Nov 2026· Journal of Legal Affairs and Dispute Resolution in Engineering and Construction· 0 citations· 16 references
TL;DR
Model-based life-cycle evaluation indicates that AI-optimized PPP contracts reduce bridges reaching emergency condition by 30%–40% over a 30-year horizon while lowering life-cycle costs by 8%–12% compared with rule-based policies, providing infrastructure agencies and private concessionaires with an integrated AI-driven life-cycle management platform.
Abstract
Aging bridges, tight budgets, and procurement inefficiencies require a data-driven approach to maintenance contracts. Existing evidence shows that information and communication technology (ICT)–based construction management improves site productivity but remains unevenly adopted, a significant percentage of consultant tenders were single bid with systematically higher award rates, and public–private partnership (PPP) models for bridges that use Markovian deterioration modeling and performance-based payments can incentivize preventive maintenance, but they remain sensitive to prediction errors. Building on these strands, we propose an artificial intelligence (AI)–enabled framework that predicts the risk and cost impact of single-bid procurement, forecasts bridge condition trajectories using ICT-derived inspection and monitoring data, and optimizes PPP payment schemes for life-cycle cost, service level, and robustness. Empirically, a dataset of 8,000–10,000 design and supervision tenders and a bridge inventory of 820 highway bridges are combined. Gradient-boosted trees and deep neural networks will predict the probability of single-bid tenders and the associated award premium and multistep bridge condition transitions at 5-year intervals, using traffic, structural type, condition indices, and intervention history as features. A reinforcement learning–based design module searches performance indicators and payment curves to generate PPP schemes that minimize net present cost and bridges reaching the worst condition state while constraining downside risk via conditional value at risk. Model-based life-cycle evaluation indicates that AI-optimized PPP contracts reduce bridges reaching emergency condition by 30%–40% over a 30-year horizon while lowering life-cycle costs by 8%–12% compared with rule-based policies, providing infrastructure agencies and private concessionaires with an integrated AI-driven life-cycle management platform.
Uncertainty in infrastructure deterioration and maintenance cost forecasting continues to weaken the effectiveness of conventional maintenance contracts, contributing to budget overruns, delayed interventions, and inefficient risk allocation. This study develops a machine learning (ML)–enhanced adaptive performance-based maintenance contract (APBMC) framework that integrates hybrid Markov–ML deterioration forecasting, dynamic payment adjustment logic, and parametric risk-sharing provisions within a unified decision support structure for bridge maintenance. The framework is calibrated using a 10-year dataset from 68 US bridges (2014–2023), incorporating inspection records, structural health monitoring (SHM) summaries, traffic loading, maintenance histories, and climate-exposure variables. A hybrid Markov–ML architecture is used to predict condition-state transitions and quantify uncertainty, and the resulting forecasts are translated into contract trigger points, adaptive maintenance responses, payment adjustments, and risk financing activation rules. The framework is evaluated through historical back-testing, scenario-based simulation, and sensitivity analysis of trigger thresholds, calibration settings, and risk-sharing configurations. Results indicate 91% overall predictive accuracy, with calibration error below 3% in the contract-relevant trigger region. Relative to the lump-sum baseline, the proposed APBMC framework reduces mean life-cycle maintenance cost by 22%, improves response time to critical repairs by 31%, and lowers major rehabilitation frequency by up to 18%. The integrated risk financing layer performs effectively under both condition-based triggers, with annual activation probabilities of 0.14–0.36, and flood-based triggers, with probabilities of 0.05–0.09, reducing the likelihood of unfunded major rehabilitation from 18% to below 5%. Sensitivity analysis further identifies stable operating regions for condition thresholds and model-mixing settings that improve cost certainty while maintaining resilience. The proposed APBMC framework demonstrates the value of coupling predictive analytics, adaptive contracting, and risk financing to support more resilient, transparent, and performance-oriented infrastructure maintenance governance.
Odey Alshboul, Ali Shehadeh· Journal of Infrastructure Sy...· 0 citations
Sustainable highway maintenance is increasingly important as road agencies face ageing assets, fiscal constraints and growing requirements for service reliability and resilience. Although digital technologies are widely used in inspection, prediction and construction control, less is known about how they support governance across the full maintenance process. This study examines a Chinese scientific highway maintenance pilot through a document-based qualitative case study. Drawing on project documents and public reports, it develops a framework linking three mechanisms: datafied demand assessment, model-based decision-making and adaptive scheduling. The findings show how digital inspection, remote sensing, multi-source data models and smart construction-control platforms turn dispersed deterioration information into traceable condition evidence, translate this evidence into life-cycle maintenance priorities and connect planning with implementation feedback. Project-reported indicators also suggest gains in inspection efficiency and monitoring timeliness, although the evidence does not permit a comprehensive assessment of sustainability outcomes. Together, the mechanisms strengthen the capacity to move from reactive repair towards evidence-based life-cycle maintenance, resource-conscious prioritisation and adaptive service delivery. The study contributes to sustainable transport infrastructure research by explaining the governance processes through which digital technologies can support highway maintenance and the conditions shaping their transferability.
Ran Huang, Guoping Yuan, Jingxian Wang· Sustainability· 0 citations
Construction contract durations are fixed during procurement, yet delivery often changes after risks materialize and formal extensions of time are approved. Although delays, extension-of-time claims, change orders, and risk-based duration estimation are well studied, less is known about how contract-amendment records can be converted into duration multipliers for planning. This paper develops a quantitative, document-based Risk-Calibrated Duration Multiplier framework linking initially contracted duration, approved extensions, and documented risk causes. The framework was applied to 197 signed works contracts from 60 projects within a broader portfolio of 63 EU-funded water and wastewater infrastructure projects, predominantly administered under FIDIC Red and Yellow Book conditions. The analysis combined duration multipliers, impact-weighted attribution of multi-risk amendments, risk-time coefficients, bootstrap uncertainty assessment, concentration indicators, benchmark regression models, and reconstruction validation. For completed contracts, the mean multiplier was 1.372, with P50, P80, and P90 values of 1.233, 1.635, and 1.886. Public-law procedural and design risk categories accounted for 60.9% of the total extension premium. The results show that contract-amendment records can be transformed into statistically interpretable planning parameters and used as a portfolio learning and contract-governance tool for more realistic infrastructure contract planning.
Probabilistic risk management has become central to delivering safer and more resilient building projects under growing cost, schedule, and sustainability pressures. This study synthesizes how probability-based approaches have been applied in building-related risk research and identifies unresolved gaps that limit their practical impact. Using a PRISMA-guided systematic literature review of the Scopus database, we screened 165 records and qualitatively analyzed 39 Q1–Q4 journal articles published between 2015 and 2025. The review applies a multi-dimensional framework that classifies studies by risk type, project type, life-cycle stage, building type, methodology, and geographic context. Quantitative designs dominate, particularly Monte Carlo simulation and Bayesian or Dynamic Bayesian Network models, which are frequently embedded in BIM-enabled and Digital Twin environments for cost, safety, and seismic performance assessment. Evidence shows that construction and financial risks, commercial and residential buildings, and construction and operation–maintenance stages attract most scholarly attention, while pre-construction phases, infrastructure assets, and developing-country contexts remain under-explored. The review develops an integrated conceptual map that links probabilistic techniques with risk categories and project settings, and highlights the citation influence of seminal contributions. It also reveals methodological imbalances (limited mixed-methods and participatory studies) and weak integration of probabilistic risk assessment with sustainability and resilience objectives. Future research should extend probabilistic risk models to under-represented geographies and project types, exploit hybrid quantitative–qualitative and AI-enhanced approaches, and embed climate and circular-economy considerations into construction risk decision-support tools.
Dariyono, Oei Fuk Jin Oei Fuk Jin· Jurnal Teknik Sipil dan Arsi...· 0 citations
Background: Traditional value-based ABC inventory classification allocates protection according to economic value, overlooking operational risk factors such as demand variability, lead time, and assembly criticality, and it couples safety-stock and replenishment-cycle decisions. Methods: We propose a Hybrid Risk-Value framework that decouples these two decisions: stock-keeping units (SKUs) are segmented by multivariate K-means clustering on operational risk variables to set safety-stock factors (Z), while ABC economic value sets replenishment cycle coverages (d). The framework is validated through stochastic discrete-event simulation on an anonymized dataset of 200 SKUs from an automotive supplier, under base, high-demand-variability, and extended-lead-time scenarios (20 replications each), and is benchmarked against both classic ABC and a coupled ABC-XYZ policy. Results: Across all scenarios, the Hybrid framework reduces average inventory investment and total logistical cost by approximately 26–28% relative to ABC (p<0.001) while maintaining the service level; stockout days remain statistically unchanged except under extended lead times. The coupled ABC-XYZ benchmark performs almost identically to ABC, indicating that the gains arise from decoupling rather than from variability-based segmentation alone. Conclusions: Decoupling safety-stock and replenishment decisions offers a capital-efficient, data-driven alternative to static financial segmentation for resilient industrial inventories.
Leonardo G. Hernández Landa, Carolina Solís Peña, Juan M. Hernández Ramos et al.· Logistics· 0 citations
The reliability of critical financial infrastructure has become a strategic imperative as digital payment platforms, central bank digital currencies (CBDCs), and real-time settlement systems expand globally. This article investigates the theoretical foundations and practical application of a multi-level Service Level Indicator (SLI) and Service Level Objective (SLO) model designed specifically for critical financial infrastructure environments. The study examines how technical observability metrics can be systematically mapped to business scenarios, regulatory compliance requirements, and operational continuity objectives. Using a comparative analytical framework and case-study evidence drawn from CBDC integration practice at a systemically important bank, the research demonstrates that hierarchically structured SLI/SLO contracts, combined with AI-driven observability, reduce mean time to recovery (MTTR) by an order of magnitude and enable proactive error budget management. The findings reveal that a four-layer SLI/SLO hierarchy covering business outcomes, service contracts, component metrics, and infrastructure signals is necessary and sufficient for aligning engineering reliability work with financial regulatory mandates. The article will be of interest to financial technology architects, reliability engineers, banking regulators, and researchers working at the intersection of distributed systems engineering and financial services compliance.
Natallia Kalivoshka· International Journal Of Eng...· 0 citations
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
MIT News · Artificial Intelligence· news.mit.eduAug 24, 2026
