fields from limited number sensors leveraging dynamic spatiotemporal feature extraction mapping. The methodology consists four key stages: (1) low‐fidelity field reconstruction data using constrained QR decomposition, (2) dimensionality reduction both HFWP reconstructions to extract dominant features, (3) mapping the reduced‐order representations long short‐term memory network, (4) over time. proposed approach, which predicts time history coefficients various directions, validated tunnel data, with case studies multiple façades—including windward, right‐side, leeward surfaces—under placement scenarios. also evaluated against alternative ML models, demonstrating superior accuracy reconstructing full field. results highlight robustness generalization capability model across different directions configurations, making it practical solution real‐time estimation health monitoring digital twin applications.

Язык: Английский

---

An interactive platform of deep reinforcement learning and wind tunnel testing

Physics of Fluids, Год журнала: 2024, Номер 36(11)

Опубликована: Ноя. 1, 2024

Flow around bluff bodies is a classic problem in fluid mechanics, and flow control critical approach for manipulating the aerodynamic characteristics of bodies. Recently, deep reinforcement learning (DRL) has emerged as highly potential method control. However, application DRL to wind tunnel testing involves significant obstacles, which can be classified into software, hardware, interaction challenges. These challenges make DRL-based particularly complex challenging many researchers. To address these challenges, this paper proposes novel platform, named DRLinWT. DRLinWT introduces universal adapter capable managing interactive communications across multiple mainstream communication protocols integrates commonly used libraries, thereby significantly reducing cost between algorithms tests. Using experiment square cylinder three fields varying complexity was conducted.

Язык: Английский

---