Improving the Prediction of Cement Compressive Strength by Coupling of Dynamical Models

The dynamic approach of two well-known techniques has been used to predict a cement’s 28-day compressive strength: Multiple linear regression (MLR), and artificial neural networks (ANN). The modeling is based on Portland cement data and utilizes daily physical, chemical analyses, and early strength results at days 1 and 7. Two kinds of models have been built, containing the 1-day strength as an independent variable, or both 1and 7-day strength. The models are dynamic because they are applied to a movable past period of TD days to calculate the parameters, and then used for a future period of TF days. The comparison is based on the residual error of the testing period, and TD, TF have been optimized. Eight ANNs of different complexity have been developed, but some of them are suffering from over-fitting. A third model has also been created with the coupling of the initial two. The time parameters as well as the filtering and weighting coefficients of the coupled model have been optimized. The simple ANNs with one node in the hidden layer, sigmoid or hyperbolic functions and bias, show better performance. The combination of the coupled model with these two best ANN techniques provides an improved prediction of 28-day strength compared with the initial model containing the 1-day strength. The sensitivity also of TF parameter is lower providing certain benefit in daily industrial application. The implementation of these methods in cement process control can contribute to quality improvement by maintaining a low variance of typical strength.

[1]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

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

[3]  U. Yildiran,et al.  Neural network based control of a cement mill by means of a VSS based training algorithm , 2002, Industrial Electronics, 2002. ISIE 2002. Proceedings of the 2002 IEEE International Symposium on.

[4]  Hong-Guang Ni,et al.  An Algorithm of Neural Network and Application to Data Processing in Concrete Engineering , 2003, Informatica.

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

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

[7]  Vitaly Schetinin.  A Learning Algorithm for Evolving Cascade Neural Networks , 2004, Neural Processing Letters.

[8]  Turan Özturan,et al.  COMPARISON OF CONCRETE STRENGTH PREDICTION TECHNIQUES WITH ARTIFICIAL NEURAL NETWORK APPROACH , 2008 .

[9]  G. Trtnik,et al.  Prediction of concrete strength using ultrasonic pulse velocity and artificial neural networks. , 2009, Ultrasonics.

[10]  Leonardo Franco,et al.  Active Learning Using a Constructive Neural Network Algorithm , 2009, Constructive Neural Networks.

[11]  S. Barai,et al.  Prediction of Compressive Strength of Cement Using Gene Expression Programming , 2009 .

[12]  Okan Karahan,et al.  Comparison of artificial neural network and fuzzy logic models for prediction of long-term compressive strength of silica fume concrete , 2009, Adv. Eng. Softw..

[13]  Dan Yang,et al.  Application of generalized regression neural network in prediction of cement properties , 2010, 2010 International Conference On Computer Design and Applications.

[14]  Paratibha Aggarwal,et al.  Prediction of Compressive Strength of SCC Containing Bottom Ash using Artificial Neural Networks , 2011 .

[15]  J. Dolado,et al.  Recent advances in modeling for cementitious materials , 2011 .

[16]  Zhou Yong,et al.  The prediction research about the strength of cement based on principal component neural network , 2011, 2011 IEEE 3rd International Conference on Communication Software and Networks.

[17]  Horst-Michael Groß,et al.  Comparison of Long-Term Adaptivity for Neural Networks , 2012, ICANN.

[18]  Dimitris Tsamatsoulis.  Prediction of cement strength: analysis and implementation in process quality control , 2012 .

[19]  Ouahab Kadri,et al.  Fault diagnosis of rotary kiln using SVM and binary ACO , 2012 .

[20]  Lin Wang,et al.  Predicting Cement Compressive Strength Using Double-Layer Multi-expression Programming , 2012, 2012 Fourth International Conference on Computational and Information Sciences.

[21]  V. K. Saxena,et al.  Artificial Neural Network Modeling of Ball Mill Grinding Process , 2013 .

[22]  Sakshi Gupta,et al.  Using Artificial Neural Network to Predict the Compressive Strength of Concrete containing Nano-silica , 2013 .

[23]  D. Tsamatsoulis,et al.  Optimizing the Sulphates Content of Cemen tUsing Multivariable Modelling and Uncertainty Analysis , 2013 .

[24]  Construction of a Dynamic Neural Network Model as a Stage of Grate Cooler Automation , 2013 .

[25]  Majid AhmedOleiwi,et al.  Neural Network Control for PPDCV Clinker Cooler System , 2014 .

[26]  Ruoyu Jin,et al.  Prediction of compressive strength of “green” concrete using artificial neural networks , 2014 .

[27]  Dimitris C. Tsamatsoulis,et al.  Application of the Static and Dynamic Models in Predicting the Future Strength of Portland Cements , 2014, 2014 International Conference on Mathematics and Computers in Sciences and in Industry.

[28]  Shervin Motamedi,et al.  Estimating unconfined compressive strength of cockle shell-cement-sand mixtures using soft computing methodologies , 2015 .

[29]  Shervin Motamedi,et al.  Application of adaptive neuro-fuzzy technique to predict the unconfined compressive strength of PFA-sand-cement mixture , 2015 .

[30]  D. Tsamatsoulis.  Optimizing the Cement Compressive Strength Prediction by Applying Coupled Linear Models , 2015 .

[31]  Comparison of Dynamic Linear and Neural Network Models in Predicting Cement Compressive Strength , .