Adaptive Real-Time Strain-Rate Control in CRS Consolidation Testing Using SARSA Reinforcement Learning
Downloads
This study presents a reinforcement-learning framework for real-time strain-rate control in Constant Rate of Strain (CRS) consolidation testing to hasten the testing process using the SARSA algorithm. The controller adaptively adjusts deformation rate based on evolving pore-pressure ratio, with a reward strategy designed to maintain an average pore-pressure ratio near 30% to ensure partially drained conditions consistent with CRS theory. Two normally consolidated clays with contrasting compressibility were modeled numerically using a 1-D CRS consolidation model to evaluate learning and testing performance. The results show that the SARSA agent autonomously learns soil-specific strain-rate policies and maintains smooth effective stress trajectories and stable pore-pressure ratio responses. Test duration reductions of 60-75% were achieved depending on soil type. The interpreted compression index (Cc) remains consistent with the baseline CRS values, confirming that reinforcement-learning-based strain-rate control can accelerate testing without compromising data integrity. The study demonstrates the feasibility of reinforcement learning for CRS testing and highlights practical potential for soil-responsive, adaptive strain-rate control. Current limitations include simulation-based evaluation, discretized action selection, and the need for multiple runs to achieve optimal convergence.
Downloads
[1] Smith, R. E., & Wahls, H. E. (1969). Consolidation Under Constant Rates of Strain. Journal of the Soil Mechanics and Foundations Division, 95(2), 519–539. doi:10.1061/jsfeaq.0001263.
[2] Gibson, R. E., England, G. L., & Hussey, M. J. L. (1967). The theory of one-dimensional consolidation of saturated clays. Geotechnique, 17(3), 261–273. doi:10.1680/geot.1967.17.3.261.
[3] Wang, W., Ke, L., & Gu, Y. (2024). A Strain-Controlled Finite Strain Model for CRD Consolidation of Saturated Clays Considering Non-Linear Compression and Permeability Relationships. Water (Switzerland), 16(19), 2858. doi:10.3390/w16192858.
[4] Singh, D. J., Paramkusam, B. R., & Prasad, A. (2022). Determination of Consolidation Parameters of Geomaterials Using Modified CRS Consolidation Testing System. KSCE Journal of Civil Engineering, 26(3), 1066–1079. doi:10.1007/s12205-021-0386-1.
[5] Prativi, A., Mochtar, N. E., & Mochtar, I. B. (2025). Assessment of Primary and Secondary Compression Parameters of Tropical Fibrous Peat Using Improved-CRS Consolidation Test. Civil Engineering Journal (Iran), 11(5), 1756–1771. doi:10.28991/CEJ-2025-011-05-03.
[6] Head, K. H. (1986). Manual of soil laboratory testing: Volume 1: Soil classification and compaction tests. Pentech Press, London, United Kingdom.
[7] Wissa, A. E. Z., Christian, J. T., Davis, E. H., & Heiberg, S. (1971). Consolidation at constant rate of strain. Journal of the Soil Mechanics and Foundations Division, 97(10), 1393–1413. doi:10.1061/JSFEAQ.0001679.
[8] ASTM D4186. (2012). Standard Test Method for One-Dimensional Consolidation Properties of Saturated Cohesive Soils Using Controlled-Strain Loading. ASTM International, Pennsylvania, United States. doi:10.1520/D4186_D4186M-12E01.
[9] Gorman, C., Hopkins, T., Deen, R., & Drnevich, V. (1978). Constant-Rate-of-Strain and Controlled-Gradient Consolidation Testing. Geotechnical Testing Journal, 1(1), 3–15. doi:10.1520/gtj10363j.
[10] Sheahan, T. C., & Watters, P. J. (1997). Experimental Verification of CRS Consolidation Theory. Journal of Geotechnical and Geoenvironmental Engineering, 123(5), 430–437. doi:10.1061/(asce)1090-0241(1997)123:5(430).
[11] Leroueil, S., & Hight, D. (2013). The Behaviour and Properties of Soft Soils. Géotechnique, 63(4), 393–409. doi:10.1680/geot.2013.63.4.393.
[12] Deltares. (2024). Evaluation linear isotach model: Laboratory study and literature review (Contribution to Regio Deal Bodemdaling Groene Hart, Project 42). Deltares, Delft, Netherlands.
[13] Viet, T. T., & Dung, P. H. (2024). Effect of Strain Rate on Consolidation Characteristics of Artificial Silty Clay: Insights from Modified Constant Rate of Strain Tests. International Journal of GEOMATE, 27(124), 87–94. doi:10.21660/2024.124.4705.
[14] Chen, B., Cai, Z., & Bergés, M. (2019). Gnu-RL: A precocial reinforcement learning solution for building HVAC control using a differentiable MPC policy. BuildSys 2019 - Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, 316–325. doi:10.1145/3360322.3360849.
[15] Asghari, V., Wang, Y., Biglari, A. J., Hsu, S.-C., & Tang, P. (2022). Reinforcement Learning in Construction Engineering and Management: A Review. Journal of Construction Engineering and Management, 148(11), 03122009. doi:10.1061/(asce)co.1943-7862.0002386.
[16] Wang, Z., & Hong, T. (2020). Reinforcement learning for building controls: The opportunities and challenges. Applied Energy, 269, 115036. doi:10.1016/j.apenergy.2020.115036.
[17] Mahmud Al-Neami, M. (2013). Effect of Loading Duration on the Parameters Obtained from Consolidation Test. Engineering and Technology Journal, 31(19), 59–69. doi:10.30684/etj.31.19a.5.
[18] Sridharan, A., Sivapullaiah, P., & Stalin, V. (1994). Effect of Short Duration of Load increment on the Compressibility of Soils. Geotechnical Testing Journal, 17(4), 488–496. doi:10.1520/gtj10309j.
[19] Won, J.-Y., Porter, B., & Cotton, B. (2010). End of Primary Consolidation for the Gulf Coast Soils. GeoFlorida, 1108–1115. doi:10.1061/41095(365)110.
[20] Crawford, C. B. (1986). State of the Art: Evaluation and Interpretation of Soil Consolidation Tests. ASTM Special Technical Publication, 1986, 71–103. doi:10.1520/stp34607s.
[21] Liu, H., Lin, P., & Wang, J. (2023). Machine learning approaches to estimation of the compressibility of soft soils. Frontiers in Earth Science, 11, 1147825. doi:10.3389/feart.2023.1147825.
[22] Yousefpour, N., & Fallah, S. (2018). Applications of Machine Learning in Geotechnics. Proceedings of the Civil Engineering Research in Ireland Conference, Dublin, Ireland.
[23] Kim, M., Senturk, M. A., Tan, R. K., Ordu, E., & Ko, J. (2024). Deep Learning Approach on Prediction of Soil Consolidation Characteristics. Buildings, 14(2), 450. doi:10.3390/buildings14020450.
[24] Dayan, P., & Watkins, C. J. (2002). Reinforcement learning. Stevens’ Handbook of Experimental Psychology, 103.
[25] Bufacchi, R. J., & Iannetti, G. D. (2019). The Value of Actions, in Time and Space. Trends in Cognitive Sciences, 23(4), 270–271. doi:10.1016/j.tics.2019.01.011.
[26] Sutton, R. S., & Barto, A. G. (1998). Reinforcement learning: An introduction. MIT Press, Cambridge, United States.
[27] Perkins, T. J., & Precup, D. (2002). A convergent form of approximate policy iteration. Proceedings of the 16th International Conference on Neural Information Processing Systems, 1627-1634. doi:10.5555/2968618.2968820.
[28] Zou, S., Xu, T., & Liang, Y. (2019). Finite-sample analysis for SARSA with linear function approximation. Advances in Neural Information Processing Systems, 778, 8668 - 8678. doi:10.5555/3454287.3455065.
[29] Zhang, S., des Combes, R. T., & Laroche, R. (2023). On the Convergence of SARSA with Linear Function Approximation. Proceedings of Machine Learning Research, 202, 41613–41646.
[30] Tata, G., & Austin, E. (2021). Investigation of Maximization Bias in Sarsa Variants. 2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings, 1–8. doi:10.1109/SSCI50451.2021.9660081.
[31] Achiam, J., Held, D., Tamar, A., & Abbeel, P. (2017). Constrained policy optimization. Proceedings of the 34th International Conference on Machine Learning (ICML 2017), 70, 22–31.
[32] Sadeghi Eshkevari, S., Sadeghi Eshkevari, S., Sen, D., & Pakzad, S. N. (2023). Active structural control framework using policy-gradient reinforcement learning. Engineering Structures, 274, 115122. doi:10.1016/j.engstruct.2022.115122.
[33] Yao, Y., Tam, V. W. Y., Wang, J., Le, K. N., & Butera, A. (2024). Automated construction scheduling using deep reinforcement learning with valid action sampling. Automation in Construction, 166, 105622. doi:10.1016/j.autcon.2024.105622.
[34] Kulhawy, F. H. (1992). Effect of lateral stress on CPT penetration pore pressures. Journal of Geotechnical Engineering, 118(10), 1657–1660. doi:10.1061/(ASCE)0733-9410(1992)118:10(1657.2).
[35] Marinho, F. A. M. (2005). Nature of Soil–Water Characteristic Curve for Plastic Soils. Journal of Geotechnical and Geoenvironmental Engineering, 131(5), 654–661. doi:10.1061/(asce)1090-0241(2005)131:5(654).
[36] Chai, J., & Carter, J. P. (2011). Deformation Analysis in Soft Ground Improvement. Geotechnical, Geological, and Earthquake Engineering. Springer, Dordrecht, Germany. doi:10.1007/978-94-007-1721-3.
- Authors retain all copyrights. It is noticeable that authors will not be forced to sign any copyright transfer agreements.
- This work (including HTML and PDF Files) is licensed under a Creative Commons Attribution 4.0 International License.
