This study aims to develop combined methods with dual and triple use of different non-destructive test (NDT) methods and to examine the effectiveness of these methods. For this purpose, nine different high-strength concrete series were produced, and destructive and NDT methods were applied to these samples on the 3rd and 90th days. Surface hardness, ultrasonic pulse velocity, and penetration resistance were considered from NDT methods. Analyses were made on the response surface method using the NDT measurements and compressive strength values obtained, and four different mathematical models were developed. Models 1, 2, and 3 were designed with dual use of NDT methods, and model 4 was designed with triple use. The absolute relative deviation values for all the developed models’ early and final-age strengths were below 10%. It is of great importance to determine concrete quality with high accuracy and practicality, especially in places like Elazig, where there are thousands of newly constructed buildings since the Sivrice-Elazig earthquake, and rapid production is required. Therefore, it is thought that determining the strength values with high accuracy using the developed combined methods without damaging the building element will provide benefits in terms of time, labor, and cost.
This study aims to predict the final‐age compressive strengths of sustainable concrete series produced using different aggregate types with high accuracy using an artificial intelligence model and to reduce environmental degradation and conserve rapidly decreasing natural resources within the scope of sustainable development and circular economy goals. For this purpose, 45 different sustainable concrete series containing all‐natural, recycled, natural, and recycled concrete aggregates were produced and subjected to compressive strength tests at 7 and 28 days. In addition, this study also considers whether deep neural network models, which have gained popularity in recent years but have high time and resource costs, or shallow models are more suitable for determining the compressive strength values with high accuracy. For this purpose, a method is proposed that can automatically generate the optimal neural network model using a metaheuristic approach that eliminates the human factor. For this purpose, the proposed method was extensively compared with different classical machine learning algorithms. The proposed method predicted the 7 and 28‐day compressive strength with a coefficient of determination of 0.999 and presented better compressive strength predictions than all other algorithms. Considering the number of buildings to be constructed after earthquakes, the widespread use of concrete, and the importance of compressive strength, the proposed method will likely provide significant gains within sustainable development, circular economy, and disaster risk reduction.
26 February 2024 in Construction and Building Materials