Artificial Intelligence for Compressive Strength Prediction of Concrete

Compression strength is the most important factor in concrete structures, and there are two methods to evaluate that compressive strength, destructive and non-destructive method. This work presents a study on the deference and comparison between Destructive (compressive strength test) and a Non-Destructive Method (Rebound Hammer and Ultrasonic test) for testing the compressive strength of concrete.The investigations aimed to develop the method of assessment the strength of concrete of both non-destructive tests with greater accuracy. Destructive method, to determine the strength of the in-situ concrete, and also destructive testing (DT), includes methods where the material is broken down in order to determine its mechanical properties. From the obtained results it is observed that the Rebound Hammer readings increased with the compressive strength of concrete. And the Ultrasonic pulse velocity were greatly influenced by the cements and aggregate, extent of moist curing and presence of flaws and voids in concrete, more than their influence on the measured strengths. This demonstrates the limitation of using ultrasonic pulse velocity tests for estimating compressive strength of concrete. Combined use of Ultrasonic pulse velocity (UPV) and Rebound Hammer tests for assessment of concrete strength in structures with greater reliability.

The current study aimed to investigate the possibility of predicting the compressive strength of geopolymer mortar by mix design parameters, ultrasonic pulse velocity (UPV) and machine learning techniques. Here the geopolymer mortar is produced from eggshell ash and rice husk ash as precursors, NaOH solution as activator and quarry waste as fine aggregate. Twenty-seven combinations of geopolymer mix and a total of 189 mortar cubes were cast and tested for UPV and compressive strength. Seven different machine learning techniques were used to predict the compressive strength assessment tools: linear regression, artificial neural networks, boosted tree regression, random forest regression, K-Nearest Neighbor, support vector regression and XGboost. Among the diverse machine learning models evaluated in this study, XGboost exhibited remarkable efficacy in forecasting the compressive strength of geopolymer mortar. The investigation conducted using SHAP indicates that the concentration of UPV shows the most substantial influence on the prediction of compressive strength.

Waste marble, an industrial byproduct generated from marble cutting and polishing processes, can be effectively utilized as a partial replacement in concrete mixtures. Incorporating waste marble in concrete not only addresses environmental concerns related to marble waste disposal but also contributes to the sustainability of construction materials. Using machine learning (ML) to predict the impact of waste marble on the compressive strength of traditional concrete offers several advantages over repeated laboratory experiments. ML offers a powerful alternative to costly and time-consuming laboratory experiments, enabling faster and more sustainable exploration of the potential of waste marble in improving concrete’s compressive strength. This research has focused on evaluating the impact of waste marble on the compressive strength of traditional concrete using machine learning (ML). Advanced ML techniques such as the Group Methods Data Handling Neural Network (GMDH-NN), Support Vector Regression (SVR), K-Nearest Neighbors (kNN) and Adaptive Boosting (AdaBoost) have been applied in this research work. The GMDH-NN model was created using GMDH Shell 3.0 software, while AdaBoost, SVR and kNN models were created using “Orange Data Mining” software version 3.36. Error indices such as the sum of squared error (SSE), mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), and Error (%), and performance metrics such as Accuracy % and the R2 between predicted and calculated compressive strength parameters were used to evaluate the overall behavior of the models. Finally, the Hoffman sensitivity analysis procedure was applied to determine the individual relative impact of the input variables on the output. At the end of the processes, a total of 1135 waste marble concrete entries were collected containing constituents such as the cement density (C), waste marble (WM), fine aggregate (FAg), coarse aggregate (CAg), water (W), superplasticizer (PL) and curing age (Age) used as input variables of the waste marble concrete model. The records were divided into training set (900 records = 80%) and validation set (235 records = 20%) following standard partitioning pattern reported in the literature. The kNN and AdaBoost, with SSE of 1408.5 MPa2 and 1397 MPa2 respectively and a tie Accuracy of 95.5% and R2 of 0.985 showed the best models suggesting excellent model performance while GMDH-NN showed the worst. Conversely, RF balances accuracy and model complexity, making it a practical alternative to kNN and AdaBoost. And lastly, Age, Coarse Aggregates, Water, and Plasticizer play the most significant roles in determining the compressive strength, while Cement, Waste Marble, and Fine Aggregates have comparatively smaller impacts. However, considering the standard proportion required for waste marble powder to replace cement, it showed a remarkable influence on the behavior of the concrete thus a recommended potential for its used as replacement for cement.

Analysis of the accuracy of in-situ concrete characteristic compressive strength assessment in real structures using destructive and non-destructive testing methods

Combined Use of Non-Destructive Tests for Assessment of Strength of Concrete in Structure

The Structural Health monitoring with Schmidt Rebound Hammer is being widely used by many consultants. The rebound hammer is use for Concrete structures for predicting the service life. The present research work attempted to interpret different Concrete mix designs by Surface hardness method, which gives a test method for structural health assessment by a suitable correlation between Rebound hammer number and Concrete compressive strength. Thus, the objectives of this present research are threefold. First, this research will examine the influence of conditioning such as drying condition on the results of Schmidt hammer test performed on Concrete cubes with different Mixtures proportion. In which W/C ratio, Slump, Grade of concrete, Fine aggregate, Coarse aggregate, Cement content, and Water content under two different conditions such as Slump, and W/C ratio value was varied with constant Compressive strength as in the First case and Compressive strength, and W/C ratio value varied with constant Slump as in the Second case. Seventy-two concrete cubes (100 mm3) with Grades of concrete ranges from 25 to 40 N/mm2 were prepared and tested using Schmidt Rebound hammer equipment. The non-destructive test parameters were relate to different Mixtures proportion in ordered to characterize Mix designs. Second, this research will examine the influence of the hardness value on compressive strength. Third, this research will also aims to develop non-destructive charts for different concrete mixtures proportion. Thus, the Schmidt hammer test due to the developed chart gave a better value. This implied that the developed chart was more suitable for normal strength concrete as well as minimising inaccuracy in non-destructive tests.

Experimental investigation and AI prediction modelling of ceramic waste powder concrete – An approach towards sustainable construction

Non Destructive Testing (NDT) methods are used to review or measure the materials or designs without annihilating their surface, item uprightness and future handiness. The overall objective of the research is to assess the strength of concrete in existing structures using Nondestructive Tests at Kachankawal Rural Municipality, Jhapa District of Nepal.Rebound hammer test and ultrasonic pulse velocity tests were used for determining the compressive strength of concrete. The existing Reinforced Concrete Cement culverts were used for 9 existing structures. Average rebound number were taken and calculated from each sample. From the average rebound number were taken to determine the grade of concrete along with corresponding compressive strength. Similarly, the Ultrasonic Pulse Velocity tests were done on same existing structures and path length and time were noted for assessing the corresponding compressive strength and the quality of concrete. Triangulation among rebound hammer test, ultrasonic pulse velocity test and proposed initial grading were validated using chi square test. Relation between compressive strength with rebound hammer and ultrasonic pulse velocity were analyzed using linear regression model. Chi square confirms variation in compressive strength between calculated compressive strength and standard compressive strength. The relation of compressive strength (y) at R² = 1 with rebound number (x) and ultrasonic pulse velocity (x) could be expressed as y = 0.9306x - 2.7233 and y = 2.904 x + 10.119 respectively. The study is a guiding tool for concern authority and professionals to make effective decision regarding further structural development and budget allocation of the existing structures.

Evaluating compressive strength of concrete made with recycled concrete aggregates using machine learning approach

Concrete compressive strength prediction using ultrasonic pulse velocity through artificial neural networks

This study conducts an extensive comparative analysis of computational intelligence approaches aimed at predicting the compressive strength (CS) of concrete, utilizing two non-destructive testing (NDT) methods: the rebound hammer (RH) and the ultrasonic pulse velocity (UPV) test. In the ensemble learning approach, the six most popular algorithms (Adaboost, CatBoost, gradient boosting tree (GBT), random forest (RF), stacking, and extreme gradient boosting (XGB)) have been used to develop the prediction models of CS of concrete based on NDT. The ML models have been developed using a total of 721 samples, of which 111 were cast in the laboratory, 134 were obtained from in-situ testing, and the other samples were gathered from the literature. Among the three categories of analytical models—RH models, UPV models, and combined RH and UPV models; seven, ten, and thirteen models have been used respectively. AdaBoost, CatBoost, GBT, RF, Stacking, and XGB models have been used to improve the accuracy and dependability of the analytical models. The RH-M5, UPV-M6, and C-M6 (combined UPV and RH model) models were found with highest performance level amongst all the analytical models. The MAPE value of XGB was observed to be 84.37%, 83.24%, 77.33%, 59.46%, and 81.08% lower than AdaBoost, CatBoost, GBT, RF, and stacking, respectively. The performance of XGB model has been found best than other soft computing techniques and existing traditional predictive models.

Experimental and machine learning approaches to investigate the application of sugarcane bagasse ash as a partial replacement of fine aggregate for concrete production

This paper investigates the relationship between the ultrasonic pulse velocity (UPV) and the compressive strength of concrete. The specimens used in the study were made of concrete with varied aggregate contents from 1000 to 1400 kg/m<SUP>3</SUP>. The specimens were made and tested at the Hawler Construction Laboratories (HCLabs) in Erbil, Kurdistan Region of Iraq. The UPV measurement and compressive strength tests were carried out at the concrete age of 28 days. The experimental results show that the relationship between UPV and the compressive strength of concrete is significantly influenced by the coarse aggregate content. Relationships are established for the range of contents of coarse aggregates and discussed.

This paper presents a systematic review of studies related to Artificial Intelligence (AI) and Machine Learning (ML) applications in Supply Chain Management (SCM). Our systematic search studied 109 journal articles published between 2007 and 2025. It was presented definitions for AI, ML, and SCM and a bibliometric analysis was carried out to examine trends and patterns in the existing literature. The 109 articles were grouped into five clusters based on keywords and abstracts, identifying promising research areas and proposes directions for future investigations. The current literature on AI and ML in SCM is expanding, with an increasing number of publications and growing diversity in applications, although significant gaps remain warranting attention. Various AI and ML techniques, including supervised learning algorithms, neural networks, and optimization techniques, have been studied in scenarios such as demand forecasting, inventory management, and risk analysis. Additionally, AI and ML methods are expected to gain broader acceptance in SCM scenarios, such as, application of Generative AI (GenAI) and Large Multimodal Models (LMMs); Quantum ML techniques to handle with large SCM data; to implement SHAP (SHapley Additive exPlanations) for demand forecasting and fraud detection; and to use Generative AI models (like, GPT-4) to generate synthetic supply chain scenarios.

In the design of new structures, EN 1992‐1‐1 normatively regulates the correlation between the compressive strength and tensile strength of concrete, in accordance with EN 206‐1. However, as there are many time‐ and load‐dependent impacts on existing structures, the relationship described by EN 1992‐1‐1 cannot be assumed without any further observations for existing structures. At the moment, there is no comprehensive investigation on the influences of, for example, subsequent hardening and carbonation on the concrete compressive or tensile strength. The tensile strength of concrete defined in EN 1992‐1‐1 is based on a water storage and a testing age of 28 days. Furthermore, the in‐situ tensile strength is affected by micro‐crack formation cause of internal stresses due to outflow of hydration heat, for example. Generally, there is a different influence of micro‐crack formation on the tensile strength of concrete than on the compressive strength of concrete. The actual value of the in‐situ tensile strength of concrete affects the shear force resistance and the load‐bearing capacity of anchors with concrete cone failure as decisive failure mode. Within the framework of a research project (SWD‐10.08.18.7‐13.01), financed by “Forschungsinitiative Zukunft Bau”, an initiative of the Federal Institute for Research on Building, Urban Affairs and Spatial Development (BBR) structural investigations on the correlation between the compressive and tensile strength of old concretes have been performed. Below, the results of the research project are presented.