Journals / Research on Engineering Structures and Materials / 2022 / Cilt: 8 - Sayı: 2

An artificial neural network for the prediction of the strength of supplementary cementitious concrete

Pages
421–430
Publication Date
2022-10-19
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The ANN models predict concrete strength with excellent accuracy, and the findings show that utilizing ANNs to predict concrete strength is both practicable and advantageous.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Supplementary materials (SM) for cement replacement became more feasible in the previous decade due to their pozzolanic strength and durability properties.
📊
Key Findings & Data:With ANN and input parameters, a total of 324 distinct data points for SM concrete were utilized to estimate SM concrete strength.
💡
Conclusion & Impact:The ANN models predict concrete strength with excellent accuracy, and the findings show that utilizing ANNs to predict concrete strength is both practicable and advantageous.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters

Abstract

Supplementary materials (SM) for cement replacement became more feasible in the previous decade due to their pozzolanic strength and durability properties. The strength variation according to the age of the binding material is a critical subject for SM concrete. The time of water curing is critical in order to maintain the pozzolanic reaction in SM concrete, which assists in the development of strength in cementitious properties. In this study, the laboratory results of concrete specimens were assessed for various mix designs, and the obtained corresponding strengths were also predicted with ANN techniques. The difference between experimental and ANN predicted values was marginally low. Thus, the ANN model applicability emphasized the productive use in predicting the strength of supplementary materials like fly ash or any similar pozzolanic mineral admixture. This research proposes an ANN-based technique for predicting the strength of fly ash added SM concrete. Typical experimental data is used to build, train, and test the artificial neural network (ANN) model. With ANN and input parameters, a total of 324 distinct data points for SM concrete were utilized to estimate SM concrete strength. Various combinations of layers, number of neurons, and learning rate were examined during the training phase. When the root mean square error (RMSE) reached or remained below 0.001, the training was stopped, and the findings were verified using a test data set. With respect to the relative error provided for trained model data, the results achieved were typically below 10% for compressive strength and below 5% for split tensile strength. The ANN models predict concrete strength with excellent accuracy, and the findings show that utilizing ANNs to predict concrete strength is both practicable and advantageous.

🔖

Cite This Article

MAHAJAN, L., BHAGAT, S. (2022). An artificial neural network for the prediction of the strength of supplementary cementitious concrete. Research on Engineering Structures and Materials, Cilt: 8 - Sayı: 2, 421–430. https://ajindex.com/articles/588837

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (12)

  1. Gursel AP, Masanet E, Horvath A, Stadel A. Life-cycle inventory analysis of concrete production: a critical review. Cement and Concrete Composites, 2014; 51: 38-48.
  2. Mehta PK. Greening of the concrete industry for sustainable development. Concrete International, 2002; 24:7 23- 28
  3. Mahajan LS, Bhagat SR. Strength Assessment of Concrete using Fly Ash and Metakaolin, In proceeding: International Conference on Advances in Concrete Technology materials and construction practices, Excel India Publishers, New Delhi, 2016; 113- 114
  4. Li VC, Wang S, Wu C, Tensile Strain-Hardening Behavior of Polyvinyl Alcohol Engineered Cementitious Composite (PVA-ECC). Materials Journal, 2001; 98: 483-492
  5. Wang S, Li VC. Engineered Cementitious Composites with High-Volume Fly Ash., ACI Materials Journal, 2007; 104: 233-241.
  6. Yang EH, Yang Y, Li VC. Use of high volumes of fly ash to improve ECC mechanical properties and material greens. ACI Materials Journal, 2017; 104: 620-628
  7. Oztas A, Pala M, Ozbay E, Kanca E, Caglar N, Bhatti MA. Predicting the Compressive Strength and Slump of High Strength Concrete using Neural Network. Construction and Building Materials, 2006; 20: 769-75.
  8. Gunasekara C, Setunge S, Law DW, Willis N, Burt T. Engineering Properties of Geopolymer Aggregate Concrete. Journal of Materials in Civil Engineering, 2018; 30:11 04018299
  9. Hong-Guang N, Ji-Zong W. Prediction of Compressive Strength of Concrete by Neural Networks. Cement and Concrete Research, 2000; 30: 1245-50.
  10. Priyadharshini P, Mohan Ganesh G; Santhi AS. (2011) Experimental Study on Cold Bonded Fly Ash Aggregates. International Journal of Civil and Structural Engineering 2011; 2:2 493-501 [11] Peng CH, Yeh IC, Lien LC. Building Strength Models for High-Performance Concrete at Different Ages using Genetic Operation Trees, Nonlinear Regression, and Neural Networks. Engineering Composites, 2010; 26: 61-73.
  11. Shi L, Lin STK, Lu Y, Ye L, Zhang YX. Artificial Neural Network Based Mechanical and Electrical Property Prediction of Engineered Cementitious Composites. Construction and Building Materials, 2018; 174: 667-74.
  12. Karna