Artificial intelligence for prognostics and health management in off-highway vehicles: a systematic review of methods, data challenges, and deployment considerations
Aug 2026· Frontiers of Mechanical Engineering· Vol 12· 0 citations· 47 references
TL;DR
This systematic review synthesizes AI-driven prognostic methods, data challenges, and deployment considerations specific to off-highway operation, and contrasts the primary prognostic frameworks—data-driven, physics-based, and hybrid—and the role of knowledge-based expert systems in delivering interpretable alerts.
Abstract
Off-highway machines, agricultural harvesters, construction excavators, and mining haul trucks operate under extreme load variability, harsh unstructured environments, and constrained sensor instrumentation, creating prognostic conditions fundamentally different from on-road vehicles. While AI-enabled predictive maintenance has matured for passenger vehicles and well-instrumented industrial assets, and off-highway telematics adoption is expanding rapidly, its translation to these software-defined field machines remains insufficiently addressed. This systematic review synthesizes AI-driven prognostic methods, data challenges, and deployment considerations specific to off-highway operation. Following a PRISMA 2020 protocol, the 2014–2025 literature is screened across seven databases, with the 51 studies retained for synthesis additionally quantified by method family, equipment sector, and publication year to expose the relative scarcity of off-highway-specific evidence, and a wide range of methodologies is synthesized, from foundational supervised learning (SVMs, Random Forests) and advanced deep learning (CNNs, LSTMs for RUL prediction) to unsupervised (Autoencoders), ensemble, and transfer-learning techniques. The review contrasts the primary prognostic frameworks—data-driven, physics-based, and hybrid—and the role of knowledge-based expert systems in delivering interpretable alerts. A significant focus is placed on the data pipeline, including sensor selection strategies, data quality, feature engineering, severe class imbalance, and labeling complexity. Implementation hurdles such as operating-condition variability, model validation, the computational constraints of edge devices, and Explainable AI (XAI) are further examined, with a critical analysis of where each method degrades under field variability. Finally, emerging directions are explored, including Digital Twins and Edge Computing, closing with reformulated, off-highway-specific research gaps for real-world deployment.
Artificial intelligence, when responsibly implemented, represents a transformative adjunct to traditional safety practices – capable of significantly improving construction site safety performance globally – but it must be deployed in tandem with organizational commitment, worker training, and robust safety cultures.
Musaed M. Al-Thubaiti, Saeed S. Al-Shahrani, Ryan A. Alsaihaty· World Journal of Advanced En...· 0 citations
Traffic accidents involving heavy vehicles remain a critical safety challenge, with human factors being the primary contributors to fatality risks. While machine learning has been widely used for accident prediction, the lack of model interpretability often hinders its application in real-world policy-making. This study proposes a robust intelligent framework to classify truck driver fatalities on Brazilian federal highways by specifically isolating human-factor variables. Leveraging an extensive dataset from the Brazilian Federal Highway Police (2013–2025), we conducted a comparative analysis of three ensemble-based algorithms: Random Forest, XGBoost, and LightGBM. To ensure model stability and generalization, hyperparameter optimization was executed using RandomizedSearchCV with five-fold cross-validation. The experimental results demonstrate that while Random Forest achieved high training accuracy, LightGBM emerged as the superior model for safety-critical deployment, achieving a balanced ROC-AUC of 0.843 and a superior recall, effectively minimizing life-threatening false negatives. Furthermore, this research integrates SHAP (SHapley Additive exPlanations) to provide a knowledge-based interpretation of the model's decisions. The XAI analysis reveals that “Accident Type” and specific “Human Factor Categories” are the most significant predictors of fatality. The findings provide a transparent, data-driven decision support tool for transportation authorities to implement targeted interventions, bridging the gap between complex black-box models and actionable road safety knowledge.
Rossi Passarella, Fauziah Rachel Audrey Chelsea, Novi Yusliani· Intelligent Data Analysis· 0 citations
Rotating machinery is essential to energy, aerospace, manufacturing, and other safety-critical industries. Although deep-learning-based fault diagnosis has achieved high accuracy, its black-box nature limits trust, verification, and industrial deployment. This review examines explainable artificial intelligence for rotating machinery fault diagnosis and classifies existing methods into ante hoc and post hoc approaches according to their integration with model architectures. Their physical interpretability, applicable fault scenarios, explanation quality, computational overhead, robustness, and edge-deployment potential are critically compared. Quantitative criteria, including fidelity, stability, robustness, localization, and physical consistency are discussed to support objective evaluation of explanations. The review further highlights the gap between laboratory validation and industrial operation, particularly under sensor degradation, electromagnetic interference, variable working conditions, limited computing resources, and scarce fault data. It also discusses how model-relative explanations can be mapped to calibrated vibration quantities, fault-characteristic frequencies, industrial diagnostic standards, and actionable maintenance decisions. The distinction between correlation-based attribution and causal root-cause analysis is clarified, together with the role of digital twins and human-in-the-loop decision support. Finally, future research priorities are identified in standardized benchmarking, robust lightweight models, causal reasoning, and human-centered industrial deployment.
Shengnan Tang, Zeng-Yu Ren, Lei-Qi Zheng et al.· Italian National Conference...· 0 citations
Underground coal mining remains one of the most hazardous industrial activities worldwide, particularly in emerging economies where complex geological conditions, methane emissions, roof instability, dust exposure, and equipment-related accidents continue to threaten worker safety. India, the world's second-largest coal producer, operates numerous underground mines under challenging geotechnical and environmental conditions. Despite significant advancements in mechanization and monitoring technologies, accident investigations indicate that a substantial proportion of mining incidents remain attributable to delayed hazard detection, fragmented monitoring systems, and limited predictive capabilities. Conventional safety management approaches are largely reactive, relying on threshold-based alarms and post-event analysis rather than proactive risk prediction. This study proposes a Mining 5.0-oriented intelligent safety framework that integrates Artificial Intelligence of Things (AIoT), Physics-Informed Neural Networks (PINNs), wearable sensing technologies, and Digital Twin models for real-time hazard prediction and decision support in underground coal mines. The proposed framework combines data from methane sensors, temperature sensors, air velocity monitors, geotechnical instruments, equipment health monitoring systems, and wearable devices measuring worker location, physiological status, and environmental exposure. These heterogeneous data streams are fused within a Digital Twin environment that continuously replicates underground mine conditions. PINNs are employed to incorporate ventilation physics, methane transport dynamics, and geomechanical principles into machine-learning models, thereby improving prediction accuracy and interpretability under sparse or uncertain data conditions. The study identifies critical research gaps in existing mine safety systems, including inadequate integration of physical laws with AI models, limited utilization of worker-centric sensing technologies, and the absence of comprehensive Digital Twin platforms for proactive safety management. To address these gaps, a socio-technical framework is developed that enables continuous risk assessment, predictive analytics, and human-AI collaborative decision-making. The proposed approach is expected to enhance situational awareness, reduce accident probability, improve emergency preparedness, and support sustainable Mining 5.0 transformation in India.
S. Kushwaha, R. Chaurasia· International Journal of Sci...· 0 citations
Emissions monitoring in the United States is being reconstructed around dense, heterogeneous sensing and algorithmic inference. Low-cost electrochemical and optical sensors, mobile platforms, aircraft-mounted imaging spectrometers, point-in-space continuous monitors, and polar-orbiting and geostationary satellites now generate observations at scales and frequencies that regulatory reference networks were never designed to provide, and machine learning increasingly mediates the step from raw signal to reported emission or exposure. This review critically appraises what that reconstruction has demonstrated, what remains uncertain, and where confidence is currently misplaced. Evidence was assembled through registry-based bibliographic searching and verified source-by-source, with emphasis on studies conducted in United States settings and published from 1995 onwards. Four findings recur across otherwise separate literatures. First, reported model performance is dominated by co-location conditions rather than deployment conditions, and cross-site, cross-season and cross-instrument transfer degrades in ways that headline coefficients of determination conceal. Second, blind controlled-release testing has become the strongest evidentiary design available for methane sensing and has no established equivalent in ambient sensor calibration, producing a marked asymmetry in the quality of validation evidence between adjacent fields. Third, heavy-tailed and intermittent emission distributions break the sampling assumptions embedded in both survey design and supervised learning, so that platform-specific estimates diverge for structural rather than analytical reasons. Fourth, fusion across platforms with different detection thresholds is frequently treated as additive when it is in fact a partial-detection problem requiring explicit statistical treatment. Errors in fused products are spatially structured and correlate with monitor density, so that inferential accuracy is lowest where policy attention is greatest. Priorities identified include standardised blind evaluation for ambient sensing, detection-probability-aware fusion, distribution-shift-resilient calibration, and reporting practices that expose spatial error structure rather than aggregate it away.
Emmanuel Kiplagat Teigong, Y. Magdalene· Asian journal of current res...· 0 citations
Mechanical failures in critical offshore components, such as pumps and compressors, constitute a major challenge and can contribute non-productive causes to the field in deepwater operations, estimated to account for up to 20% of total downtime, with substantial production and environmental impacts. Existing data-driven predictive maintenance solutions are often computationally intensive and ill-suited for operators with limited digital infrastructure. To address these limitations, we developed a novel, lightweight predictive maintenance framework that combines gradient-boosted decision trees (LightGBM) with real-time anomaly detection to forecast equipment failure risks in resource-constrained offshore environments. This solution, called OffshoreGuard, is validated on the NASA C-MAPSS FD001 benchmark dataset and integrates a prototype dashboard with a Large Language Model (LLM) interface to enable natural-language querying and automated maintenance report generation. The framework achieved a risk classification F1 score of 86.58% at 92.29% precision, a RUL estimation RMSE of 18.42 cycles with a relative error of 18.55%, and an anomaly detection F1 score of 73.39%. With a total serialised model footprint of 1.6 MB, OffshoreGuard is deployable on standard web infrastructure at zero licensing cost, offering an affordable and scalable solution for asset managers in the West African energy sector to enhance operational safety, reduce non-productive time, and extend equipment life cycles.
O. E. Lawal, N. N. Shiaki, G. K. Bagai et al.· SPE Nigeria Annual Internati...· 0 citations