Lithium-based batteries have the potential to undergo thermal runaway (TR), during which mixtures of gases are released. The purpose of this study was to assess the explosibility of the gaseous emission from LIBs of an NMC-based cathode during thermal runaway. In the current project, a series of pouch lithium-based battery cells was exposed to abuse conditions (thermal) to study the total amount of gases released and the composition of the gas mixture. First, the battery cells were placed in a closed vessel, and the pressure and temperature rise inside the vessel were measured. In a second step, the composition of gases was analysed using a Fourier transform Infrared (FTIR) spectrometer. We found that the amount of released gases was up to 102 ± 4 L, with a clear dependence on the battery capacity. This study showed that the concentration of gaseous emissions such as carbon monoxide (CO), methane (CH₄), ethylene (C₂H₄), ethane (C₂H₆), and hydrogen cyanide (HCN) increased with higher cell capacity. Of the five studied flammable gases, the maximum concentrations of carbon monoxide (16.85 vol%), methane (7.6 vol%), and ethylene (7.86 vol%) were identified to be within their explosible range. Applying Le Chatelier’s law, a calculated lower explosion limit (LEL) of 7% in volume fraction was obtained for the gas mixture. The upper explosion limit (UEL) of the gas mixture was also found to be 31% in volume. A filter comprising pyrobubbles was used for the removal of the studied gas components released during the thermal abuse. The investigation revealed that the pyrobubbles filter was highly effect in the removal of HCN (up to 94% removal) and CO₂ (up to 100% removal). Herein, we report the dependency of the method of thermal runaway trigger on the measured maximum temperature.

Effective early fire detection is crucial for preventing damage to people and buildings, especially in fire-prone historic structures. However, due to the infrequent occurrence of fire events throughout a building’s lifespan, real-world data for training models are often sparse. In this study, we applied feature representation transfer and instance transfer in the context of early fire detection using multi-sensor nodes. The goal was to investigate whether training data from a small-scale setup (source domain) can be used to identify various incipient fire scenarios in their early stages within a full-scale test room (target domain). In a first step, we employed Linear Discriminant Analysis (LDA) to create a new feature space solely based on the source domain data and predicted four different fire types (smoldering wood, smoldering cotton, smoldering cable and candle fire) in the target domain with a classification rate up to 69% and a Cohen’s Kappa of 0.58. Notably, lower classification performance was observed for sensor node positions close to the wall in the full-scale test room. In a second experiment, we applied the TrAdaBoost algorithm as a common instance transfer technique to adapt the model to the target domain, assuming that sparse information from the target domain is available. Boosting the data from 1% to 30% was utilized for individual sensor node positions in the target domain to adapt the model to the target domain. We found that additional boosting improved the classification performance (average classification rate of 73% and an average Cohen’s Kappa of 0.63). However, it was noted that excessively boosting the data could lead to overfitting to a specific sensor node position in the target domain, resulting in a reduction in the overall classification performance.

This work analyzes a new indoor laboratory dataset looking at early fire indicators in controlled and realistic experiments representing different incipient fire scenarios. The experiments were performed within the constraints of an indoor laboratory setting using multiple distributed sensor nodes in different room positions. Each sensor node collected data of particulate matter (PM), volatile organic compounds (VOCs), carbon monoxide (CO), carbon dioxide (CO${}_2$), hydrogen (H${}_2$), ultraviolet radiation (UV), air temperature, and humidity in terms of a multivariate time series. These data hold immense value for researchers within the machine learning and data science communities who are keen to explore innovative and advanced statistical and machine learning techniques. They serve as a valuable resource for the development of early fire detection systems. The analysis of the collected data was carried out depending on the Manhattan distance between the fire source and the sensor node. We found that especially larger particles (>0.5 $\mathsf{\mu }$m) and VOCs show a significant dependency with respect to the intensity as a function of the Manhattan distance to the source. Moreover, we observed differences in the propagation behavior of VOCs, PM, and CO, which are particularly relevant in incipient fire scenarios due to the presence of strand propagation effects.

The present work examines 75 Ah nickel–cobalt–manganese (NMC)/graphite-based pouch cells with respect to their expansion behavior. The focus is on cell expansion due to critical cells according to the installation conditions of a battery module. Strain gauges were used for monitoring. By comparing the cell expansion in standard conditioning to that in an abuse (overcharging), information can be acquired about the suitability of the expansion behavior for early detection of critical cell states and to avoid resulting damage, e.g., cell opening or cell fire. The sequence of critical cell events has been shown to be easily reproducible; especially the first significant cell expansion due to internal gas formation, which was a reliable detection criterion for critical cell states.

Multi-sensor data from a small laboratory setup was used to create a new feature space with linear discriminant analysis (LDA) to improve the classification of different fire materials. The LDA parameters were applied to a real room dataset to evaluate classification models. Data transformation using LDA improved the classification rate by up to 17% compared to principal component analysis (PCA) approaches used in previous studies.

This work analyzes a new indoor laboratory data set looking at early fire indicators in controlled and realistic experiments representing different incipient fire scenarios. The experiments were performed within the confines of an indoor laboratory setting using multiple distributed sensor nodes on different room positions. Each sensor node collected data of particulate matter (PM), volatile organic compounds (VOC), CO, CO2, H2, UV, air temperature and humidity in terms of a multivariate time series. These data hold immense value for researchers within the machine learning and data science communities who are keen on exploring innovative advanced statistical and machine learning techniques. They serve as a valuable resource for the development of early fire detection systems. The analysis of the collected data was carried out in dependence of the manhattan distance between the fire source and the sensor node. We found that especially larger particles (> 0.5 μm) and VOCs show a significant dependency with respect to the intensity as a function of the manhattan distance to the source. Moreover, we observed differences in the propagation behavior of VOCs, PM, and CO, which are particularly relevant in incipient fire scenarios due to the presence of strand popagation effects.