Real-time monitoring and prediction method of commercial building fire temperature field based on distributed optical fiber sensor temperature measurement system

Liu, Gang; Meng, Hongrong; Qu, Guanhua; Wang, Lan; Ren, Lei; Lu, Hansong

doi:10.1016/j.jobe.2023.106403

Cited by 6 publications

(6 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By 2022, one of the most cited research papers proposes and tests deep learning models trained with real seismic data to detect earthquakes in fiber optic distributed acoustic sensor (DAS) measurements [40]. On the other hand, among the most recent researches, a sensor arrangement method based on the characteristics of the sensor and the fire field is proposed to better reflect the temperature changes of the fire in the building space and conduct high temperatures by establishing several prediction models using different algorithms based on the dataset and the models built by artificial neutral network (ANN) and long short-term memory (LSTM) to obtain better performance [3]. In terms of the most representative authors on the subject, Figure 3 shows the main references in the field of study of fiber optic sensors and machine learning, the figure shows that, the group in yellow corresponds to the authors with more publications and more citations, the group in blue corresponds to the authors with more citations, but no more publications, and the group in green corresponds to the most cited authors, but with fewer publications.…”

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

“…On the other hand, several models using artificial neutral network (ANN), long short-term memory (LSTM), and pattern recognition algorithms have been developed to improve the response of fiber optic sensors when this technology is used to monitor the structural health of buildings [66,67]. In addition, ML techniques have been proposed to identify, localize, quantify, and visualize cracks through intelligent interpretation of strain distributions measured by distributed fiber optic sensors [3]. Similarly, ML techniques have been used to detect fatigue [68], vibration [69], and stress [9] in mechanical and civil structures.…”

Section: Analysis Of Thematic Evolutionmentioning

confidence: 99%

“…These sensors identify anomalies in the input data received by the implemented systems [2]. Sensor design has evolved to include features that provide greater precision in operation [3]. Bioelectrical, biophysical, and biochemical signals can be employed in various contexts, including sports development, medical analysis and prevention, as well as rehabilitation [4].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Machine Learning Applications in Optical Fiber Sensing: A Research Agenda

Reyes-Vera,

Valencia-Arias,

García-Pineda

et al. 2024

Sensors

View full text Add to dashboard Cite

The constant monitoring and control of various health, infrastructure, and natural factors have led to the design and development of technological devices in a wide range of fields. This has resulted in the creation of different types of sensors that can be used to monitor and control different environments, such as fire, water, temperature, and movement, among others. These sensors detect anomalies in the input data to the system, allowing alerts to be generated for early risk detection. The advancement of artificial intelligence has led to improved sensor systems and networks, resulting in devices with better performance and more precise results by incorporating various features. The aim of this work is to conduct a bibliometric analysis using the PRISMA 2020 set to identify research trends in the development of machine learning applications in fiber optic sensors. This methodology facilitates the analysis of a dataset comprised of documents obtained from Scopus and Web of Science databases. It enables the evaluation of both the quantity and quality of publications in the study area based on specific criteria, such as trends, key concepts, and advances in concepts over time. The study found that deep learning techniques and fiber Bragg gratings have been extensively researched in infrastructure, with a focus on using fiber optic sensors for structural health monitoring in future research. One of the main limitations is the lack of research on the use of novel materials, such as graphite, for designing fiber optic sensors. One of the main limitations is the lack of research on the use of novel materials, such as graphite, for designing fiber optic sensors. This presents an opportunity for future studies.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Analysis Of Thematic Evolutionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning Applications in Optical Fiber Sensing: A Research Agenda

Reyes-Vera,

Valencia-Arias,

García-Pineda

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Currently, there are mainly three fire prevention modes: sensor warning, active extinguishing with fire-extinguishing agents, and passive fire prevention [ 4 , 5 , 6 ]. The sensor early-warning system adopts a physical method of non-contact temperature measurement, combined with a fire alarm algorithm built into the monitoring front-end hardware for intelligent judgment and a timely alarm, to prevent imminent fire crises [ 7 , 8 ]. Active extinguishing refers to the use of fire-extinguishing agents to prevent combustible gases, liquids, and solids from coming into contact with combustion aids such as air, oxygen, or other oxidizing agents, thereby achieving a flame-retardant effect [ 9 , 10 ].…”

Section: Introductionmentioning

confidence: 99%

A Novel Inorganic Aluminum Phosphate-Based Flame Retardant and Thermal Insulation Coating and Performance Analysis

Cai

Guo

et al. 2023

Materials

View full text Add to dashboard Cite

Currently, most thin-layer expandable coatings are polymer-based, with very few inorganic expandable coatings. Due to the high environmental friendliness of inorganic coatings, studying new types of inorganic coatings is of great significance. A novel amorphous aluminum phosphate-based flame-retardant coating was prepared by modifying it with nano-silica, hollow silica beads, hollow glass microspheres, and boron carbide. A comprehensive study was conducted on the flame retardancy and thermal insulation performance, composition and structural evolution under flame and physical and chemical properties, and the mechanisms of flame retardancy and thermal insulation were elucidated. Large-plate combustion testing, bonding strength testing, XRD, IR, TG-DSC, and SEM testing were all applied in this work. The synergistic effect of the four fillers was very obvious, and a series of AP22XY (nano-silica/silica beads/hollow glass microspheres/boron carbide = 2:2:0:4, 2:2:1:3, 2:2:2:2, 2:2:3:1, 2:2:4:0) coatings were prepared. The change in the ratio of glass microspheres to boron carbide had a significant impact on the composition and structural evolution of the coating, thus reflecting its effectiveness as a flame retardant and thermal insulation. Although decreasing the ratio would promote the formation of borosilicate glass and Al18B4O33 and improve the thermal stability of coatings, the structure inside of the coating, especially the skeleton, would be dense, which is not conducive to thermal insulation. When the ratio of glass microspheres to boron carbide is 3:1, AP2231 shows the best fire resistance. Under the combustion of butane flame at about 1200–1300 °C, the backside temperature reaches a maximum of 226 °C at 10 min, and then the temperature gradually decreases to 175 °C at 60 min. This excellent performance is mainly attributed to three aspects: (1) the foaming and expandability of coatings when exposed to fire, (2) the multiple endothermic reactions the coating undergoes, and (3) the improvement effect of boron carbide. Additionally, AP2231 shows the best bonding performance with a strength of close to 4.5 MPa after combustion, because of the appropriate content matching between borosilicate glass, Al18B4O33, and hollow glass microspheres. The coating has potential application prospects in the construction and transportation fields, such as the protection of structural steel, fire prevention in subways and tunnels, and the prevention of lithium battery fires.

show abstract

Combinatorial machine learning approaches for high-rise building cost prediction and their interpretability analysis

Liu,

Lin

2024

Journal of Asian Architecture and Building Engineering

View full text Add to dashboard Cite

Real-time monitoring and prediction method of commercial building fire temperature field based on distributed optical fiber sensor temperature measurement system

Cited by 6 publications

References 56 publications

Machine Learning Applications in Optical Fiber Sensing: A Research Agenda

Machine Learning Applications in Optical Fiber Sensing: A Research Agenda

A Novel Inorganic Aluminum Phosphate-Based Flame Retardant and Thermal Insulation Coating and Performance Analysis

Combinatorial machine learning approaches for high-rise building cost prediction and their interpretability analysis

Contact Info

Product

Resources

About