International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 11 Issue: 05 | May 2024
www.irjet.net
p-ISSN: 2395-0072
Prediction of Recycled Coarse Aggregate Concrete Strength Using Machine Learning Techniques Kashish Singh1, Himanshu Khokhar1, Harshita Singh1, Faraz Khan1, Dr. Kunal Bisht1, Ms. Shikha Tyagi1, Mr. Praveen Kumar Yadav2 Department of civil engineering, KIET Group of institution, ghaziabad1 Department of civil engineering, ITS Engineering college, greater noida2 Affiliated to Dr. A.P.J. Abdul kalam technical university, Lucknow ------------------------------------------------------------------------***------------------------------------------------------------------------learning algorithms power a diverse range of 1. Abstract
applications, including customized suggestions on streaming platforms and predictive maintenance in manufacturing. Machine learning is employed in banking to detect fraud and facilitate algorithmic trading. In healthcare, it assists in diagnosing diseases and developing individualized treatment strategies. Marketing efforts utilize machine learning to segment customers and deliver tailored advertisements, while autonomous cars depend on it for navigation and obstacle detection.
This research presents a machine learning methodology for accurately forecasting the compressive strength of recycled concrete aggregate (RCA) material. Data from curated datasheet on RCA concrete samples, including mix proportions, curing conditions, and compressive strength test results, were used to train and test various machine learning models. The random forest model outperformed others, achieving an R-squared value of 0.798. This machine learning technique offers a reliable way of predicting RCA concrete's compressive strength, enabling engineers to optimize mix designs and improve the quality and longevity of recycled concrete constructions, promoting sustainable construction practices.
2.2 Application of Machine Learning in Different Fields Machine learning is now essential in several fields because it can extract valuable information and patterns from data, resulting in improved decisionmaking and efficiency. Machine learning algorithms are widely used in finance for risk assessment, algorithmic trading, and fraud detection. Through the analysis of past data, these algorithms can detect suspicious patterns that are symptomatic of deceiving conduct. As a result, they play a crucial role in protecting financial institutions and their clients. Furthermore, machine learning facilitates tailored financial suggestions grounded on human preferences and risk profiles, optimizing investment approaches and enhancing consumer contentment. Machine learning is essential in healthcare for illness detection, optimizing therapy, and analyzing medical imaging. Medical professionals utilize machine learning algorithms to analyze intricate medical pictures, identify abnormalities, and forecast the advancement of diseases.
2. Introduction 2.1 Machine Learning Introduction Machine learning is a part of artificial intelligence that signifies a fundamental change in the way computers may independently acquire knowledge and adjust their behavior based on input. Machine learning algorithms differ from traditional programming in that they acquire knowledge from data rather than relying on explicit instructions. This allows them to analyze patterns and correlations and make predictions, classifications, and judgments autonomously, without the need for human interaction. However, the nonlinear behavior of concrete regression models created using this approach may not adequately reflect its underlying nature. The fundamental principle of machine learning is statistical learning, in which computers utilize mathematical models to identify patterns and derive insights from datasets of different sizes and levels of complexity. Machine learning is wellsuited for jobs that include complicated rules that cannot be directly coded, or for activities where patterns are concealed within large volumes of data. Machine learning is widely employed in nearly all industries and respects of contemporary life. Machine
© 2024, IRJET
|
Impact Factor value: 8.226
2.3 Applications in the Civil Industry Modern modeling tools in civil engineering include artificial intelligence and machine learning. Experimentation validates the output models of these approaches, which model responses using input parameters. Machine learning algorithms are used in construction to estimate concrete strength. [1-5], Machine learning is crucial in the civil sector for
|
ISO 9001:2008 Certified Journal
|
Page 2341