Using mathematical models and artificial neural networks for predicting the compressive strength of concrete with steel fibers exposed to high temperatures
In this study mathematical methods and artificial neural network (ANN) model are used to predict the compressive strength of concrete with steel fibers exposed at high temperatures. The data used in the models construction were obtained from laboratory experiments. The compressive strength was experimentally determined for specimens containing three volume fractions of steel fibers 0.19%,0.25%, 0.5% were used and two different water/cement ratios (w/c of 0.35 and 0.45). Specimens were subjected to various heating-cooling cycles from the room temperature to 200, 400, and 600°C. The inputs models of ANN were temperature, w/c, percentage of porosity, ultrasonic pulse velocity; percentage of steel fibers and percentage superplasticizer, the output was the compressive strength of concrete. Four mathematical models were development to predict the compressive strength. Three mathematical models including a number of functions to express the strength-porosity relationship, and other model used to establish the relationships between strength and ultrasonic pulse velocity. Mathematical methods, artificial neural network and their results were evaluated and compared. The results show that ANN has good potential to be used as a tool for predicting the compressive strength of concrete with steel fibers exposed to high temperatures.
J. Appl. Eng. Sci. Technol. (JAEST - ISSN 2352-9873) is a peer-reviewed quarterly journal dedicated to the applied engineering sciences and technology. The JAEST provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge.
There is no submission or publication fee for papers published in the JAEST.
Authors who publish in the JAEST agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in the JAEST.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in the JAEST.
- Authors are permitted to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access). Any such posting made before acceptance and publication of the Work shall be updated upon publication to include a reference to the JAEST and a link to the online abstract for the final published Work in the Journal.