Automation in Construction最新文献

This paper presents a full suite of Robotic Tower Crane (RTC) technologies that can be seamlessly implemented on traditional saddle-jib tower cranes to boost the construction safety and productivity. The robotisation of tower cranes enables the RTC capabilities of automatic path planning for point-to-point movement, and dynamic obstacle avoidance with re-planning. While the former fast generates the RTC path based on decoupling of vertical and horizontal movements, the latter takes a ‘hoist-first’ approach to prioritise safety. A motion compensation algorithm is developed for multi-step speed control to achieve the exact displacement based on dynamically optimizing the time duration at each planned velocity. The implementation of the RTC system has demonstrated a comprehensive approach that combines laboratory simulations, hardware-in-the-loop testing, and live demos for on-site deployment. A comparative performance and operational time study reveals the RTC's superior precision and consistency over human operators.

While traditional manual knowledge management methods indicate the intelligent approach in the whole-process engineering consulting, related studies like NLP technologies still demonstrated the feasibility and difficulties in processing the complex unstructured long-text consulting knowledge text. To optimize, by firstly incorporating multi attention mechanisms to realize complex long-text knowledge processing and subsequently integrating optimized BERT model RoBRETa and CASREL model for jointly extracting entities and relationships from texts, this paper proposes a LF-CASREL model to optimizes existing knowledge management techniques. Validation experiment with a knowledge graph and question-answering interactions after jointly extraction through LF-CASREL with a precision of 88.89 %, a recall of 77.25 %, and a F1 score of 68.99 % under practical random noise influence demonstrates the practicality of the proposed method. Overall, the proposed LF-CASREL is convenient and beneficial for project managers, engineering consultants, and decision-makers in deeper understanding and management of whole-process engineering consulting, providing valuable insights for future research.

Current 2D and 3D image-based crack detection methods in transportation infrastructure often struggle with noise robustness and feature diversity. To overcome these challenges, the paper use CSF-CrackNet, a self-adaptive 2D3D image fusion model utilizes channel and spatial modules for automated pavement crack segmentation. CSF-CrackNet consists of four parts: feature enhanced and field sensing (FEFS) module, channel module, spatial module, and semantic segmentation module. A multi-feature image dataset was established using a vehicle-mounted 3D imaging system, including color images, depth images, and color-depth overlapped images. Results show that the mean intersection over union (mIOU) of most models under the CSF-CrackNet framework can be increased to above 80 %. Compared with original RGB and depth images, the average mIOU increases with image fusion by 10 % and 5 %, respectively. The ablation experiment and weight significance analysis further demonstrate that CSF-CrackNet can significantly improve semantic segmentation performance by balancing information between 2D and 3D images.

Computer vision-based semantic segmentation methods are currently the most widely used for automated detection of structural cracks in buildings and pavements. However, these methods face persistent challenges in detecting fine cracks with small widths and in distinguishing cracks from background stains. This paper addresses these issues by introducing MambaCrackNet, a new network architecture for pixel-level crack segmentation. MambaCrackNet incorporates residual visual Mamba blocks and integrates visual Mamba and convolutional neural network-based segmentation techniques. This approach effectively enhances the detection of fine cracks, reduces misdetections of background stains, and remains robust to variations in patch size and training sample sizes, making it highly practical for engineering applications. On two open access crack datasets, MambaCrackNet outperformed mainstream crack segmentation models, achieving MIoU scores of 0.8939 and 0.8560 and F1-scores of 0.8817 and 0.8412.

Road maintenance is crucial for road comfort. Inappropriate maintenance construction works may cause waste in budget and extra greenhouse gas emissions. Previous studies designed construction plans based on experience and the current distress stage of the road, without considering the cost and carbon emissions between different construction plans throughout the life cycle. The road deterioration tendency, however, is complicated and depends on multiple factors. This paper presents a two-layer multi-objective optimization maintenance decision support system based on 10-year maintenance and inspection historical data. Pareto frontier is used to provide a maintenance construction plan to a hundred-meter interval. A case study demonstrates that this approach can increase road performance by 6.6 %, reduce costs by 69.56 %, and reduce carbon emissions by 88.2 % compared with the practical maintenance plan. This study considered the data-driven deterioration tendency, carbon emission, and cost associated with various construction methods in maintenance strategy formulation.

Damage identification in post-earthquake reinforced concrete (RC) structures based on semantic segmentation has been recognized as a promising approach for rapid and non-contact damage localization and quantification. In damage segmentation tasks, damage regions are often set against complex backgrounds, featuring irregular geometric boundaries and intricate textures, posing significant challenges to model segmentation performance. Additionally, the absence of public datasets exacerbates these challenges, hindering advancements in this field. In this paper, a pyramid Haar wavelet downsampling attention UNet (PHA-UNet) semantic segmentation network is proposed, and a database containing 1400 images of damaged RC components (PEDRC-Dataset) with pixel-level annotations is established. In the proposed PHA-UNet, attention mechanisms, multiscale feature fusion, Haar wavelet downsampling, and transfer learning are introduced to address above challenges. Finally, the proposed PHA-UNet is compared with four existing image segmentation architectures on both the Cityspace and the PEDRC-Dataset.

The accurate assessment and effective management of deep excavation risk have faced longstanding challenges due to the highly complicated and uncertain construction process. A digital twin, designed with the data-mechanism-fused (DMF) physical and virtual models, is developed to solve problems by integrating Building Information Modeling (BIM), data mining (DM), and physical mechanisms. In the DMF physical model, a mechanical model is embedded into the digital twin to implement real-time interaction and inversion between field-measured and simulated data, thus revealing the evolution law of mechanical properties and creating a multi-source DMF database. In the virtual model, the random forest (RF) regression is applied to fully learn the multisource database and accurately predict retaining wall behaviors on behalf of excavation risk. The proposed digital twin facilitates practical applications to imitate physical construction process, predict excavation-induced behavior, and realize closed-loop risk management with a high degree of automation, intelligence, and reliability.

Falling hazards pose significant health and safety risks to workers. This paper investigated the correlation between visual attention and brain activity in the recognition of human and object falling hazards. Seventy construction workers were recruited and asked to identify hazards depicted in images while undergoing eye tracking and electroencephalography. Raw electroencephalography and eye movement data were cleaned using band-pass filtering and independent component analysis. The time-frequency representation method was then employed to compute the fixed correlation power spectrum. Compared with fixation onset, a distinct time lag in brain responses was observed during the identification of human and object falling hazards. The different refixations typically occurred around the peak of fixation-related power, corresponding to different trends over time. These results may help to enhance construction safety management based on physiological monitoring, provide a design basis for brain–computer interface safety warning devices, and improve the efficiency of hazard identification.

Predictive maintenance decisions can promote resilient sewers, however, interpretable and accurate corrosion predictions are challenging because of the dynamics of corrosion stages and environmental conditions. In this paper, a 3D point-cloud data-based Bayesian model updating approach is presented to predict the critical parameter evolution of concrete sewer corrosion. The proposed approach adopts a novel distribution-based updating strategy to address the multivariate and asymmetric nature of massive point-cloud data. The effectiveness of the proposed method is investigated using two publicly available sewer corrosion datasets from Perth, Australia and Texas, USA. The Perth case results show that critical parameters after Bayesian updating have the same trends as the in situ monitoring data, which provides interpretability for ultimate decision-making. The Texas case results show that the proposed framework enables more accurate service life predictions than the non-updated Pomeroy model. The proposed approach achieves interpretable and intelligent decision-making, contributing to improved sewer predictive maintenance.

Blockchain and Interplanetary File System (IPFS) integration holds great promise for enhancing transparency and traceability in precast construction supply chain management (PCSCM). However, such integration faces challenges regarding unauthorized access to confidential data, which can lead to significant consequences, such as financial losses and legal issues. Regarding this gap, this paper proposes a hybrid privacy-preserving access control mechanism for securing blockchain-IPFS information-sharing in PCSCM with confidentiality considerations. Multiple privacy-preserving techniques (e.g., information-sharing channels, symmetric and asymmetric encryption, and lightweight proxy re-encryption) are leveraged. A prototype system demonstrates its feasibility and effectiveness, achieving demonstrably low network latency (millisecond level), efficient encryption (millisecond level), and robust data security within both blockchain and IPFS. This research contributes to a deeper understanding of blockchain-IPFS integration and provides a valuable reference point for future research and practical adoption.