Main Article Content
Abstract
Abstract
The optimization of concrete compressive strength is crucial for the development of durable and high-performance concrete structures. Thisㅤstudyㅤinvestigatesㅤthe applicationㅤof Artificial NeuralㅤNetworksㅤ(ANN) using Multi-Layer Perceptron (MLP) regression techniques to optimize the mix design of concrete. By leveraging MLP, a type of ANN known for its ability to model complex non-linear relationships, we aim to predict and enhance the compressiveㅤstrength of concrete based on various mix proportions. The study utilizes a dataset comprising different mix designs, including cement, water, aggregates, and admixtures. The MLP model is trained and validated using this dataset, demonstrating its capability to accurately predict concrete compressive strength. Results indicate that the MLP-based ANN model outperforms traditional mix design methods, providing more precise and reliable predictions. This approach not only enhancesㅤtheㅤunderstandingㅤofㅤtheㅤrelationships between mix components and compressive strength but also offers a robust tool for engineers to optimize concrete mixes effectively. The findings highlight the potential of integrating advanced computational techniques in civil engineering to achieve superior material performance..
Keywords: Optimization, Artificial Neural Networks, Multi-Layer Perceptron, Concrete Mix Design, Construction Materials
Abstrak
Optimasi kuat tekan beton sangat penting untuk pengembangan struktur beton yang tahan lama dan berkinerja tinggi. Studi ini meneliti penerapan Jaringan Syaraf Tiruan (JST) menggunakan teknik regresi Multi-Layer Perceptron (MLP) untuk mengoptimalkan desain campuran beton. Dengan memanfaatkan MLP, jenis JST yang dikenal karena kemampuannya untuk memodelkan hubungan non-linear yang kompleks, kami bertujuan untuk memprediksi dan meningkatkan kuat tekan beton berdasarkan berbagai proporsi campuran. Studi ini menggunakan dataset yang terdiri dari berbagai desain campuran, termasuk semen, air, agregat, dan bahan tambahan. Model MLP dilatih dan divalidasi menggunakan dataset ini, menunjukkan kemampuannya untuk memprediksi kuat tekan beton dengan akurat. Hasil penelitian menunjukkan bahwa model JST berbasis MLP mengungguli metode desain campuran tradisional, memberikan prediksi yang lebih tepat dan andal. Pendekatan ini tidak hanya meningkatkan pemahaman tentang hubungan antara komponen campuran dan kuat tekan, tetapi juga menawarkan alat yang kuat bagi para insinyur untuk mengoptimalkan campuran beton secara efektif. Temuan ini menyoroti potensi integrasi teknik komputasi canggih dalam teknik sipil untuk mencapai kinerja material yang unggul
Kata kunci: Optimasi, Jaringan Syaraf Tiruan, Multi-Layer Perceptron, Desain Campuran Beton, Material Konstruksi
Keywords
Article Details
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License