A Bayesian machine learning approach for inverse prediction of high-performance concrete ingredients with targeted performance

Abstract High-performance concrete (HPC) plays an important role in improving the sustainability and reliability of buildings and infrastructures. Machine learning predictive models have been used for predicting concrete performance from ingredients, however it remains a challenge to achieve inverse prediction of ingredients from targeted performances. This study proposes an in-house coded informatics-based materials analysis framework to enable computational design of HPC with targeted strength performance. The Gaussian processes (GP) emulator is used to construct the surrogate predictive model based-on 453 experimental measurements. The validity of the GP emulator is assessed using the leave-one-out cross-validation (LOO-CV) and also a separate validation dataset. The variance-based global sensitivity analysis, Sobol indices, is applied to understand the impact of physical ingredients on the HPC performances. The results suggest that the trained GP emulator can provide sufficiently accurate and reliable predictions, as well as reflect the real-world physicochemical nature of HPC materials. The inverse material design is achieved by the Bayesian inference method with a Markov chain Monte Carlo stochastic sampling method, the Metropolis-Hastings (MH) algorithm. Combining with the Bayesian inference method, the proposed design framework can infer a list of potential HPC formulae of a targeted performance, each evaluated by the likelihood of resulting in the targeted strength. The data-driven material analysis and design framework proposed in this study provides a novel approach to achieve performance-based design of HPC, with the potential to maximise resource efficiency and reduce economical cost. The methodology presented in this study can also be extended to be applied to a wide range of construction materials, targeting difference service performances including durability.

[1]  I-Cheng Yeh,et al.  Analysis of Strength of Concrete Using Design of Experiments and Neural Networks , 2006 .

[2]  Xu Ji,et al.  Prediction of concrete compressive strength: Research on hybrid models genetic based algorithms and ANFIS , 2014, Adv. Eng. Softw..

[3]  J. Ideker,et al.  Advances in alternative cementitious binders , 2011 .

[4]  J. H. Bungey,et al.  Prediction of the concrete compressive strength by means of core testing using GMDH-type neural network and ANFIS models , 2012 .

[5]  J. Hogden,et al.  Statistical inference and adaptive design for materials discovery , 2017 .

[6]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[7]  Min-Yuan Cheng,et al.  High-performance Concrete Compressive Strength Prediction using Time-Weighted Evolutionary Fuzzy Support Vector Machines Inference Model , 2012 .

[8]  I-Cheng Yeh,et al.  Computer-aided design for optimum concrete mixtures , 2007 .

[9]  R. Snellings,et al.  Reactivity of supplementary cementitious materials (SCMs) in cement blends , 2019, Cement and Concrete Research.

[10]  I-Cheng Yeh,et al.  Knowledge discovery of concrete material using Genetic Operation Trees , 2009, Expert Syst. Appl..

[11]  P. Aitcin.  The durability characteristics of high performance concrete: a review , 2003 .

[12]  D. Krige.  A statistical approach to some basic mine valuation problems on the Witwatersrand, by D.G. Krige, published in the Journal, December 1951 : introduction by the author , 1951 .

[13]  Jui-Sheng Chou,et al.  Concrete compressive strength analysis using a combined classification and regression technique , 2012 .

[14]  Filip De Turck,et al.  Blind Kriging: Implementation and performance analysis , 2012, Adv. Eng. Softw..

[15]  Prasanna V. Balachandran,et al.  Machine learning guided design of functional materials with targeted properties , 2019, Computational Materials Science.

[16]  A. OHagan,et al.  Bayesian analysis of computer code outputs: A tutorial , 2006, Reliab. Eng. Syst. Saf..

[17]  Mohammad Hossein Fazel Zarandi,et al.  Fuzzy polynomial neural networks for approximation of the compressive strength of concrete , 2008, Appl. Soft Comput..

[18]  M. Isabel Asensio,et al.  Sensitivity analysis and parameter adjustment in a simplified physical wildland fire model , 2015, Adv. Eng. Softw..

[19]  Yuan Yao,et al.  Kriging meta‐model assisted calibration of computational fluid dynamics models , 2016 .

[20]  Agus Sudjianto,et al.  Blind Kriging: A New Method for Developing Metamodels , 2008 .

[21]  F. Larrard.  Concrete Mixture Proportioning: A Scientific Approach , 1999 .

[22]  S Roberts,et al.  Gaussian processes for time-series modelling , 2013, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[23]  Lixing Han,et al.  Implementing the Nelder-Mead simplex algorithm with adaptive parameters , 2010, Computational Optimization and Applications.

[24]  S. Akyuz,et al.  An experimental study on optimum usage of GGBS for the compressive strength of concrete , 2007 .

[25]  Jui-Sheng Chou,et al.  Smart Artificial Firefly Colony Algorithm‐Based Support Vector Regression for Enhanced Forecasting in Civil Engineering , 2015, Comput. Aided Civ. Infrastructure Eng..

[26]  Youssef M. Marzouk,et al.  Improved profile fitting and quantification of uncertainty in experimental measurements of impurity transport coefficients using Gaussian process regression , 2015 .

[27]  I. Sobola,et al.  Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates , 2001 .

[28]  M. Okada,et al.  Bayesian inference of ferrite transformation kinetics from dilatometric measurement , 2020 .

[29]  Radford M. Neal.  Priors for Infinite Networks , 1996 .

[30]  V. M. Malhotra.  Performance of Superplasticizers in Concrete: Laboratory Investigation-Part 1 , 1977 .

[31]  Rafat Siddique,et al.  Recent advances in understanding the role of supplementary cementitious materials in concrete , 2015 .

[32]  I-Cheng Yeh,et al.  Modeling of strength of high-performance concrete using artificial neural networks , 1998 .

[33]  Guowei Ma,et al.  A hybrid intelligent system for designing optimal proportions of recycled aggregate concrete , 2020 .

[34]  Guowei Ma,et al.  Intelligent mixture design of steel fibre reinforced concrete using a support vector regression and firefly algorithm based multi-objective optimization model , 2020 .

[35]  Duo Zhang,et al.  Carbonation Curing of Precast Fly Ash Concrete , 2016 .

[36]  C. Shi,et al.  A review on ultra high performance concrete: Part I. Raw materials and mixture design , 2015 .

[37]  Mohammad Iqbal Khan,et al.  Predicting properties of High Performance Concrete containing composite cementitious materials using Artificial Neural Networks , 2012 .

[38]  M. A. Bhatti,et al.  Predicting the compressive strength and slump of high strength concrete using neural network , 2006 .

[39]  Ji Soo Ahn,et al.  Using a Gaussian process regression inspired method to measure agreement between the experiment and CFD simulations , 2019 .

[40]  Mustafa Tokyay,et al.  Strength prediction of fly ash concretes by accelerated testing , 1999 .

[41]  Jeong-Soo Park,et al.  A statistical method for tuning a computer code to a data base , 2001 .

[42]  V. Malhotra.  Effect of repeated dosages of superplasticizers on slump, strength and freeze-thaw resistance of concrete , 1981 .

[43]  Willy Bauwens,et al.  Sobol' sensitivity analysis of a complex environmental model , 2011, Environ. Model. Softw..

[44]  Jeffrey W. Bullard,et al.  RETRACTED: Experimental investigation and comparative machine-learning prediction of strength behavior of optimized recycled rubber concrete , 2020 .

[45]  Dookie Kim,et al.  An improved application technique of the adaptive probabilistic neural network for predicting concrete strength , 2009 .