Estimation of Ultimate Bearing Capacity in Rock-Socketed Piles Using Optimized Machine Learning Approaches
Rock-socketed piles, frequently employed in soft ground foundations, represent a matter of paramount issue in research, design, and construction, primarily because of their bearing capacity. The precise estimation of the Ultimate Bearing Capacity (Qu) of these rock-socketed piles proves to be a form...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Bilijipub publisher
2023-12-01
|
| Series: | Advances in Engineering and Intelligence Systems |
| Subjects: | |
| Online Access: | https://aeis.bilijipub.com/article_186528_de4caa0aeef17acfd8d6504f81778d47.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823856400961372160 |
|---|---|
| author | Ali Hassan Hamza Rashid |
| author_facet | Ali Hassan Hamza Rashid |
| author_sort | Ali Hassan |
| collection | DOAJ |
| description | Rock-socketed piles, frequently employed in soft ground foundations, represent a matter of paramount issue in research, design, and construction, primarily because of their bearing capacity. The precise estimation of the Ultimate Bearing Capacity (Qu) of these rock-socketed piles proves to be a formidable challenge, primarily due to the inherent uncertainties associated with the myriad factors influencing this capacity. This article introduces an innovative methodology for the precise prediction of Qu. This approach leverages the Naive Bayes (NB) algorithm to construct exact and comprehensive predictive models. To enhance the model's precision, the study incorporates two state-of-the-art meta-heuristic algorithms, the Artificial Hummingbird Algorithm (AHA) and the Improved Grey Wolf Optimizer (IGWO), into the analysis. This amalgamation gives rise to three distinct models: NBAH, NBIG, and the NB hybrid models. Moreover, the implemented method is assessed against the results obtained from experiments by some evaluators including R2, RMSE, RSR, MAE, WAPE, and SI. Of these models, the NBIG model emerges as a standout performer, boasting remarkable R2 value of 0.993 (lower than 1% enhanced performance compared to NBAH) and an ideal RMSE of 1381.3 (about 16% lower than that of NBAH) during the training phase. These impressive metrics underscore the model's exceptional accuracy and unwavering dependability in predicting the Qu of rock-socketed piles. |
| format | Article |
| id | doaj-art-1437ed784e244de29627d243169afbef |
| institution | Kabale University |
| issn | 2821-0263 |
| language | English |
| publishDate | 2023-12-01 |
| publisher | Bilijipub publisher |
| record_format | Article |
| series | Advances in Engineering and Intelligence Systems |
| spelling | doaj-art-1437ed784e244de29627d243169afbef2025-02-12T08:47:31ZengBilijipub publisherAdvances in Engineering and Intelligence Systems2821-02632023-12-010020410712010.22034/aeis.2023.427941.1150186528Estimation of Ultimate Bearing Capacity in Rock-Socketed Piles Using Optimized Machine Learning ApproachesAli Hassan0Hamza Rashid1Department of Mechatronics Engineering, Center of Industrial Electronics (CIE), University of Southern Denmark, Sønderborg, 6400, DenmarkDepartment of Mechatronics Engineering, Center of Industrial Electronics (CIE), University of Southern Denmark, Sønderborg, 6400, DenmarkRock-socketed piles, frequently employed in soft ground foundations, represent a matter of paramount issue in research, design, and construction, primarily because of their bearing capacity. The precise estimation of the Ultimate Bearing Capacity (Qu) of these rock-socketed piles proves to be a formidable challenge, primarily due to the inherent uncertainties associated with the myriad factors influencing this capacity. This article introduces an innovative methodology for the precise prediction of Qu. This approach leverages the Naive Bayes (NB) algorithm to construct exact and comprehensive predictive models. To enhance the model's precision, the study incorporates two state-of-the-art meta-heuristic algorithms, the Artificial Hummingbird Algorithm (AHA) and the Improved Grey Wolf Optimizer (IGWO), into the analysis. This amalgamation gives rise to three distinct models: NBAH, NBIG, and the NB hybrid models. Moreover, the implemented method is assessed against the results obtained from experiments by some evaluators including R2, RMSE, RSR, MAE, WAPE, and SI. Of these models, the NBIG model emerges as a standout performer, boasting remarkable R2 value of 0.993 (lower than 1% enhanced performance compared to NBAH) and an ideal RMSE of 1381.3 (about 16% lower than that of NBAH) during the training phase. These impressive metrics underscore the model's exceptional accuracy and unwavering dependability in predicting the Qu of rock-socketed piles.https://aeis.bilijipub.com/article_186528_de4caa0aeef17acfd8d6504f81778d47.pdfultimate bearing capacitynaive bayesartificial hummingbird algorithmimproved grey wolf optimizer |
| spellingShingle | Ali Hassan Hamza Rashid Estimation of Ultimate Bearing Capacity in Rock-Socketed Piles Using Optimized Machine Learning Approaches Advances in Engineering and Intelligence Systems ultimate bearing capacity naive bayes artificial hummingbird algorithm improved grey wolf optimizer |
| title | Estimation of Ultimate Bearing Capacity in Rock-Socketed Piles Using Optimized Machine Learning Approaches |
| title_full | Estimation of Ultimate Bearing Capacity in Rock-Socketed Piles Using Optimized Machine Learning Approaches |
| title_fullStr | Estimation of Ultimate Bearing Capacity in Rock-Socketed Piles Using Optimized Machine Learning Approaches |
| title_full_unstemmed | Estimation of Ultimate Bearing Capacity in Rock-Socketed Piles Using Optimized Machine Learning Approaches |
| title_short | Estimation of Ultimate Bearing Capacity in Rock-Socketed Piles Using Optimized Machine Learning Approaches |
| title_sort | estimation of ultimate bearing capacity in rock socketed piles using optimized machine learning approaches |
| topic | ultimate bearing capacity naive bayes artificial hummingbird algorithm improved grey wolf optimizer |
| url | https://aeis.bilijipub.com/article_186528_de4caa0aeef17acfd8d6504f81778d47.pdf |
| work_keys_str_mv | AT alihassan estimationofultimatebearingcapacityinrocksocketedpilesusingoptimizedmachinelearningapproaches AT hamzarashid estimationofultimatebearingcapacityinrocksocketedpilesusingoptimizedmachinelearningapproaches |