DATA-DRIVEN APPROACH FOR PREDICTING CONCRETE STRENGTH USING AI-ML ALGORITHM

This paper presents a data-driven approach for predicting concrete strength using an artificial intelligence (AI) algorithm. The conventional methods for estimating concrete strength often contrast, the proposed approach utilizes a large dataset of historical concrete strength measurements and employs an AI algorithm to develop a predictive model. The model is trained to learn the complex relationships between various input parameters and the corresponding concrete strength. The paper outlines the methodology, discusses the dataset used, explains the AI algorithm employed, and presents the results of the predictive model. The findings demonstrate the effectiveness of the data-driven approach in accurately predicting concrete strength, thereby offering potential benefits in construction planning and quality control. Predicting the strength of concrete is of paramount importance in the construction industry as it influences the structural integrity and durability of concrete structures. Traditionally, concrete strength prediction has relied on empirical relationships based on material composition and testing. However, these approaches often suffer from limitations in accuracy and lack the ability to capture complex interactions among various influencing factors. This abstract presents a data-driven approach for predicting concrete strength using artificial intelligence and machine learning algorithms. By leveraging the power of AI and ML, the proposed approach aims to improve the accuracy and efficiency of concrete strength prediction. The data-driven approach utilizes a diverse set of input variables, including concrete mix proportions, curing conditions, and environmental factors, to train AI and ML models. These models, such as artificial neural networks, decision trees, or support vector machines, are capable of learning complex patterns and non-linear relationships from historical data. Through the training process, the models establish correlations between the input variables and concrete strength, enabling accurate predictions. To develop the predictive models, a large dataset of concrete mix designs and corresponding strength test results is collected. The dataset is carefully curated to include a wide range of concrete compositions, curing durations, and environmental conditions to capture the variability of real-world scenarios. The collected data is preprocessed to handle missing values, normalize variables, and remove outliers, ensuring the robustness of the models. The trained AI and ML models are then validated using an independent dataset to assess their predictive performance. Furthermore, sensitivity analyses are performed to identify the most influential factors affecting concrete strength. The application of AI and ML algorithms in concrete strength prediction has significant implications for the construction industry. It enables engineers and practitioners to make informed decisions during the design and construction phases, leading to improved structural performance, cost-effectiveness, and sustainability. Moreover, the data-driven approach reduces the reliance on time-consuming and costly experimental tests, providing a faster and more efficient means of assessing concrete strength.