Estimation of concrete materials uniaxial compressive strength using soft computing techniques
This study addresses a critical gap in concrete strength prediction by conducting a comparative analysis of three deep learning algorithms: convolutional neural networks (CNNs), gated recurrent units (GRUs), and long short-term memory (LSTM) networks. Unlike previous studies that employed various ma...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-11-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844023097104 |
| _version_ | 1797429617422761984 |
|---|---|
| author | Matiur Rahman Raju Mahfuzur Rahman Md Mehedi Hasan Md Monirul Islam Md Shahrior Alam |
| author_facet | Matiur Rahman Raju Mahfuzur Rahman Md Mehedi Hasan Md Monirul Islam Md Shahrior Alam |
| author_sort | Matiur Rahman Raju |
| collection | DOAJ |
| description | This study addresses a critical gap in concrete strength prediction by conducting a comparative analysis of three deep learning algorithms: convolutional neural networks (CNNs), gated recurrent units (GRUs), and long short-term memory (LSTM) networks. Unlike previous studies that employed various machine learning algorithms on diverse concrete types, our study focuses on mixed-design concrete and fine-tuned deep learning algorithms. The objective is to identify the optimal deep learning (DL) algorithm for predicting concrete uniaxial compressive strength, a crucial parameter in construction and structural engineering. The dataset comprises experimental records for mixed-design concrete, and models were developed and optimized for predictive accuracy. The results show that the CNN model consistently outperformed GRU and LSTM. Hyperparameter tuning and regularization techniques further improved model performance. This research offers practical solutions for material property prediction in the construction industry, potentially reducing resource burdens and enhancing efficiency and construction quality. |
| first_indexed | 2024-03-09T09:15:42Z |
| format | Article |
| id | doaj.art-4dec94c61b254578880a6e8183c1574b |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-03-09T09:15:42Z |
| publishDate | 2023-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-4dec94c61b254578880a6e8183c1574b2023-12-02T07:06:03ZengElsevierHeliyon2405-84402023-11-01911e22502Estimation of concrete materials uniaxial compressive strength using soft computing techniquesMatiur Rahman Raju0Mahfuzur Rahman1Md Mehedi Hasan2Md Monirul Islam3Md Shahrior Alam4Department of Civil Engineering, International University of Business Agriculture and Technology, Dhaka, 1230, BangladeshDepartment of Civil Engineering, International University of Business Agriculture and Technology, Dhaka, 1230, Bangladesh; Department of Civil Engineering, Kunsan National University, 558 Daehakro, Gunsan, Jeollabugdo, 54150, Republic of Korea; Corresponding author. Department of Civil Engineering, International University of Business Agriculture and Technology, Dhaka, 1230, Bangladesh.Department of Computer Science and Engineering, International University of Business Agriculture and Technology, Dhaka, 1230, BangladeshDepartment of Civil Engineering, International University of Business Agriculture and Technology, Dhaka, 1230, BangladeshDepartment of Civil Engineering, International University of Business Agriculture and Technology, Dhaka, 1230, Bangladesh; Local Government Engineering Department (LGED), LGED Bhaban, Dhaka, 1207, BangladeshThis study addresses a critical gap in concrete strength prediction by conducting a comparative analysis of three deep learning algorithms: convolutional neural networks (CNNs), gated recurrent units (GRUs), and long short-term memory (LSTM) networks. Unlike previous studies that employed various machine learning algorithms on diverse concrete types, our study focuses on mixed-design concrete and fine-tuned deep learning algorithms. The objective is to identify the optimal deep learning (DL) algorithm for predicting concrete uniaxial compressive strength, a crucial parameter in construction and structural engineering. The dataset comprises experimental records for mixed-design concrete, and models were developed and optimized for predictive accuracy. The results show that the CNN model consistently outperformed GRU and LSTM. Hyperparameter tuning and regularization techniques further improved model performance. This research offers practical solutions for material property prediction in the construction industry, potentially reducing resource burdens and enhancing efficiency and construction quality.http://www.sciencedirect.com/science/article/pii/S2405844023097104Concrete compressive strengthDeep learningComparative analysisModel optimizationMix design |
| spellingShingle | Matiur Rahman Raju Mahfuzur Rahman Md Mehedi Hasan Md Monirul Islam Md Shahrior Alam Estimation of concrete materials uniaxial compressive strength using soft computing techniques Heliyon Concrete compressive strength Deep learning Comparative analysis Model optimization Mix design |
| title | Estimation of concrete materials uniaxial compressive strength using soft computing techniques |
| title_full | Estimation of concrete materials uniaxial compressive strength using soft computing techniques |
| title_fullStr | Estimation of concrete materials uniaxial compressive strength using soft computing techniques |
| title_full_unstemmed | Estimation of concrete materials uniaxial compressive strength using soft computing techniques |
| title_short | Estimation of concrete materials uniaxial compressive strength using soft computing techniques |
| title_sort | estimation of concrete materials uniaxial compressive strength using soft computing techniques |
| topic | Concrete compressive strength Deep learning Comparative analysis Model optimization Mix design |
| url | http://www.sciencedirect.com/science/article/pii/S2405844023097104 |
| work_keys_str_mv | AT matiurrahmanraju estimationofconcretematerialsuniaxialcompressivestrengthusingsoftcomputingtechniques AT mahfuzurrahman estimationofconcretematerialsuniaxialcompressivestrengthusingsoftcomputingtechniques AT mdmehedihasan estimationofconcretematerialsuniaxialcompressivestrengthusingsoftcomputingtechniques AT mdmonirulislam estimationofconcretematerialsuniaxialcompressivestrengthusingsoftcomputingtechniques AT mdshahrioralam estimationofconcretematerialsuniaxialcompressivestrengthusingsoftcomputingtechniques |