Search results

Fall accidents can cause casualties and economic losses in the construction industry. Fall portents, such as loss of balance (LOB) and sudden sways, can result in fatal, nonfatal or attempted fall accidents. All of them are worthy of studying to take measures to prevent future accidents. Detecting fall portents can proactively and comprehensively help managers assess the risk to workers as well as in the construction environment and further prevent fall accidents.

This study focused on the postures of workers and aimed to directly detect fall portents using a computer vision (CV)-based noncontact approach. Firstly, a joint coordinate matrix generated from a three-dimensional pose estimation model is employed, and then the matrix is preprocessed by principal component analysis, K-means and pre-experiments. Finally, a modified fusion K-nearest neighbor-based machine learning model is built to fuse information from the x, y and z axes and output the worker's pose status into three stages.

The proposed model can output the worker's pose status into three stages (steady–unsteady–fallen) and provide corresponding confidence probabilities for each category. Experiments conducted to evaluate the approach show that the model accuracy reaches 85.02% with threshold-based postprocessing. The proposed fall-portent detection approach can extract the fall risk of workers in the both pre- and post-event phases based on noncontact approach.

First, three-dimensional (3D) pose estimation needs sufficient information, which means it may not perform well when applied in complicated environments or when the shooting distance is extremely large. Second, solely focusing on fall-related factors may not be comprehensive enough. Future studies can incorporate the results of this research as an indicator into the risk assessment system to achieve a more comprehensive and accurate evaluation of worker and site risk.

The proposed machine learning model determines whether the worker is in a status of steady, unsteady or fallen using a CV-based approach. From the perspective of construction management, when detecting fall-related actions on construction sites, the noncontact approach based on CV has irreplaceable advantages of no interruption to workers and low cost. It can make use of the surveillance cameras on construction sites to recognize both preceding events and happened accidents. The detection of fall portents can help worker risk assessment and safety management.

Existing studies using sensor-based approaches are high-cost and invasive for construction workers, and others using CV-based approaches either oversimplify by binary classification of the non-entire fall process or indirectly achieve fall-portent detection. Instead, this study aims to detect fall portents directly by worker's posture and divide the entire fall process into three stages using a CV-based noncontact approach. It can help managers carry out more comprehensive risk assessment and develop preventive measures.

The spatial–temporal conflicts in the construction process of concrete arch dams are related to the construction quality and duration, especially for pouring blocks with a continuous high-strength and high-density construction process. Furthermore, the complicated construction technology and limited space resources aggravate the spatial–temporal conflicts in the process of space resource allocation and utilization, directly affecting the pouring quality and progress of concrete. To promote the high-strength, quality-preserving and rapid construction of dams and to clarify the explosion moment and influence degree of the spatial–temporal conflicts of construction machinery during the pouring process, a quantification method and algorithm for a “Conflict Bubble” (CB) between construction machines is proposed based on the “Time–Space Microelement” (TSM).

First, the concept of a CB is proposed, which is defined as the spatial overlap of different entities in the movement process. The subsidiary space of the entity is divided into three layered spaces: the physical space, safe space and efficiency space from the inside to the outside. Second, the processes of “creation,” “transition” and “disappearance” of the CB at different levels with the movement of the entity are defined as the evolution of the spatial–temporal state of the entity. The mapping relationship between the spatial variation and the running time of the layered space during the movement process is defined as “Time–Space” (TS), which is intended to be processed by a microelement.

The quantification method and algorithm of the CB between construction machinery are proposed based on the TSM, which realizes the quantification of the physical collision accident rate, security risk rate and efficiency loss rate of the construction machinery at any time point or time period. The risk rate of spatial–temporal conflicts in the construction process was calculated, and the outbreak condition of spatial–temporal conflict in the pouring process was simulated and rehearsed. The quantitative calculation results show that the physical collision accident rate, security risk rate and efficiency loss rate of construction machinery at any time point or time period can be quantified.

This study provides theoretical support for the quantitative evaluation and analysis of the spatial–temporal conflict risk in the pouring construction process. It also serves as a reference for the rational organization and scientific decision-making for pouring blocks and provides new ideas and methods for the safe and efficient construction and the scientific and refined management of dams.

This study aims to modify the human factors analysis and classification system (HFACS) to make it suitable for collapse accident analysis in construction. Based upon the modified HFACS, distribution patterns of causal factors across multiple levels were discerned among causal factors of various stakeholders at construction sites. It explored the correlations between two causal factors from different levels and further determined causation paths from two perspectives of level and stakeholder.

The main research framework consisted of data collection, coding and analysis. Collapse accident reports were collected with adequate causation information. The modified HFACS was utilized for coding causal factors across all five levels in each case. A hybrid approach with two perspectives of level and stakeholder was proposed for frequency analysis, correlation analysis and path identification between causal factors.

Eight causal factors from external organizations at the fifth level were added to the original HFACS. Level-based correlation analyses and path identification provided safety managers with a holistic view of inter-connected causal factors across five levels. Stakeholder-based correlation analyses between causal factors from the fifth level and its non-adjacent levels were implemented based on client, government and third parties. These identified paths were useful for different stakeholders to develop specific safety plans for avoiding construction collapse accidents.

This paper fulfils an identified need to modify and utilize the HFACS model for correlation analysis and path identification of causal factors resulting in collapse accidents, which can provide opportunities for tailoring preventive and protective measures at construction sites.