Genetic programming for experimental big data mining: A case study on concrete creep formulation

Abstract

This paper proposes a new algorithm called multi-objective genetic programming (MOGP) for complex civil engineering systems. The proposed technique effectively combines the model structure selection ability of a standard genetic programming with the parameter estimation power of classical regression, and it simultaneously optimizes both the complexity and goodness-of-fit in a system through a non-dominated sorting algorithm. The performance of MOGP is illustrated by modeling a complex civil engineering problem: the timedependent total creep of concrete. A Big Data is used for the model development so that the proposed concrete creep model-referred to as a "genetic programming based creep model" or "G-C model" in this study-is valid for both normal and high strength concrete with a wide range of structural properties. The G-C model is then compared with currently accepted creep prediction models. The G-C model obtained by MOGP is simple, straightforward to use, and provides more accurate predictions than other prediction models.

A hybrid computational approach for seismic energy demand prediction

“…The effectiveness of MGGP has been proved in the works reported by Gandomi et al (e.g. Gandomi and Alavi 2012a,b, Gandomi et al 2013, Babanajad et al 2013, Gandomi et al 2016.…”

“…There are two groups of models which can be used for modeling the complex nonlinear engineering systems: phenomenological and behavioral (Gandomi et al 2016). Phenomenological models need a predefined structure obtained from the physical laws requiring a previous understanding about the system.…”

“…Although one of the main advantages of behavioral modeling techniques is their independence on prior knowledge about the governing physical relationships of input and outputs (Walter andPronzato 1997, Metenidis 2004), most of these models need the user to pre-assign a formulation pattern requiring optimization of its unknown coefficients. Concerning the complex engineering systems, the use of conventional techniques such as regression analysis cannot be guaranteed to find an accurate and reliable behavioral model (Gandomi et al 2016). It has been well recognized that most of the structural earthquake engineering problems such as determining earthquake response of inelastic structures could be considered as such complex problems.…”

Flood Management, Flood Forecasting and Warning System

“…Besides these methods, artificial intelligence and machine learning as a quick and powerful tool [23][24][25] can be used to predict and manage the flood. Bardestani et al used ANFIS which is a combination of Neural Network and Fuzzy Logic in Water Resources [26].…”

Gene expression programming application for prediction of ultimate axial strain of FRP-confined concrete

“…GEP was recently devised by various researchers for developing complex relations between experimental data as an efficient alternative to traditional regression and machine learning methods (e.g., artificial neural networks and ANN) [12][13][14]. GEP has been used by some researchers to solve engineering problems [15][16][17][18][19][20][21][22][23].…”