Explore the vast range of titles available.

This article discusses fundamental issues associated with the functional reliability of selected fire alarm systems (FASs) in operation during building fires. FASs operate under diverse external or internal natural environmental conditions, and the operational process of FAS should take into account the impacts of physical phenomena that occur during fires. Their operation is associated with the constant provision of reliability. FAS designers should also consider the system’s reliability when developing fire control matrices, tables, algorithms, or scenarios. All functions arising from an FAS control matrix should be implemented with a permissible reliability level, RDPN(t), prior to, as well as during, a fire. This should be assigned to the controls saved in the fire alarm control unit (FCP). This article presents the process by which high temperatures generated during a fire impact the reliability of FAS functioning. It was developed considering selected critical paths for a specific scenario and the control matrix for an FAS. Such assumptions make it possible to determine the impact of various temperatures generated during a fire on the reliability of an FAS. To this end, the authors reviewed that the waveform of the R(t) function changes for a given FAS over time, Δt, and then determined the fitness paths. The critical paths are located within the fire detection and suppression activation process, using FAS or fixed extinguishing devices (FEDs), and the paths were modeled with acceptable and unacceptable technical states. The last section of this article defines a model and graph for the operational process of a selected FAS, the analysis of which enables conclusions to be drawn that can be employed in the design and implementation stages.

Modern fire alarm systems are essential for public safety, yet they often fail to exploit the wealth of historical alarm data and the complex spatiotemporal dependencies inherent in urban environments. Graph Neural Networks (GNNs) are currently among the most popular methods for handling complex spatiotemporal dependencies. While a range of dynamic GNN approaches have been proposed, many existing GNN-based predictors still rely on a static topology, which limits their ability to fully capture the evolving nature of risk propagation. Furthermore, even among dynamic graph methods, most focus on temporal link prediction or social interaction modeling, with limited exploration in safety-critical applications such as fire alarm prediction. DeaGAT dynamically updates inter-building edge weights through an attention mechanism, enabling the graph structure to evolve in response to shifting risk patterns. A margin-based contrastive learning objective further enhances the quality of node embeddings by distinguishing subtle differences in risk states. In addition, DeaGAT jointly models static building attributes and dynamic alarm sequences, effectively integrating long-term semantic context with short-term temporal dynamics. Extensive experiments on real-world datasets, including comparisons with state-of-the-art baselines and comprehensive ablation studies, demonstrate that DeaGAT achieves superior accuracy and F1-score, validating the effectiveness of dynamic graph updating and contrastive learning in enhancing proactive fire early-warning capabilities.

The article presents issues regarding the impact of operating conditions on the functional reliability of representative fire alarm systems (FASs) in selected critical infrastructure buildings (CIB). FAS should operate correctly under variable environmental conditions. FASs ensure the safety of people and CIB. Operational measurements for 10 representative systems were conducted in order to determine the impact of environmental conditions on FAS reliability. Selected operational indices were also determined. The next stage involved developing two models of representative FASs and the availability, pre-ageing time and operating process security indices. Determining operational indices is a rational selection of FAS technical and organizational solutions that enables the reliability level to be increased. Identifying the course of the FAS operating process security hazard changes in individual system lines, particularly at the initial operation stage, enables people that supervise the operation to affect operating parameters on an ongoing basis. The article is structured in the following order: issue analysis, FAS power supply in CIB, operational test results, selected FAS operating process models, determination of operational and security indices, and conclusions.

International Maritime Organization (IMO) has set regulations governing the installation of fire alarm systems on ships. The basic principle of the control system is to control the system output by comparing the actual output with the desired output. This study aims to determine the causes of false alarms on the fire alarm system on ships and to describe recommendations and solutions for failures in the fire alarm system on ships. This type of research uses a mix of methods by utilizing primary and secondary data. The data is processed by quantitative analysis and qualitative research. The results of this study indicate that the cause of the False Alarm on the Fire Alarm System is caused by the MFCA, Smoke Detector, and Cable Installation. The case that occurred in KL. 02 Sultan Hasanuddin there is no correlation between false alarms on the Fire Alarm System. The Smoke Detector correlation data with the False Alarm Fire Alarm System shows that there is a correlation with the Pearson Correlation of 0.857 > 0.4973.

The paper presents a method for assessing operation processes for Fire Alarm Systems (FAS) applied in civil structures, based on use analysis. Individual FAS devices include components with varying ‘lifetimes’ and damage intensities λ. This is because these elements are operated in different internal and external environments. Probability distributions with various damage λ and recovery µ intensity values must, hence, be taken into account for the FAS operation process and to determine the R(t) reliability. The life cycle of elements comprising a FAS can be divided into three distinguishing time periods. The first is the so-called ‘childhood’. The second, the longest, is characterized by damage intensity λ = const, and the third period is where FAS is unfit more frequently. Based on knowledge of actual FAS operation process data, it is possible to determine damage λ and recovery µ intensity parameters. Such data can be employed to determine FAS reliability parameters within the presented service life intervals. The authors of the article first discuss the basic issues associated with FAS, followed by analyzing the current status of the topic. They also present power supply matters and system solution examples, develop an operation process model and determine selected operational indicators for the structures in question. The paper ends with conclusions.

Indoor fires can have devastating consequences, highlighting the importance of developing effective alarm systems for early fire detection and suppression. This paper proposes a new machine-learning model for indoor fire detection using an indoor fire dataset. The dataset contains information on Humidity, Temperature, Freon Halogen Gas Sensor Module, Total Volatile Organic Compounds, and Estimated Concentration of Carbon Dioxide measures while various indoor materials, such as carton, clothing, and electrical fires of a closed room. It has been observed that commercial fire alarms often do not give early warnings and causing significant damage to the properties. Using decision treebased algorithms, the proposed model can distinguish between fire, no fire, and fire but no alarm conditions. Experimental results show that the Random Forest-based model can identify these conditions with 99.66% accuracy and 99.64% F1_score. The outcome of this paper will contribute to the development of smart indoor-fire alarm systems with early-warning capability.

The article reviews issues associated with the use of electronic fire alarm systems (FAS). They are operated in various environments and buildings with varying volumes. FAS have to function properly under different operating conditions associated with their operation, as well as power supply and information inflow. Due to their functions, i.e., ensuring the safety of people, vehicles, logistics bases, airports, etc., FAS have to exhibit an appropriately organized reliability structure associated with their implementation and power supply. Operational studies involving FAS operated in various facilities were conducted to this end. The authors determined damage and recovery time intensities. FAS reliability indicators were also determined. The article presents graphs associated with developing the energy balance for selected FAS. The graphs are consistent with the latest and applicable legal regulations. The next stage of the work related to this article was developing an FAS operation process model and conducting computer simulations in order to determine reliability indicators. Such an approach to the FAS operation process enables a rational selection of technical and organizational solutions aimed at guaranteeing reliability in the course of executing operational tasks associated with ensuring fire safety. FAS operational analysis, developing balance graphs and models, as well as the computer simulation, enabled inferring conclusions that might be useful to the process of engineering and operating such systems.

In the artificial intelligence age, multifunctional and intelligent fireproof fabric-based electronics are urgently needed. Herein, a novel thread-shaped all-fabric-based piezoresistive sensor (denoted as TAFPS) with properties such as flame retardancy, fire-warning, and piezoresistivity is proposed, which is composed of an inner nickel-plated fabric electrode, a multifunctional double helix fabric, and an external flame-retardant encapsulation fabric. Owing to the multiple flame-retardant properties of glass fiber tubular fabric, aminated carbon nanotubes (ACNTs), and ammonium polyphosphate, the char residue of the TAFPS reaches 40.3 wt% at 800°C. In addition, the heat-sensitive effect of ACNTs during combustion causes a rapid decrease in the TAFPS resistance, triggering the fire alarm system within 2 s. Additionally, benefiting from the force-sensitive behavior of the double helix layer and tightly wrapped pattern of the external heat-shrinkable tubular fabric, TAFPS demonstrated a high sensitivity of 4.40 kPa −1 (0–5.81 kPa) and good stability for 10000 s. Considering its excellent flame resistance, high sensitivity, and agreeable stability, the developed TAFPS can be integrated into fire suits to monitor the exercise training process and the external fire environment. This work offers a novel approach for fabricating all-fabric-based piezoresistive sensors in the future for fire prevention and fire alarms, with promising applications in fire protection, the Internet of Things, and smart apparel.

This paper proposes a video-based smoke detection technique for early warning in antifire surveillance systems. The algorithm is developed to detect the smoke behavior in a restricted video surveillance environment, both indoor (e.g., railway carriage, bus wagon, industrial plant, or home/office) or outdoor (e.g., storage area or parking area). The proposed technique exploits a Kalman estimator, color analysis, image segmentation, blob labeling, geometrical features analysis, and M of N decisor, in order to extract an alarm signal within a strict real-time deadline. This new technique requires just a few seconds to detect fire smoke, and it is 15 times faster compared to the requirements of fire-alarm standards for industrial or transport systems, e.g., the EN50155 standard for onboard train fire-alarm systems. Indeed, the EN50155 considers a response time of at least 60 s for onboard systems. The proposed technique has been tested and compared with state-of-art systems using the open access Firesense dataset developed as an output of a European FP7 project, including several fire/smoke indoor and outdoor scenes. There is an improvement of all the detection metrics (recall, accuracy, F1 score, precision, etc.) when comparing Advanced Video SmokE Detection (AdViSED) with other video-based antifire works recently proposed in literature. The proposed technique is flexible in terms of input camera type and frame size and rate and has been implemented on a low-cost embedded platform to develop a distributed antifire system accessible via web browser.

The early detection of fire is of utmost importance since it is related to devastating threats regarding human lives and economic losses. Unfortunately, fire alarm sensory systems are known to be prone to failures and frequent false alarms, putting people and buildings at risk. In this sense, it is essential to guarantee smoke detectors’ correct functioning. Traditionally, these systems have been subject to periodic maintenance plans, which do not consider the state of the fire alarm sensors and are, therefore, sometimes carried out not when necessary but according to a predefined conservative schedule. Intending to contribute to designing a predictive maintenance plan, we propose an online data-driven anomaly detection of smoke sensors that model the behaviour of these systems over time and detect abnormal patterns that can indicate a potential failure. Our approach was applied to data collected from independent fire alarm sensory systems installed with four customers, from which about three years of data are available. For one of the customers, the obtained results were promising, with a precision score of 1 with no false positives for 3 out of 4 possible faults. Analysis of the remaining customers’ results highlighted possible reasons and potential improvements to address this problem better. These findings can provide valuable insights for future research in this area.