Search Results (47)

Fire incident reports contain detailed textual narratives that capture causal factors often overlooked in structured records, while financial damage amounts provide measurable outcomes of these events. Integrating these two sources of information is essential for uncovering interpretable links between descriptive causes and their economic consequences. To this end, we develop a data-driven framework that constructs a composite Risk Index, enabling systematic quantification of how specific keywords relate to property damage amounts. This index facilitates both the identification of high-impact terms and the aggregation of risks across semantically related clusters, thereby offering a principled measure of fire-related financial risk. Using more than a decade of Korean fire investigation reports on the chemical industry classified as Special Buildings (2013–2024), we employ topic modeling and network-based embedding to estimate semantic similarities from interactions among words, and subsequently apply Lasso regression to quantify their associations with property damage amounts, thereby estimating the fire risk index. This approach enables us to assess fire risk not only at the level of individual terms, but also within their broader textual context, where highly interactive related words provide insights into collective patterns of hazard representation and their potential impact on expected losses. The analysis highlights several domains of risk, including hazardous chemical leakage, unsafe storage practices, equipment and facility malfunctions, and environmentally induced ignition. The results demonstrate that text-derived indices provide interpretable and practically relevant insights, bridging unstructured narratives with structured loss information and offering a basis for evidence-based fire risk assessment and management. The derived Risk Index provides practical reference data for both safety management and insurance underwriting by enabling the prioritization of preventive measures within industrial sites and offering quantitative guidance for assessing facility-specific risk levels in insurance decisions. An R implementation of the proposed framework is openly available for public use. Full article

The production environments of coal mines are inherently complex, with interrelated disaster risks that challenge safety management. Current prediction systems struggle with fragmented data, limited mechanistic understanding, and inadequate early warnings, falling short of modern coal mine safety needs. This paper advances the thesis that artificial intelligence, including machine learning, deep learning, and Large Language Model, provides essential tools for overcoming these prediction challenges in coal mining. We review AI-based approaches for forecasting coal and gas outbursts, mine fires, water disasters, roof collapses, and dust disasters, analyzing them through technical principles, application scenarios, and empirical outcomes. The analysis clarifies how AI improves risk prediction accuracy, enhances data integration, and enables smarter decision-making for safety. By examining the five major hazards, we highlight ongoing challenges in AI implementation and outline pathways for future development, emphasizing the importance of large models and autonomous agents. Our findings support the creation of advanced AI-driven safety and early warning systems for coal mines. Full article

This article reveals the nature, causes, and main stages of occurrence and development of endogenous fires in coal mines. It is emphasized that one of the key tasks of fire protection specialists is the most accurate determination of the stage of oxidation and self-heating of coal. A review of existing gas analysis methods for identifying the initial and subsequent stages of endogenous fire development is conducted. Particular attention is focused on the importance of obtaining prompt reliable information on the self-heating temperature of coal and the dynamics of its change in the early stages of the process. Since self-heating zones are usually inaccessible for direct instrumental control, the main source of information is the gas analysis of air samples. The authors present the results of research on the dependence of the indicator gas content on the coal self-heating temperature. Based on the Graham criterion, the stages of thermal development of the process are predicted. Correlation dependencies between temperature and integral parameters of indicator gas concentrations are developed, allowing for a sufficient degree of reliability in determining the stages of coal self-heating and spontaneous combustion. Based on the results of the work, methodological recommendations for the prevention and warning of endogenous fires in coal mines and opencasts are proposed. They are based on the most informative and accessible signs suitable for quantitative assessment. The implementation of these recommendations will improve the level of industrial safety and reduce the risks of fires and explosions during mining operations. Full article

Mine fire is caused by external heat source or coal seam spontaneous combustion, and there are serious hidden dangers in mining operation. The existing detection methods have high cost, limited coverage and delayed response. An edge intelligent fire detection system based on multi-source information fusion is proposed. We enhance the YOLOv5s backbone network by (1) optimized small-target detection and (2) adaptive attention mechanism to improve recognition accuracy. In order to overcome the limitation of video only, a dynamic weighting algorithm combining video and multi-sensor data is proposed, which adjusts the strategy according to the real-time fire risk index. Deploying quantitative models on edge devices can improve underground intelligence and response speed. The experimental results show that the improved YOLOv5s is 7.2% higher than the baseline, the detection accuracy of the edge system in the simulated environment is 8.28% higher, and the detection speed is 26% higher than that of cloud computing. Full article

With the development of the mining industry, safety issues in underground operations are becoming increasingly relevant. Complex gas conditions in mines, including the presence of explosive and toxic gases, pose a serious threat to the lives of miners and the stability of production processes. This paper describes the development and modeling of an integrated fire monitoring and automatic extinguishing system that combines gas collection, concentration analysis, and rapid response to emergencies. The main components of the system include the following: a gas collection module that uses an array of highly sensitive sensors to continuously measure the concentrations of methane (CH₄), carbon monoxide (CO), and hydrogen sulfide (H₂S) with an accuracy of up to 95%; a gas analysis module that uses data processing algorithms to identify gas concentration threshold exceedances (e.g., CH₄ > 5% vol. or CO > 20 ppm); and an automatic fire extinguishing module that activates nitrogen supply, ventilation, and aerosol/powder fire extinguishers when a threat is detected. Simulation results in MATLAB/Simulink showed that the system reduces the concentration of hazardous gases by 30% within the first 2 s after activation, which significantly increases safety. Additionally, scenarios with various types of fires were analyzed, confirming the effectiveness of the extinguishing modules in mines up to 500 m deep. The integrated system achieves 95% gas detection accuracy, 90 ms response latency, and 40% hazard reduction within 3 s of activation, verified in 500 m deep mine simulations. Quantitative comparison shows a 75% faster response time and 10% higher detection accuracy than conventional systems. The proposed system demonstrates high reliability in difficult conditions, reducing the risk of fires by 75% compared to traditional methods. This work opens up prospects for practical application in the coal industry, especially in regions with a high risk of spontaneous coal combustion, such as India and Germany. Full article

The manuscript examines the cause-and-effect relationships of fires in the Republic of Serbia over a fifteen-year period, primarily from the aspect of human safety. For this purpose, numerical variables describing the number of injuries and deaths in fires were introduced, on which various analysis and modeling techniques were implemented, which can be viewed in the context of data mining (DM). First, for both observed variables, stochastic modeling of their temporal dynamics was analyzed, and subsequently, cluster analysis of the values of these variables was performed using two different methods. Finally, by interpreting these variables as outputs (objectives) for the classification problem, several decision trees were formed that describe the influence and relationship of different fire causes on situations in which injuries or human casualties occur or not. In that way, several different types of fires have been identified, including rare but deadly incidents that require urgent preventive measures. Key risk factors such as fire cause, location, season, etc., have been found to significantly influence human casualties. These findings provide practical insights for improving fire protection policies and emergency response. Through such a comprehensive analysis, it is believed that some important results have been obtained that precisely describe the specific relationships between the causes and consequences of fires occurring in the Republic of Serbia. Full article

This paper explores the implementation of battery electric vehicles (BEVs) in underground mining operations, focusing on their benefits, challenges, and safety considerations. The study examines the shift from traditional diesel-powered machinery to BEVs in response to increasing environmental concerns and stricter emission regulations. It discusses various lithium-ion battery chemistries used in BEVs, particularly lithium–iron–phosphate (LFP) and nickel–manganese–cobalt (NMC), comparing their performance, safety, and suitability for underground mining applications. The research highlights the significant benefits of BEVs, including reduced greenhouse gas emissions, improved air quality in confined spaces, and potential ventilation cost savings. However, it also addresses critical safety concerns, such as fire risks associated with lithium-ion batteries and the emission of toxic gases during thermal runaway events. The manuscript emphasises the importance of comprehensive risk assessment and mitigation strategies when introducing BEVs to underground mining environments. It concludes that while BEVs offer promising solutions for more sustainable and environmentally friendly mining operations, further research is needed to ensure their safe integration into underground mining practices. This study contributes valuable insights to the ongoing discussion on the future of mining technology and its environmental impact. Full article

There is no doubt that additive manufacturing (AM) with mortars presents an opportunity within the framework of a circular economy that should not be overlooked. The concepts of reduce, reuse, and recycle are fully aligned with this technology. One of the less explored possibilities is the utilisation of mining tailings as aggregates in printing mortars. This idea not only incorporates the concept of recycling but also contributes to a reduction in the production of potentially hazardous waste that would otherwise require storage in dams, thereby decreasing long-term environmental risks and improving the management of mineral resources. We employed a mortar composed of 12.5% material derived from mining tailings to highlight aspects of AM that are typically not subject to analysis, such as the necessity of considering contact interfaces between layers in structural design, the stackability of layers during the construction process, and the behaviour under fire and seismic events, which must be taken into account during the operational phase. Without aiming for exhaustiveness, we conducted a series of tests and computational modelling to show the significance of these factors, with the intention of drawing the attention of different stakeholders—including construction companies, regulatory authorities, standardisation agencies, insurers, and end-users. Full article

Coal accounts for over half of India’s energy needs currently. However, it has resulted in significant environmental impacts such as altering land cover and land surface temperatures. This study quantifies the land surface temperature (LST) of Dhanbad City (India)—home to India’s largest coal reserves. It uses the Landsat 8 image data to evaluate urban and rural temperature variations across different land use–land cover (LULC) classes. Using a Geographically Weighted Regression Model (GWR), we examined the spatial heterogeneity of the LST using key environmental indices, such as the Normalized Difference Vegetation Index (NDVI), Modified Normalized Difference Water Index (MNDWI), Normalized Difference Moisture Index (NDMI), and Normalized Difference Barren Index (NDBI). The seasonal LST variations revealed significant urban–rural area temperature disparities, with rural regions exhibiting stronger correlations with the key indices above. The GWR model accounted for 78.31% of the spatial variability in LST, with unexplained heterogeneity in urban areas linked to anomalies identified in the coal mining area fire map. These findings underscore the necessity of targeted mitigation strategies to reduce high LST values in coal fire-affected regions, with localized spatial measures in mining areas. Full article

Facing the severe global wildfire challenge and the need for advanced prediction, this study analysed the evolving research in forest fire prediction using an LDA-BERT similarity model. Due to climate change, human activities, and natural factors, forest fires threaten ecosystems, society, and the climate system. The vast existing literature on forest fire prediction makes it challenging to identify research themes manually. The proposed LDA-BERT model combines LDA and BERT. LDA was used for topic mining, determining the optimal number of topics by calculating the semantic consistency. BERT was employed in word vector training, using topic word probabilities as weights. The cosine similarity algorithm and normalisation were used to measure the topic similarity. Through empirical research on 13,552 publications from 1980–2023 retrieved from the Web of Science database, several key themes were identified, such as “wildfire risk management”, “vegetation and habitat changes”, and “climate change and forests”. Research trends show a shift from macro-level to micro-level studies, with modern technologies becoming a focus. Multidimensional scaling revealed a hierarchical theme distribution, with themes closely related to forest fires being dominant. This research offers valuable insights for the scientific community and policymakers, facilitating understanding these changes and contributing to wildfire mitigation. However, it has limitations like subjectivity in theme-representative word selection and needs further improvement in threshold setting and model performance evaluation. Future research can optimise these aspects and integrate emerging technologies to enhance forest fire prediction research. Full article

The improvement of safety conditions on hazardous rock slopes in civil work, mining and quarrying, and urban environments can be achieved through the use of explosives for the removal of unstable rock elements and final profiling. This technique is often applied because, in most cases, drill and blast operations, where they can be used, are cheaper and faster than other techniques and require fewer subsequent maintenance interventions. Blasting represents a suitable and effective solution in terms of different geometries, rock formation types, access to site, safety, and the long-term durability of results. The primary purpose of this approach is the improvement of the safety conditions of sites, depending on their local features, as well as the safety of workers, so that the blasting scheme, geometry, and firing can be carefully adapted, thus imposing relevant limitations on the operating techniques. All these constraints associated with complex logistics make it difficult to standardize the demolition technique, due to different situations in terms of extension, location, fracturing state, and associated traffic risk. Considering the significant number of influencing factors for both the rock mass features and for the topography, the present research has been necessarily validated through the analysis of several case histories, thus on an experiential basis focusing on some simple control parameters to help engineers and practitioners regarding the first design and control of blasting schemes. Full article

Global change and disturbance ecology, including the risks and benefits of wildfires for humans, sustainability of ecosystems and biodiversity, is a current research topic in applied science. Fires and their impacts are often considered in the context of climate change, carbon dioxide emissions and air pollution. Despite a significant decline in wildfires at the global scale in recent decades (cf. Global Wildfire Information System (GWIS)), it is a widespread conviction that the burned area is increasing due to global warming. In an attempt to identify how this discrepancy has arisen, we analysed IPCC reports from 2018–2023 via text mining including word frequency analyses and compared considerations about wildfires and fire weather with findings from ecology and public information on the internet. Both a negativity bias and repetition bias were identified. Numerous examples of disasters and models indicating a global increase of wildfires are composed of alarming messages. Examples of decreasing wildfires and the global decline are much less frequently communicated. Important facts are ignored, especially in summaries for policymakers. Measured against fire-ecological conditions and benefits for the nature, alarming trends and risks due to climate change are exaggerated. We therefore call for a comprising and differentiated reflection of ecological conditions and processes in the future. Full article

Aiming at the complex conditions of the coexistence of the explosive gases in the coal mines and the risk of spontaneous coal combustion, the effect of encapsulation, oxygen barrier and different microcapsules on methane and long-chain alkanes has been studied. A non-toxic microcapsule comprising the anti-explosion fire-extinguishing polymeric material with neutral pH value, biodegradability and full solubility in water has been developed. The fire-extinguishing platform system has been used to test and analyze the fire-extinguishing effect, explosion suppression efficiency and package efficiency of the oil-pan fires and solid stacks. It is revealed that the microcapsule fire-extinguishing technology has a strong fire-extinguishing effect and can better inhibit the methane explosion, owing to its effective enveloping effect on methane, thus making it difficult to reignite. The developed technology is of theoretical significance and has a practical application value for studying the flame retardation and fire-extinguishing behavior of combustible substances. Full article

Forest fires are sudden and difficult to extinguish, so early risk assessment is crucial. However, there are currently a lack of suitable knowledge-mining algorithms for forest fire risk assessment. This article proposes an improved continuous Apriori algorithm to mining forest fire rules by introducing prior knowledge to classify input data and enhance its ability to process continuous data. Meanwhile, it constructs an ontology to provide a standardized expression platform for forest fire risk assessment. The improved continuous Apriori algorithm cooperates with ontology and applies the mining rules to the forest fire risk assessment results. The proposed method is validated using the forest fire data from the Bejaia region in Algeria. The results show that the improved continuous Apriori algorithm is superior to the raw Apriori algorithm and can mine the rules ignored by the raw Apriori algorithm. Compared to the raw Apriori algorithm, the number of generated rules increased by 191.67%. The method presented here can be used to enhance forest fire risk assessments and contribute to the generation and sharing of forest-fire-related knowledge, thereby alleviating the problem of insufficient knowledge in forest fire risk assessment. Full article

Methane explosions often occur during the closure process of mine fire zones, during which the concentration of combustible gases such as monoxide and ethylene produced by coal combustion dynamically changes, which changes the risk of methane explosion. Therefore, studying the gas concentration distribution and methane explosion limits during the process of mine closure is of great significance for disaster prevention and control. In this paper, a three-dimensional physical model of gob was built, and the distribution of monoxide and ethylene in the process of fire zone closure was investigated. Further, the explosion limits of methane enriched with CO and C₂H₄ in the closed fire zone of gob were analyzed. The results indicate that CO and C₂H₄ would form a small-scale accumulation phenomenon near the fire zone after the closure of the fire zone, and when the fire zone is closed for more than 15 min, the mixed combustible gases in the environment lose their explosiveness. Full article