Automatic Data Generation Method for Precise Ceiling Temperature Prediction of Cables Fire in the Utility Tunnel and Full-Scale Experimental Verification.
Saved in:
| Title: | Automatic Data Generation Method for Precise Ceiling Temperature Prediction of Cables Fire in the Utility Tunnel and Full-Scale Experimental Verification. |
|---|---|
| Authors: | Sun, Bin1 (AUTHOR), Xu, Zhao-Dong2 (AUTHOR) xuzhaodongseu@126.com |
| Source: | Fire Technology. Sep2022, Vol. 58 Issue 5, p2847-2869. 23p. |
| Subjects: | Ceilings, Building material testing, Temperature distribution, Fire detectors, Temperature, Cables, Forecasting |
| Abstract: | Being impossible to carry out ceiling temperature prediction in tunnel fires, the specific fire scene (fire type, fire location, number of fire sources, etc.) are unknown in the commonly used physical model-based methods. To address the difficulty, this study proposes a novel automatic data generation method to perceive the ceiling temperature distribution in tunnel fires based on BP neural network by using some limited real-time sensor data. The method belongs to one new kind physical model-free data-driven-updated methods, which can be universally applicable and not limited to the specific fire scene. In addition, a full-scale burning test in China's largest tunnel fire experimental platform was conducted to support the ability and effectiveness of the method. Compared to the measurement results, the method is an effective way to study the ceiling temperature character in tunnel fires and its prediction precision is better than the traditional BP neural network algorithm. Meanwhile, model parameters are further analyzed, and the recommended parameters are given. The method can be used as a good numerical tool, addressing the precise ceiling temperature prediction in tunnel fires. [ABSTRACT FROM AUTHOR] |
| Copyright of Fire Technology is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
Be the first to leave a comment!
