-Determining accurate concrete strength is a major civil engineering problem. Test results of 28-day concrete cylinder represent the characteristic strength of the concrete that has been prepared and cast to form the concrete work. It is important to wait 28 days to ensure the quality control of the process, although it is very time consuming. Machine learning techniques are progressively used to simulate the characteristic of concrete materials and have developed into an important research area. This study proposed a comprehensive study using an advanced machine learning technique to predict the compressive strength of concrete from early age test results. In this case, early age test data are being used to get reliable values of the two constants which are required for the prediction. A total of 28 historical cases were used to establish the intelligence prediction model. Obtained results show the performance of the advanced hybrid machine learning technique in predicting the concrete strength with a relatively high accuracy measured by four error indicators. Therefore, the proposed study can offer a high benefit for construction project managers in decision-making processes based on early strength test results.

One of the most commonly used materials in civil engineering is concrete; not only is it cheap and strong, but it is also efficient and convenient. The efficiency of concrete is based on the easiness to place and to compact, which is usually known as workability. However, concrete strength and workability works in different ways; hence it is important to divide concrete into two groups: concrete with low workability and concrete with high workability, in order to achieve a more accurate prediction. Since there is a lot of variations of concrete mix designs, the relationship between each mixture is complex and, thus, requires advanced prediction methods in order to find the most accurate relationships between concrete mix proportion and its compression test result.–Recently, many studies have been conducted on applying multiple artificial intelligence (AI) methods in building different complex and challenging prediction models. Thus, this research employs ensemble machine learning methods to precisely forecast compression strength of concrete mix proportion. The accuracy of the proposed method was calculated using two performance measurements. Subsequently, the study has successfully built the prediction model that can accurately map the relationship between concrete mix proportion and compressive strength.

Concrete is the most used material in infrastructure development, especially in a developing country. The concrete used in project must not only satisfy the desired concrete strength, but also the workability. Additionally, due to different conditions in construction projects, the requirement for workability varies. Workability can be measured using several methods. Previously, traditional trial-and-error of concrete mix design were used to achieve desired slump and flow test value. However, the experiment is often inexpensive, and the obtained results may not be sufficiently accurate. Recently, the potential of the AI method has been gaining increased attention as the new and promising alternative method to predict slump and flow tests, based on historical data. Thus, this study develops an effective hybrid AI-based method to predict slump and flow tests from the given concrete mixture dataset. A total of 103 historical data are used. At the beginning, the samples are separated into two groups using k-means clustering. Each cluster is modelled using the ensemble of six prediction methods, which are REG, CART, GENLIN, CHAID, ANN and SVM. The obtained results show that our proposed method can build the prediction method with a high accuracy, measured by several performance indicators.