Computational Technology Resources - CCP

Keywords: adaptive networked-based fuzzy system, high performance concrete, silica fume, super plasticizer.

Summary

In this paper, the application of an Adaptive Network Based Fuzzy Inference System (ANFIS) in the estimation of compressive strength of high performance concrete (HPC) was investigated. ANFIS is a hybrid structure that is based on fuzzy If-Then Rules that are represented in a network [1]. This system has powerful capability to model the complicated systems. Using some experimental data, ANFIS can adapt its coefficient so that it responds to inputs with minimum errors.

In this research, the properties of concrete have been introduced as input parameters of the ANFIS models. The HPC properties that are used in this paper include fine aggregates (FA), coarse aggregates (CA), water (W), silica fume (SF), super-plasticizer (SP), and cement materials (C). The output of the model is the 28- day compressive strength of HPC.

To predict the compressive strength of HPC with ANFIS, totally 429 records collected from three different resources. Some data was collected from laboratory works carried out in Isfahan University of Technology and a laboratory in Poland. Some other records were collected from concrete mixes made in the Tehran telecommunication tower (Milad tower) construction site. Records were randomly divided into two sets. One set is called training set that is used to train the ANFIS models and another set called testing pairs that were used for evaluation of models performances.

Totally 56 different ANFIS models with various membership functions (MFs) were used to predict the compressive strength of HPC. These models were evaluated with root means square and correlation factors. Finally with comparison of the capabilities of the models, some models were proposed as optimum models. It was found that model with triangular membership function (trimf) and St334333 structure (4 MFs for super plasticizer and 3 MFs for other concrete mix components) is the best model to predict the HPC's compressive strength regarding its components. Moreover the results of the study show that St433333 (4 MF for coarse CA and 3 MFs for other concrete mix components) is the best structure for the ANFIS models with trapezoidal (trapmf), generalized bell-shape (gbellmf), pi- shape (pimf), and Gaussian (gauss2mf) membership functions.

References

1: Jang, J.S.R., "ANFIS: Adaptive-Network-Based Fuzzy Inference System", IEEE, Tran. On System Man, and Cybernetics, Vol. 23, No. 3, May/June, 1993. doi:10.1109/21.256541

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £95 +P&P)

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Proceedings ISSN 1759-3433 CCP: 80 PROCEEDINGS OF THE FOURTH INTERNATIONAL CONFERENCE ON ENGINEERING COMPUTATIONAL TECHNOLOGY Edited by: B.H.V. Topping and C.A. Mota Soares Paper 138 Application of an Adaptive Neuro-Fuzzy System in the Prediction of HPC Compressive Strength A.A. Ramezanianpour+ and J. Sobhani+ and M. Sobhani* +Department of Civil and Environmental Engineering, Amir Kabir University of Technology, Tehran, Iran Department of Graduate Studies, Azad Islamic University, Tehran Southern Branch, Tehran, Iran doi:10.4203/ccp.80.138 purchase the full-text of this paper Full Bibliographic Reference for this paper A.A. Ramezanianpour, J. Sobhani, M. Sobhani, "Application of an Adaptive Neuro-Fuzzy System in the Prediction of HPC Compressive Strength", in B.H.V. Topping, C.A. Mota Soares, (Editors), "Proceedings of the Fourth International Conference on Engineering Computational Technology", Civil-Comp Press, Stirlingshire, UK, Paper 138, 2004. doi:10.4203/ccp.80.138 Keywords:* adaptive networked-based fuzzy system, high performance concrete, silica fume, super plasticizer. Summary In this paper, the application of an Adaptive Network Based Fuzzy Inference System (ANFIS) in the estimation of compressive strength of high performance concrete (HPC) was investigated. ANFIS is a hybrid structure that is based on fuzzy If-Then Rules that are represented in a network [1]. This system has powerful capability to model the complicated systems. Using some experimental data, ANFIS can adapt its coefficient so that it responds to inputs with minimum errors. In this research, the properties of concrete have been introduced as input parameters of the ANFIS models. The HPC properties that are used in this paper include fine aggregates (FA), coarse aggregates (CA), water (W), silica fume (SF), super-plasticizer (SP), and cement materials (C). The output of the model is the 28- day compressive strength of HPC. To predict the compressive strength of HPC with ANFIS, totally 429 records collected from three different resources. Some data was collected from laboratory works carried out in Isfahan University of Technology and a laboratory in Poland. Some other records were collected from concrete mixes made in the Tehran telecommunication tower (Milad tower) construction site. Records were randomly divided into two sets. One set is called training set that is used to train the ANFIS models and another set called testing pairs that were used for evaluation of models performances. Totally 56 different ANFIS models with various membership functions (MFs) were used to predict the compressive strength of HPC. These models were evaluated with root means square and correlation factors. Finally with comparison of the capabilities of the models, some models were proposed as optimum models. It was found that model with triangular membership function (trimf) and St334333 structure (4 MFs for super plasticizer and 3 MFs for other concrete mix components) is the best model to predict the HPC's compressive strength regarding its components. Moreover the results of the study show that St433333 (4 MF for coarse CA and 3 MFs for other concrete mix components) is the best structure for the ANFIS models with trapezoidal (trapmf), generalized bell-shape (gbellmf), pi- shape (pimf), and Gaussian (gauss2mf) membership functions. References 1 Jang, J.S.R., "ANFIS: Adaptive-Network-Based Fuzzy Inference System", IEEE, Tran. On System Man, and Cybernetics, Vol. 23, No. 3, May/June, 1993. doi:10.1109/21.256541 purchase the full-text of this paper (price £20) go to the previous paper go to the next paper return to the table of contents return to the book description purchase this book (price £95 +P&P)
Back to top	©Civil-Comp Limited 2023 - terms & conditions