Benny Raphael

Automation of construction processes facilitates increased productivity and overall higher project performance. This paper presents a methodology for comparative assessment of different construction processes and selection of an optimal solution based on appropriate automation implementation. Construction processes are quantitatively evaluated using a methodology combining case-based reasoning and compositional modeling. Through the generation of many combinations of process fragments that are compiled from case libraries, potential solutions are explored and evaluated. An example involving solutions such as RCC frame construction, precast construction, and modular steel frame construction is described in this paper. The study demonstrates the possibility of selection of suitable construction processes based on the quantitative assessment of a large number of potential solutions. Processes are modelled by decomposing them up to the elementary tasks and appropriate level of automation is identified in all the tasks.

Existing studies on automated construction equipment monitoring have focused mainly on activity recognition rather than fault detection. This paper proposes a novel equipment activity recognition and fault detection framework called hybrid unsupervised and supervised machine learning (HUS-ML). HUS-ML first identifies normal operations and known faulty conditions through supervised learning. Then, an anomaly detection algorithm is applied to spot any unseen faulty conditions. The framework is tested using acceleration measurements from a low-rise automated construction system prototype. HUS-ML outperformed the conventional machine learning approach in activity recognition and fault detection with an average F1 score of 86.6%. The conventional approach failed to detect unseen faulty operations. HUS-ML identified known faulty operations and unseen faulty operations with F1 scores of 98.11% and 76.19%, respectively. The generalizability of the framework is demonstrated by validating it on an independent benchmark dataset with good results.

Concrete 3D Printing (3DP) is a potential technology for increasing automation and introducing digital fabrication in the construction industry. Concrete 3D Printing provides a significant advantage over conventional or precast methods, such as the prospects of topologically optimized designs and integrating functional components within the structural volume of the building components. Many previous studies have compiled state-of-art studies in design parameters, mix properties, robotic technologies, and reinforcement strategies in 3D printed elements. However, there is no literature review on using concrete 3D Printing technology to fabricate structural load-carrying elements and systems. As concrete 3DP is shifting towards a large-scale construction technology paradigm, it is essential to understand the current studies on structural members and focus on future studies to improve further. A systematic literature review process is adopted in this study, where relevant publications are searched and analyzed to answer a set of well-defined research questions. The review is structured by categorizing the publications based on issues/problems associated with structural members and the recent technology solutions developed. It gives an overall view of the studies, which is still in its nascent stage, and the areas which require future focus on 3D printing technology in large-scale construction projects.

Light shelves are designed to distribute daylight deeper into the room and reduce energy consumption. While many studies have investigated the daylighting performance of light shelves, there are not much work done on the heat reflected by them. This paper aims to experimentally evaluate the radiant heat reflected from light shelves and analyse the trade-off between the transmission of heat and light. The study involves an experimental setup with controlled conditions and a novel methodology to quantify the reflected radiation. About 5 million data points for heat flux data were collected from light shelves made of eight different materials. Results showed that the mirror glass surface with high specular reflectivity, has maximum direct heat transmission of 10.4 W/m2 along with maximum illuminance. However, aluminium with lesser illuminance than mirror glass exhibits a maximum overall heat transmission of 35.8 W/m2. Also, polished black granite slab showed negligible reflected heat and moderate illuminance. Thus, this study helps us select materials for light shelves to reduce heat transmission without significantly affecting reflected light.

A robust monitoring system is essential for ensuring safety and reliability in automated construction. Activity recognition is one of the critical tasks in automated monitoring. Existing studies in this area have not fully exploited the potential for enhancing the performance of machine learning algorithms using domain knowledge, especially in problem formulation. This paper presents a hierarchical machine learning framework for improving the accuracy of identification of Automated Construction System (ACS) operations. The proposed identification framework arranges the operations to be identified in the form of a hierarchy and uses multiple classifiers that are organized hierarchically for separating the operation classes. It is tested on a laboratory prototype of an ACS, which follows a top-down construction method. The ACS consists of a set of lightweight and portable machinery designed to automate the construction of the structural frame of low-rise buildings. Accelerometers were deployed at critical locations on the structure. The acceleration data collected while operating the equipment were used to identify the operations through machine learning techniques. The performance of the proposed framework is compared with that of the conventional approach for equipment operation identification which involves a flat list of classes to be separated. The performance was comparable at the top level. However, the hierarchical framework outperformed the conventional one when fine levels of operations were identified. The versatility and noise tolerance of the hierarchical framework are also reported. Results demonstrate that the framework is robust, and it is feasible to identify the ACS operations precisely. Although the proposed framework is validated on a full-scale prototype of the ACS, the effects of strong ambient disturbances on actual construction sites have not been evaluated. This study will support the development of an automated monitoring system and assist the main operator to ensure safe operations. The high-level operation details collected for this purpose can also be utilised for project performance assessment and progress monitoring. The potential application of the proposed hierarchical framework in the operation recognition of conventional construction equipment is also outlined.

Purpose: The aim of this paper is to synthesize knowledge related to performance evaluation of automated construction processes during the planning and execution phases through a theme-based literature classification. The primary research question that is addressed is “How to quantify the performance improvement in automated construction processes?” Design/methodology/approach: A systematic literature review of papers on automated construction was conducted involving three stages-planning, conducting and reporting. In the planning stage, the purpose of the review is established through key research questions. Then, a four-step process is employed consisting of identification, screening, shortlisting and inclusion of papers. For reporting, observations were critically analysed and categorized according to themes. Findings: The primary conclusion from this study is that the effectiveness of construction processes can only be benchmarked using realistic simulations. Simulations help to pinpoint the root causes of success or failure of projects that are either already completed or under execution. In automated construction, there are many complex interactions between humans and machines; therefore, detailed simulation models are needed for accurate predictions. One key requirement for simulation is the calibration of the models using real data from construction sites. Research limitations/implications: This study is based on a review of 169 papers from a database of peer-reviewed journals, within a time span of 50 years. Originality/value: Gap in research in the area of performance evaluation of automated construction is brought out. The importance of simulation models calibrated with on-site data within a methodology for performance evaluation is highlighted.

Concrete 3D printing has the potential to reduce material and process waste in construction. Thus, it contributes to making the construction industry more sustainable through the use of digital-fabrication technologies. While concrete 3D printing is attractive due to its potential to realize complex designs, practical challenges include an increased chance of defects and deformities. Quality assessment of 3D-printed elements is essential for large-scale implementation. Workability of concrete is known to decrease with printing time and it impacts extrudability. It is usually visible in 3D-printed elements, with the lower layers having a smooth finish, while the top layers have cracks and discontinuities. A computer-vision-based quality assessment method is proposed in this paper using a two-bin Linear Binary Pattern textural analysis. Information entropy is used as the metric for measuring the texture variation within each layer and its changes over the layers are studied. A higher entropy value is found for layers having deformities. Finally, through the error-minimization technique, a threshold entropy value is calculated and, using this, the printed layers can be assessed and corrective actions taken. This paper contributes to developing a non-intrusive quality assessment technique for concrete 3D-printed elements.

Construction automation helps to improve productivity and project performance. This study demonstrates a methodology for evaluating project performance improvement through appropriate automation of construction processes. This quantitative evaluation approach involves a compositional modeling driven case-based reasoning methodology. Potential processes for executing the activities in a project can be explored by generating combinations of process fragments compiled from cases. This approach is demonstrated through an example of RCC column construction. It is shown that a large number of processes are possible even for simple tasks and a systematic procedure for evaluation is necessary for identifying the appropriate level of automation.

Although the energy efficiency of light shelves has been studied, the thermal effects due to reflected solar radiation from light shelves have yet to be adequately investigated in previous research. The key research questions are whether this radiation results in additional heat load in buildings in tropical climates and how this can be reduced. In this work, the performance of an exterior aluminium light shelf is studied experimentally using a scaled prototype. The total amount of heat transmitted by the light shelf is about 40 W/ m2, which is close to the average thermal transmission of the envelope of a low-energy building. Experimental data analysis has revealed two components of the radiant heat transmitted by a light shelf: a) a direct instantaneous reflection of infrared radiations and b) secondary long-wave radiation resulting from the heating up of the light shelf material. The secondary radiation is a significant part of the overall heat transmitted by the light shelf. The light shelf was actively cooled by circulating water through hydronic radiant capillary mat tubes to reduce this component, and the radiant heat transmitted was measured. These experiments showed that an actively cooled light shelf could considerably reduce the secondary radiant heat transmitted through a clerestory window. A significant decrease in secondary heat transmission within a range of 3.8–5.9 W/m2 was observed when compared to an identical light shelf that was not cooled. This reduction is about 10% of the total heat transmitted by the light shelf.

Machine learning techniques have been successfully implemented for the identification of various construction activities using sensor data. However, there are very few studies on activity recognition in the automated construction of low-rise residential buildings. Automated construction is faster than conventional construction, with minimal human involvement. This requires high accuracy of identification for monitoring its operations. This paper discusses the development and testing of machine learning classifiers to identify normal automated construction operations with high precision. The framework developed in this work involves decomposing the activity recognition problem into a hierarchy of learning tasks in which activities at the lower levels have more details. The top recognition level divides the equipment states into two classes: 'Idle' and 'Operations'. The second recognition level divides the 'operations' into major classes depending on the top-level activities performed by the equipment. The third recognition level further divides the activities into subclasses and so on. Since the number of classes and the similarity between them increase with the recognition level, identification becomes extremely difficult. The identification framework developed in this study classifies operations belonging to the parent class at each level in the hierarchy. The efficacy of this framework is demonstrated with a case study of a topdown modular construction system. In this construction system, the modules of a structural frame are assembled and lifted starting with the top floor followed by the ones below. The accelerometer data collected during top-down construction is used to identify the construction operations. The proposed framework shows superior performance over conventional identification using a flat list of classes.