A Comparative Study Using ANFIS and ANN for Determining the Compressive Strength of Concrete

Veena Kashyap, Arunava Poddar, Navsal Kumar, Rabee Rustum

Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)peer-review

Abstract

The determination of compressive strength (CS) of concrete is carried out by using soft computing techniques (ANFIS and ANN). Ninety-three observations were extracted from various literatures. Sixty-five random data points from the whole data set were used for training, leaving 28 for testing. Aspect ratio, percentage of fiber, and the number of days were used as input parameters to predict the CS of concrete by using coconut fiber. This chapter concluded that ANFIS triangular-based model performs well for the determination of CS of concrete with a coefficient of correlation, root mean square error and mean absolute error values of 0.97, 1.56, and 1.01 and 0.84, 3.87, and 2.70 for the training data set and testing stage respectively as compared to other membership functions. The results showed the improved execution of the ANFIS model as compared to the ANN model for determining the CS of concrete.
Original languageEnglish
Title of host publicationApplications of Computational Intelligence in Concrete Technology
EditorsSakshi Gupta, Parveen Sihag, Mohindra Singh Thakur, Utku Kose
PublisherCRC Press
Chapter5
Number of pages19
ISBN (Electronic)9781003184331
DOIs
Publication statusPublished - 2022

Fingerprint

Dive into the research topics of 'A Comparative Study Using ANFIS and ANN for Determining the Compressive Strength of Concrete'. Together they form a unique fingerprint.

Cite this