Institute of Fundamental Technological Research
Polish Academy of Sciences

Partners

Ali Behnood

Purdue University (US)

Recent publications

Behnood A.^♦, Olek J.^♦, Glinicki M.A., Predicting modulus elasticity of recycled aggregate concrete using M5' model tree algorithm, CONSTRUCTION AND BUILDING MATERIALS, ISSN: 0950-0618, DOI: 10.1016/j.conbuildmat.2015.06.055, Vol.94, pp.137-147, 2015

Abstract:
The use of recycled aggregates in concrete is on the rise, driven by economic and environmental concerns. However, most of the existing models to predict the value of elastic modulus of concrete were developed for virgin aggregates and, as a result, they may often be inaccurate when applied to concrete made with recycled aggregate. In this study, the M5′ model tree algorithm was used to predict the elastic modulus of recycled aggregate concrete. The main advantages of the model tree algorithms are: (a) they output relatively simple mathematical models (formulas) and (b) are more convenient to develop and employ compared with other soft computing methods. To develop the model tree presented in this paper, over 450 data records were collected from internationally published literature. Error measures were used to compare the performance of the M5′ algorithm output to the output from other existing models. The results showed that the model developed using the M5′ algorithm has accuracy over 80 percent, which is well above the accuracy the other models.

Keywords:
M5′ model tree, Modulus of elasticity, Recycled aggregate, Concrete

Affiliations:

Behnood A.	-	Purdue University (US)
Olek J.	-	Purdue University (US)
Glinicki M.A.	-	IPPT PAN

List of chapters in recent monographs

Behnood A.^♦, Olek J.^♦, Glinicki M.A., Proc. Int. Symp. Brittle Matrix Composites, BMC-11, Warsaw, September 28-30, 2015, rozdział: Predicting compressive strength of recycled concrete aggregate using M5' model, Institute of Fundamental Technological Research, A.M.Brandt, J.Olek, M.A.Glinicki, C.K.Y.Leung, J.Lis (Eds.), 1, pp.381-391, 2015

Conference papers

Behnood A.^♦, Olek J.^♦, Glinicki M.A., Predicting compressive strength of recycled aggregate concrete using M5′ model, BMC-11, 11th International Symposium on Brittle Matrix Composites, 2015-09-28/09-30, Warsaw (PL), pp.381-391, 2015

Abstract:
Construction industry demands large quantity of recycled materials for sustainable development. The use of recycled aggregate (RA) as a replacement for natural aggregate (NA) represents a sensible approach from technical, environmental, and economic points of view. Due to the substantial differences in the properties of RA and NA, predicting the performance of recycled aggregate concrete has been a concern in many design applications. In this study, M5´ model tree algorithm was used to develop a new model to predict the compressive strength of recycled aggregate concrete. Compared to other soft computing methods, the model tree algorithms offer the following advantages: (a) greater transparency with respect to development of model equations and (b) relative ease of development and implementation. To develop the model tree, 270 data sets were collected from international published literature. The results show that the developed model tree algorithm can well predict the compressive strength of recycled aggregate concrete.

Keywords:
M5´ model tree, modulus of elasticity, recycled aggregate, concrete

Affiliations: