基于FDS的模糊神经网络灭火模型在民航火灾中的应用  

Application of FDS-based fuzzy neural network fire suppression model to civil aviation fires

作　　者：陈智 刘康 CHEN Zhi;LIU Kang(AVIC Xi’an Aircraft Industry Group Company LTD,Xi’an 710089,China)

机构地区：[1]中航西安飞机工业集团股份有限公司,西安710089

出　　处：《自动化与仪器仪表》2024年第5期46-49,54,共5页Automation & Instrumentation

基　　金：陕西省教育厅2018年科学研究项目(18JK0400)。

摘　　要：民航火灾具有高风险和严重后果,因此,需要有效的灭火模型来提高灭火策略和救援行动的效率。本研究采用火灾动力学模拟软件进行民航火灾模拟,并利用模糊神经网络来构建灭火模型。通过收集和分析民航火灾相关数据和实验结果,使用FDS模拟不同火灾场景,并优化模糊神经网络灭火模型的参数。结果显示,模型在训练集上性能良好,均方误差达到0.001,随着样本数量增加,误差最低为1.994%。火灾模拟揭示了氧气浓度和温度分布,强调了氧气不均匀分布和高温区域。该模型在评估火灾情况和指导灭火措施方面具有良好的应用前景,可以提高民航火灾的灭火效率和安全性。Civil aviation fires have high risks and serious consequences,therefore an effective firefighting model is needed to improve the efficiency of firefighting strategies and rescue operations.This study used fire dynamics simulation software for civil aviation fire simulation and constructed a fire extinguishing model using fuzzy neural networks.By collecting and analyzing data and experimental results related to civil aviation fires,FDS is used to simulate different fire scenarios,and the parameters of the fuzzy neural network fire extinguishing model are optimized.The results show that the model performs well on the training set,with a mean square error of 0.001.As the number of samples increases,the lowest error is 1.994%.The fire simulation revealed the distribution of oxygen concentration and temperature,emphasizing the uneven distribution of oxygen and high-temperature areas.This model has good application prospects in evaluating fire situations and guiding firefighting measures,which can improve the firefighting efficiency and safety of civil aviation fires.

关 键 词：FDS 模糊神经网络 消防模拟 火势控制 

分 类 号：V27[航空宇航科学与技术—飞行器设计] TP29[自动化与计算机技术—检测技术与自动化装置]