Abstract: A device for detecting a thermal runaway of a battery module with a number of cells includes a current acquisition module that is configured to capture a set of currents, and a temperature acquisition module that is configured to capture a set of temperatures. The device includes a state of charge capturing module that is configured to capture a set of states, and a resistance calculation module that is configured to derive a set of resistances. The device includes a temperature prediction module that is configured to calculate a set of temperature predictors, and a runaway prediction module that is configured to calculate a set of runaway predictors. A warning module that is configured to set a warning indicator when at least one runaway predictor value of the set of runaway predictors exceeds a predefined threshold value.

Abstract: Method for determining the degradation of a battery module or a battery cell that each deliver energy to an electric load, wherein a) a battery parameter set comprising an actual temperature of the battery module is captured, b) a load parameter set is captured, c) an environmental parameter set is captured, d) a machine learning model is set up and trained with the battery parameter set, the load parameter set and the environmental parameter set, e) a predicted temperature and a standard deviation thereof is calculated using the machine learning model, and the degradation of the battery module is determined using a predicted temperature, the standard deviation and the actual temperature, where a change over the time of the probability of measuring the actual module or cell temperature, which is normal distributed, is an indicator for the degradation of the battery module or battery cell.

Abstract: A method for enhancing a battery module model of a battery module type includes a) exposing a battery module to a first environment and measuring an initial battery parameter, b) training the battery module model of the battery module type with the initial battery parameter based on machine learning techniques, c) operating the battery module at a second environment with changing environmental conditions and capturing an operating battery parameter, d) training the battery module model with the operating battery parameter, e) calculating an end-of life (EOL) parameter (40) relating to an EOL prediction of the battery module, where if the EOL parameter exceeds a predetermined threshold value, then the method continues with step f), other a return to step c) occurs, f) exposing the battery module to a third environment and measuring a final battery parameter, and g) training the battery module model with the final battery parameter.

Abstract: A device for detecting a thermal runaway of a battery module with a number of cells includes a current acquisition module that is configured to capture a set of currents, and a temperature acquisition module that is configured to capture a set of temperatures. The device includes a state of charge capturing module that is configured to capture a set of states, and a resistance calculation module that is configured to derive a set of resistances. The device includes a temperature prediction module that is configured to calculate a set of temperature predictors, and a runaway prediction module that is configured to calculate a set of runaway predictors. A warning module that is configured to set a warning indicator when at least one runaway predictor value of the set of runaway predictors exceeds a predefined threshold value.