Rule-based Mamdani type fuzzy logic model for the prediction of compressive strength of silica fume included concrete using non-destructive test results

• Published in: Neural computing & applications Vol. 22; no. 6; pp. 1133 - 1139
• Main Authors: Subaşı, Serkan, Beycioğlu, Ahmet, Sancak, Emre, Şahin, İbrahim
• Format: Journal Article
• Language: English
• Published: London Springer-Verlag 01-05-2013; Springer
• Subjects: Applied sciences; Artificial Intelligence; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Computer science; control theory; systems; Data Mining and Knowledge Discovery; Exact sciences and technology; General logic; Image Processing and Computer Vision; Learning and adaptive systems; Logic and foundations; Mathematical logic, foundations, set theory; Mathematics; Original Article; Probability and Statistics in Computer Science; Sciences and techniques of general use; Fuzzy logic; Compressive strength; Non-destructive testing; Silica fume; Neural computation; Fuzzy system; Experimental test; Prediction theory; Neural network; Silica; Statistical test; Experimental result; Non destructive test; Logic model
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-012-0879-4

In this study, a fuzzy logic model for predicting compressive strength of concretes containing silica fume (SF) (0, 5, 10%) has been developed using non-destructive testing results [ultrasonic pulse velocity (km/s) and Schmidt hardness (
R
)]. Experimental results of non-destructive tests and the amount of the SF were used to construct the model. Result have shown that fuzzy logic systems have strong potential for predicting 7, 28, and 90 days compressive strength using ultrasonic pulse velocity (km/s), Schmidt hardness (
R
), and silica fume content (%) as inputs.