Construction Site Research Articles

Review of AGV Obstacle Avoidance Algorithm Based on Machine Vision

With the development trend of unmanned and intelligent, it has become a development trend for AGV to leave human operators and perform diversified tasks. However, operating in complex environments such as urban streets, mines, and construction sites is a difficult problem that needs to be solved currently. Obstacles in complex environments pose a serious threat to the AGV trolley in operation. Obstacle avoidance technology has become a key part of the AGV trolley’s task decision-making system and plays an important role in ensuring the safe operation of the AGV trolley and improving work efficiency. This article first elaborates on the concept of the AGV trolley obstacle avoidance algorithm and the evaluation criteria for the optimal path, then elaborates and compares the advantages and disadvantages of different types of obstacle avoidance algorithms such as optimization-based, potential field-based, and machine learning-based obstacle avoidance algorithms, and finally obtains the research focus and direction of the AGV trolley.

An Image-Based Intelligent System for Addressing Risk in Construction Site Safety Monitoring Within Civil Engineering Projects

In the construction industry, safety is of paramount importance given the complex and dynamic nature of construction sites, which are prone to various hazards, like falls from heights, being hit by falling objects, and structural collapses. Traditional safety management strategies, such as manual inspections and safety training, have shown significant limitations. This study presents an intelligent monitoring and analysis system for construction site safety based on an image dataset. A specifically designed Construction Site Safety Image Dataset, comprising 10 distinct classes of objects, is utilized and divided into training, validation, and test subsets. InceptionV3 and MobileNetV2 are chosen as pre-trained models for feature extraction and are modified through truncation and compression to better suit the task. A novel feature fusion architecture is introduced, integrating these modified models, along with a Squeeze-and-Excitation block. Experimental results demonstrate that the proposed model achieves a mean average precision (mAP) of 0.90 at an IoU threshold of 0.5, with high accuracies for classes like “Safety Cone” (91%) and “Machinery” (93%) but relatively lower accuracy for “Vehicle” (57%). The training process exhibits smooth convergence, and compared to prior methods, such as YOLOv4 and SSD, the proposed framework shows superiority in regard to precision and recall. Despite its achievements, the system has limitations, including reliance on visual data and dataset imbalance. Future research directions involve incorporating multi-modal data, conducting real-world deployments, and optimizing for edge deployment, aiming to further enhance construction site safety.

Study of the Hydrological and Erosion Characteristics of Typical Spoil Heaps in the Yangtze River Delta of China

Spoil heaps have become a major source of anthropogenic soil erosion, but the hydrological responses and erosion mechanisms of in situ slopes under rainstorms remain poorly understood. We performed simulated rainfall experiments at real estate (Site A), railway (Site B), and railway station (Site C) construction sites, as well as spoil sites (Site D) in China’s Yangtze River Delta. Rainfall parameters, surface runoff, interflow, vertical soil moisture profiles, and sediment yield were monitored: (1) Hydrological responses differed significantly across the sites due to soil structure complexity; stable erosion after the first rainfall event was not achieved at any site except Site C. Soil erosion was the strongest at Site C, followed by Sites D, B, and A. After the second rainfall event, erosion was stable, increasing, and decreasing at Sites A, B and C, and D, respectively. (2) Runoff and the soil loss rate were positively correlated (R2 > 0.7), and the slopes of the fitted regression lines were highest for Sites B and C, followed by Sites D and A. (3) Soil erodibility values based on field data were 0.0029, 0.1164, 0.1974, and 0.0989 t·hm2·h·hm−2·MJ−1·mm−1 for Sites A, B, C, and D, respectively. (4) The soil bulk density, gravel content, and silt content were key factors contributing to the severe erosion of field spoil heaps. Spoil heaps from different project types exhibited distinct hydrological and erosional behaviors, which necessitates targeted mitigation strategies to reduce severe erosion and landslide risks.

The effectiveness of safety signs on construction sites: A study of key influencing factors and action paths.

Safety signs are an important tool for safety management on the construction site. In order to cope with the current safety challenges faced by the construction industry, it is urgent for us to strengthen the in-depth research and wide application of its scientific and effective nature. Establish an index system of influencing factors for the effectiveness of construction site safety signs, identify key influencing factors, clarify the action path between factors, and put forward improvement measures, in order to significantly reduce the safety risk of construction site, ensure the safety of construction personnel and the smooth progress of operation. Social Network Analysis (SNA) was used to identify the key influencing factors and key action paths of the effectiveness of safety signs on construction sites. The influencing factor index system includes 4 first-level indicators and 35 second-level indicators, establishes a social network of influencing factors for the effectiveness of construction site safety signs. The results show that among the 15 key influencing factors, organizational factors account for a large proportion, revealing the important position of organizational factors in safety sign management. According to the analysis results of the action path, the degree of sign damage has a comprehensive impact on the effectiveness of safety signs, and the attitude of management and management measures have direct and indirect effects. Based on the research results, this paper analyzes and puts forward suggestions for improvement, in order to better improve the effectiveness of safety signs.

Compressive Strength Behavior of Recycled Concrete with Fine Aggregate Replacement Using Rubber Crumb

The use of recycled materials in concrete has drawn considerable attention in recent years as it means to enhance sustainability, strength, minimize landfill waste, cut carbon emissions and diminish the environmental influence of construction methods. This study focuses on investigating the compressive strength behaviour and sustainability analysis of rubberized concrete incorporating recycled aggregates. In this study, compressive strength tests have been conducted following standardized procedures to assess the load bearing capacity of rubberized concrete at different curing periods. The results will provide valuable information for engineers, researchers, and policymakers engaged in the development and utilization of sustainable construction practices. Recycle aggregates size ranging from 4.75 mm to 25 mm collected from crushing pile head from various construction site are utilized in this experimental research and also rubber crumbs are used as a partial substitute of fine aggregate at percentages of 6%,12%,18% and 25%, while maintaining a constant ratio of cement to water 0.45. The study was conducted at three different curing days of 7 days, 14 days and 28 days. From the test result, it has been noticed that conventional concrete has achieved the most effective result compared to the other percentages of mixtures of rubber crumb. Additionally, the compressive strength has been gradually decreased up to 56.82% in tandem with the increasing percentage of rubber crumb replacement in the specimens.

Recent Techniques for Automated Construction Site Monitoring and Management

Recent Techniques for Automated Construction Site Monitoring and Management

Follow me or get out of my way! Leadership styles in the Irish construction industry

In Ireland, research has identified that when it comes to management styles across all industries, Irish managers are among the most easy-going in Europe. However, the dynamic and complex nature of the construction industry makes management and leadership much more difficult compared with other industries, where relationships between the workforce are more fluid. Therefore, this study aims to identify and analyse leadership styles used in the Irish construction industry and document which styles, if any, are the most successful to implement in practice on-site. This pilot study encompasses a qualitative research method, incorporating seven semi-structured individual interviews with construction professionals in various management and leadership roles on projects across Ireland. The data are qualitatively assessed using thematic analysis, and the results are centred around four key themes: the characteristics of effective leaders; how leaders create a vision; how leaders motivate the workforce; and how leadership is used as a success factor on construction projects. Results indicate that sometimes various styles are used simultaneously or in an ad hoc manner, depending on the situation. Overall, the key contribution of this research encourages a more formalised and strategic approach to delivering leadership on-site and ensuring project success on construction sites in Ireland.

Determinants of smart locker adoption in last mile construction retail

PurposeSmart lockers have emerged as an innovative technology to address the challenges of last mile delivery. The increasing difficulty in accessing construction sites, exacerbated by denser traffic and limited space in urban centres, could be alleviated through centralized collection hubs. However, consumer willingness to adopt this solution remains crucial. This study aims to identify the critical success factors influencing the adoption of smart lockers for last-mile deliveries, focusing on the construction materials retail sector.Design/methodology/approachCritical success factors of the adoption of smart lockers were identified based on the theories of Resource Matching Theory, the Theory of Transaction Cost Economics and the Theory of Perceived Value. Subsequently, by using DEMATEL, the relative relevance of each factor was observed, as well as the cause-and-effect relationships between pairs of factors.FindingsThe results indicate that perceived value is the most influential factor from the respondents’ perspective. In the decision-making process, convenience, reliability and relative advantage were identified as priorities. Transaction costs were found to be the least significant among effect factors, while privacy assurance was ranked as the lowest in importance compared to other factors.Originality/valueGrounded in Resource Matching Theory, Transaction Cost Economics and the Theory of Perceived Value, this study explores the interconnections among factors affecting consumer adoption of smart lockers in the retail. It offers practical insights for construction material companies to effectively implement smart lockers in their last-mile delivery systems.

A Critical Analysis of Enhancing Health and Safety for Productivity in the Construction Industry

The construction sector is among the most dangerous sectors in the world which presents unique risks to occupational health and safety. It faces a wide range of occupational health and safety risks and related threats to worker productivity, which have consistently resulted in a high number of workplace injuries including fatal ones and worker productivity losses along with the ensuing problems with quality, cost, time, etc. As a result, of all industries, the construction sector has the second-highest rate of workplace fatalities The main objective of this study was to provide a framework for leveraging Building Information Modelling (BIM) to create a productivity and safety monitoring system and to critically analyze how using Building Information Modelling (BIM) might help the construction sectors in Singapore become more productive and perform better in terms of safety. The study developed IPASS to manage risk by controlling hazards by considering important safety and productivity factors at the project level, adhering to the conceptual framework. This development was done in five main steps. The first step was a literature review, the second was a review of case studies, the third was questionnaire design, the fourth was data collection analysis and the fifth was the integration of productivity and safety using BIM. These results showed the creation of IPASS, which can analyze data from BIM models to produce productivity and safety rankings for building projects. The study showed how BIM may be used to track safety and productivity as a project develops and improves performance in both areas. It was proposed that IPASS makes it possible for project stakeholders to collaborate since they may base their work on evaluations of safety and productivity performance both before and after projects begin. For the IPASS application, it is recommended that the BIM model that has been provided to the authorities should be utilized for the productivity and safety of construction sites in Singapore.

Framework of an Implementation Strategy for a Modular Construction Toolkit Design in Construction Companies

This paper presents a production flow-oriented framework for measuring and enhancing productivity in construction projects. Departing from traditional resource-based approaches, the proposed framework integrates value stream mapping with advanced simulation techniques and real-world data acquisition to comprehensively assess process performance. The simulation model employs a Monte Carlo method, incorporating lognormal distributions to generate realistic process durations for key construction activities. This approach effectively captures both central tendencies and variability while preventing the occurrence of unrealistically short process times. Data were collected from an actual construction site in Munich, where piles were constructed using Kelly drilling machines with a diameter of 50 cm and a depth of 12 m, followed by reinforcing and concreting. On-site measurements were obtained via manual recording and automated sensor technologies, including camera-based monitoring and data from construction equipment. The simulated and measured process times were compared using density graphs and statistical indicators. This showed that some of the processes are very similar to the reference processes but that there are also significant differences in variability and durations. These findings highlight the necessity for process-specific productivity benchmarks and underscore the importance of a flexible, production flow-oriented approach that can be adopted to the unique operational requirements of individual companies. The framework provides a robust tool for productivity assessment and offers practical insights for optimizing construction processes and reducing schedule variability.

Study on the Failure Mechanism of Deep Foundation Pit of High-Rise Building: Comprehensive Test and Microstructure Coupling

Under the adverse geological conditions of silty soft soil in coastal, lakeside, and river areas of countries worldwide, safety and quality during deep foundation pit construction are research challenges that researchers must overcome. Through 3D simulation, micro-finite element coupling modeling and construction site monitoring tests, this paper comprehensively analyzes the formation mechanism and causes of deep foundation pit foundation quality defects and diseases under the most unfavorable environment and multi-factor interference and puts forward scientific treatment suggestions. The research process accurately applies multidisciplinary coupling model research such as computer science, instrument science and technology, and material mechanics to solve the impact of multi-factor and uncertain environments on construction. The final research results provide sufficient theoretical and physical cases for improving the safety and stability of deep foundation pits under soft foundation conditions and provide rich practical specifications for the testing, monitoring and construction of similar projects; it provides a strong guarantee for the global deep foundation pit monitoring and early warning system under soft foundation conditions.

SD-YOLOv5: a rapid detection method for personal protective equipment on construction sites

With the rapid growth of urbanization, construction sites are increasingly confronted with severe safety hazards. Personal protective equipment (PPE), such as helmets and safety vests, plays a critical role in mitigating these risks; however, ensuring proper usage remains challenging. This paper presents SD (Small object detection and DilateFormer attention mechanism)-YOLOv5s, an improved PPE detection algorithm based on YOLOv5s, designed to enhance the detection accuracy of small objects, such as helmets, in complex construction environments. The proposed model incorporates a dedicated feature layer for small target detection and integrates the DilateFormer attention mechanism to balance detection performance and computational efficiency. Experimental results on the CHV dataset demonstrate that SD-YOLOv5s achieves an average precision (AP) of 93.7%, representing an improvement of 2.8 percentage points over the baseline YOLOv5s (AP = 90.9%), while reducing the model’s parameter count by up to 14.6%. These quantitative improvements indicate that SD-YOLOv5s is a promising solution for real-time PPE monitoring on construction sites, although further validation on larger and more diverse datasets is warranted.

Lightweight construction safety behavior detection model based on improved YOLOv8

This paper studies a lightweight construction safety behavior detection model based on improved YOLOv8, aiming to improve the detection accuracy of safety behaviors on construction sites and achieve lightweight models. YOLO (You Only Look Once) is an object detection algorithm that can achieve real-time and efficient object detection by dividing images into grids and predicting the bounding boxes and categories of objects in each grid. Traditional YOLO models often have problems of missed detection and insufficient feature processing when dealing with complex scenes, especially when facing large-scale data sets. In order to solve this problem, this paper improves on the basis of YOLOv8 and uses a lighter Mobilenetv3 as the backbone network to replace the original CSPDARKNET53 to reduce the amount of calculation and improve the processing speed. At the same time, the receptive field is expanded by combining the Receptive Field Block (RFB) module, the ability to capture multi-scale features is enhanced, and the Global Attention Mechanism (GAM)-Attention mechanism is introduced to enhance the recognition ability of local features. Through experimental results, the improved YOLOv8 model performed excellently in detecting five common unsafe behaviors of construction workers, with an mAP of 0.86, a precision of 0.84, a recall rate of 0.87, an F1 value of 0.85, and an IoU of 0.8, which are significantly better than traditional methods. This shows that the model has successfully achieved the goal of lightweight while improving detection accuracy, and has broad application prospects.

Research on Remaining Useful Life Prediction Method for Bucket Elevator Bearings Based on Multi-module Adversarial Domain Generation

Abstract Predicting the remaining useful life (RUL) of construction site bucket elevators using deep learning faces significant challenges due to variations in working conditions, which lead to data distribution divergences and limit the applicability of traditional transfer learning methods. To overcome these challenges, this study presents the Multi-module Adversarial Regularization and Synthesis for Domain Generalization with Domain-Adversarial Neural
Network (MARS-DG-DANN) framework. The framework integrates a time series predictive auxiliary and regularization model for feature extraction, a deep adversarial generative model to enhance domain generalization, and a multi-source domain adaptation technique for handling augmented domains. It further incorporates innovative methods, including a lossless spiral matrix signal transformation and an alternating training strategy for the generative model. Validation experiments conducted across three distinct conditions demonstrated the robustness and accuracy of the proposed framework in RUL prediction. By effectively addressing domain shifts, the MARS-DG-DANN framework significantly enhances the generalization performance of predictive models, providing a reliable solution for applications under diverse working conditions.

Exploration of UAVs in the Field of Smart Construction

The construction industry is one of the largest sectors in the world. However, traditional construction remains labor-intensive and currently faces numerous challenges, including project delays, poor quality, and management complexity. As a result, there is a rapidly growing demand for digitization and intelligent transformation within the industry. This paper aims to provide an overview of the current utilization and future prospects of UAVs in smart construction. With the advancement of new technologies (wireless communication, high-capacity batteries, and intelligent algorithms), drones are increasingly demonstrating their high-performance capabilities, diverse categories, and versatile applications, and have already made significant inroads in intelligent construction. Based on recent research and developments, this paper explores the applications, challenges, and safety concerns associated with UAVs. A comprehensive discussion is conducted on UAV classifications, current research status, and their applications in popular fields such as smart construction sites and intelligent operation and maintenance (O&M). Finally, research gaps are identified, and future research directions for UAVs are proposed.

Step-by-Step Construction of an RCC Building: A Practical Approach

This paper explains the full construction process of an RCC (Reinforced Cement Concrete) building in a step-by-step way. It starts from clearing the site and goes up to the final finishing of the building. The report includes the tools, materials, and safety measures used during the work. The aim is to help civil engineering students understand how buildings are made on real construction sites and how to apply their classroom knowledge in the field. This project provides a basic and practical understanding of RCC construction for beginners..

The Distinct Seasonality of Early Modern Casual Labor and the Short Durations of Individual Working Years: Sweden 1500–1800

Abstract This article makes use of nearly 25,000 observations representing over 95,000 paid workdays across over 300 years to investigate individual work patterns, work availability, and the changes in work seasonality over time. This sample is comprised of workers in the construction industry, and includes unskilled men and women as well as skilled building craftsmen – the industry that is often used to estimate comparative real wages through early modern Europe. Data come predominantly from Scania, the southernmost region in modern day Sweden, and especially from Malmö, the largest town in the region. Findings indicate that workers probably do not engage in paid labour on a purely labour-supply-based schedule, but are strongly impacted by the demand for construction labour, which was highly seasonal and impacted by local labour institutions. Seasonality was stronger further back in the past, indicating that finding long-term work may have been more difficult in earlier periods. A typical work year could probably not have been longer than 150 days, and would be made up of shorter work spells at several different sites. This is not enough work to meet standard assumptions of 250 days, or enough work for an unskilled man to support his family at a respectable level. Individual workers rarely worked more than a handful of days in a year on a construction site, even when labour demand was high, indicating that they did not maximize their income from waged labour.

Effects of UAV imagery overlap on photogrammetric data quality for construction applications

UAV photogrammetry is a remote sensing method that safely collects spatial data, used in construction inspection, progress tracking, and infrastructure evaluation. This technique generates multiple output products, including point clouds and 3D textured mesh models, using structure-from-motion (SfM) algorithms on UAV-captured photos. Despite its widespread application, the required percentage of aerial imagery overlap—crucial for determining UAV flight patterns, post-processing time, and output quality—remains empirically unsupported and thus arbitrarily defined. Different SfM software can yield varying quality outputs from the same data set, emphasizing the need to evaluate these discrepancies, particularly how overlap percentages affect output quality. This study gathered UAV photogrammetric data from a construction site, created three imagery datasets with varying overlaps, and processed them with two SfM tools, Pix4Dmapper and DroneDeploy. Analysis methods included surface and volume density checks, visual inspections, and defect analysis. Findings suggest that while image overlap percentage crucially impacts output quality, significant differences between high and medium overlaps compared to low overlap were not observed. Optimal results were achieved with a manual UAV operation at 15 meters altitude, 55–60% frontal and 45% side overlaps, a ground sampling distance of 0.4–0.7 cm/pixel, and good lighting, without the need for Ground Control Points.

The Prefabrication of Glued Timber Houses for Residential Construction in Poland

Many countries, including Poland, are currently testing the construction of multi-family houses using a prefabricated system of glued laminated timber (CLT). Poland has a great potential for the application of wood technologies in the housing sector. The purpose of the article is to analyse the real advantages of this technology, as well as the difficulties and threats. It is important to determine the boundary conditions for the location of this type of construction, such as the legal system in force in each country, especially with regard to the fire protection of buildings, the availability of local wood resources, as well as the transport distance between the place of extraction of the raw wood material, the place of production of the CLT panels, the prefabrication of the elements and the final location of the construction site. A separate problem to be considered is overcoming the mental barrier in a society that is accustomed to the durability of a house as a concrete or brick structure, and that associates wood with impermanence. Other bottlenecks to development are the high price of imported panels, the low level of CLT production in Poland and the social acceptance of wooden structures as a long-term, stable and safe housing solution.

Socio-Cultural Context of Aklanon’s House Construction

Abstract The research delved on the Socio – Cultural significance of Aklanon House Construction. Details were kept into consideration and importance such as the construction site, shape of the building, the arrangement of rooms and the position of all structures for house truly influence life’s direction, living and fortune. Through the utilization of qualitative research design specifically narrative inquiry, experiences and cultural beliefs of house builder and constructors can be recognize and be appreciated. The research was conducted at Libacao, in the Southern part of Aklan and considered as one of the oldest towns. Participants were house owners, carpenters, an engineer and an architect. Results revealed that beliefs were attached before, during and house construction. Along with the beliefs and practices, the impact of house construction were household good fortune, feeling of blissfulness, success, harmony, optimism and good life.