Predicting the diffusion rule of toxic gas plays a distinctly important role in emergency capability assessment and rescue work. Among diffusion prediction models, the traditional artificial neural network has exhibited excellent performance not only in prediction accuracy but also in calculation time. Nevertheless, with the continuous development of deep learning and data science, some new prediction models based on deep learning algorithms have been shown to be more advantageous because their structure can better discover internal laws and external connections between input data and output data. The long short-term memory (LSTM) network is a kind of deep learning neural network that has demonstrated outstanding achievements in many prediction fields. This paper applies the LSTM network directly to the prediction of toxic gas diffusion and uses the Project Prairie Grass dataset to conduct experiments. Compared with the Gaussian diffusion model, support vector machine (SVM) model, and back propagation (BP) network model, the LSTM model of deep learning has higher prediction accuracy (especially for the prediction at the point of high concentration values) while avoiding the occurrence of negative concentration values and overfitting problems found in traditional artificial neural network models.

In this article, some of the combustion properties of three carbonate solvent mixtures commonly used as the electrolytes of lithium ion batteries are considered by means of the ISO 5660 cone calorimeter. Experimental findings reveal that the heat release rate, the most important parameter in fire science, exhibits a significant variation among the carbonate mixtures. Other key parameters governing the fire-induced hazards such as total heat release, mass loss rate, combustion efficiency, and concentration of the major exhaust gases are also determined and analyzed. Furthermore, as some researchers argue that oxygen consumption calorimetry is likely to over-predict the chemical heat release for lithium ion cells, another thermal chemistry method based on stoichiometry for heat release rate calculation is adopted. Heat release rate results of the three carbonate solvent mixtures obtained by these two separate methods are found to be in good agreement. Thus, oxygen consumption calorimetry is considered to be an appropriate technique to determine the heat release in fires in relation to electrolytes of lithium ion batteries.