Artificial neural network (ANN) approach to predict unconfined compressive strength (UCS) of oil and gas well cement reinforced with nanoparticles

Abstract The prediction of unconfined compressive strength (UCS) of oil well cement class “H” based on the artificial neural network (ANN) modeling approach is presented in this study. 195 cement samples were embedded with varying dosages of strength enhancing pre-dispersed nanoparticles consisting of nanosilica (nano-SiO2), nanoalumina (nano-Al2O3), and nanotitanium dioxide (nano-TiO2) at various simulated wellbore temperatures. The efficacy of the pre-dispersed nanoparticle solutions was analyzed by transmission electron microscope (TEM) images. Nano-SiO2 and nano-Al2O3 displayed excellent dispersibility throughout the solution. However, nano-TiO2 readily agglomerates which, at high concentrations, is detrimental to the UCS of cement. 70% of the data set was used to train the ANN model, 15% was used for validation, and 15% was used to test the model. The model consisted of one input layer with five nodes, one hidden layer with 12 nodes, and one output layer with one node. 12 nodes in the hidden layer resulted in the lowest mean squared error (MSE). The model parameters were saved and used after seven epochs during training, at which point the validation error began to increase leading to overfitting. The statistical performance measures consisting of MSE, the square root of the coefficient of determination (R), and the mean absolute percentage error (MAPE) showed values close to zero, one, and less than five percent, respectively. The statistical performance measures of the ANN model displayed superior results when compared to the measures obtained by the multi-linear (MLR) and random forest (RF) regression algorithms. The developed ANN model displays high predictive accuracy and can replace, or be used in combination with, destructive UCS tests which can save the petroleum industry time, resources, and capital.

[1]  Mohammadmehdi Choolaei,et al.  The effect of nanosilica on the physical properties of oil well cement , 2012 .

[2]  Xiang-guo Li,et al.  Effects of Nano-TiO2 on the Toughness and Durability of Cement-Based Material , 2015 .

[3]  Faruq Mohammad,et al.  Synergistic effect of nano-silica slurries for cementing oil and gas wells , 2020 .

[4]  Xin Wang.  Effects of nanoparticles on the properties of cement-based materials , 2017 .

[5]  Taghi Ebadi,et al.  The Effect of Nanosilica on Cement Matrix Permeability in Oil Well to Decrease the Pollution of Receptive Environment , 2011 .

[6]  Hyunjun Kim,et al.  Prediction Model for Mechanical Properties of Lightweight Aggregate Concrete Using Artificial Neural Network , 2019, Materials.

[7]  Samwel Daud Lupyana,et al.  Effect of Nano-SiO2, Nano-TiO2 and Nano-Al2O3 Addition on Fluid Loss in Oil-Well Cement Slurry , 2019 .

[8]  C. Poon,et al.  The effect of nanoalumina on early hydration and mechanical properties of cement pastes , 2019, Construction and Building Materials.

[9]  C. Poon,et al.  Prediction of compressive strength of recycled aggregate concrete using artificial neural networks , 2013 .

[10]  D. Unruh,et al.  Permeability and elastic properties assessment of alumina nanofiber (ANF) cementitious composites under simulated wellbore cyclic pressure , 2020 .

[11]  B. D. Ikotun,et al.  Prediction of compressive and flexural strengths of a modified zeolite additive mortar using artificial neural network , 2018, Construction and Building Materials.

[12]  Jose M. Adam,et al.  Estimation of the axial behaviour of masonry walls based on Artificial Neural Networks , 2013 .

[13]  L. Torres-Martínez,et al.  Engineering of SiO 2 Nanoparticles for Optimal Performance in Nano Cement-Based Materials , 2009 .

[14]  Seyedalireza Khatibi,et al.  A Novel Nanosilica-Based Solution for Enhancing Mechanical and Rheological Properties of Oil Well Cement , 2018, Day 3 Thu, October 25, 2018.

[15]  Manan Shah,et al.  A comprehensive review of the application of nano-silica in oil well cementing , 2020, Petroleum.

[16]  Gökhan Kaplan,et al.  Artificial Neural Network Estimation of the Effect of Varying Curing Conditions and Cement Type on Hardened Concrete Properties , 2019 .

[17]  Ana Guerrero,et al.  Improvement of initial mechanical strength by nanoalumina in belite cements , 2007 .

[18]  R. L. Dillenbeck,et al.  Characterizing Casing-Cement-Formation Interactions Under Stress Conditions: Impact on Long-Term Zonal Isolation , 2004 .

[19]  Andries P. Engelbrecht,et al.  Optimizing the number of hidden nodes of a feedforward artificial neural network , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[20]  Doug Schmucker,et al.  Not As Bad As It Seems: Teaching Probability And Statistics In Civil Engineering , 2004 .

[21]  A. Viloria,et al.  Estimating strength properties of geopolymer self-compacting concrete using machine learning techniques , 2020, Journal of Materials Research and Technology.

[22]  A. Ghahremaninezhad,et al.  The Effect of Curing Temperature on the Properties of Cement Pastes Modified with TiO2 Nanoparticles , 2016, Materials.

[23]  Pål Skalle,et al.  Cement sheath modification using nanomaterials for long-term zonal isolation of oil wells: Review , 2017 .

[24]  Subana Shanmuganathan,et al.  Artificial Neural Network Modelling: An Introduction , 2016 .

[25]  Samwel Daud Lupyana,et al.  Nanotechnology in the petroleum industry: Focus on the use of nanosilica in oil-well cementing applications - A review , 2020 .

[26]  C. Poon,et al.  Hydration and properties of nano-TiO2 blended cement composites , 2012 .

[27]  Łukasz Sadowski,et al.  Prediction of Concrete Compressive Strength by Evolutionary Artificial Neural Networks , 2015 .

[28]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[29]  K. Surowiec,et al.  Mechanical, rheological, and stability performance of simulated in-situ cured oil well cement slurries reinforced with alumina nanofibers , 2019 .

[30]  Erwan Scornet,et al.  A random forest guided tour , 2015, TEST.

[31]  Marek Słoński,et al.  A comparison of model selection methods for compressive strength prediction of high-performance concrete using neural networks , 2010 .

[32]  Rajendra Kumar Sharma,et al.  Prediction of Compressive Strength of Concrete Using Artificial Neural Network and Genetic Programming , 2016 .

[33]  S. Ridha,et al.  The Strength Compatibility of Nano-SiO 2 Geopolymer Cement for Oil Well under HPHT Conditions , 2015 .

[34]  Qiang Zhou,et al.  Estimation of compressive strength of hollow concrete masonry prisms using artificial neural networks and adaptive neuro-fuzzy inference systems , 2016 .

[35]  M. Amin,et al.  Influence of carbon nanotubes, nanosilica and nanometakaolin on some morphological-mechanical properties of oil well cement pastes subjected to elevated water curing temperature and regular room air curing temperature , 2017 .

[36]  M. Geiker,et al.  Nanorubber-modified cement system for oil and gas well cementing application , 2017 .

[37]  Md. Safiuddin,et al.  Modeling of Compressive Strength for Self-Consolidating High-Strength Concrete Incorporating Palm Oil Fuel Ash , 2016, Materials.

[38]  M. Ataei,et al.  Fe2O3 nanoparticles improve the physical properties of heavy-weight wellbore cements: A laboratory study , 2015 .

[39]  Ashok K. Santra,et al.  Influence of Nanomaterials in Oilwell Cement Hydration and Mechanical Properties , 2012 .

[40]  Ardavan Yazdanbakhsh,et al.  Carbon Nano Filaments in Cementitious Materials: Some Issues on Dispersion and Interfacial Bond , 2009, SP-267: Nanotechnology of Concrete: The Next Big Thing is Small.

[41]  Harun Tanyildizi,et al.  Estimation of compressive strength of self compacting concrete containing polypropylene fiber and mineral additives exposed to high temperature using artificial neural network , 2012 .

[42]  A. Murat Ozbayoglu,et al.  Computational intelligence models for PIV based particle (cuttings) direction and velocity estimation in multi-phase flows , 2019, Journal of Petroleum Science and Engineering.