Aug 2026· World Journal of Advanced Engineering Technology and Sciences· 0 citations
TL;DR
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.
Abstract
Construction sites consistently rank among the most hazardous work environments worldwide, contributing a disproportionate share of occupational injuries and fatalities. This paper provides a comprehensive review of how artificial intelligence (AI) technologies are being leveraged to enhance safety in construction, synthesizing findings from engineering, computer science, safety management, and related fields. The discussion spans current AI applications – including computer vision for real-time hazard detection, robotics and autonomous systems for risk elimination, machine learning-based predictive analytics for accident prevention, and natural language processing for safety knowledge mining – as well as future directions and global implementation challenges. Real-world examples from diverse regions illustrate AI’s potential, such as computer vision systems monitoring worker compliance and predictive algorithms that forecast incidents before they occur. Quantitative findings from recent studies are highlighted, including reductions in accident rates and improved detection accuracy, with statistical tables summarizing key data. While AI offers powerful new tools for mitigating construction risks (e.g., identifying unsafe conditions, augmenting worker decision-making, and removing personnel from harm’s way), this review also addresses hurdles such as data quality, worker acceptance, regulatory concerns, and the need fo,r integrated, “human-in-the-loop” safety management approaches. The paper concludes that AI, 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.
The mining industry continues to face significant safety challenges, particularly with powered haulage equipment (PHE). PHE incidents account for a substantial percentage of mining-related fatalities, often resulting from vehicle collisions, equipment rollovers, operator errors, and blind-spot hazards. Despite the industry’s efforts to improve safety protocols, fatal accidents involving haulage trucks remain persistent. The mining industry has increasingly adopted automation to enhance operational efficiency and improve safety, particularly in surface mines where haulage truck accidents remain a critical concern. Automation has significantly reduced human exposure to hazardous tasks by removing operators from dangerous environments, thereby mitigating risks associated with human error and fatigue-related accidents. However, achieving zero fatalities in mining operations remains an ongoing challenge, necessitating a deeper evaluation of current technologies and safety interventions. This paper explores the review and integration of advanced safety technologies, such as real-time monitoring, machine learning-based predictive models, and enhanced automation frameworks to improve hazard detection and response time. A structured methodology is employed to review automated systems, accident data analysis, and an assessment of automation technologies in active mining operations. Specific findings highlight the impact of automation on reducing accident rates, the effectiveness of various intervention strategies, and challenges in full-scale implementation. The novelty of this paper lies in its roadmap to achieving zero fatalities through a review of structured integration of automation and predictive safety interventions. It outlines the broader benefits of Automated Haulage Systems, including productivity gains and operational cost reductions, contributing to the ongoing discourse on mining safety by providing a data-driven framework for the successful implementation of automated haulage trucks, ensuring a safer and more efficient mining environment.
Auto repair workshops are high-risk environments where workers face frequent accidents caused by slips, trips, heavy lifting, exposure to hazardous substances, and malfunctioning equipment. Despite advances in occupational health and safety (OHS) regulations, accident rates in Romania and across the European Union remain above average, highlighting the need for new preventive strategies. This paper explores how artificial intelligence (AI) can be systematically applied to reduce operational and safety risks in auto repair shops. Accident statistics and a detailed risk assessment of slips, trips, and falls provide the foundation for analyzing AI-based solutions, including computer vision, augmented reality, smart floors, voice assistance, and predictive analytics. A six-month pilot project conducted in a Romanian auto repair shop demonstrated a 28% reduction in minor accidents, faster hazard detection, and measurable economic benefits, while also revealing challenges such as false positives, resistance to change, and maintenance requirements. The findings confirm that AI can move workplace safety from reactive to preventive management by enabling real-time monitoring, proactive alerts, and predictive forecasting. The study concludes that AI, when combined with training and organizational adaptation, can significantly enhance worker protection, operational efficiency, and sustainability in the automotive repair sector.
A. Cană, Claudia Borda, Adrian Moise et al.· Optimizing the Future: Manag...· 0 citations
This study formally evaluates the effectiveness of AI models over multiple iterations of the models’ architecture for the domain-specific application of automated construction hazard assessment from multimodal inputs and introduces and validates high-fidelity, game engine-based synthetic images as a solution.
Trevor Neece, A. Fascetti· Journal of computing in civi...· 1 citation· ⚡1
Job Safety Analysis (JSA) and pre-task planning can benefit from prior incident records, yet historical accident data is often stored as unstructured narratives that are difficult to consult at the point of planning. A novel framework centered on large language models (LLMs) for highway construction safety reporting and planning is proposed as a foundation for future agentic applications, prioritizing deterministic, local inferencing. The first aim is to enable classification and quality scoring of incident narratives for existing and future reporting purposes. The second is to evaluate retrieval of relevant historical accidents, related imagery, and trusted industry documents for incorporation into daily safety plans. Neural probes were trained to classify incidents along four multiclass and two binary Occupational Injury and Illness Classification System (OIICS) fields and to derive an overall quality score, evaluated on a test set of over 15,000 narratives and a held-out set of 100 author-labeled records, benchmarked against a majority-vote LLM ensemble. The retrieval of historical accidents, reference imagery, and industry documents was benchmarked across embedding models using standard information retrieval metrics. OIICS classification reached 75% held-out accuracy, though the two binary flags were degenerate. The quality score, while meaningful on one database, was distorted on out-of-distribution fatalities in the held-out dataset. Accident retrieval recovered relevant incidents far above chance, performing best on lexically distinct construction activities. On document question answering, an open-weight decoder embedding model surpassed proprietary models. Overall, this work provides a new framework rooted in local inferencing and text embedding models for future agentic applications, with emphasis on bridging external data to JSA reports.
M. Smetana, Trevor Neece, Lev Khazanovich· 0 citations
The mining industry is a risky sphere of industry that is characterized by unstable geological conditions, the dangerous environment, and the active use of machinery. Traditional safety systems are based on manual surveillance and limits-like warnings, which are reactive in nature and cannot be used to mitigate the risk early enough. This paper suggests a next-generation AI system that can be used to predict hazards on-site and optimize safety in mining systems. The framework combines IoT-permitted environmental sensing, computer vision, and sophisticated machine learning models to continuously determine the level of gases, the structural integrity, machine well-being, and workers. The deep learning is also used in estimating non-destructive ore quality by using image-based mineral analysis, which facilitates effective resource management. Long short-term memory networks (LSTM) and Autoencoders are predictive models that learn and identify anomalies, predict possible failures, and calculate a dynamic risk index. The analytics dashboard is a cloud-driven solution with a hierarchy of alerts that allow proactive action to be taken. The accuracy in hazard detection and ore prediction is high in an experimental result and has a significant improvement in accuracy compared to traditional systems. The proposed architecture will contribute to the operational safety, efficiency, and sustainability and will lead to intelligent and autonomous mining ecosystems.
S. Santhoshkumar, Thota Bramaramba, Pasupuleti Sankar· 2026 6th International Confe...· 0 citations
Suggestions for ensuring safe person detection using AI in industrial environments are offered, including suggestions for ensuring safe person detection using AI in industrial environments.
Iwo Kurzidem, Andrea Matic-Flierl, Poulami Sinhamahapatra et al.· 0 citations