Abstract: The invention relates to a method for locally determining at least one characteristic value of a battery cell, wherein time series of voltages and time or another measure of a state-of-health indicator of a cell are supplied to a further neural network, wherein the further neural network is a network designed for sequence-to-sequence deep learning, and for obtaining a second indicator from the further neural network, wherein the second indicator is a further measure for the expected degradation of the cell. The invention also relates to a device for carrying out the method.

Abstract: There is provided a method for the activation of a fuel cell. An exemplary method comprises operating the fuel cell entirely or partially at least briefly in an electrolysis regimen during galvanic operation.

Abstract: There is provided a method for the activation of a fuel cell. An exemplary method comprises operating the fuel cell entirely or partially at least briefly in an electrolysis regimen during galvanic operation.

Abstract: The invention relates to a device (2) for determining the density of an electrolyte (4). Said device (2) comprises at least two immersion tubes (9, 10) provided with an open orifice (52) and immerging at different depths in the electrolyte (4), whereby said immersion tubes can be respectively filled with gas to a depth (21, 22) which is allocated thereto and each tube has a different gas depth (d) with respect to the other. A least one differential pressure sensor (16) is used to define the difference in pressure inside the immersion tubes (9, 10). An electrode (11, 19) is respectively provided inside the immersion tubes (9, 10), whereby said electrode is connected to a voltage source (5, 35) in order to produce the required depth (21, 22) of gas so that said immersion tubes (9, 10) can be filled therewith upon contact with the electrolyte(4).