Predictive Method for Spontaneous Combustion of Coal Stockpile using in Deep Neural Network

摘要

The present invention relates to a low-carbon spontaneous ignition prediction method using a deep neural network, the method comprising: inputting temperature and environmental information related to low-carbon spontaneous ignition to an input layer node of a deep neural network; And estimating low-carbon spontaneous ignition using the Sigmoid activation function at the hidden layers 1 and 2 nodes of the deep neural network and outputting the output to the output layer node.