Reimagining unbound road pavement technology: Integrating testing, design, construction and performance in the post-digital era

Transportation Geotechnics, Journal Year: 2024, Volume and Issue: 47, P. 101274 - 101274

Published: May 19, 2024

Language: Английский

---

Augmented intelligence framework for real-time ground assessment under significant uncertainty

Engineering With Computers, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 11, 2025

Abstract Real-time assessment of unsaturated soils through deflection tests is challenging due to the complex effects water and air in soil pores, which significantly impact test outcomes but are difficult quantify, especially when key data like gravimetric content suction incomplete or missing. While human expertise intuition valuable high-pressure scenarios ground during compaction, they prone biases. AI-driven solutions excel at processing datasets often require highly specialised inputs, may not always be readily available. This paper aims develop a robust pragmatic approach decision-support by combining insight with AI’s computational power principles from mechanics. outlines limitations current practices discusses challenges developing reliable using on soils. To address these challenges, an augmented intelligence framework introduced that leverages fuzzy inputs for missing information incorporates sophisticated self-improving mechanism estimate data, based insights gained calibration. enhances after validation recent field trial particularly uncertain subsurface conditions. The study also demonstrates framework’s resilience qualitative assessments, maintaining accuracy across range assumptions about content.

Language: Английский

---

Extension of the Boussinesq’s equation to reflect the actual changes in vertical stresses in geomaterials using LWD loading

International Journal of Pavement Engineering, Journal Year: 2025, Volume and Issue: 26(1)

Published: Feb. 13, 2025

Language: Английский

---

Real-time inference of compacted soil properties using deflection tests: An AI-driven solution informed by unsaturated soil mechanics principles

Computers and Geotechnics, Journal Year: 2024, Volume and Issue: 173, P. 106543 - 106543

Published: June 27, 2024

This paper presents a novel Artificial Intelligence (AI)-driven tool designed to convert deflection test results into crucial soil parameters essential for quality assurance in compaction projects. The accurate determination of these parameters, such as density and void ratio, is imperative ensuring the structural integrity infrastructures constructed on soils. Moreover, it facilitates utilization modern non-destructive equipment endeavors. notably challenging unsaturated soils owing intricate interplay among factors suction, moisture content, resulting deflection. pioneering address challenges. By integrating mechanics with advanced AI techniques, particularly reinforcement learning, leverages diverse array inputs, including in-situ data, experimental observations, physics-based modeling. integration enables dynamic adaptation changing field conditions tool's real-time adaptability predictive accuracy. Field trials validated efficacy predicting properties accurately without direct measurements content or variables often unmeasured practical unique capability underscores significant advancements assessment soils, illustrating transformative potential geotechnical engineering mechanics.

Language: Английский

---

Parameters in play: AlphaZero-Inspired AI for autonomous parameter identification in soil constitutive and finite element models

Computers and Geotechnics, Journal Year: 2024, Volume and Issue: 174, P. 106657 - 106657

Published: Aug. 12, 2024

In geotechnical engineering, the precise identification of essential soil parameters from sensing and experimental data is vital for accuracy constitutive finite element models. However, complexity sophisticated models often makes this task challenging. Traditional optimization methods that rely on gradient information fall short in class problems, due to their struggle with black box lacking clear pathways. Gradient-free methods, though circumventing need direct data, can still miss out integrating previous insights when faced new information. To tackle these issues, our study presents a cutting-edge method inspired by mechanisms underlying AlphaZero, DeepMind's acclaimed algorithm excels mastering complex strategic games through autonomous learning. By adopting comparable self-learning technique, approach reinvents parameter advanced as game. It draws parallel between optimizing model developing victorious chess tactics. This utilizes blend deep learning initial estimations Monte Carlo Tree Search (MCTS) finer adjustments, promoting self-enhancing calibration process. Such an paves way more self-reliant intelligent methodology data. The outcomes demonstrate robustness versatility across various models, ranging applications involving inverse analyses using include interactions mechanical devices unsaturated soils.

Language: Английский

---

Reimagining Unbound Road Pavement Technology: Integrating Testing, Design, Construction and Performance in the Post-Digital Era

Published: Jan. 1, 2024

The Industry 4.0 revolution signifies a pivotal transition in pavement technology, emphasising the integration of digital and physical systems to revamp traditional, empirical-based design, construction, maintenance practices. This shift promises enhanced efficiency, sustainability, move towards integrated practices, highlighted by adopting "Digital Twin" technology. Unlike traditional Building Information Modeling (BIM), Digital Twin technology offers real-time, dynamic representation infrastructure, enabling improved asset management through distributed sensing predictive performance analytics. Leveraging findings from Australian Research Council (ARC)'s Transformation Hub for Smart Next Generation Transport Pavements (SPARC Hub), this paper focuses on testing, condition assessment into lifecycle unbound road pavements,. outlines how such technological streamlines decision-making processes significantly boosts functionality longevity infrastructures. Despite facing challenges like cost, data security, need specialised skills, potential technologies improve durability, sustainability is significant. Future research directions are identified overcome implementation barriers, explore untapped potentials, assess benefits approaches engineering, aiming forge more resilient, efficient, sustainable networks future generations.

Language: Английский

---

Optimization of reduction gear in anchor winch based on modal analysis

Vibroengineering PROCEDIA, Journal Year: 2024, Volume and Issue: 56, P. 62 - 67

Published: Oct. 18, 2024

In order to achieve more scientific design of the reduction gear and reduce material waste, pre-stressed modal analysis method was combined with multi-objective optimization algorithm optimize structure basic body. The model simplified parameterized maximum stress equivalent stiffness under different parameter size combinations were obtained through finite element analysis. Separately, genetic clustering method, neural network Kriging used construct response surface function. Through error verification comparison, it found that suitable for model. variable extremum search, sequential quadratic programming compared analyzed. results show mass can be reduced by 39.9 %, while remains unchanged, is not reduced, a good effect achieved.

Language: Английский

---

From Non-destructive Testing to Ground Property Inference: Integration of AI and Unsaturated Soil Dynamics

Lecture notes in civil engineering, Journal Year: 2024, Volume and Issue: unknown, P. 183 - 189

Published: Oct. 21, 2024

Language: Английский

---

Dynamic response analysis and optimization of orbital support structure

Vibroengineering PROCEDIA, Journal Year: 2024, Volume and Issue: 57, P. 140 - 146

Published: Dec. 12, 2024

In order to further enhance the stability of orbital transportation, modal characteristics support structure were simulated and analyzed. The multi-objective optimization method was applied design for lightweighting while increasing first-order natural frequency reducing stress peak. Using ANSYS Workbench, parametric finite element model established, length intermediate rod, lateral rib regarded as parameterized dimensions. Through dynamic characteristic analysis, frequencies, shapes, harmonic response obtained. Parametric samples obtained by using Latin square method, approximate fitted polynomial function. Multi-Objective Genetic Algorithm Sequential Quadratic Programming calculation. results indicate that structurally lightened can attain higher strength stiffness.

Language: Английский

---