电气火灾神经网络模型设计

Electrical fire neural network model design

在去年所有火灾的起因中,电气引发的火灾占比高达三成,造成的经济损失更是无法估量,如何减少电气火灾发生的频率一直是一个难题。本文先是采用自组织竞争神经网络进行电气回路的故障判定,有效的判断电气回路是否存在火灾隐患;然后采用SOM自组织神经网络对存在火灾隐患的回路进行故障分类,达到了进一步细化故障的目的,做到了提前预警电气火灾,减少电气火灾的发生频率。

In last year,the cause of all fires,electrical causes accounted for up to30%,the economic losses caused is incalculable,how to reduce the frequency of electrical fires has been a difficult problem. In this paper,the neural network model is used to determine and classify the fire,which can effectively determine whether there are faults in the electrical circuit and classify the faults in the electrical circuit with hidden dangers. The network model in this paper can reduce the frequency of electrical fire to a certain extent.