Design of an Energy Pile Based on CPT Data Using Soft Computing Techniques
The present study focused on the design of geothermal energy piles based on cone penetration test (<i>CPT</i>) data, which was obtained from the Perniö test site in Finland. The geothermal piles are heat-capacity systems that provide both a supply of energy and structural support to civi...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-12-01
|
Series: | Infrastructures |
Subjects: | |
Online Access: | https://www.mdpi.com/2412-3811/7/12/169 |
_version_ | 1797457159808614400 |
---|---|
author | Pramod Kumar Pijush Samui |
author_facet | Pramod Kumar Pijush Samui |
author_sort | Pramod Kumar |
collection | DOAJ |
description | The present study focused on the design of geothermal energy piles based on cone penetration test (<i>CPT</i>) data, which was obtained from the Perniö test site in Finland. The geothermal piles are heat-capacity systems that provide both a supply of energy and structural support to civil engineering structures. In geotechnical engineering, it is necessary to provide an efficient, reliable, and precise method for calculating the group capacity of the energy piles. In this research, the first aim is to determine the most significant variables required to calculate the energy pile capacity, i.e., the pile length (<i>L</i>), pile diameter (<i>D</i>), average cone resistance (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>q</mi><mrow><mi>c</mi><mn>0</mn></mrow></msub></mrow></semantics></math></inline-formula>), minimum cone resistance (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>q</mi><mrow><mi>c</mi><mn>1</mn></mrow></msub></mrow></semantics></math></inline-formula>), average of minimum cone resistance (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>q</mi><mrow><mi>c</mi><mn>2</mn></mrow></msub></mrow></semantics></math></inline-formula>), cone resistance (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>q</mi><mi>c</mi></msub></mrow></semantics></math></inline-formula>), Young’s modulus (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>E</mi></semantics></math></inline-formula>), coefficient of thermal expansion (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>α</mi><mi>c</mi></msub></mrow></semantics></math></inline-formula>), and temperature change (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>Δ</mo><mi>T</mi></mrow></semantics></math></inline-formula>). The values of <i>q<sub>c</sub></i><sub>0</sub><i>, q<sub>c</sub></i><sub>1</sub><i>, q<sub>c</sub></i><sub>2</sub><i>, q<sub>c</sub>,</i> and <i>E</i> are then employed as model inputs in soft computing algorithms, which includes random forest (<i>RF</i>), the support vector machine (<i>SVM</i>), the gradient boosting machine (<i>GBM</i>), and extreme gradient boosting (<i>XGB</i>) in order to predict the pile group capacity. The developed soft computing models were then evaluated by using several statistical criteria, and the lowest system error with the best performance was attained by the <i>GBM</i> technique. The performance parameters, such as the coefficient of determination (<i>R</i><sup>2</sup>), root mean square error (<i>RMSE</i>), mean absolute error (<i>MAE</i>), mean biased error (<i>MBE</i>), median absolute deviation (<i>MAD</i>), weighted mean absolute percentage error (<i>WMAPE</i>), expanded uncertainty (<i>U</i><sub>95</sub>), global performance indicator (<i>GPI</i>), Theil’s inequality index (<i>TIC</i>), and the index of agreement (<i>IA</i>) values of the testing data for the <i>GBM</i> models are 0.80, 0.10, 0.08, −0.01, 0.06, 0.21, 0.28, −0.00, 0.11, and 0.94, respectively, demonstrating the strength and capacity of this soft computing algorithm in evaluating the pile’s group capacity for the energy pile. Rank analysis, error matrix, Taylor’s diagram, and the reliability index have all been developed to compare the proposed model’s accuracy. The results of this research also show that the <i>GBM</i> model developed is better at estimating the group capacity of energy piles than the other soft computing models. |
first_indexed | 2024-03-09T16:18:11Z |
format | Article |
id | doaj.art-d87a093c794346b7883d13f6d8f41f93 |
institution | Directory Open Access Journal |
issn | 2412-3811 |
language | English |
last_indexed | 2024-03-09T16:18:11Z |
publishDate | 2022-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Infrastructures |
spelling | doaj.art-d87a093c794346b7883d13f6d8f41f932023-11-24T15:37:49ZengMDPI AGInfrastructures2412-38112022-12-0171216910.3390/infrastructures7120169Design of an Energy Pile Based on CPT Data Using Soft Computing TechniquesPramod Kumar0Pijush Samui1Department of Civil Engineering, National Institute of Technology, Patna 800005, IndiaDepartment of Civil Engineering, National Institute of Technology, Patna 800005, IndiaThe present study focused on the design of geothermal energy piles based on cone penetration test (<i>CPT</i>) data, which was obtained from the Perniö test site in Finland. The geothermal piles are heat-capacity systems that provide both a supply of energy and structural support to civil engineering structures. In geotechnical engineering, it is necessary to provide an efficient, reliable, and precise method for calculating the group capacity of the energy piles. In this research, the first aim is to determine the most significant variables required to calculate the energy pile capacity, i.e., the pile length (<i>L</i>), pile diameter (<i>D</i>), average cone resistance (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>q</mi><mrow><mi>c</mi><mn>0</mn></mrow></msub></mrow></semantics></math></inline-formula>), minimum cone resistance (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>q</mi><mrow><mi>c</mi><mn>1</mn></mrow></msub></mrow></semantics></math></inline-formula>), average of minimum cone resistance (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>q</mi><mrow><mi>c</mi><mn>2</mn></mrow></msub></mrow></semantics></math></inline-formula>), cone resistance (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>q</mi><mi>c</mi></msub></mrow></semantics></math></inline-formula>), Young’s modulus (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>E</mi></semantics></math></inline-formula>), coefficient of thermal expansion (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>α</mi><mi>c</mi></msub></mrow></semantics></math></inline-formula>), and temperature change (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>Δ</mo><mi>T</mi></mrow></semantics></math></inline-formula>). The values of <i>q<sub>c</sub></i><sub>0</sub><i>, q<sub>c</sub></i><sub>1</sub><i>, q<sub>c</sub></i><sub>2</sub><i>, q<sub>c</sub>,</i> and <i>E</i> are then employed as model inputs in soft computing algorithms, which includes random forest (<i>RF</i>), the support vector machine (<i>SVM</i>), the gradient boosting machine (<i>GBM</i>), and extreme gradient boosting (<i>XGB</i>) in order to predict the pile group capacity. The developed soft computing models were then evaluated by using several statistical criteria, and the lowest system error with the best performance was attained by the <i>GBM</i> technique. The performance parameters, such as the coefficient of determination (<i>R</i><sup>2</sup>), root mean square error (<i>RMSE</i>), mean absolute error (<i>MAE</i>), mean biased error (<i>MBE</i>), median absolute deviation (<i>MAD</i>), weighted mean absolute percentage error (<i>WMAPE</i>), expanded uncertainty (<i>U</i><sub>95</sub>), global performance indicator (<i>GPI</i>), Theil’s inequality index (<i>TIC</i>), and the index of agreement (<i>IA</i>) values of the testing data for the <i>GBM</i> models are 0.80, 0.10, 0.08, −0.01, 0.06, 0.21, 0.28, −0.00, 0.11, and 0.94, respectively, demonstrating the strength and capacity of this soft computing algorithm in evaluating the pile’s group capacity for the energy pile. Rank analysis, error matrix, Taylor’s diagram, and the reliability index have all been developed to compare the proposed model’s accuracy. The results of this research also show that the <i>GBM</i> model developed is better at estimating the group capacity of energy piles than the other soft computing models.https://www.mdpi.com/2412-3811/7/12/169thermal loadenergy pilesmachine learning algorithmsreliability analysismodel comparison |
spellingShingle | Pramod Kumar Pijush Samui Design of an Energy Pile Based on CPT Data Using Soft Computing Techniques Infrastructures thermal load energy piles machine learning algorithms reliability analysis model comparison |
title | Design of an Energy Pile Based on CPT Data Using Soft Computing Techniques |
title_full | Design of an Energy Pile Based on CPT Data Using Soft Computing Techniques |
title_fullStr | Design of an Energy Pile Based on CPT Data Using Soft Computing Techniques |
title_full_unstemmed | Design of an Energy Pile Based on CPT Data Using Soft Computing Techniques |
title_short | Design of an Energy Pile Based on CPT Data Using Soft Computing Techniques |
title_sort | design of an energy pile based on cpt data using soft computing techniques |
topic | thermal load energy piles machine learning algorithms reliability analysis model comparison |
url | https://www.mdpi.com/2412-3811/7/12/169 |
work_keys_str_mv | AT pramodkumar designofanenergypilebasedoncptdatausingsoftcomputingtechniques AT pijushsamui designofanenergypilebasedoncptdatausingsoftcomputingtechniques |