Ensemble machine learning model for corrosion initiation time estimation of embedded steel reinforced self-compacting concrete

Published on Dec 1, 2020in Measurement3.364
· DOI :10.1016/J.MEASUREMENT.2020.108141
Babatunde Abiodun Salami6
Estimated H-index: 6
(UPM: King Fahd University of Petroleum and Minerals),
Syed M Rahman6
Estimated H-index: 6
(UPM: King Fahd University of Petroleum and Minerals)
+ 2 AuthorsSalah U. Al Dulaijan1
Estimated H-index: 1
(UPM: King Fahd University of Petroleum and Minerals)
Sources
Abstract
Abstract Corrosion initiation time of embedded steel is an important service life parameter, which depends on concrete material make-up, exposure environment, and duration of exposure. The determination of corrosion initiation time in the laboratory is arduous due to the activities involving the data gathering process. This study leverages the capability of machine learning (ML) models to estimate corrosion initiation time of embedded steel through corrosion potential measurement. Self-compacting concrete specimens were prepared with limestone powder addition to Portland cement. The corrosion potentials of the embedded steel in the specimens were measured during their exposure to 5% sodium chloride for an 8-month exposure period. Models were developed to estimate the corrosion potential of embedded steel using concrete mixtures and exposure periods as input variables. Comparing the performance results of the algorithms using correlation coefficient (CC) and root mean square error (RMSE) proved that random forest, an ensemble ML technique, to be the most efficient in estimating the corrosion initiation time of embedded steel in SCC.
📖 Papers frequently viewed together
2013
18 Citations
References63
Newest
#1Jonbi JonbiH-Index: 3
#2Mohamad Ali Fulazzaky (Ton Duc Thang University)H-Index: 4
Abstract The use of fly ash as a cement substitute may reduce the increasing cement demand and prevents an increased emission of carbon dioxide (CO2) into the atmosphere. This study aims to produce some compositions of geopolymer paving block (GPB) using different ratios of NaOH/Na2SiO3 combined with fly ash. The empirical models were developed to predict the performance of the GPB samples through the verification of the water absorption and compressive strength. The results showed that an optim...
4 CitationsSource
#2Musa Hakan ArslanH-Index: 9
Last. Ahmet OzkisH-Index: 1
view all 4 authors...
Abstract In this study, to observe the behavior of chemical anchors embedded in concrete under the tensile effect, 108 different anchor specimens were prepared with different parameters as concrete compressive strength, reinforcement bar diameters, anchor depths, sizes of drilled holes, cleanliness of the drilled holes. Pull-out tests were conducted and obtained data were examined with the axial-load capacities and the failure situations. Finally, the depth of anchors, compressive strength and r...
5 CitationsSource
#1Christoph Völker (BAM: Bundesanstalt für Materialforschung und -prüfung)H-Index: 25
#1Christoph Völker (BAM: Bundesanstalt für Materialforschung und -prüfung)H-Index: 2
Last. Gino Ebell (BAM: Bundesanstalt für Materialforschung und -prüfung)H-Index: 4
view all 3 authors...
This work presents machine learning-inspired data fusion approaches to improve the nondestructive testing of reinforced concrete. The principal effects that are used for data fusion are shown theoretically. Their effectiveness is tested in case studies carried out on large-scale concrete specimens with built-in chloride-induced rebar corrosion. The dataset consists of half-cell potential mapping, Wenner resistivity, microwave moisture and ground penetrating radar measurements. Data fusion is bas...
3 CitationsSource
#1Trilok GuptaH-Index: 13
#2K.A. Patel (Institute of Infrastructure Technology Research and Management)H-Index: 1
Last. Sandeep Chaudhary (IITI: Indian Institute of Technology Indore)H-Index: 20
view all 5 authors...
Abstract Considering scarcity of natural sand, waste rubber tyre can be an alternate ingredient for replacement of conventional fine aggregates in the production of concrete. Use of the waste rubber tyre in building materials is beneficial from sustainable and economical points of view. A systematic and comprehensive experimental study was conducted earlier by the authors for the mechanical and durable properties of rubberised concrete subjected to elevated temperature. However, there is non-ava...
19 CitationsSource
#1Qinghua Han (CEA: China Earthquake Administration)H-Index: 2
#2Changqing Gui (MOE: Chinese Ministry of Education)H-Index: 1
Last. Giuseppe Lacidogna (Polytechnic University of Turin)H-Index: 37
view all 4 authors...
Abstract The prediction results of high-performance concrete compressive strength (HPCCS) based on machine learning methods are seriously influenced by input variables and model parameters. This study proposes a method with two stages to select proper variables, simplify parameter settings, and predict HPCCS. The appropriate variables are selected in the first stage by measuring their importance based on random forest, and then are optimized to predict HPCCS in the second stage. The results show...
27 CitationsSource
#1Bradley C. BoehmkeH-Index: 8
#1Brad BoehmkeH-Index: 2
Last. Brandon Greenwell (Wright State University)H-Index: 7
view all 2 authors...
53 CitationsSource
#1Yuguo Yu (UNSW: University of New South Wales)H-Index: 9
#2Di Wu (UNSW: University of New South Wales)H-Index: 24
Last. Wei Gao (UNSW: University of New South Wales)H-Index: 31
view all 5 authors...
Abstract The adverse impacts of material deterioration on structural durability and human safety have become increasingly recognised. This paper is concerned with novel metamodeling on the degradation of cementitious composites and structures under environmental attacks. The material deterioration represents a chemophysical process, consisting of the reactive transportations of multiple species. Various coupling effects and associated uncertainties, both material and environmental, may be involv...
10 CitationsSource
#1Gokhan Bayar (Zonguldak Karaelmas University)H-Index: 2
#2Turhan Bilir (Istanbul University)H-Index: 17
Abstract In this study, the crack pattern and propagation in a random concrete surface has been examined using machine learning algorithm called voronoi diagrams. A random photo of a concrete crack located on the surface is taken from a common source and the crack dimensions and directions have been measured. After then, the crack has been divided into 12 parts to evaluate the machine learning algorithm’s capability for estimating the crack pattern including its direction. Consequently, it has b...
18 CitationsSource
#1Ali Bagheri (Swinburne University of Technology)H-Index: 11
#2Ali Nazari (Swinburne University of Technology)H-Index: 51
Last. Jay Sanjayan (Swinburne University of Technology)H-Index: 66
view all 3 authors...
Abstract This paper employs artificial intelligence methods in order to create a function for compressive strength of the boroaluminosilicate geopolymers based on mixture proportion variables. Boroaluminosilicate geopolymers (BASGs), a group of boron-based alkali-activated materials, not only minimise the carbon footprint in the construction industry but also decrease the consumption of energy and natural resources. Australian fly ash and iron making slag are activated in sodium and boron-based ...
10 CitationsSource
#1Nhat-Duc Hoang (Duy Tan University)H-Index: 24
Abstract Estimating punching shear capacity is an important task in the design of steel fibre reinforced concrete (SFRC) flat slabs. The accuracy of commonly employed empirical design equations can potentially be improved with the use of machine learning. This study relies on a piecewise multiple linear regression (PMLR) and artificial neural network (ANN) approaches to construct a prediction model that can approximate the mapping function between the punching shear capacity of SFRC flat slabs a...
17 CitationsSource
Cited By7
Newest