E-mail Alert
RSS
-
摘要:
针对飞行过程中，在高空气压较低，飞机货舱若发生火灾，烟雾颗粒半空悬浮，传统烟雾探测器难以检测，且在其它环境亦存在误漏报率较高，难以可视化等问题，设计了一款图像型火灾探测器，采用改进YOLOv5s算法实现烟火目标检测。首先将骨干网络替换为GhostNet轻量级骨干网络，便于硬件部署；在骨干网络与融合网络的连接处嵌入了协同注意力模块，强化对有效特征的提取。接着，针对火灾目标的发展变化特性，对特征融合网络中的C3结构进行改进，搭建了VoV-GSCSP模块，同时在融合网络和检测头之间嵌入Slim-ASFF模块，共同加强不同尺度特征融合的同时，实现了整体网络的进一步轻量化。最后，将回归损失替换为Focal EIOU，解决了惩罚项失效问题，并且提高了对正样本的预测能力。图像型航空火灾探测器以国产AI芯片RK3588为核心，连接CMOS图像传感器进行数据采集，通过网络实现与机载显示系统的信息交互。测试结果表明：在模拟飞机货舱顶部四角布置设备，可实现10 s内火焰报警，20 s内烟雾报警，为确保航空器安全提供了一种可行的解决方案。
Abstract:Due to the low high air pressure during the flight, if a fire occurs in the cargo hold of the aircraft, the smoke particles are suspended in mid-air. The traditional smoke detector is difficult to detect, and there is also a high false alarm rate and difficult visualization in other environments, an image-based fire detector was designed, and the improved YOLOv5s algorithm was used to realize the pyrotechnic target detection. First, the backbone network is replaced with a lightweight GhostNet backbone network to facilitate hardware deployment. A collaborative attention module is embedded in the connection between the backbone and the converged network to strengthen the extraction of effective features. Then, according to the development and change characteristics of fire targets, the C3 structure in the feature fusion network was improved, the VoV-GSCSP module was built, and the Slim-ASFF module was embedded between the fusion network and the detection head, so as to jointly strengthen the feature fusion of different scales and realize the further lightweight of the overall network. Finally, the regression loss is replaced by focal EIOU, which solves the problem of penalty term failure and improves the prediction ability of positive samples. The image-based aviation fire detector takes the domestic AI chip RK3588 as the core, connects to the CMOS image sensor for data collection, and realizes information interaction with the airborne display system through the network. The test results show that the equipment can be arranged at the top four corners of the cargo compartment of the simulated aircraft, which can realize the flame alarm within 10 seconds and the smoke alarm within 20 seconds, which provides a feasible solution for ensuring the safety of the aircraft.
-
Key words:
- RK3588 /
- fire-and-smoke detection /
- improvement of YOLOv5s /
- lightweight
-
Overview: To address the challenges of traditional smoke detectors in identifying replaced smoke in the cargo hold of high-altitude, low-pressure aircraft, an innovative image-based fire-and-smoke detection system was developed using the domestic RK3588 embedded AI chip. This system employs an enhanced YOLOv5s detection algorithm tailored specifically for fire-and-smoke detection, incorporating several critical improvements to achieve high precision and operational efficiency. The backbone network of YOLOv5s is replaced with the lightweight GhostNet architecture, which significantly reduces computational requirements and the model’s parameter size, making it highly suitable for deployment on embedded devices with limited resources. To enhance feature extraction, a collaborative attention module is integrated between the backbone and the feature aggregation network, ensuring that critical features are captured effectively for better detection outcomes. In addition, the C3 structure in the feature fusion network is substituted with the VoV-GSCSP module. This modification not only enhances the integration of multi-scale features but also reduces computational complexity, enabling the system to handle high-resolution images more efficiently. To further optimize the system’s performance, the Slim-ASFF module is inserted between the feature fusion network and the detection head. This addition improves the combination of feature maps across varying scales, ensuring accurate detection of both small and large fire-and-smoke instances. The regression loss function is also updated by replacing the standard loss function with Focal EIOU. This improvement addresses challenges related to aspect ratio variations in the original loss function, enhancing the system’s ability to identify positive samples while reducing false alarms effectively. Experimental results on a self-constructed fire-and-smoke dataset demonstrate the system achieves a 2.0% increase in mean Average Precision at a 0.5 threshold (mAP50) and a 2.2% improvement at 0.5:0.95 thresholds (mAP50:95). These results demonstrate the algorithm’s effectiveness under challenging conditions, such as low light and high turbulence environments, making it highly reliable for real-world applications. The hardware of this system is centered around the RK3588 embedded processing board, which interfaces with a CMOS image sensor for real-time data acquisition. The processing board includes an RTSP streaming server, enabling the host computer to access the visual interface via the onboard LAN and an assigned IP address. Testing in a simulated cabin of 15 m × 8 m × 4 m demonstrated reliable performance, with flame alarms triggered within 10 seconds and smoke alarms within 20 seconds. All functional indicators met rigorous design specifications, confirming the system as a scalable, efficient, and reliable solution for fire-and-smoke detection in aircraft cargo holds. By combining advanced deep learning techniques, lightweight architectures, and optimized hardware, this system ensures compliance with the stringent demands of real-time monitoring in airborne environments.
-
-
图 2 图像型航空火灾探测器硬件整体结构
Figure 2. Overall structure of the image-based aviation fire detector hardware
图 5 可视化界面。(a)多传感器并行显示；(b)火焰弹图报警及文字提示；(c)烟雾弹图报警及文字提示
Figure 5. Visual interface. (a) Multi-sensor parallel display; (b) Flame bomb diagram alarm and text prompt; (c) Smoke grenade map alarm and text prompt
图 10 GS bottleneck模块和VoV-GSCSP模块结构。(a) GS bottleneck模块结构；(b) VoV-GSCSP模块结构
Figure 10. Structure of the GS bottleneck module and VoV-GSCSP module. (a) GS bottleneck module structure; (b) VoV-GSCSP module structure
图 12 试验环境示意图。(a)大型高空环境模拟装置；(b)舱内试验环境
Figure 12. Schematic diagram of the test environment. (a) Large-scale high-altitude environment simulation device; (b) In-cabin test environment
表 1 火灾检测网络消融实现结果
Table 1. Implementation results of the fire detection network ablation
Model GhostNet Coordinated
attentionLightweight feature
fusion networkSlim-ASFF Loss function AP50
/%AP
/%Params/M FLOPs/G YOLOv5s 89.4 47.9 7.1 16.5 The model of
this article√ 86.8 45.0 5.0 10.6 √ √ 87.4 45.7 5.0 10.7 √ √ √ 88.5 46.9 4.2 8.5 √ √ √ √ 90.1 48.6 4.4 8.9 √ √ √ √ √ 91.4 50.1 4.4 8.9 
下载: 导出CSV
表 2 轻量级目标检测网络对比实验结果
Table 2. Comparative experimental results of lightweight object detection networks
下载: 导出CSV
表 3 不同工况下系统对烟火的平均响应时间
Table 3. Average response time of system to fireworks under different working conditions
Test environment Project 2 m 3 m 4 m / Number of tests 30 30 30 / Alarm times 30 30 30 Bright environment Polyurethane foam board (fire)/s 5.2 6.8 7.8 Cotton rope (fire)/s 5.0 6.5 7.4 Smoke cake (smoke)/s 11.0 13.0 17.0 Dark environment Polyurethane foam board (fire)/s 6.3 7.4 8.3 Cotton rope (fire)/s 5.5 6.9 7.8 Smoke cake (smoke)/s 12.0 15.0 19.0
下载: 导出CSV
表 4 本文探测器与传统火灾探测器对比实验结果
Table 4. Experimental results of the detector in this paper compared with the traditional fire detector
Test materials Number
of trialsNumber of
detector alarms
in this paperNumber of alarms
from traditional fire
detectorsThe slowest response
time of the detector in
this paper/sThe slowest response
time of traditional fire
detectors/sThe average response
time of the detector in
this paper/sThe average response
time of traditional fire
detector/sPolyurethane foam
board (fire)10 10 5 9.0 108 6.5 97 Smoke cake (smoke) 10 10 7 16.5 57 12.0 45
下载: 导出CSV
表 5 不同环境光线影响下的探测器虚警率
Table 5. False alarm rate of detector under the influence of different environmental light
Project Interference source 1 Interference source 2 Interference source 3 Number of tests 30 30 30 False alarm rate 0 0 0
下载: 导出CSV
-
[1] 胡君健, 谢启源, 戎军, 等. 感烟火灾探测器的抗干扰实验及其分析[J]. 火灾科学, 2005, 14(2): 111−116. doi: 10.3969/j.issn.1004-5309.2005.02.009
Hu J J, Xie Q Y, Rong J, et al. Experimental analysis on nuisance immunity of smoke detectors[J]. Fire Saf Sci, 2005, 14(2): 111−116. doi: 10.3969/j.issn.1004-5309.2005.02.009
[2] Zhang R, Zhang W, Liu Y Y, et al. An efficient deep neural network with color-weighted loss for fire detection[J]. Multimed Tools Appl, 2022, 81(27): 39695−39713. doi: 10.1007/s11042-022-12861-9
[3] 高锴. 浅谈图像感烟探测产品在飞机货仓火灾探测中的应用[J]. 品牌与标准化, 2016, (7): 75−78. doi: 10.3969/j.issn.1674-4977.2016.07.006
Gao K. Application of image smoke detection products in aircraft cargo compartment fire detection[J]. Brand Stand, 2016, (7): 75−78. doi: 10.3969/j.issn.1674-4977.2016.07.006
[4] Blake D. Aircraft cargo compartment smoke detector alarm incidents on U. S. -registered aircraft, 1974–1999[R]. Atlantic City: Federal Aviation Administration, 2000.
[5] 何志祥, 王立纲, 孟超, 等. 基于多数据融合的复合火灾探测系统设计[J]. 消防科学与技术, 2019, 38(7): 977−980. doi: 10.3969/j.issn.1009-0029.2019.07.022
He Z X, Wang L G, Meng C, et al. Design of composite fire detection system based on multi-data fusion[J]. Fire Sci Technol, 2019, 38(7): 977−980. doi: 10.3969/j.issn.1009-0029.2019.07.022
[6] 张红梅, 叶慧, 郑罡, 等. 多传感器飞机货舱火警探测系统研究[J]. 重庆理工大学学报(自然科学), 2017, 31(7): 176−181. doi: 10.3969/j.issn.1674-8425(z).2017.07.028
Zhang H M, Ye H, Zheng G, et al. Research on the multi sensor fire detection system in aircraft cargo[J]. J Chongqing Univ Technol (Nat Sci), 2017, 31(7): 176−181. doi: 10.3969/j.issn.1674-8425(z).2017.07.028
[7] 何永勃, 张文杰, 杨伟, 等. 飞机货舱复合烟雾探测方法研究[J]. 中国安全科学学报, 2019, 29(1): 43−48. doi: 10.16265/j.cnki.issn1003-3033.2019.01.008
He Y B, Zhang W J, Yang W, et al. Research on multi-sensor smoke detection method for aircraft cargo compartment[J]. China Saf Sci J, 2019, 29(1): 43−48. doi: 10.16265/j.cnki.issn1003-3033.2019.01.008
[8] 王哲. 飞机货舱防火设计要求研究[J]. 航空标准化与质量, 2014, (5): 13−15, 34. doi: 10.13237/j.cnki.asq.2014.05.004
Wang Z. Research on fire protection design requirements for aircraft cargo compartments[J]. Aeronaut Stand Qual, 2014, (5): 13−15, 34. doi: 10.13237/j.cnki.asq.2014.05.004
[9] 张小雪, 王雨, 吴思远, 等. 基于级联稀疏查询机制的轻量化火灾检测算法[J]. 光电工程, 2023, 50(10): 230216. doi: 10.12086/oee.2023.230216
Zhang X X, Wang Y, Wu S Y, et al. An improved lightweight fire detection algorithm based on cascade sparse query[J]. Opto-Electron Eng, 2023, 50(10): 230216. doi: 10.12086/oee.2023.230216
[10] Han K, Wang Y H, Tian Q, et al. GhostNet: more features from cheap operations[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, 2020: 1577–1586. https://doi.org/10.1109/CVPR42600.2020.00165.
[11] Zhang Y F, Ren W Q, Zhang Z, et al. Focal and efficient IOU loss for accurate bounding box regression[J]. Neurocomputing, 2022, 506: 146−157. doi: 10.1016/j.neucom.2022.07.042
[12] Lin T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection[C]//Proceedings of 2017 IEEE International Conference on Computer Vision, Venice, 2017: 2999–3007. https://doi.org/10.1109/ICCV.2017.324.
[13] Hou Q B, Zhou D Q, Feng J S. Coordinate attention for efficient mobile network design[C]//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, 2021: 13708–13717. https://doi.org/10.1109/CVPR46437.2021.01350.
[14] Li H L, Li J, Wei H B, et al. Slim-neck by GSConv: a better design paradigm of detector architectures for autonomous vehicles[Z]. arXiv: 2206.02424, 2024. https://arxiv.org/abs/2206.02424v1.
[15] Liu S T, Huang D, Wang Y H. Learning spatial fusion for single-shot object detection[Z]. arXiv: 1911.09516, 2019. https://doi.org/10.48550/arXiv.1911.09516.
[16] Li C Y, Li L L, Jiang H L, et al. YOLOv6: a single-stage object detection framework for industrial applications[Z]. arXiv: 2209.02976, 2022. https://doi.org/10.48550/arXiv.2209.02976.
[17] Wang C Y, Bochkovskiy A, Liao H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, 2023: 7464–7475. https://doi.org/10.1109/CVPR52729.2023.00721.
[18] Liu W, Anguelov D, Erhan D, et al. SSD: single shot MultiBox detector[C]//Proceedings of the 14th European Conference on Computer Vision, Amsterdam, 2016: 21–37. https://doi.org/10.1007/978-3-319-46448-0_2.
[19] Tan M X, Pang R M, Le Q V. EfficientDet: scalable and efficient object detection[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, 2020: 10778–10787. https://doi.org/10.1109/CVPR42600.2020.01079.
[20] Wang C Y, Ye I H, Liao H Y M. YOLOv9: learning what you want to learn using programmable gradient information[C]//Proceedings of the 18th European Conference on Computer Vision, Milan, 2024: 1–21. https://doi.org/10.1007/978-3-031-72751-1_1.
[21] Wang A, Chen H, Liu L H, et al. YOLOv10: real-time end-to-end object detection[Z]. arXiv: 2405.14458, 2024. https://doi.org/10.48550/arXiv.2405.14458.
[22] Zhao Y, Lv W Y, Xu S L, et al. DETrs beat YOLOs on real-time object detection[C]//Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, 2024: 16965–16974. https://doi.org/10.1109/CVPR52733.2024.01605.
[23] 中华人民共和国国家质量监督检验检疫总局, 中国国家标准化管理委员会. 特种火灾探测器: GB 15631–2008[S]. 北京: 中国标准出版社, 2009.
General Administration of Quality Supervision, Inspection and Quarantine of the People’s Republic of China, Standardization Administration of the People's Republic of China. Special type fire detectors: GB 15631–2008[S]. Beijing: Standards Press of China, 2009.
[24] 闵芳. 盘点世界各国大型运输机[J]. 生命与灾害, 2013, 3: 34−37. https://cqvip.com/doc/journal/972803679
Min F. Overview of large transport aircraft in various countries[J]. Life Disaster, 2013, 3: 34−37. https://cqvip.com/doc/journal/972803679
-
点击扫一扫
图(13)
表(5)
计量
- 文章访问数:
- PDF下载数:
- 施引文献: 0
