Ultrasonic strength evaluation of underwater heterogeneous concrete using random forest model constrained by physical laws
Compressive strength evaluation of concrete is crucial for the safety of underwater structures. However, the concrete heterogeneity impedes accurate evaluation based on empirical formulas (EF) derived from linear regression. This study proposes a four-phase model to formulate physical laws (PL). The...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-07-01
|
| Series: | Case Studies in Construction Materials |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214509524013032 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841561285613846528 |
|---|---|
| author | Yunfei Zou Zijian Wang Zhishen Wu |
| author_facet | Yunfei Zou Zijian Wang Zhishen Wu |
| author_sort | Yunfei Zou |
| collection | DOAJ |
| description | Compressive strength evaluation of concrete is crucial for the safety of underwater structures. However, the concrete heterogeneity impedes accurate evaluation based on empirical formulas (EF) derived from linear regression. This study proposes a four-phase model to formulate physical laws (PL). The concrete heterogeneity including sand-aggregate ratio (S/A), water-cement ratio (W/C), and diameter of average aggregate (Da), is considered along with the Rayleigh (R) and pressure (P) wave velocities. The proposed PLs are used to constrain the fitness functions of Particle Swarm (PS) optimization and Genetic Algorithms (GA), and the Random Forest (RF) model is enhanced to PL-PS-RF and PL-GA-RF models. Ultrasonic and compressive tests are performed on 96 specimens with 32 different mix parameters to train the models. The maximum error significantly decreases from 20 MPa to 5 MPa with the PL-PS-RF model. Parameter analysis reveals the mechanisms behind the improvements. The proposed methodology improves the evaluation accuracy and the testing is extended from an aerial to an underwater environment. |
| format | Article |
| id | doaj-art-b4c734ef4a5941fd8c64d15eac0f6ede |
| institution | Kabale University |
| issn | 2214-5095 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Case Studies in Construction Materials |
| spelling | doaj-art-b4c734ef4a5941fd8c64d15eac0f6ede2025-01-03T04:08:42ZengElsevierCase Studies in Construction Materials2214-50952025-07-0122e04151Ultrasonic strength evaluation of underwater heterogeneous concrete using random forest model constrained by physical lawsYunfei Zou0Zijian Wang1Zhishen Wu2Key Laboratory of C & PC Structures Ministry of Education, National and Local Unified Engineering Research Center for Basalt Fiber Production and Application Technology, Southeast University, Nanjing 211189, ChinaKey Laboratory of C & PC Structures Ministry of Education, National and Local Unified Engineering Research Center for Basalt Fiber Production and Application Technology, Southeast University, Nanjing 211189, ChinaCorresponding author.; Key Laboratory of C & PC Structures Ministry of Education, National and Local Unified Engineering Research Center for Basalt Fiber Production and Application Technology, Southeast University, Nanjing 211189, ChinaCompressive strength evaluation of concrete is crucial for the safety of underwater structures. However, the concrete heterogeneity impedes accurate evaluation based on empirical formulas (EF) derived from linear regression. This study proposes a four-phase model to formulate physical laws (PL). The concrete heterogeneity including sand-aggregate ratio (S/A), water-cement ratio (W/C), and diameter of average aggregate (Da), is considered along with the Rayleigh (R) and pressure (P) wave velocities. The proposed PLs are used to constrain the fitness functions of Particle Swarm (PS) optimization and Genetic Algorithms (GA), and the Random Forest (RF) model is enhanced to PL-PS-RF and PL-GA-RF models. Ultrasonic and compressive tests are performed on 96 specimens with 32 different mix parameters to train the models. The maximum error significantly decreases from 20 MPa to 5 MPa with the PL-PS-RF model. Parameter analysis reveals the mechanisms behind the improvements. The proposed methodology improves the evaluation accuracy and the testing is extended from an aerial to an underwater environment.http://www.sciencedirect.com/science/article/pii/S2214509524013032Ultrasonic testingCompressive strengthUnderwaterRandom forestParticle swarm optimizationGenetic algorithm |
| spellingShingle | Yunfei Zou Zijian Wang Zhishen Wu Ultrasonic strength evaluation of underwater heterogeneous concrete using random forest model constrained by physical laws Case Studies in Construction Materials Ultrasonic testing Compressive strength Underwater Random forest Particle swarm optimization Genetic algorithm |
| title | Ultrasonic strength evaluation of underwater heterogeneous concrete using random forest model constrained by physical laws |
| title_full | Ultrasonic strength evaluation of underwater heterogeneous concrete using random forest model constrained by physical laws |
| title_fullStr | Ultrasonic strength evaluation of underwater heterogeneous concrete using random forest model constrained by physical laws |
| title_full_unstemmed | Ultrasonic strength evaluation of underwater heterogeneous concrete using random forest model constrained by physical laws |
| title_short | Ultrasonic strength evaluation of underwater heterogeneous concrete using random forest model constrained by physical laws |
| title_sort | ultrasonic strength evaluation of underwater heterogeneous concrete using random forest model constrained by physical laws |
| topic | Ultrasonic testing Compressive strength Underwater Random forest Particle swarm optimization Genetic algorithm |
| url | http://www.sciencedirect.com/science/article/pii/S2214509524013032 |
| work_keys_str_mv | AT yunfeizou ultrasonicstrengthevaluationofunderwaterheterogeneousconcreteusingrandomforestmodelconstrainedbyphysicallaws AT zijianwang ultrasonicstrengthevaluationofunderwaterheterogeneousconcreteusingrandomforestmodelconstrainedbyphysicallaws AT zhishenwu ultrasonicstrengthevaluationofunderwaterheterogeneousconcreteusingrandomforestmodelconstrainedbyphysicallaws |