Search results

This paper aims to propose a new deep learning technique to detect the type of material to improve automated construction quality monitoring.

A new data augmentation approach that has improved the model robustness against different illumination conditions and overfitting is proposed. This study uses data augmentation at test time and adds outlier samples to training set to prevent over-fitted network training. For data augmentation at test time, five segments are extracted from each sample image and fed to the network. For these images, the network outputting average values is used as the final prediction. Then, the proposed approach is evaluated on multiple deep networks used as material classifiers. The fully connected layers are removed from the end of the networks, and only convolutional layers are retained.

The proposed method is evaluated on recognizing 11 types of building materials which include 1,231 images taken from several construction sites. Each image resolution is 4,000 × 3,000. The images are captured with different illumination and camera positions. Different illumination conditions lead to trained networks that are more robust against various environmental conditions. Using VGG16 model, an accuracy of 97.35% is achieved outperforming existing approaches.

It is believed that the proposed method presents a new and robust tool for detecting and classifying different material types. The automated detection of material will aid to monitor the quality and see whether the right type of material has been used in the project based on contract specifications. In addition, the proposed model can be used as a guideline for performing quality control (QC) in construction projects based on project quality plan. It can also be used as an input for automated progress monitoring because the material type detection will provide a critical input for object detection.

Several studies have been conducted to perform quality management, but there are some issues that need to be addressed. In most previous studies, a very limited number of material types were examined. In addition, although some studies have reported high accuracy to detect material types (Bunrit et al., 2020), their accuracy is dramatically reduced when they are used to detect materials with similar texture and color. In this research, the authors propose a new method to solve the mentioned shortcomings.

This paper aims to propose an automatic imaging network design to improve the efficiency and accuracy of automated construction progress monitoring. The proposed method will address two shortcomings of the previous studies, including the large number of captured images required and the incompleteness and inaccuracy of generated as-built models.

Using the proposed method, the number of required images is minimized in two stages. In the first stage, the manual photogrammetric network design is used to decrease the number of camera stations considering proper constraints. Then the image acquisition is done and the captured images are used to generate 3D points cloud model. In the second stage, a new software for automatic imaging network design is developed and used to cluster and select the optimal images automatically, using the existing dense points cloud model generated before, and the final optimum camera stations are determined. Therefore, the automated progress monitoring can be done by imaging at the selected camera stations to produce periodic progress reports.

The achieved results show that using the proposed manual and automatic imaging network design methods, the number of required images is decreased by 65 and 75 per cent, respectively. Moreover, the accuracy and completeness of points cloud reconstruction is improved and the quantity of performed work is determined with the accuracy, which is close to 100 per cent.

It is believed that the proposed method may present a novel and robust tool for automated progress monitoring using unmanned aerial vehicles and based on photogrammetry and computer vision techniques. Using the proposed method, the number of required images is minimized, and the accuracy and completeness of points cloud reconstruction is improved.

To generate the points cloud reconstruction based on close-range photogrammetry principles, more than hundreds of images must be captured and processed, which is time-consuming and labor-intensive. There has been no previous study to reduce the large number of required captured images. Moreover, lack of images in some areas leads to an incomplete or inaccurate model. This research resolves the mentioned shortcomings.

This study aims to propose the adoption of artificial neural network (ANN)-based prediction intervals (PIs) to give more reliable prediction of labour productivity using historical data.

Using the proposed PI method, various sources of uncertainty affecting predictions can be accounted for, and a PI is proposed instead of a less reliable single-point estimate. The proposed PI consists of a lower and upper bound in which the realization of the predicted variable, namely, labour productivity, is anticipated to fall with a defined probability and represented in terms of a confidence level (CL).

The proposed PI method is implemented on a case study project to predict labour productivity. The quality of the generated PIs for the labour productivity is investigated at three confidence levels. The results show that the proposed method can predict the value of labour productivity efficiently.

This study is the first attempt in construction management to undertake a shift from deterministic point predictions to interval forecasts to improve the reliability of predictions. The proposed PI method will help project managers obtain accurate and credible predictions of labour productivity using historical data. With a better understanding of future outcomes, project managers can adopt appropriate improvement strategies to enhance labour productivity before commencing a project.

Point predictions provided by traditional deterministic ANN-based forecasting methodologies may be unreliable due to the different sources of uncertainty affecting predictions. The current study proposes ANN-based PIs as an alternative and robust tool to give a more reliable prediction of labour productivity using historical data. Using the proposed method, various sources of uncertainty affecting the predictions are accounted for, and a PI is proposed instead of a less reliable single point estimate.

The dilemma faced by many batch‐manufacturing operations is the trade‐off between reducing lead times and manufacturing throughput. Using Little’s Law and the theory‐of‐constraints analysis, the authors have developed a methodology to optimise such dilemmas. The solution to this problem is to find the point in the operation of the plant where throughput is maintained at acceptable levels, but the lead time through the plant is maintained at or near a minimum. At such a point, the optimum level of work in progress (WIP) will be obtained. Such principles have been applied in this research project to a metals manufacturer. The difficulty with this case study is that complexity of the product mix and manufacturing flow renders simple analysis incomplete. By utilising a discrete event simulation of the manufacturing facility, we have been able to identify bottlenecks within the plant. From here we have developed a tool that automatically predicts the optimum level of WIP, depending upon such parameters as product mix and batch sizes. The results show significant improvement over the current practices, and over maintaining a constant WIP level. The results highlight the power of the constraint principles, and the value in evaluating and choosing the best methods for managing change through simulation.

The purpose of this paper is to analyse teleoperation of an ABB industrial robot with an ABB IRC5 controller. A method to improve motion smoothness and decrease latency using the existing ABB IRC5 robot controller without access to any low-level interface is proposed.

The proposed control algorithm includes a high-level proportional-integral-derivative controller (PID) controller used to dynamically generate reference velocities for different travel ranges of the tool centre point (TCP) of the robot. Communication with the ABB IRC5 controller was performed utilising the ABB PC software development kit. The multitasking feature of the IRC5 controller was used to enhance the communication frequency between the controller and the remote application. Trajectory tracking experiments of a pre-defined three-dimensional trajectory were carried out and the benefits of the proposed algorithm were demonstrated. The robot was intentionally installed on a wobbly table and its vibrations were recorded using a six-degrees-of-freedom force/torque sensor fitted to the tool mounting interface of the robot. The robot vibrations were used as a measure of the smoothness of the tracking movements.

A communication rate of up to 250 Hz between the computer and the controller was established using C# .Net. Experimental results demonstrating the robot TCP, tracking errors and robot vibrations for different control approaches were provided and analysed. It was demonstrated that the proposed approach results in the smoothest motion with tracking errors of < 0.2 mm.

The proposed approach may be employed to produce smooth motion for a remotely operated ABB industrial robot with the existing ABB IRC5 controller. However, to achieve high-bandwidth path following, the inherent latency of the controller must be overcome, for example by utilising a low-level interface. It is particularly useful for applications including a large number of short manipulation segments, which is typical in teleoperation applications.

Using the proposed technique, off-the-shelf industrial robots can be used for research and industrial applications where remote control is required.

Although low-level control interface for industrial robots seems to be the ideal long-term solution for teleoperation applications, the proposed remote control technique allows out-of-the-box ABB industrial robots with IRC5 controllers to achieve high efficiency and manipulation smoothness without requirements of any low-level programming interface.

The aim of this study is to examine whether there are significant differences between female and male entrepreneurs’ use of consultation during business start-ups.

Using several statistical tools, including ANOVA and seemingly unrelated regressions, empirical analyses are conducted on a unique and firm-level panel database of 837 female- and 1926 male-owned active small firms.

The results indicate that gender may be an important variable in the use of advice among small business owners in Sweden. Female owners in this study are shown to be more eager than male owners to use external business advice, and do so to a higher extent.

One implication of this study is that firms may not be able to use all business advice types simultaneously during their start-up stage, so an ordered list of consultancy services would help them prioritize and adjust their needs accordingly. Because the use of business advice is context-based, the findings of this study may not be generalized to firms in other countries. This paper shows some gender-based attributes/features relating to the use of business advice, which need to be better integrated into policymaking for the future assistance of small businesses.

This article focuses on an important issue and is unique partly because few studies have examined the relationship between gender and external business advice. By explicitly and empirically examining this issue, this article makes a contribution to the small- and medium-sized enterprises’ literature.