Fire early warning device and fire extinguishing system for electrical power distribution cabinet

Abstract

The invention discloses a fire early warning device and a fire extinguishing system for an electrical power distribution cabinet, and belongs to the technical field of alarm. The fire early warning device comprises a fire identification model which is trained through a Bayesian network, and the training process comprises the following steps: deducing the distribution of a hidden variable Z according to the parameters of the Bayesian network at the current time and the data vector of the ith training set, and calculating the expectation of log-likelihood about Z; acquiring parameters of the Bayesian network at the next time t + 1 according to the expectation; calculating an error of training the Bayesian network by the data vector of the ith training set; further updating Bayesian network parameters according to the error; and the steps are repeatedly executed, training of the Bayesian network is carried out, verification is carried out on the verification set until a stop condition is reached, training of the Bayesian network is completed, and the fire identification model is obtained. According to the method, the Bayesian network is trained into the fire recognition model through the observable variables and the hidden variables, so that the fire recognition capability is improved.

Images