Device and method for determining the composition and / or the concentration of bad gases in the anode of a fuel cell

Abstract

The invention relates to a device (55) for determining the composition and / or the concentration of bad gases in the anode (6) of a fuel cell (4) of a fuel cell system (2), which device comprises: a hydrogen sensor (44) which is designed to measure the hydrogen concentration in the exhaust gases (38, 50, 70) of the fuel cell (4) during operation of the fuel cell system (2); and a data model (54) which is designed and trained so as to be able to determine the composition and / or the concentration of the bad gases in the anode (6) of the fuel cell (4) from a hydrogen concentration, measured by the hydrogen sensor (44), in the exhaust gases (38, 50, 70) of the fuel cell (4).

Description

[0001] R.415968

[0002] - 1 -

[0003] Description

[0004] title

[0005] Device and method for determining the composition and / or concentration of bad gases in the anode of a fuel cell

[0006] The invention relates to a device and a method for determining the composition and / or concentration of contaminants in the anode of a fuel cell. The invention also relates to a fuel cell system equipped with a device according to the invention and to a motor vehicle with such a fuel cell system.

[0007] State of the art

[0008] To reduce harmful emissions from motor vehicles, electric motors are increasingly being used in vehicles instead of combustion engines. To supply these electric motors with electrical energy, fuel cells powered by hydrogen can also be used instead of batteries.

[0009] PEM fuel cell systems comprise at least one fuel cell with a polymer electrolyte membrane (PEM) and convert hydrogen into electrical energy using oxygen, generating waste heat and water in the process.

[0010] A PEM fuel cell comprises an anode supplied with hydrogen, a cathode supplied with oxygen or air, and a polymer electrolyte membrane placed between them. Several such fuel cells can be stacked to increase the electrical voltage provided by the fuel cells. Within this stack, also known as a "fuel cell stack," are supply channels that provide the individual cells with hydrogen and air and remove the oxygen-depleted humid air and the depleted anode exhaust. R.415968

[0011] - 2 -

[0012] To improve the efficiency of the fuel cell system, an approach has become established in which the still hydrogen-rich anode exhaust gas is enriched with fresh hydrogen using gas supply units and then fed back to the anode inlet. This process is called recirculation.

[0013] During operation of the fuel cell, nitrogen from the air supplied to the cathode of the fuel cell passes through diffusion processes to the anode side of the membrane. Nitrogen is an inert gas for the electrochemical reaction taking place in the fuel cell. As such, it reduces the cell voltage and, if present in excessively high concentrations at the anode, can damage the fuel cell membrane because it is no longer adequately supplied with hydrogen.

[0014] Therefore, from time to time, a portion of the recirculating gas is diverted from the recirculation loop and replaced with fresh, hydrogen-rich fuel to lower the nitrogen concentration in the recirculation loop. This process is called purging. While frequent purging keeps the nitrogen concentration in the recirculation loop low, it also reduces the efficiency of the fuel cell because hydrogen is also removed from the system and lost during purging.

[0015] Another source of contaminants is contaminants already present in the supplied hydrogen-rich fuel. This means that during purging, new contaminants are always introduced into the anode along with the fresh hydrogen. In addition to nitrogen, the supplied fuel may also contain other contaminants, such as helium and / or argon.

[0016] It is an object of the invention to provide a device and a method that makes it possible to determine the composition and / or concentration of bad gases in the anode of a fuel cell of the fuel cell system during the ongoing operation of a fuel cell system.

[0017] Disclosure of the invention

[0018] The invention comprises a training method for training a data model to determine the composition and / or concentration of bad gases in the anode of a fuel cell of a fuel cell system. R.415968

[0019] - 3 -

[0020] The training procedure involves operating the fuel cell system at various operating points, particularly at different operating points with varying current draw, and measuring the hydrogen concentration in the fuel cell's exhaust gases and the composition and / or concentration of bad gases in the fuel cell's anode at each of these operating points. The data model is then trained with the measured values ​​so that, after training, the data model is able to correlate a hydrogen concentration measured in the fuel cell's exhaust gases with a composition and / or concentration of bad gases in the fuel cell's anode.

[0021] The invention also includes a method for determining the composition and / or concentration of unwanted gases in the anode of a fuel cell of a fuel cell system. Such a method comprises measuring the hydrogen concentration in the exhaust gases of the fuel cell during the operation of the fuel cell system and, using a data model trained with a method according to the invention as previously described, determining the composition and / or the concentration of unwanted gases in the anode of the fuel cell from the hydrogen concentration measured in the exhaust gases of the fuel cell.

[0022] The invention also includes a device for determining the composition and / or concentration of contaminants in the anode of a fuel cell of a fuel cell system. A device according to the invention comprises a hydrogen sensor configured to measure the hydrogen concentration in the fuel cell's exhaust gases during operation of the fuel cell system, and a data model configured and trained to determine the composition and / or concentration of contaminants in the fuel cell's anode from the hydrogen concentration in the fuel cell's exhaust gases measured by the hydrogen sensor. The data model can, in particular, be trained using a training method according to the invention, as previously described.

[0023] The invention also includes a fuel cell system with at least one fuel cell having an anode and a cathode, wherein the fuel-R.415968

[0024] - 4 -

[0025] The fuel cell system comprises a device according to the invention for determining the composition and / or concentration of bad gases in the anode of at least one fuel cell of the fuel cell system.

[0026] The invention further comprises a motor vehicle with at least one electric motor and a fuel cell system, which includes a device according to the invention for determining the composition and / or the concentration of bad gases in the anode of the at least one fuel cell of the fuel cell system.

[0027] The methods and the device according to the invention make it possible to determine the composition and / or concentration of bad gases in the anode of the at least one fuel cell of the fuel cell system on the basis of parameters of the fuel cell system that can be easily measured or otherwise determined during operation.

[0028] The harmful gases can include both harmful gases that have diffused from the cathode of the fuel cell through the membrane into the anode, and harmful gases that are contained in the fuel supplied to the anode.

[0029] Knowing the composition and / or concentration of contaminants in the anode of the fuel cell(s) of the fuel cell system enables efficient operation of the fuel cell system. Excessive wear and tear of the fuel cell(s) and damage to the fuel cell(s), which can result from operating the fuel cell(s) with an excessively high concentration of contaminants in the anode, can be reliably prevented with the aid of the invention.

[0030] Therefore, a device and method according to the invention make it possible to operate a fuel cell system very efficiently and to extend the service life of the fuel cell(s) of the fuel cell system.

[0031] In one embodiment, the data model can include a neural network. Neural networks provide efficient data models that are well-trainable. R.415968

[0032] - 5 -

[0033] In one embodiment, a method or training method according to the invention comprises setting or measuring at least one further parameter of the fuel cell system and making it available to the data model as an input parameter. By considering further parameters in the data model, the quality of the results provided by the data model can be improved even further.

[0034] The further parameters may in particular include at least one of the following parameters: the mass flow rate of the exhaust gases flowing out of the anode of the at least one fuel cell; the rotational speed of a recirculation blower designed to convey the anode exhaust gases through an anode recirculation circuit; the temperature of the exhaust gases flowing out of the anode; the pressure of the exhaust gases in the anode recirculation circuit; the operating point of the fuel cell system, in particular the electrical current drawn from the fuel cell system.

[0035] In one embodiment, the device comprises at least one of the following sensors: a mass flow sensor designed and configured to measure the mass flow of the exhaust gases flowing out of the anode of the at least one fuel cell; a speed sensor designed and configured to measure the rotational speed of a recirculation fan in the anode recirculation circuit; a temperature sensor designed and configured to measure the temperature of the exhaust gases flowing out of the anode; a pressure sensor designed and configured to measure the pressure of the exhaust gases in the anode recirculation circuit; and / or a current sensor designed and configured to measure an electric current drawn from the fuel cell system.

[0036] In one embodiment, a method or training method according to the invention further comprises purging the anode recirculation circuit of the fuel cell system by temporarily opening a purge valve. The additional parameters provided to the data model as supplementary parameters may, in this case, include parameters of the purge valve, for example, a characteristic curve of the purge valve, a pressure differential of the anode exhaust gases at the purge valve, and / or a temperature of the anode exhaust gases at the purge valve. R.415968

[0037] - 6 -

[0038] In one embodiment, a method or training method according to the invention comprises purging the fuel cell system with different opening states and / or with different opening times of the purge valve.

[0039] By taking into account additional parameters measured during the purging of the anode recirculation circuit of the fuel cell system, the quality of the results provided by the data model can be further improved.

[0040] In one embodiment, a method or training method according to the invention comprises mixing the gas mixture taken from the anode recirculation circuit during purging with cathode exhaust gases exiting the cathode of the fuel cell in order to reduce the concentration of combustible hydrogen in the exhaust gases.

[0041] In one embodiment, a training method according to the invention comprises determining the temporal profile, i.e., the change in hydrogen concentration over time, in the gas mixture thus generated and taking it into account as a further parameter when training the data model.

[0042] In one embodiment, a method according to the invention comprises purging the anode recirculation circuit of the fuel cell system depending on the previously determined composition and / or concentration of bad gases in the anode of the fuel cell and / or limiting the electric current that can be extracted from the fuel cell.

[0043] These measures can prevent inefficient operation of the fuel cell system, damage, and / or excessive wear of the fuel cell resulting from an excessive concentration of contaminants in the anode. This can extend the service life of the fuel cell system.

[0044] Brief description of the characters

[0045] Figure 1 shows a schematic view of a fuel cell system according to the invention with a device according to the invention for determining the R.415968

[0046] - 7 -

[0047] Composition and / or concentration of harmful gases in the fuel cell.

[0048] Figure 2 shows a flowchart of a method according to the invention for training a data model that makes it possible to determine the composition and / or concentration of bad gases in the fuel cell.

[0049] Figure 3 shows a flowchart of a method according to the invention which makes it possible to determine the composition and / or concentration of bad gases in the fuel cell.

[0050] Figure 4 shows a schematic view of a motor vehicle equipped with an electric motor and a fuel cell system according to the invention.

[0051]

[0052] Figure 1 shows a schematic view of a fuel cell system 2 comprising a device 52 according to the invention, which is designed and configured to carry out methods according to the invention for training and using a data model 54 to determine the composition and / or concentration of bad gases in the anode 6 of at least one fuel cell 4 of the fuel cell system 2.

[0053] The fuel cell system 2 comprises at least one fuel cell 4 with an anode 6 and a cathode 8. A membrane 10, in particular a polymer electrolyte membrane 10, is arranged between the anode 6 and the cathode 8.

[0054] Although only a single fuel cell 4 is shown in Figure 1 for the sake of simplicity, the invention can also be used in combination with fuel cell systems 2 that have several fuel cells 4. In particular, a fuel cell system can have several fuel cells 4 that are combined to form a fuel cell stack. R.415968

[0055] - 8 -

[0056] Gaseous oxygen (O2), for example in the form of oxygen-containing air from the environment, is supplied to the cathode 8 of the fuel cell 4 through an air inlet 81. The exhaust gases 80 produced in the cathode 8 during operation of the fuel cell 4 are discharged from the cathode 8 through a cathode outlet 82.

[0057] The anode 6 of the least one fuel cell 4 is supplied with gaseous fuel, which contains in particular hydrogen (H2), by means of a hydrogen supply system 12.

[0058] The hydrogen supplied to the anode 6 of at least one fuel cell 4 reacts with the oxygen supplied to the cathode at or within the membrane 10 to form water (H₂O). During this reaction, an electrical voltage U is generated between electrodes 6a and 8a, which are located in the anode 6 and cathode 8 of the fuel cell 4, respectively. An electric current i can thus be drawn from the at least one fuel cell 4, which makes it possible to drive electrical loads, such as electric motors.

[0059] The fuel cell system 2 also includes a cooling system 15, which is designed and configured to cool the at least one fuel cell 4 during operation. The cooling system 15 can be configured to optionally operate in a heating mode, in which it heats the at least one fuel cell 4 so that the at least one fuel cell 4 can always be operated at temperatures favorable for efficient operation.

[0060] The hydrogen supply system 12 comprises a fuel source 14, for example a hydrogen tank 14 or a hydrogen cylinder 14, which provides gaseous hydrogen as fuel 90 via an optional shut-off valve 16. The fuel 90 supplied from fuel source 14 can contain undesirable gases, such as nitrogen and / or helium, in addition to hydrogen.

[0061] Since the hydrogen introduced into the anode 6 of a fuel cell 4 does not react completely to form water during a single flow through the anode 6, the hydrogen-containing anode exhaust gases flowing out of the anode 6 are returned to the anode 6 by an anode recirculation circuit 18. This allows a large portion of the hydrogen contained in the anode exhaust gases to be used for fuel cell 4.

[0062] - 9 -

[0063] The generation of electrical energy can be used to increase the efficiency of the fuel cell system 2.

[0064] In the anode recirculation circuit 18, a water separator 20 is provided downstream of a gas outlet 62 of the anode 6 in order to separate water contained in the gas mixture exiting the anode 6 from the gas mixture.

[0065] The water separator 20 is equipped with a drain valve 22, which makes it possible to remove the water separated from the water separator 20 by opening the drain valve 22 from the water separator 20.

[0066] During operation of at least one fuel cell 4, nitrogen diffuses from the air supplied to the cathode 8 of the fuel cell 4 through the membrane 10 from the cathode 8 into the anode 6 of the fuel cell 4 and accumulates over time in the anode recirculation circuit 18. As a result, and due to the undesirable gases already contained in the supplied fuel 90, the proportion of undesirable gases in the gas mixture circulating in the anode recirculation circuit 18 increases during operation of the fuel cell 4 at the expense of the hydrogen content.

[0067] In order to enable the most efficient operation possible of the fuel cell 4, the anode recirculation circuit 18 is regularly purged with hydrogen-rich fuel 90 from the fuel source 14 in order to reduce the proportion of bad gases in the gas mixture circulating in the anode recirculation circuit 18 and to increase the hydrogen content in the gas mixture again.

[0068] A purge valve 24 is provided at a gas outlet 21 of the water separator 20 for purging the anode recirculation circuit 18. By opening the purge valve 24, nitrogen-rich gas mixture can be released from the anode recirculation circuit 18 to reduce the nitrogen concentration in the anode recirculation circuit 18.

[0069] The fluids 60 discharged from the anode recirculation circuit 18 through the drain valve 22 and the purge valve 24 are mixed with the cathode gases 80 exiting the cathode 8 of the at least one fuel cell 4 in order to increase the concentration of hydrogen in the R.415968

[0070] - 10 -

[0071] Fuel cell system 2 to reduce the exhaust gases emitted, and released into the environment through an exhaust outlet 75.

[0072] A hydrogen sensor 44 is provided at the exhaust outlet 75, which makes it possible to measure the concentration of hydrogen in the exiting exhaust gas mixture 70.

[0073] Another gas outlet 23 of the water separator 20 is connected to a suction inlet 27 of a jet pump 26. The inlet of a drive nozzle in the jet pump 26 is fluidically connected to the fuel source 14 via the shut-off valve 16 and a hydrogen metering valve 28.

[0074] Hydrogen-containing fuel 90, supplied from the fuel source 14 to the inlet of the drive nozzle of the jet pump 26, drives the jet pump 26. This causes the gas mixture exiting the anode 6 of the at least one fuel cell 4 to be drawn into the suction inlet 27 of the jet pump 26 after passing through the water separator 20. The drawn-in gas mixture mixes in and downstream of the jet pump 26 with the hydrogen-containing fuel 90 supplied from the fuel source 14.

[0075] The gas mixture 38 enriched in this way with hydrogen-containing fuel 90 is then supplied to the anode 6 through a gas inlet 61.

[0076] A recirculation blower 25 can be provided between the gas outlet 23 of the water separator 20 and the suction inlet 27 of the jet pump 26, which makes it possible to assist the flow of the gas mixture 38 in the anode recirculation circuit 18. The recirculation blower 25 is driven by a motor 29, which is controlled by a motor controller 31.

[0077] A temperature sensor 40 and a pressure sensor 42 are provided on the anode gas supply line 30, which extends from the outlet of the jet pump 26 to the gas inlet 61 of the anode 6, which make it possible to measure the temperature and pressure of the gas mixture 38 that is supplied to the anode 6 of the fuel cell 4.

[0078] Temperature and pressure sensors 40, 42 can also be provided at other locations in the anode recirculation circuit 18. Temperature and pressure R.415968

[0079] - 11 -

[0080] Sensors 40, 42, which are not explicitly shown in Figure 1, can be provided, for example, between the gas outlet 62 of the anode 6 and the water separator 20, the gas outlet 23 of the water separator 20 and the recirculation blower 25 and / or between the recirculation blower 25 and the suction inlet 27 of the jet pump 26.

[0081] A mass flow sensor 46 is provided between the gas outlet 62 of the anode 6 and the water separator 20, which makes it possible to measure the mass flow of the gas mixture exiting the anode 6.

[0082] A speed sensor 48 can be provided on the recirculation blower 25, which makes it possible to measure the speed of the recirculation blower 25.

[0083] An electrical current sensor 45 is provided on at least one of the electrodes 6a, 8a of the at least one fuel cell 4, which makes it possible to measure the electrical current i that is taken from the at least one fuel cell 4.

[0084] Heating elements 50 can be provided at various points in the anode recirculation circuit 18, which are shown by way of example in Figure 1, to heat the flowing gas mixture 38. The positions of the heating elements 50 shown in Figure 1 are only examples and are not exhaustive.

[0085] Figure 1 also shows a control device 55, which is configured to control the components, in particular the valves 16, 26, 22, 24, the recirculation fan 25, the heating elements 50 and / or the cooling system 15 of the fuel cell system 2, in order to operate the fuel cell system 2 in a desired, most efficient operating state. For this purpose, the control device 55 is connected to the valves 16, 26, 22, 24, the recirculation fan 25, the heating elements 50 and / or the cooling system 15 via wireless or wired connections (not shown in Figure 1).

[0086] A fuel cell system 2 according to the invention also comprises a device 52 for determining the composition and / or concentration of bad gases in the anode 6 of the fuel cell 4, which is hereinafter also referred to as the bad gas determination device 52. R.415968

[0087] - 12 -

[0088] The bad gas detection device 52 can be designed as part of the control device 55 or separately from the control device 55.

[0089] The bad gas detection device 52 comprises a data model 54, for example a neural network, which is designed and trainable or trainable in such a way that it is able to determine the composition and / or the concentration of bad gases in the anode 6 of the fuel cell 4 from the hydrogen concentration measured by the hydrogen sensor 44 in the exhaust gas mixture 70 of the fuel cell 4.

[0090] Figure 2 shows a flowchart of a method 100 according to the invention for training the data model 54. The training method 100 is intended to enable the data model 54, after completion of the method 100, to determine the composition and / or the concentration of bad gases in the anode 6 of the fuel cell 4 of the fuel cell system 2 on the basis of data provided by the data model 54, which in particular include the hydrogen concentration in the exhaust gas mixture 70 of the fuel cell 4.

[0091] The training procedure 100 comprises operating the fuel cell system successively at various operating points, in particular with different current draw i (step 110), and at each of the operating points: measuring the hydrogen concentration by measuring the exhaust gas mixture 70 emitted from the fuel cell 4 into the environment (step 120); measuring the composition and / or concentration of bad gases in the anode 6 of the fuel cell 4 with a bad gas sensor 65 inserted into the anode 6 of the fuel cell 4 (step 130); and training the data model 54 with the values ​​thus measured in order to enable the data model 54, after completion of the training phase, to associate a composition and / or concentration of bad gases in the anode 6 of the fuel cell 4 with a hydrogen concentration measured in the exhaust gas mixture 70 of the at least one fuel cell 4.

[0092] To train data model 54, it is necessary to measure the composition and / or concentration of bad gases in the anode 6 of fuel cell 4. R.415968

[0093] - 13 -

[0094] To measure the composition and / or concentration of bad gases in the anode 6 of the fuel cell 4, at least one suitable bad gas sensor 65 is inserted into the anode 6 of the fuel cell 4.

[0095] After completion of the training phase, the composition and / or concentration of the contaminants in the anode 6 of the fuel cell 4 can be determined using the data model 54 trained according to the invention. Therefore, after completion of the training phase, it is no longer necessary to measure the composition and / or concentration of contaminants in the anode 6 of the fuel cell 4. The contaminant sensor 65 can therefore be removed from the anode 6 of the fuel cell 4 after completion of the training phase.

[0096] The training of the data model 54 with a training method 100 according to the invention can be carried out in particular under laboratory conditions under which all parameters of the fuel cell system 2, in particular the composition and / or the concentration of bad gases in the anode 6 of the fuel cell 4, can be controlled or measured with high accuracy.

[0097] The data obtained during the training of data model 54 can be used for a large number of structurally identical fuel cell systems 2. Therefore, it is sufficient to perform the complex training of data model 54 once on an exemplary fuel cell system 2 in order to later use the data obtained to determine the composition and / or the concentration of unwanted gases in the anode 6 of the fuel cells 4 of a large number of structurally identical fuel cell systems 2.

[0098] In addition to the parameters mentioned so far, further parameters of the fuel cell system 2 can be used to train the data model 54. These additional parameters can include, in particular, one or more of the following: the mass flow rate of the anode exhaust gases flowing out of the anode 6 of the at least one fuel cell 4, the rotational speed of the recirculation blower 25, the temperature and / or pressure of the gas mixture circulating in the anode recirculation circuit 18 38.R.415968

[0099] - 14 -

[0100] The other parameters can also include falling edges, maximum and / or minimum values ​​and / or plateaus over time, i.e. the change in the hydrogen concentration measured by the hydrogen sensor 44 over time in the exhaust gas mixture 70.

[0101] The training procedure 100 for training the data model 54 may, in particular, include purging the anode recirculation circuit 18 of the fuel cell system 2 by temporarily opening the purge valve 24. In this case, further parameters may be used for training the data model 54. These further parameters may, in particular, include parameters of the purge valve 24, for example, a characteristic curve of the purge valve 24, a pressure difference of the gas mixture at the purge valve 24, and / or a temperature of the gas mixture measured at the purge valve 24.

[0102] In order to train the data model 54 as comprehensively as possible, the anode recirculation circuit 18 of the fuel cell system 2 can be purged in the training phase with different opening states of the purge valve 24 and / or with different opening times of the purge valve 24.

[0103] The training procedure 100 for training the data model 54 may in particular include determining the course, in particular an increase in the hydrogen concentration in the exhaust gas mixture 70, during the purging of the anode recirculation circuit 18 and taking it into account when training the data model 54.

[0104] If the hydrogen concentration in the exhaust gas mixture 70 rises very rapidly after the purge valve 24 is opened, there is a large amount of hydrogen or hydrogen mixed with helium present in the anode recirculation circuit 18. If the hydrogen concentration in the exhaust gas mixture 70 rises less rapidly, there is less hydrogen in the gas mixture circulating in the anode recirculation circuit 18.

[0105] Figure 3 shows a flowchart illustrating a method 200 according to the invention for determining the composition and / or concentration of bad gases in the anode 6 of the fuel cell 4. R.415968

[0106] - 15 -

[0107] The procedure 200 includes operating the fuel cell system 2 (step 210) and measuring the hydrogen concentration in the exhaust gas mixture 70 of the fuel cell system 2 during the operation of the fuel cell system 2 (step 220).

[0108] The hydrogen concentration measured in the exhaust gas mixture 70 during the operation of the fuel cell system 2 is then fed to the data model 54 as an input parameter in step 230. The data model 54 has been trained, as described above, to determine in the next step 240 the composition and / or the concentration of the bad gases in the anode 6 of the fuel cell 4 based on the hydrogen concentration measured in the exhaust gas mixture 70, in particular based on the time course of the measured hydrogen concentration.

[0109] Method 200 can include measuring at least one further parameter of the fuel cell system 2 in steps 220 and 230 and feeding it into the data model 54 as an additional input parameter. This can further improve the quality of the results provided by the data model 54.

[0110] These additional parameters may in particular include at least one of the following parameters: the mass flow rate of the anode exhaust gases flowing out of the anode 6 of the fuel cell 4; the rotational speed of the recirculation blower 25; the temperature and / or the pressure of the gas mixture 38 in the anode recirculation circuit 18 and / or the operating point of the fuel cell system 2, in particular the electric current i taken from the at least one fuel cell 4.

[0111] The other parameters can also include falling edges, maximum and / or minimum values ​​and / or plateaus in the time course of the hydrogen concentration measured by the hydrogen sensor 44 in the exhaust gas mixture 70.

[0112] A method 200 according to the invention for determining the composition and / or concentration of bad gases in the anode 6 of the fuel cell 4 can also include temporarily opening the anode recirculation circuit 18 of the fuel cell system 2 in a step 215.

[0113] - 16 -

[0114] The purge valve 24 is to be flushed. In this case, further parameters of the fuel cell system 2, which are associated with the purging of the anode recirculation circuit 18, can be measured and made available to the data model 54 as additional parameters. In this way, the quality of the results provided by the data model 54 can be further improved.

[0115] The other parameters may include, in particular, parameters of the purge valve 24, for example the characteristic curve of the purge valve 24, the pressure difference of the gas mixture 38 at the purge valve 24 and / or the temperature of the gas mixture 38 measured at the purge valve 24 in the anode recirculation circuit 18.

[0116] The method 200 may in particular include measuring the course, in particular the increase, of the hydrogen concentration in the exhaust gas mixture 70 of the fuel cell 4 during the purging of the anode recirculation circuit 18 and making it available to the data model 54 as an additional input parameter.

[0117] By measuring and taking into account the temporal evolution of the hydrogen concentration in the exhaust gas mixture 70 of the fuel cell 4, the quality of the results provided by the data model 54 can be further improved.

[0118] Optionally, the procedure 200 can also include purging the anode recirculation circuit 18 of the fuel cell system 2 by opening the purge valve 24 in step 250, depending on the previously determined composition and / or concentration of the bad gases in the anode 6 of the fuel cell 4, and / or limiting the maximum electrical current i that can be extracted from the fuel cell 4 in step 260.

[0119] These measures reliably prevent inefficient operation of the fuel cell 4, excessive wear of the fuel cell 4 and damage to the fuel cell 4, which can result from operating the fuel cell 4 with an excessively high concentration of bad gases in the anode 6 of the fuel cell 4.

[0120] A device 52 according to the invention and methods 100, 200 according to the invention therefore make it possible to operate a fuel cell system 2 very efficiently. R.415968

[0121] - 17 -

[0122] operate and extend the service life of the fuel cell(s) 4 of the fuel cell system 2.

[0123] Figure 4 shows a schematic view of a motor vehicle 1 with an electric motor 5, which is supplied with electrical energy by a fuel cell system 2 according to the invention.

[0124] The motor vehicle 1 has four wheels 3 and at least one electric motor 5, which is designed and intended to drive at least two of the four wheels 3 of the motor vehicle 1. The electric motor 5 can also be intended to drive all four wheels 3 of the motor vehicle 1.

[0125] In an alternative embodiment, which is not explicitly shown in the figures, an electric motor 5 can be provided on at least one of the wheels 3, in particular on each of the wheels 3, of the motor vehicle 1 for driving the respective wheel 3.

[0126] The electric motor 5 is supplied with electrical energy via a motor controller 7, which is provided by the fuel cell system 2. The electric motor 5 can also be supplied with electrical energy from a high-voltage battery 13, which is electrically charged by the fuel cell system 2.

[0127] A fuel cell system 2 according to the invention can also be used in motor vehicles 1 that have more or less than four wheels 3.

Claims

R.415968 - 18 - 1. Training procedure for training a data model (54) to determine the composition and / or concentration of bad gases in the anode (6) of a fuel cell (4) of a fuel cell system (2), wherein the training procedure comprises: to operate the fuel cell system (2) at different operating points and at each of these operating points; the hydrogen concentration in the exhaust gases (70) of the fuel cell (4) as well as the composition and / or concentration of bad gases in the anode (6) of the fuel cell (4) to measure and to train the data model (54) with the measured values ​​so that, after completion of the training procedure, the data model (54) is able to assign a composition and / or a concentration of bad gases in the anode (6) of the fuel cell (4) to a measured hydrogen concentration in the exhaust gases (70) of the fuel cell (4).

2. Training method according to claim 1, wherein the bad gases comprise bad gases that have diffused from the cathode (8) of the fuel cell (4) into the anode (6), and / or bad gases that are contained in the fuel supplied to the anode (6).

3. Training method according to claim 1 or 2, wherein the training method further comprises adjusting or measuring at least one further parameter of the fuel cell system (2) and taking it into account when training the data model (54); R.415968 - 19 - wherein at least one further parameter includes in particular at least one of the following parameters: the mass flow of the exhaust gases (38, 50, 70) flowing out of the anode (6); the rotational speed of a recirculation fan (25); the temperature of the exhaust gases (38, 50, 70); the pressure of the exhaust gases (38, 50, 70); the operating point of the fuel cell system (2), in particular the electrical current that is drawn from the fuel cell system (2).

4. Training method according to one of the preceding claims, wherein the training method comprises purging an anode recirculation circuit (18) of the fuel cell system (2) by opening a purge valve (24); and wherein the further parameters comprise parameters of the purge valve (24), in particular a characteristic curve of the purge valve (24), a pressure differential at the purge valve (24) and / or a temperature at the purge valve (24); wherein the training procedure in particular includes flushing the fuel cell system (2) with different opening states and / or with different opening times of the flushing valve (24).

5. Training method according to claim 4, wherein the method comprises mixing the gas mixture (60) taken from the anode recirculation circuit (18) during purging with cathode gases (80) exiting from the cathode (8) of the fuel cell (4) and determining the time course of the hydrogen concentration in the gas mixture (70) produced by the mixing and taking it into account when training the data model (54).

6. Method for determining the composition and / or concentration of bad gases in the anode (6) of a fuel cell (4) of a fuel cell system (2), wherein the method comprises, R.415968 - 20 - to measure the hydrogen concentration in the exhaust gases (38, 50, 70) of the fuel cell (4) during the operation of the fuel cell system (2); and using a data model (54) that has been trained using a training method according to one of the preceding claims, to determine the composition and / or the concentration of the bad gases in the anode (6) of the fuel cell (4) from the measured hydrogen concentration in the exhaust gases (38, 50, 70) of the fuel cell (4); wherein the bad gases include in particular bad gases that have diffused from the cathode (8) of the fuel cell (4) into the anode (6) and / or bad gases that are contained in the fuel supplied to the anode (6).

7. The method of claim 6, wherein the method further comprises adjusting or measuring at least one further parameter of the fuel cell system (2) and making it available to the data model (54) for determining the composition and / or concentration of bad gases in the anode (6) of the fuel cell (4); wherein at least one further parameter includes in particular at least one of the following parameters: the mass flow of the exhaust gases (38, 50, 70); the rotational speed of a recirculation fan (25); the temperature of the exhaust gases (38, 50, 70); the pressure of the exhaust gases (38, 50, 70); the operating point of the fuel cell system (2), in particular the electrical current that is drawn from the fuel cell system (2).

8. The method of claim 6 or 7, wherein the method further comprises purging an anode recirculation circuit (18) of the fuel cell system (2) by opening a purge valve (24); and wherein the further parameters R.415968 - 21 - Parameters of the purge valve (24), in particular a characteristic curve of the purge valve (24), a pressure differential at the purge valve (24) and / or a temperature at the purge valve (24); wherein the method in particular comprises purging the fuel cell system (2) with different opening states and / or with different opening times of the purge valve (24).

9. Method according to claim 8, to mix the gas mixture (60) taken from the anode recirculation circuit (18) during purging with cathode gases (80) exiting from the cathode (8) of the fuel cell (4) and to determine the change in hydrogen concentration over time in the gas mixture (70) produced by the mixing and to make it available to the data model (54) as a further parameter.

10. Method according to claim 8 or 9, wherein the method comprises purging the anode recirculation circuit (18) of the fuel cell system (2) and / or limiting the electrical current extractable from the fuel cell (4) depending on the previously determined composition and / or concentration of bad gases in the anode (6) of the fuel cell (4).

11. Method or training method according to any of the preceding claims, wherein the data model (54) comprises a neural network.

12. Device (55) for determining the composition and / or concentration of bad gases in the anode (6) of a fuel cell (4) of a fuel cell system (2), wherein the device (55) comprises: a hydrogen sensor (44) designed to measure the hydrogen concentration in the exhaust gases (38, 50, 70) of the fuel cell (4) during the operation of the fuel cell system (2); and a data model (54) that is designed and trained to be able to determine the composition and / or the concentration of the bad gases in the anode (6) of the fuel cell (4) from a hydrogen concentration in the exhaust gases (38, 50, 70) of the fuel cell (4) measured by the hydrogen sensor (44): R.415968 - 22 - wherein the data model (54) has been trained in particular using a training method according to any one of claims 1 to 5.

13. Device according to claim 12, wherein the device comprises at least one of the following sensors (42, 44, 46, 48, 49): a mass flow sensor (46) which is designed and configured to measure a mass flow of the exhaust gases (38); a speed sensor (48) which is designed and configured to measure the speed of a recirculation blower (25); a temperature sensor (40) which is designed and configured to measure the temperature of the exhaust gases (38, 50, 70); a pressure sensor (42) designed and configured to measure the pressure of the exhaust gases (38, 50, 70); and a current sensor (49) designed and configured to measure an electric current drawn from the fuel cell system (2); and wherein the data model (54) is designed to take into account at least one further parameter when determining the composition and / or concentration of bad gases in the anode (6) of the fuel cell (4); wherein at least one further parameter includes in particular at least one of the following parameters: the mass flow of the exhaust gases (38, 50, 70); the rotational speed of a recirculation fan (25); the temperature of the exhaust gases (38, 50, 70); R.415968 - 23 - the pressure of the exhaust gases (38, 50, 70); the operating point of the fuel cell system (2), in particular the electrical current drawn from the fuel cell system (2); the time course of hydrogen concentration in a gas mixture (70) containing gas (50) taken from the anode recirculation circuit (18) and cathode exhaust gases (80).

14. Fuel cell system (2) comprising at least one fuel cell (4) having an anode (6) and a cathode (8), wherein the fuel cell system (2) comprises a device (55) according to claim 12 or 13 for determining the composition and / or concentration of bad gases in the anode (6) of the at least one fuel cell (4) of the fuel cell system (2).

15. Motor vehicle (1) with at least one electric motor (5) and a fuel cell system (2) according to claim 14, which is designed and configured to provide electrical energy for driving the electric motor (5).

Images