Large concrete structures need to be inspected in order to assess their current physical and functional state, to predict future conditions, to support investment planning and decision making, and to allocate limited maintenance and rehabilitation resources. Current procedures in condition and safety assessment of large concrete structures are performed manually leading to subjective and unreliable results, costly and time-consuming data collection, and safety issues. To address these limitations, automated machine vision-based inspection procedures have increasingly been proposed by the research community. This paper presents current achievements and open challenges in vision-based inspection of large concrete structures. First, the general concept of Building Information Modeling is introduced. Then, vision-based 3D reconstruction and as-built spatial modeling of concrete civil infrastructure are presented. Following that, the focus is set on structural member recognition as well as on concrete damage detection and assessment exemplified for concrete columns. Although some challenges are still under investigation, it can be concluded that vision-based inspection methods have significantly improved over the last 10 years, and now, as-built spatial modeling as well as damage detection and assessment of large concrete structures have the potential to be fully automated.
In emergency scenarios, immediate reconnaissance efforts are necessary. These efforts often take months to complete in full. While underway, building occupants are unable to return to their homes/businesses, and thus, the impact on the society of the disaster-stricken region is increased. In order to mitigate the impact, researchers have focused on creating a more efficient means of assessing the condition of buildings in the post-disaster state. In this paper, a machine vision-based methodology for real-time post-earthquake safety assessment is presented. A novel method of retrieving spalled properties on reinforced concrete (RC) columns in RC frame buildings using image data is presented. In this method, the spalled region is detected using a local entropy-based approach. Following this, the depth properties are retrieved using contextual information pertaining to the amount and type of reinforcement which is exposed. The method is validated using a dataset of damaged RC column images.
Drift capacity of reinforced concrete (RC) columns is an important indicator to quantify the seismic vulnerability of RC frame buildings; however, it is challenging to accurately predict this value as the nonlinear behavior can vary greatly by column type. This article proposes a novel, local machine learning (ML) model, called locally weighted least squares support vector machines for regression (LWLS‐SVMR), which integrates LS‐SVMR and locally weighted training criteria to enhance and generalize the prediction of the drift capacity of RC columns, regardless of the type. A database of 160 circular RC columns covering flexure‐, shear‐, and flexure–shear‐critical specimens was developed to train and test the proposed LWLS‐SVMR. The proposed LWLS‐SVMR was validated by comparison with popular existing global and local learning approaches as well as a traditional empirical equation, and the results demonstrated that the proposed LWLS‐SVMR is superior to all other approaches and thus, is a promising artificial intelligence technique for enhancing the prediction of drift capacity, universally across RC flexure‐, shear‐, and flexure–shear‐critical columns. The LWLS‐SVMR exhibits capabilities which may yield it a feasible approach to predict complex, nonlinear behavior in a broad‐spectrum manner.
12Pressurized fresh-water fluid-distribution networks are key strategic infrastructure elements. 13 On average, 20% of water is lost by way of leaks around the world. This illustrates the need for 14 more efficient management of pressurized fluid-distribution networks. This paper presents a 15 system identification methodology known as error-domain model falsification adapted for 16 performance assessment of water distribution networks and more specifically, to detect leak 17 regions in these networks. In addition, a methodology to approximate the demand at nodes in 18 water-supply networks is presented and a methodology for estimating uncertainties through 19 experimentation is described. The use of error-domain model falsification for practical use in 20 water distribution networks shows great potential. Finally, two case studies are presented. The 21 first case study is from the water-distribution network of the city of Lausanne. An experimental 22 campaign was carried out on this network to simulate leaks by opening hydrants. The second 23 case study is from a water-distribution network of the commune of Bagnes, and a leak scenario 24 was evaluated. These two case studies illustrate, using full-scale measurements, the potential 25 of error-domain model falsification for the performance assessment of water-distribution 26 networks. 27 28 29Moser, G., Paal, S.G. and Smith, I.F.C. "Leak detection of water supply networks using error-domain model falsification"Annually, 184 billion USD are spent on clean water supply worldwide. However, collectively, 31 water utilities lose an estimated 9.6 billion USD each year due to water leakage (Sensus 2012). 32Water supply networks lose an average of 20% of their water supply ( Figure 1). The Sensus 33 report also includes an estimate that if leaks were reduced by 5% and pipe bursts by 10%, 34 utilities could save up to 4.6 billion USD. 35 Currently, most utilities react to leakage on an ad-hoc basis, responding to leaks and bursts and 36 repairing infrastructure only as required by leakage events. There is a need for more rational 37 and systematic strategies for managing infrastructure. Monitoring of water-supply networks 38 could support this need and sensor-based diagnostic methodologies have the potential to 39 provide enhanced management support. 40 Detecting leaks in water distribution networks is not a new challenge. Several studies over the 41 past century have involved leak detection in fresh-water supply-networks. Hope (1892) studied 42 water losses, and Babbitt et al. (1920) described examples of leak-detection methods such as 43 visual observation and sounding through the soil with a steel rod. Water-hammer techniques 44 and acoustic measurements, considered to be more advanced leak detection techniques, have 45 also been developed. In addition, water loss and related costs have been highlighted for many 46 decades (Niemeyer 1940; Johnson 1947). 47 Studies involving various leak-detection methodologies have continued into this century. Leak-48 noise corre...
14This paper presents a methodology for comparing the performance of model-reduction strategies 15 to be used with a diagnostic methodology for leak detection in water distribution networks. The 32Finally this paper describes a Pareto analysis that is used to select the reduction strategy that is a 33 good compromise between reduction of computational time and performance of the diagnosis. In 34 this context, the extension strategy is the most attractive. 35 36
Small data sets are an extremely challenging problem in the machine learning (ML) realm, and in specific, in regression scenarios, as the lack of relevant data can lead to ML models that have large bias. However, there are many applications for which a purely data‐driven procedure would be advantageous, but a large amount of data are not available. This article proposes a novel regression‐based transfer learning (TL) model to address this challenge, where TL is defined as knowledge transfer from a large, relevant data set (source domain data) to a small data set (target domain data). The proposed TL model is termed double‐weighted support vector transfer regression (DW‐SVTR), which couples least squares support vector machines for regression (LS‐SVMR) with two weight functions. The first weight function uses kernel mean matching (KMM) to reweight the source domain data such that the mean values of the source and target domain data in a reproduced kernel Hilbert space (RKHS) are close. In this way, the source domain data points relevant to the target domain points have a larger weight than irrelevant source domain points. The second weight is a function of estimated residuals, which aims to further reduce the negative interference of irrelevant source domain points. The proposed approach is assessed and validated via simulated data and by enhanced shear strength prediction of nonductile columns based on limited availability of nonductile column data. Specifically, the results for the latter show that the proposed DW‐SVTR can reduce the root mean square error (RMSE) by 34% and enhance the coefficient of determination (R2) by 229%. These numerical results demonstrate that the DW‐SVTR significantly reduces the effect of small sample bias and improves prediction performance compared to standard ML methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.