Estimating Cement Compressive Strength from Microstructure Images Using Broad Learning System

The microstructure images of cement are often used as the main data source for estimating compressive strength. They contain ample physical properties during the hydration process. Different gray values represent different substances in the grayscale image of cement. Deep learning algorithm based on microstructure images have been proposed to estimate cement compressive strength (CCS). However, there are a large number of parameters that need to be adjusted in deep structure. The high-efficiency system named broad learning system (BLS) is tried to use to estimate the cement compressive strength. The original cement microstructure images and the extracted features are used as input respectively, the connection weights can be obtained directly by calculating pseudo inverse matrix of feature matrix of microstructure image. If the structure is not sufficient to gain suitable result, BLS only calculates the pseudo inverse matrix of additional nodes to improve accuracy. The experiment shows that the broad learning structure (BLS) is an effective and efficient method on estimating cement compressive strength by contrasting with deep learning structure.

[1]  Dejan J. Sobajic,et al.  Learning and generalization characteristics of the random vector Functional-link net , 1994, Neurocomputing.

[2]  Yoh-Han Pao,et al.  Stochastic choice of basis functions in adaptive function approximation and the functional-link net , 1995, IEEE Trans. Neural Networks.

[3]  Y. Zhang,et al.  Effects of particle size distribution, surface area and chemical composition on Portland cement strength , 1995 .

[4]  C. E. D. S. Tango.  An extrapolation method for compressive strength prediction of hydraulic cement products , 1998 .

[5]  Jin Keun Kim,et al.  Estimation of compressive strength by a new apparent activation energy function , 2001 .

[6]  Serhan Ozdemir,et al.  The use of GA-ANNs in the modelling of compressive strength of cement mortar , 2003 .

[7]  Türkay Dereli,et al.  Prediction of cement strength using soft computing techniques , 2004 .

[8]  Gokmen Tayfur,et al.  FUZZY LOGIC MODEL FOR THE PREDICTION OF CEMENT COMPRESSIVE STRENGTH , 2004 .

[9]  N. Burlion,et al.  X-ray microtomography: Application to microstructure analysis of a cementitious material during leaching process , 2006 .

[10]  A. Ozturk.  Microstructural investigation on the relationship between microstructure and compressive strength of cement mortars , 2007 .

[11]  V. Cnudde,et al.  Porosity and microstructure characterization of building stones and concretes , 2009 .

[12]  Adil Baykasoglu,et al.  Prediction and multi-objective optimization of high-strength concrete parameters via soft computing approaches , 2009, Expert Syst. Appl..

[13]  Lin Wang,et al.  Reverse extraction of early-age hydration kinetic equation from observed data of Portland cement , 2010 .

[14]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[15]  Bo Yang,et al.  Construction of dynamic three-dimensional microstructure for the hydration of cement using 3D image registration , 2014, Pattern Analysis and Applications.

[16]  Yue Li,et al.  Research Based on Scanning Electron Microscopy to Determine Original Water-Cement Ratio of Hardened Concrete , 2014 .

[17]  Haitao Zhao,et al.  Influence of Pore Structure on Compressive Strength of Cement Mortar , 2014, TheScientificWorldJournal.

[18]  Shuiwang Ji,et al.  Deep convolutional neural networks for multi-modality isointense infant brain image segmentation , 2015, NeuroImage.

[19]  Ponnuthurai N. Suganthan,et al.  Detecting Wind Power Ramp with Random Vector Functional Link (RVFL) Network , 2015, 2015 IEEE Symposium Series on Computational Intelligence.

[20]  Xiaohui Yu,et al.  Scalable Distributed Processing of K Nearest Neighbor Queries over Moving Objects , 2015, IEEE Transactions on Knowledge and Data Engineering.

[21]  Bo Yang,et al.  Building Image Feature Kinetics for Cement Hydration Using Gene Expression Programming With Similarity Weight Tournament Selection , 2015, IEEE Transactions on Evolutionary Computation.

[22]  D. Tsamatsoulis.  Improving the Prediction of Cement Compressive Strength by Coupling of Dynamical Models , 2016 .

[23]  J. Rajasankar,et al.  Kernel-based models for prediction of cement compressive strength , 2016, Neural Computing and Applications.

[24]  Yuan Zhang,et al.  Fuzzy clustering with the entropy of attribute weights , 2016, Neurocomputing.

[25]  Chalavadi Krishna Mohan,et al.  Human action recognition using genetic algorithms and convolutional neural networks , 2016, Pattern Recognit..

[26]  Bo Yang,et al.  Estimating cement compressive strength from microstructure images using convolutional neural network , 2017, 2017 IEEE Symposium Series on Computational Intelligence (SSCI).

[27]  Jie Gao,et al.  Recognition, location, measurement, and 3D reconstruction of concealed cracks using convolutional neural networks , 2017 .

[28]  C. L. Philip Chen,et al.  Broad Learning System: An Effective and Efficient Incremental Learning System Without the Need for Deep Architecture , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[29]  Lin Wang,et al.  Investigating the Evolution of a Neuroplasticity Network for Learning , 2019, IEEE Transactions on Systems, Man, and Cybernetics: Systems.