CONTROL OF A FUEL CELL SYSTEM USING CELL STRENGTH MONITORING

Abstract

This disclosure relates to a fuel cell system for vehicles that includes a controller which, among other things, regulates the stack flow and purge or drain valve operations based on an energy indicator used to monitor cell voltage. If the energy indicator exceeds a predefined threshold, the controller reduces the stack flow or adjusts the purge or drain valve—either opening it to reduce flooding or closing it to prevent desiccation.

Description

STATEMENT ON GOVERNMENT-FUNDED RESEARCH

[0001] This invention was made with government support under grant number DE-EE0009858, awarded by the U.S. Department of Energy. The government holds certain rights to the invention. AREA OF TECHNOLOGY

[0002] This disclosure concerns the operation of fuel cells. GENERAL STATE OF THE ART

[0003] Fuel cells are electrochemical devices that convert the chemical energy of hydrogen into electrical energy through a reaction with oxygen, producing water and heat as byproducts. In a typical fuel cell, hydrogen gas is introduced at the anode, where it is split into protons and electrons by a catalyst. The protons move through an electrolyte membrane to the cathode, while the electrons travel through an external circuit, generating electricity. At the cathode, the protons, electrons, and oxygen from the air combine to form water. Fuel cells are often stacked to provide the power required for various applications, including vehicles. In fuel cell vehicles, this stack supplies electricity to power the electric motor. SUMMARY

[0004] A vehicle is equipped with a fuel cell system and a control system designed to reduce the stack current of the fuel cell system when a cell voltage monitoring (CVM) energy indicator derived from filtered voltage data exceeds a predefined energy indicator threshold.

[0005] A procedure is implemented in which a purge valve or drain valve of the fuel cell system is opened after the CVM energy indicator has exceeded the energy indicator threshold.

[0006] A controller closes a purge valve or drain valve of the fuel cell system as soon as the CVM energy indicator exceeds the energy indicator threshold. BRIEF DESCRIPTION OF THE DRAWINGS Fig. Figure 1 is a block diagram of a vehicle. Fig. Figure 2 is a schematic representation of a fuel cell system. Fig. Figure 3 is a block diagram of a filter logic for generating a CVM energy indicator. Fig. 4 and Fig. Figure 5 shows diagrams of various signals captured during physical system tests, including CVM energy indicators. DETAILED DESCRIPTION

[0007] This document describes embodiments, but it is understood that these are merely examples and that other embodiments may take different forms. The figures are not necessarily drawn to scale; some features may be greatly enlarged or reduced to highlight specific details of certain components. Consequently, the disclosed structural and functional details are intended to be illustrative and not limiting, and to serve as a representative basis for the skilled person to understand the concepts.

[0008] Features illustrated and described with respect to one of the figures can be combined with features illustrated in one or more other figures to create embodiments not expressly illustrated or described. The illustrated combinations of features represent typical applications; however, other combinations and modifications consistent with the teachings of this disclosure may be desirable for specific applications or implementations.

[0009] Regarding Fig.1 A fuel cell electric vehicle (FCEV) 10 can be equipped with two onboard power sources: a fuel cell system 12 and a high-voltage (HV) battery 14. The fuel cell system 12 includes a fuel cell stack, typically comprising hundreds of fuel cells electrically connected in series. These cells are contained within a housing through which reactants and coolant are integrated into the stack via manifolds. The fuel cell system 12 is connected to a DC / DC converter 16, which regulates the voltage levels between the fuel cell system 12 and an HV bus 18, thereby enabling power transfer to the electric machine 20.

[0010] To achieve the desired power output from the fuel cell system 12, a controller 22 stabilizes voltages at both the stack and individual cell levels across all operating conditions. However, various modes—such as drying, flooding, and icing within the fuel cell stack—can destabilize these voltages, disrupt power generation, and reduce the stack's lifespan. Direct measurement of all internal states of the fuel cell stack in production vehicles is not possible. Instead, the CVM provides a method for detecting such modes within the stack of individual or multiple cells.

[0011] The fuel cell anode systems connected to Fuel Cell System 12 employ two methods for delivering hydrogen (H2): continuous flow and pulse injection. Continuous flow of H2 can be supplied using a pump or a variable-position valve. In contrast, pulse injection delivery uses an injection valve to control the anode pressure. When the anode pressure drops, the injection valve opens, allowing a rapid influx of H2 into the anode circuit. When the anode pressure is high, the valve closes, interrupting the H2 flow. This process causes fluctuations in H2 flow and partial pressure, resulting in oscillations in the voltage output of the fuel cell stack at a similar frequency to those observed during H2 injections.The HV battery 14, which is connected to both the HV rail 18 and the electric machine 20, works together with the fuel cell system 12 to deliver power to the electric machine 20, which ultimately drives the wheels 24.

[0012] The proposed techniques utilize voltage fluctuations in fuel cell systems during pulse-injected hydrogen for mode detection. Under ideal operating conditions, the amplitude of these voltage fluctuations is minimal. However, it has been repeatedly observed during a freeze-start of the fuel cell system that when icing conditions impair cell performance, the corresponding cell voltage, as monitored by the CVM, exhibits excessive oscillations closely synchronized with the hydrogen injection frequency. Shortly after such instability in a cell's voltage is observed, it is much more likely that the voltage will drop significantly below zero, leading to a cell reversal event that causes irreversible changes to the electrode catalysts within the fuel cell.

[0013] A real-time algorithm is proposed that can extract frequency-domain characteristics from CVM measurements to detect unstable voltages within a fuel cell stack. The CVM system is an essential component of fuel cell operation, as it continuously monitors the voltage across individual cells within the stack. By analyzing these frequency-domain voltage measurements, the algorithm can identify characteristic patterns that signal specific operating modes, such as flooding, drying out, or icing of the membrane electrode assembly. These voltage instabilities are related to other operating parameters, including temperature, humidity, and current draw, enabling the algorithm to accurately isolate and diagnose the operating modes.Upon identifying a mode, the system can then propose and implement specific mitigation measures to expand the operational capabilities of the fuel cell system.

[0014] The fuel cell system 26 of vehicle 28, as shown in Fig.Figure 2 shows an assembly of interconnected components, each playing a role in the system's functionality and control. At its core is the fuel cell stack 30, where the electrochemical reactions take place, converting hydrogen and oxygen into electricity, water, and heat. The fuel cell stack 30 is supplied from both the anode and cathode sides, each with its own supply and return manifolds. An anode supply manifold 32 delivers hydrogen to the anode side of the fuel cell stack 30, while a cathode supply manifold 34 provides oxygen to the cathode side. An anode return manifold 36 and a cathode return manifold 38 regulate the exhaust gases, ensuring that unreacted gases and byproducts are removed from the stack 30.

[0015] Hydrogen stored in the high-pressure tank 40 is regulated by a hydrogen pressure control valve 42, which maintains the appropriate pressure before the hydrogen enters an ejector manifold 44. The ejector 44, a crucial component in the hydrogen delivery system, helps maintain the desired hydrogen flow rate, especially under varying load conditions, thereby providing a consistent supply to the fuel cell stack 30 via the anode supply manifold 32. Controlling the hydrogen flow helps maintain the stack's performance and prevent conditions such as insufficient supply or excessive pressure buildup.

[0016] On the cathode side, the air required for oxygen supply is drawn into system 26 through an air filter 46, which removes particles and impurities. The air is then pressurized to the required operating pressure by a compressor 48 before being cooled by an intercooler 50. The cooled air flows through a gas-to-gas humidifier 52, where it is humidified to maintain the necessary humidity levels in the fuel cell stack 30. This humidified air is then supplied to the cathode side of the stack 30 via the cathode supply manifold 34. The compressor speed, which determines the rate of air delivery, is controlled by a control actuator and is adjusted based on the real-time oxygen demand of the stack 30, which fluctuates with the power output.

[0017] Humidity control is important because the gas-to-gas humidifier 52 ensures that the air entering the cathode side is sufficiently humidified, thus preventing the electrolyte membrane within the fuel cell stack 30 from drying out. Maintaining appropriate humidity levels preserves the membrane conductivity. The system 26 also includes a purge drain valve 54 (or separate purge and drain valves) that plays a role in regulating the water content within the anode side of the stack. The purge drain valve 54 removes excess water and unreacted hydrogen from the anode, preventing flooding of the membrane electrode assembly, a condition in which excessive water accumulation hinders the reaction process.

[0018] The electronic throttle 56 is another component that controls the airflow into the system 26 by adjusting the air inlet based on real-time operating requirements. The electronic throttle 56 works in conjunction with the compressor 48 and the humidifier 52 to control the oxygen supply to the cathode at the appropriate humidity and temperature levels. Suitable sensors 58, such as temperature sensors, current sensors, voltage sensors, humidity sensors, pressure sensors, mass airflow sensors, etc., are arranged in a manner common in the field to acquire the various required data. A controller 60, a central processing unit within the system 26, regulates all these operations. It can use automotive communication protocols such as CAN (Controller Area Network), LIN (Local Interconnect Network), and / or FlexRay to establish communication channels.Control unit 60 coordinates the actions of the components. Fig. 2 by using real-time data from the various sensors, including CVM, temperature, humidity and pressure sensors, to control the operation of the fuel cell stack and implement mitigation measures as needed.

[0019] Fig. Figure 3 illustrates the design flow of the CVM filter logic, a process that begins with the instantaneous CVM voltage measurements. These measurements can originate from any time-domain CVM channel reporting either single-cell or multi-cell voltage readings within the fuel cell stack 30. The flow filters and analyzes these measurements to detect specific patterns indicative of particular modes, especially those related to anode operation, including H2 injection / exhaustion and purge valve opening / closing, as associated with Fig. 2 discussed.

[0020] The process begins with the raw time-domain CVM voltage measurement, which is fed into a bandpass filter 62. The bandpass filter 62 isolates and extracts the frequency-domain characteristics of the signal. In particular, it filters out frequencies outside a small range centered around the H2 injection frequency, which is helpful in identifying oscillations associated with hydrogen delivery. The bandpass filter 62 can be implemented in real time, possibly using a digital Butterworth filter design, which is known for its flat frequency response in the passband and its sharp cutoff characteristic. The purpose of this filter is to focus the analysis on the relevant frequency range, removing noise and other irrelevant frequency components that could obscure the detection of certain modes, such as flooding or icing, within the fuel cell stack 30.

[0021] Once the signal has been refined by the bandpass filter 62, it passes to a stack current filter 64. This filter specifically targets the rate of change of the stack current, a parameter in fuel cell operation. The stack current filter 64 works by eliminating data points corresponding to large transient loads, which are periods in which the stack 30 experiences significant and rapid changes in power demand. These transients can cause considerable deviations in the CVM measurements, potentially leading to false positives or obscuring the true indicators of certain modes. By filtering out these transient effects, the stack current filter 64 allows subsequent analysis to focus solely on voltage variations related to the integrity and performance of the fuel cell stack 30 under steady-state or minor load variations.

[0022] The final step in the process is the CVM energy metric calculation 66. This calculation generates the CVM energy indicator, a metric used to assess the overall health of the fuel cell stack 30. The CVM energy metric is derived by integrating the absolute values ​​of a series of successive outputs from the stack current filter 64. This integration is performed over a sliding time window that sweeps across the filtered data in real time. By summing the absolute values, the metric captures the total energy associated with voltage fluctuations within the relevant frequency band, thus providing an indicator of potential problems within the stack 30. For example, an increase in the CVM energy indicator might signal the onset of a certain mode, such as membrane drying or flooding, prompting further investigation or immediate corrective action.

[0023] By integrating these filter stages - bandpass filtering, stack current filtering and energy metric calculation - the CVM filter logic isolates and highlights voltage fluctuations that may indicate underlying problems in the fuel cell system 26.

[0024] Fig.Figure 4 illustrates the application of the proposed CVM filter for detecting a flooding event within a fuel cell system. During this specific test, the fuel cell system experienced a low cell voltage event at approximately 3529 seconds, resulting in an automatic shutdown to protect the system. This low-voltage event was triggered by a flooding mode of the membrane electrode assembly caused by inadequate anode purge control. The annotated data show that the last anode purge event occurred at approximately 3507 seconds, after which the system continued to operate for approximately 22 seconds without anode purge.

[0025] As shown in the figure, an existing mode effect mitigation (MEM) was activated at approximately 3528 seconds when the instantaneous CVM voltage fell below the normal operating threshold. However, by this time it was too late to prevent the shutdown triggered by the flooding mode. The delay in initiating the purge allowed the flooding condition to deteriorate, resulting in the voltage drop that necessitated the system shutdown.

[0026] If the proposed CVM filter were applied to the corresponding voltage measurements, the stack's operational problem could be detected much earlier, at approximately 3522 seconds. At this point, the CVM energy indicator, as shown in the lower graph of the figure, rose above the predetermined threshold, signaling the onset of a potential condition of interest. If the mode-effect mitigation measure had been initiated at 3522 seconds instead of 3528 seconds, this 6-second margin might have been sufficient to flush the excess water from the stack, thus preventing the subsequent flooding mode and shutdown.

[0027] The next step in the analysis involved applying the same CVM filter to data from normal operation of the fuel cell system, in which no significant mode is present. In this scenario, the fuel cell system (FCS) undergoes highly dynamic operation characterized by drastic changes in stack load, as shown in the diagram above. Fig. As can be seen in Figure 5. Despite these large and frequent load fluctuations, the CVM filter isolates and processes the voltage data. The lower diagram in Fig. Figure 5 represents the CVM energy indicator, which remains below the stacking problem detection threshold throughout the test. This indicates that the filter successfully distinguishes between voltage variations induced by normal load and those that would indicate potential stacking problems. While the same threshold used to detect problems in Fig.4 was used, however, the system correctly identifies that the observed voltage changes are attributable to normal operating dynamics and not underlying problematic modes.

[0028] The design of the CVM filter can be extended to identify other modes, including an icing condition during a freeze start and a membrane electrode assembly drying condition likely to occur during high-load operation at hot ambient temperatures. Table 1 presents the proposed isolation criteria for different modes and corresponding mode effect mitigation measures that can be applied. Table 1 mode Isolation criteria FMEM measures Icing during a freeze start CVM energy of any channel > threshold; coolant inlet temperature<Schwellenwert; Stapelstrom > Threshold. Reducing the stack flow; commanding the coolant temperature to a higher setpoint; setting the cathode / anode pressure to higher setpoints; performing a purge; dropping into a low stoichiometric mode to increase heat generation; and / or adjusting the coolant flow rate. Flooding CVM energy of any channel > threshold; higher threshold > coolant inlet temperature > lower threshold; stack flow > threshold; cathode inlet humidity > threshold. Command the purge valve to open; Increase the cathode air mass flow; Increase the stack pressure; Bypass the humidifier; Command the coolant inlet temperature to a higher setpoint. within the limits of the heat control; and / or adjusting the coolant flow rate. Dehydration CVM energy of any channel > threshold; coolant inlet temperature > threshold; stack flow > threshold; cathode inlet humidity <Schwellenwert. Commands: Opening the purge valve; Reducing the cathode air mass flow; Increasing the stack pressure; Commanding the coolant inlet temperature to a lower setpoint; Reducing the setpoint of the coolant differential temperature (outlet - inlet); Reducing the stack flow if the CVM energy indicator is not reduced below the normal threshold after the timeout period.

[0029] The threshold values ​​referenced in Table 1 for different modes, such as CVM energy levels, coolant inlet temperature, stack flow, and cathode inlet humidity, are parameters that define when a specific mode effect mitigation should be triggered. These threshold values ​​can be determined through experimental testing, simulation, or data analysis.

[0030] In a test environment, a fuel cell system can be subjected to controlled conditions that simulate potential scenarios, such as icing during a freeze start, flooding, or drying out. By closely monitoring the system's behavior under these conditions, the specific CVM energy levels, temperatures, and other parameters that indicate the onset of a mode can be identified. For example, during a simulated freeze start, the coolant inlet temperature can be gradually reduced while the CVM energy indicator is monitored. The point at which the CVM energy exceeds a certain value, coupled with a drop in coolant temperature below a predefined level, can signal the threshold at which icing becomes possible. This threshold can then be used in the operating system to trigger proactive measures before icing becomes problematic.

[0031] Similarly, in the event of flooding, tests can be performed in which an anode purge valve is intentionally delayed or held back, and the corresponding effect on the stack flow and cathode inlet humidity is observed. The CVM energy indicator can be recorded along with the stack flow and humidity levels to determine at what point the system begins to flood. These tests help define threshold values ​​which, when reached, trigger actions such as increasing the cathode air mass flow or bypassing the humidifier to prevent flooding from progressing.

[0032] In addition to physical testing, simulation tools can play a role in threshold determination. Simulation models can replicate the operation of the fuel cell system under a variety of environmental conditions and load factors, enabling the prediction of system responses without the need for physical testing. For example, a simulation could model the effect of prolonged high-current operation on the probability of desiccation, helping to determine the maximum current threshold before the stack begins to lose moisture. These simulations can also account for variations in component performance, environmental factors, and system aging, providing insight into how thresholds should be set.

[0033] To facilitate the practical application of the strategies considered here, a vehicle can be equipped with a combination of sensors and diagnostic tools. A data logging system, interfaced with the vehicle's onboard diagnostics, would provide access to parameter values ​​such as fuel cell stack voltage, current draw, coolant temperature, and air mass flow rates. Additional sensors, such as thermocouples and humidity sensors, can be placed on the coolant inlet and outlet pipes to monitor temperature differentials, and on the cathode air inlet to measure humidity levels. These sensors can help detect whether the vehicle is actively controlling coolant temperature, adjusting air stoichiometry, or modifying coolant flow rates to manage specific fuel cell conditions such as icing, flooding, or drying out.

[0034] The vehicle could then be subjected to a range of controlled operating conditions to collect data. For example, the vehicle could be operated in a cold environment to observe whether the coolant inlet temperature is actively regulated to a higher setpoint during a freeze-start, indicating a strategy to prevent icing. Furthermore, varying load conditions, such as rapid acceleration or steep inclines, could be simulated to observe the vehicle's stack-flow response and any corresponding adjustments to the coolant temperature or air mass flow rates.

[0035] During these tests, the data logger could be configured to capture high-resolution time-series data, including stack current, CVM energy indicators, and sensor outputs for temperature and humidity. After processing this data to obtain the CVM energy indicator, as described in [reference to...] Fig. As described in section 3, specific patterns, such as a rapid increase in CVM energy followed by an immediate adjustment of coolant temperature or activation of purge valves, would indicate that the vehicle is taking action in response to detected fuel cell stack problems.

[0036] The timing and sequence of these responses could be monitored. For example, a delayed but significant increase in coolant temperature shortly after the CVM energy indicator rises could indicate the system's attempt to mitigate an emerging mode such as icing or flooding. Conversely, a gradual decrease in stack flow in response to persistently high CVM energy levels could indicate that the vehicle's control system is attempting to prevent a drying-out condition by regulating the load or reducing the air stoichiometry.

[0037] The algorithms, methods, or processes disclosed in this document can be supplied to or implemented by a computer, controller, or processing device, which may include any dedicated or programmable electronic control unit. These algorithms, methods, or processes can be stored as data and executable instructions in various forms, including non-writable storage media such as read-only memory (ROM) and writable storage media such as compact discs, random-access memory (RAM), or other magnetic and optical media. Furthermore, they can be implemented as software-executable objects or realized either partially or entirely as hardware components, such as application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), state machines, or a combination of firmware, hardware, and software.

[0038] Although exemplary embodiments have been described above, these are not intended to encompass all possible forms within the scope of the claims. The terminology used in the description is intended to describe, not limit, the scope, and it is understood that various modifications may be made without deviating from the nature and scope of the disclosed materials. For example, "control" and "controls" may be used interchangeably, since the functionality of a control may be distributed among several control units that can communicate using standard techniques. "Flush valve" or "drain valve" may refer to a "flush drain valve," since these valves may be integrated in certain implementations.

[0039] As already mentioned, features from different embodiments can be combined to create further embodiments that may not be expressly described or illustrated. Although some embodiments may be described as offering advantages or being preferred over others with respect to certain desirable properties, it is obvious to the person skilled in the art that compromises may be necessary to achieve the desired overall attributes of the system, which depend on specific applications and implementations. These attributes may include, among others, strength, durability, marketability, appearance, packaging, size, operability, weight, manufacturability, and ease of assembly. Therefore, embodiments described as less desirable in some respects are not outside the scope of this disclosure and may in fact be preferred for certain applications.

[0040] According to the present invention, a vehicle is provided comprising: a fuel cell system; and a controller programmed to reduce the stack current of the fuel cell system after an energy indicator for cell voltage monitoring, derived from filtered voltage data of the fuel cell system, exceeds an energy indicator threshold. According to one embodiment, the controller is further programmed to reduce the stack current in response to the energy indicator for cell voltage monitoring exceeding the energy indicator threshold when the coolant inlet temperature of the fuel cell system is less than a temperature threshold and the stack current is greater than a current threshold.

[0041] According to one embodiment, the control system is further programmed to increase the coolant inlet temperature of the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold.

[0042] According to one embodiment, the control system is further programmed to set stack current setpoints of the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold.

[0043] According to one embodiment, the control system is further programmed to purge the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold.

[0044] According to one embodiment, the control system is further programmed to change a stoichiometric operating mode of the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold.

[0045] According to one embodiment, the control system is further programmed to set a coolant flow rate of the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold.

[0046] According to the present invention, a method comprises opening a purge valve or drain valve of a fuel cell system after an energy indicator for cell voltage monitoring, derived from filtered voltage data of the fuel cell system, has exceeded an energy indicator threshold. In one aspect of the invention, the method comprises opening the purge valve or drain valve in response to the energy indicator for cell voltage monitoring exceeding the energy indicator threshold while a coolant inlet temperature of the fuel cell system is greater than a temperature threshold, a stack current of the fuel cell system is greater than a current threshold, and a cathode inlet humidity of the fuel cell system is greater than a humidity threshold.

[0047] In one aspect of the invention, the method involves increasing a cathode air mass flow of the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold.

[0048] In one aspect of the invention, the method involves increasing the pressure of the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold.

[0049] In one aspect of the invention, the method involves increasing a coolant inlet temperature of the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold.

[0050] In one aspect of the invention, the method involves adjusting a coolant flow rate of the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold.

[0051] According to the present invention, a motor vehicle power system is provided comprising: a controller programmed to close a purge valve or drain valve of a fuel cell system after an energy indicator for cell voltage monitoring, derived from filtered voltage data of the fuel cell system, exceeds an energy indicator threshold. According to one embodiment, the controller is further programmed to close the purge valve or drain valve in response to the energy indicator for cell voltage monitoring exceeding the energy indicator threshold while a coolant inlet temperature of the fuel cell system is greater than a temperature threshold, a stack current of the fuel cell system is greater than a current threshold, and a cathode inlet humidity of the fuel cell system is less than a humidity threshold.

[0052] According to one embodiment, the control system is further programmed to reduce the cathode air mass flow of the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold.

[0053] According to one embodiment, the control system is further programmed to increase the stack pressure of the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold.

[0054] According to one embodiment, the control system is further programmed to lower the coolant inlet temperature of the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold.

[0055] According to one embodiment, the control system is further programmed to change a stoichiometric operating mode of the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold. QUOTES INCLUDED IN THE DESCRIPTION

[0000] This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited patent literature

[0000] EE 0009858

[0001]

Claims

[1] Vehicle, comprising: a fuel cell system; and a controller programmed to reduce the stack current of the fuel cell system after an energy indicator for cell voltage monitoring, derived from filtered voltage data of the fuel cell system, has exceeded an energy indicator threshold. [2] Vehicle according to claim 1, wherein the control is further programmed to reduce the stack current in response to the fact that the energy indicator for cell voltage monitoring exceeds the energy indicator threshold, while a coolant inlet temperature of the fuel cell system is greater than a temperature threshold and the stack current is greater than a current threshold. [3] Vehicle according to claim 1, wherein the control is further programmed to increase a coolant inlet temperature of the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold. [4] Vehicle according to claim 1, wherein the control is further programmed to adjust electrode pressure oscillations of the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold. [5] Vehicle according to claim 1, wherein the control is further programmed to purge the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold. [6] Vehicle according to claim 1, wherein the control is further programmed to change a stoichiometric operating mode of the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold. [7] Vehicle according to claim 1, wherein the control is further programmed to set a coolant flow rate of the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold. [8] Procedures, comprehensive: Opening a purge drain valve of a fuel cell system after an energy indicator for cell voltage monitoring, derived from filtered voltage data of the fuel cell system, has exceeded an energy indicator threshold. [9] Method according to claim 8, further comprising opening the purge drain valve in response to the fact that the energy indicator for cell voltage monitoring exceeds the energy indicator threshold, while a coolant inlet temperature of the fuel cell system is greater than a temperature threshold, a stack current of the fuel cell system is greater than a current threshold, and a cathode inlet humidity of the fuel cell system is greater than a humidity threshold. [10] Method according to claim 8, further comprising increasing a cathode air mass flow of the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold. [11] Method according to claim 8, further comprising increasing a stack pressure of the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold. [12] Method according to claim 8, further comprising increasing a coolant inlet temperature of the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold. [13] Method according to claim 8, further comprising adjusting a coolant flow rate of the fuel cell system after the energy indicator for cell voltage monitoring has exceeded the energy indicator threshold. [14] Motor vehicle power system, comprising: a controller programmed to close a purge drain valve of a fuel cell system after an energy indicator for cell voltage monitoring, derived from filtered voltage data of the fuel cell system, has exceeded an energy indicator threshold. [15] Motor vehicle power system according to claim 14, wherein the control is further programmed to close the purge drain valve in response to the fact that the energy indicator for cell voltage monitoring exceeds the energy indicator threshold, while a coolant inlet temperature of the fuel cell system is greater than a temperature threshold, a stack current of the fuel cell system is greater than a current threshold, and a cathode inlet humidity of the fuel cell system is less than a humidity threshold.

Images