Jul 2026· Proceedings of the International Conference on Business Excellence· Vol 20, pp. 181 - 190· 0 citations· 14 references
Abstract
Abstract This article examines the applications of artificial intelligence (AI) in risk management process in energy sector and the emergent adoption patterns across subsectors. The paper focuses on practical and observable deployments, building on recent academic work that frames AI as a driver for the energy transition while also highlighting governance, data and cybersecurity concerns. A dataset of 50 AI use-case instances was compiled and assessed, employing a structured content analysis, which were gathered from public data available for leading energy companies. Each case was coded according to four risk management stages (identification, analysis/assessment, prediction and mitigation/treatment), a primary AI capability class (e.g. predictive maintenance, forecasting/optimization, computer vision inspection, digital twins, robotics, neuro linguistic programming (NLP)/Generative AI, cybersecurity analytics) and a dominant risk-control archetype (e.g. reliability control, inspection at scale, resilience forecasting and response optimization, operational decision support).The results suggest that AI is most frequently integrated into mitigation pathways rather than utilized as a standalone analytics layer. There are two primary patterns that emerge: (1) reliability oriented solutions that focus on time-series anomaly detection and predictive maintenance, which connect sensor signals to maintenance actions and (2) resilience and inspection oriented solutions, particularly in utilities and nuclear contexts, that prioritize interventions and reduce exposure to hazards by utilizing forecasting/optimization and computer vision/robotics methods. Subsector comparisons demonstrate domain-specific risk fit: upstream / offshore prioritize reliability control and digital twins; utilities prioritize resilience forecasting and inspection at scale; and refining/downstream prioritize decision support and compliance-linked use cases. The results indicate that the value of AI in risk management is the reduction of the detection to action cycle. Equally, to progress on the automation maturity, it is necessary to improve cybersecurity governance, transparency and validation.
AI-related innovation initiatives in the energy sector have traditionally been viewed as sources of organisational complexity and potential vulnerability. The study aimed to analyse the interplay between energy security and the resilience of energy systems, to explore emerging risks associated with digitalisation and the implementation of intelligent systems, and to evaluate the managerial and policy measures necessary for the effective integration of AI into energy infrastructure. To achieve the stated objectives, open-access sources were utilised and an integrated approach was applied, combining general scientific and specialised research methods, with particular emphasis on advanced analytical, monitoring and automated technologies. The findings underscored the importance of investing in technological, human, and regulatory capacities to fully leverage the potential of AI. At the same time, the role of AI-driven tools in modern energy systems is increasing due to their contributions to digital resilience, operational stability, predictive maintenance, cybersecurity, and strategic decision-making. However, these developments are accompanied by corresponding risks. That is why the modern management system must evolve from an administrative and control-oriented function to an intelligent, analytical mechanism that integrates human expertise with algorithmic decision-making. In this way, digital resilience extends the concept of system resilience by integrating information technologies and AI-driven analytics to anticipate, absorb, and recover from disruptions, whether caused by physical, technological, or cyber incidents. This integration reduces subjectivity, enhances the accuracy of operational decisions, and ensures a transparent, adaptive, and scientifically grounded approach to strategic coordination. By combining advanced analytics, AI-driven automation, and proactive risk management, energy systems can achieve enhanced stability, operational reliability, and cybersecurity resilience in increasingly complex and digitally interconnected environments. Furthermore, leveraging global best practices and fostering cross-border collaboration in AI innovation and cybersecurity can accelerate the transformation of energy enterprises toward sustainable, intelligent, and resilient infrastructures
O. Degtiareva, Tetiana Kuklinova, V. Slatvinska et al.· Innovation and Sustainabilit...· 0 citations
Overhead crane operations remain a high-risk activity in heavy manufacturing, yet safety management often relies on static assessments that fail to capture real-time operational dynamics. In developing economies such as Indonesia, a significant digital gap hinders the adoption of high-cost IoT solutions, leaving safety data fragmented and reactive. This study aims to bridge this gap by developing and validating a Business Intelligence (BI) Safety Dashboard that utilizes bridge technologies, defined as cost-effective digital solutions that leverage existing administrative and operational data instead of dedicated IoT infrastructure, to provide real-time predictive risk insights. Following a Design Science Research (DSR) framework, a three-year longitudinal study (2024–2026) was conducted at a metal fabrication facility in West Java. A Weighted Dynamic Risk Score (WDRS) was formulated using Data Analysis Expressions (DAX), integrating incident logs, maintenance records, and operator certification data into a unified star schema model. The results demonstrate a 95% reduction in data processing time and a 30% increase in near-miss reporting. The proposed artifact successfully identified critical risk outliers, such as Crane 08 (WDRS = 8.3), and generated spatiotemporal heatmaps that pinpointed specific risk hotspots within the facility. These findings confirm that the BI Dashboard is a feasible and highly practical solution for resource-constrained environments, providing a scalable blueprint for Indonesian SMEs to achieve Industry 4.0 safety standards by leveraging existing administrative data for predictive maintenance and proactive safety interventions.
Ridwan Kurniaji, Nur Azizah, Mohamad Rakhmansyah et al.· IAIC Transactions on Sustain...· 0 citations
Faced with multiple challenges in the power marketing business, including diversified market entities, varied user demands, complex business processes, and personalized services, the traditional risk prevention and control model is unable to adapt to complex and systemic risks. This study proposes a digital risk control philosophy featuring "data-driven, process embedding, closed-loop collaboration and intelligent evolution", and constructs an all-chain strategic system of "intelligent identification-embedded interception-closed-loop rectification-platform empowerment". Applied to the scenario of abnormal electricity price identification, the Stacking ensemble learning model achieves an AUC of 0.983 and a recall rate of 92.7%. Digital risk control enables shifts from reactive to proactive, experience to data, exhibiting three-tiered value evolution and cross-domain transferability. Enhanced by model fusion and regional adaptation, it boosts practicality and generalization, providing pathways for robust power grid risk systems.
Chengjie Wang, Dachuan Liu, Peipei You et al.· International Conference on...· 0 citations
The Taj Trapezium Zone (TTZ), which includes the industrial areas of Firozabad and Mathura, was established to shield the Taj Mahal from the harmful effects of declining air quality. Accurate Air Quality Index (AQI) forecasting is crucial for executing the Graded Response Action Plan (GRAP) of the Commission for Air Quality Management, as it necessitates early warnings of pollution episodes. This study develops machine learning–based AQI forecasting models using real-time monitoring data from the Central Pollution Control Board, which includes 18 environmental parameters collected between February 2023 and October 2025. Four ensemble algorithms—AdaBoost, XGBoost, LightGBM, and CatBoost—were employed with TimeSeriesSplit validation, Optuna-based hyperparameter tuning, and extensive preprocessing. The findings show that the tuned CatBoost model delivered the best predictive performance, with R² values of 0.995 in Firozabad and 0.951 in Mathura. SHAP analysis highlighted site-specific pollutant influences, revealing that both PM2.5 and PM10 significantly impacted AQI variations in Firozabad, while PM10 was the primary factor affecting AQI levels in Mathura. The CPCB breakpoint methodology confirmed that the predicted AQI categories align with observed classifications, ensuring reliable GRAP decision support. By enabling 72-hour advance forecasts, the proposed models offer a practical early-warning framework for proactive pollution control, targeted emission management, and enhanced air quality governance within the TTZ region.
Swati Varshney· Journal of Intelligent Decis...· 0 citations
This research investigates the transformative role of Artificial Intelligence (AI) in demand forecasting as a critical driver for organizational waste reduction and environmental sustainability. By synthesizing contemporary literature and empirical case studies, the study demonstrates that AI-driven predictive models outperform traditional reactive methods by integrating real-time data and diverse external variables. The findings establish a clear causal pathway: increased forecasting accuracy directly mitigates overproduction and stockouts, significantly reducing physical waste and CO2e emissions. However, the study also identifies critical barriers to adoption, including data silos, poor data quality, and organizational resistance. The research concludes that while AI implementation requires substantial strategic investment in data governance and cultural change, it is a vital catalyst for transitioning toward resilient, proactive supply chains. Ultimately, the successful alignment of AI with lean management principles enables organizations to achieve triple-bottom-line objectives, fostering long-term productivity and a more sustainable global economy.
Pradinsha E T, R. Reshmi· International journal of bus...· 0 citations
It is demonstrated that intelligent automation increases resilience not through extreme autonomy, but through a combination of forecasting, digital twins, hybrid rules, and managed escalation.
R. V. Khrunichev, D. Orekhvo· EKONOMIKA I UPRAVLENIE: PROB...· 0 citations