Fire Source Determination Method for Underground Commercial Streets Based on Perception Data and Machine Learning
Abstract
:1. Introduction
2. The Principle of Machine Learning Models
2.1. Decision Tree [17]
2.2. Random Forest [19]
2.3. LightGBM
2.4. Application Examples
If , then: |
If , then: |
Classify as A; |
Else |
Classify as B; |
Else |
Classify as C. |
3. Dataset Description
3.1. Introduction to CFAST
3.2. Introduction to CData
3.3. The Validity of the CFAST Model
3.4. Model Building
3.4.1. Construction of CFAST Model
- (1)
- Geometric model.
- (2)
- Determining initial conditions.
- (3)
- Fire scenario construction
3.4.2. Simulation Results
4. Machine Learning Model
4.1. Data Preprocessing
4.1.1. Label Categorization
4.1.2. Segmentation Processing
4.1.3. Data Standardization
4.1.4. Deletion of Useless Data
4.2. Feature Extraction
- ①
- Maximum (): the highest value in the selected temperature time series.
- ②
- Mean (): the arithmetic average of a selected temperature time series, which reflected the average level of a temperature segment.
- ③
- Minimum (): the lowest value in the selected temperature time series.
- ④
- Standard deviation (): the arithmetic square root of the arithmetic mean of the squared deviations from the mean of a selected temperature time series, reflecting the degree of temperature dispersion in a period. The formula for calculating standard deviation is as follows:
- ⑤
- Mean absolute deviation (MAD): the average of the absolute deviations of all individual observed values in the selected temperature time series from their arithmetic mean, which avoided the situation where errors in a temperature segment cancelled each other out. The calculation formula is as follows:
- ⑥
- Interquartile range (IQR): the interquartile range (IQR), which was the difference between the upper quartile (Q3, located at 75%) and the lower quartile (Q1, located at 25%) of the selected temperature time series, reflected the dispersion of the middle half of the temperature. The formula for calculating IQR is as follows:
- ⑦
- Coefficient of variation (c): the ratio of the standard deviation to its corresponding mean in the selected temperature time series, a normalized measure of the temperature dispersion. The calculation formula is as follows:
- ⑧
- Skewness (SK): the ratio of the difference between the mean () and median () of a selected temperature dataset to its standard deviation, reflecting the degree of skewness of the temperature. The calculation formula is as follows:
- ⑨
- Kurtosis (): the number that reflected the sharpness of the peak of the selected temperature time series at the mean value. The calculation formula is as follows, where represents the fourth central moment:
4.3. Construction of Fire Source Determination Model
4.4. Evaluation Metrics
4.5. Performance Evaluation of the Model
4.6. Kappa Coefficient
4.7. Application of Fire Source Determination Technology in Real Fire Situations
- (1)
- Real-time fire source identification
- (2)
- Fire emergency response
- (3)
- Evacuation plan optimization
- (4)
- Risk assessment and safety strategy
- (5)
- Continuous monitoring and improvement
5. Conclusions
- (1)
- The LightGBM model performed best in determination with its exceptional class differentiation ability and high-dimensional data processing capability. Its macro averages for precision, recall, and F1 score were 99.01%, 98.45%, and 99.04%, and its kappa value was 98.81%.
- (2)
- The high determination performance of the three machine learning models indicated that the fire database established through CFAST simulation, based on random sampling for determining fire conditions, was more aligned with the objective laws of the real world.
- (3)
- This study’s three machine learning models demonstrated strong classification capabilities and interpretability.
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Chinese, A.; Chinese, S. 2021 Blue Book of China’s Urban Underground Space Development; China Science Publishing &Media LTD. (CSPM): Beijing, China, 2021; pp. 5–6. [Google Scholar]
- Zhang, X.; Wan, J. Study on fire risk factors of underground commercial street based on DEMATEL/ISM. Ind. Saf. Environ. Prot. 2022, 48, 46–49. [Google Scholar]
- Song, B.; Li, J. The key elements of decision making and its application on first due commander in fire fighting. Fire Sci. Technol. 2008, 27, 277–280. [Google Scholar]
- Wu, Z.; Dang, W.; Yu, A.; Bai, Y. Discussion on quantitative risk assessment procedure in petrochemical enterprises. Saf. Health Environ. 2010, 10, 35–38. [Google Scholar]
- Shu, S.; Zhang, Y.; Lu, Z.; Wang, D.; Jiang, N. Real-time prediction of heat release rate based on machine learning. Fire Saf. Sci. 2022, 31, 8–14. [Google Scholar]
- Deng, L.; Tang, F.; Hu, P. Physical modeling and machine learning of ceiling maximum temperature rise induced by tandem heat sources with unequal heat release rates in a natural ventilation tunnel. Int. J. Heat Mass Transf. 2022, 197, 123333. [Google Scholar] [CrossRef]
- Saeed, F.; Paul, A.; Hong, W.; Seo, H. Machine learning based approach for multimedia surveillance during fire emergencies. Multimed. Tools Appl. 2020, 79, 16201–16217. [Google Scholar] [CrossRef]
- Liu, Q.; Zhu, B.; Deng, L.; Shi, H.; Liang, G. Double parameters fire detection method based on machine learning. China Saf. Sci. J. 2022, 32, 90–96. [Google Scholar]
- Hodges, J.; Lattimer, B.; Luxbacher, K. Compartment fire predictions using transpose convolutional neural networks. Fire Saf. J. 2019, 108, 102854. [Google Scholar] [CrossRef]
- Yan, D.; Feng, X. Research on Fire Source Localization Method Based on Wireless Sensor Networks. Technol. Innov. Appl. 2016, 25, 106–107. [Google Scholar]
- Sun, M. Performance Improvement for Distributed Fiber Temperature Sensor System and Research on Fire Source Localization. Ph.D. Thesis, University of Science and Technology of China, Hefei, China, 2017. [Google Scholar]
- Chu, H.; Zhao, Y.; Zhuang, B.; Wang, Y.; Yang, X. Fire location and detection system based on computer vision technology. Electron. Des. Eng. 2020, 28, 156–160+164. [Google Scholar]
- Shen, D. Application Research of Bayesian Machine Learning in Fire Forecasting and Source Intensity Back-Calculation. Master’s Dissertation, University of Science and Technology of China, Hefei, China, 2021. [Google Scholar]
- Wu, X.; Zhang, X.; Huang, X.; Xiao, F.; Usmani, A. A real-time forecast of tunnel fire based on numerical database and artificial intelligence. Build. Simul. 2022, 15, 511–524. [Google Scholar] [CrossRef]
- Zhang, X.; Wu, X.; Park, Y.; Zhang, T.; Huang, X.; Xiao, F.; Usmani, A. Perspectives of big experimental database and artificial intelligence in tunnel fire research. Tunn. Undergr. Space Technol. 2021, 108, 103691. [Google Scholar] [CrossRef]
- Wu, X.; Park, Y.; Li, A.; Huang, X.; Xiao, F.; Usimani, A. Smart detection of fire source in tunnel based on the numerical database and artificial intelligence. Fire Technol. 2021, 57, 657–682. [Google Scholar] [CrossRef]
- Breiman, L. Classification and regression trees. Rev. Des Mal. Respir. 2004, 21, 1174–1176. [Google Scholar]
- Chen, Y.; Wu, J.; Xu, K. Using Gini-index-for attribute selection in decision trees. Microcomput. Dev. 2004, 66–68. [Google Scholar]
- Breiman, L. Random forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef]
- Cao, Y.; Miao, Q.; Liu, J.; Gao, L. Advance and prospects of Adaboost algorithm. Acta Autom. Sin. 2013, 39, 745–758. [Google Scholar] [CrossRef]
- Ke, G.; Meng, Q.; Finley, T.; Wang, T.; Chen, W.; Ma, W.; Ye, Q.; Liu, T. LightGBM: A highly efficient gradient boosting decision tree. In Proceedings of the 31st Annual Conference on Neural Information Processing Systems (NIPS), Long Beach, CA, USA, 4–9 September 2017; pp. 3149–3157. [Google Scholar]
- Peacock, R.; Mcgrattan, K.; Forney, G.; Reneke, P. Cfast—Consolidated Fire and Smoke Transport (Version 7) Volume 1: Technical Reference Guide; National Institute of Standards and Technology: Gathersburg, MD, USA, 2021. [Google Scholar]
- Chow, W. Multi-cell concept for simulating fires in big enclosures using a zone model. J. Fire Sci. 1996, 14, 186–198. [Google Scholar] [CrossRef]
- Reneke, P.; Peacock, R.; Gilbert, S.; Cleary, T. Cfast—Consolidated Fire and Smoke Transport (Version 7) Volume 5: Cfast Fire Data Generator (Cdata); National Institute of Standards and Technology: Gathersburg, MD, USA, 2021. [Google Scholar]
- Peacock, R.; Forney, G.; Reneke, P. Cfast—Consolidated Fire and Smoke Transport (version 7) Volume 3: Verification and Validation Guide. National Institute of Standards and Technology: Gathersburg, MD, USA, 2021. [Google Scholar]
- Bailey, J.; Forney, G.; Taterm, P.; Jones, W. Development and validation of corridor flow submodel for CFAST. J. Fire Prot. Eng. 2002, 12, 139–161. [Google Scholar] [CrossRef]
- Jones, W.; Forney, G. Improvement in predicting smoke movement in compartmented structures. Fire Saf. J. 1993, 21, 269–297. [Google Scholar] [CrossRef]
- Fan, N. Research on Method of Fire Simulation in Long-Narrow Confined Space Based on Cfast. Master’s Thesis, AnHui University of Science and Technology, Huainan, China, 2009. [Google Scholar]
- Chow, W. Simulation of tunnel fires using a zone model. Tunn. Undergr. Space Technol. 1996, 11, 221–236. [Google Scholar] [CrossRef]
- Bruns, M. Estimating the Flashover Probability of Residential Fires Using Monte Carlo Simulations of the MQH Correlation. Fire Technol. 2018, 54, 187–210. [Google Scholar] [CrossRef]
- GB 51251-2017; Technical Standard for Smoke Management Systems in Buildings. China Planning Press: Beijing, China, 2017.
- Zhang, A.; Yang, Z. Hyperparameter tuning methods in automated machine learning. Sci. Sin. Math. 2020, 50, 695–710. [Google Scholar]
Parameter | Configuration |
---|---|
Fire simulation time (s) | 1200 |
Indoor/outdoor temperature (°C) | 20 |
Indoor/outdoor relative humidity | 50% |
Atmospheric pressure (Pa) | 101,325 |
Wind speed (m/s) | 0 |
Floor material | Insulated, no heat conduction |
Ceiling material | Gypsum board |
Wall material | Gypsum board |
Fire type | Ultra-fast fire |
Sensor | Temperature sensors set every 7 m |
Parameter | Minimum | Average | Maximum | Distribution Function |
---|---|---|---|---|
Opening Width (m) | 0.81 | 2.03 | 3.24 | Normal Distribution |
Opening Height (m) | 1.93 | 2.27 | 3.5 | Normal Distribution |
Thermal Conductivity (W/m·K) | 0.19 | 0.20 | 0.21 | Normal Distribution |
Wall Thickness (mm) | 13.5 | 14.3 | 15.9 | Normal Distribution |
Ceiling Thickness (mm) | 13.5 | 14.3 | 15.9 | Normal Distribution |
Parameter | Explanation | Tuning Range | Tuning Results |
---|---|---|---|
Max_depth | The maximum depth of the decision tree. Depth was the number of nodes along the longest path from the root to a leaf. | (1, 30) | 20 |
Min_samples_split | The minimum number of samples a node must have before it can be split. | (2, 50) | 15 |
Min_samples_leaf | The minimum number of samples a leaf node must have. | (1, 50) | 5 |
Max_features | The maximum number of features to consider when looking for the best split. | [‘sqrt’, ‘log2’] | Log2 |
Parameter | Explanation | Tuning Range | Tuning Results |
---|---|---|---|
Nestimators | The number of trees in the random forest. | (50, 300) | 238 |
Max_depth | The maximum depth of the trees. | [3, 5, 10, None] | None |
Max_features | The maximum number of features considered when finding the best split. | (1, 15) | 6 |
Min_samples_split | The minimum number of samples required to split a node. | (2, 15) | 10 |
Min_samples_leaf | The minimum number of samples required to be at a leaf node. | (1, 11) | 4 |
Bootstrap | Whether bootstrap sampling was used when building trees. | [True, False] | False |
Class_weight | The weights used for classes in handling imbalanced datasets. | [‘balanced’, ‘balanced_subsample’, None] | balanced |
Parameter | Explanation | Tuning Range | Tuning Results |
---|---|---|---|
Bagging_fraction | The proportion of sub-samples used in the bagging process. | (0.5, 1) | 0.9511 |
Min_data_in_leaf | The minimum amount of data required in a leaf node. | (1, 100) | 40 |
Max_depth | The maximum depth of the trees. | (3, 20) | 16 |
Min_split_gain | The minimum gain required to perform a split. | (0, 5) | 0.001 |
Num_leaves | The maximum number of leaf nodes in a tree. | (16, 128) | 81 |
Lambda_l1 | The weight of the L1 regularization term. | (0, 1) | 0.3516 |
Lambda_l2 | The weight of the L2 regularization term. | (0, 1) | 0.4062 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Yang, Y.; Zhang, Y.; Zhang, G.; Tang, T.; Ning, Z.; Zhang, Z.; Zhao, Z. Fire Source Determination Method for Underground Commercial Streets Based on Perception Data and Machine Learning. Fire 2024, 7, 53. https://doi.org/10.3390/fire7020053
Yang Y, Zhang Y, Zhang G, Tang T, Ning Z, Zhang Z, Zhao Z. Fire Source Determination Method for Underground Commercial Streets Based on Perception Data and Machine Learning. Fire. 2024; 7(2):53. https://doi.org/10.3390/fire7020053
Chicago/Turabian StyleYang, Yunhao, Yuanyuan Zhang, Guowei Zhang, Tianyao Tang, Zhaoyu Ning, Zhiwei Zhang, and Ziming Zhao. 2024. "Fire Source Determination Method for Underground Commercial Streets Based on Perception Data and Machine Learning" Fire 7, no. 2: 53. https://doi.org/10.3390/fire7020053
APA StyleYang, Y., Zhang, Y., Zhang, G., Tang, T., Ning, Z., Zhang, Z., & Zhao, Z. (2024). Fire Source Determination Method for Underground Commercial Streets Based on Perception Data and Machine Learning. Fire, 7(2), 53. https://doi.org/10.3390/fire7020053