Method and system for accurately controlling hydrogen stoichiometric ratio of fuel cell

Abstract

The invention relates to the technical field of fuel cells, in particular to a method and system for accurately controlling the hydrogen stoichiometric ratio of a fuel cell, and the method comprises the steps: firstly, obtaining a quantitative anode health state value through a fusion calculation model by collecting load current, anode inlet and outlet pressure, temperature, high-frequency resistance and other multi-source signals in real time; a feed-forward model based on a load current change rate predicts sudden change of hydrogen demand, and an optimal hydrogen flow instruction is jointly generated in combination with output of a PID controller which adaptively adjusts parameters according to a health state value. According to the method, the integrated diagnosis parameter, namely the anode health state value, is created, so that the internal state of the fuel cell can be accurately perceived and prospectively judged. Through deep fusion of multi-source heterogeneous information such as high-frequency resistance, anode pressure difference, current and temperature, a comprehensive index capable of comprehensively and quantitatively reflecting anode water content, gas concentration and runner smoothness is generated.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fuel cells, in particular to a method and system for precisely controlling the hydrogen stoichiometry of a fuel cell. BACKGROUND

[0002] Fuel cells, particularly proton exchange membrane fuel cells, are considered as one of the important solutions for clean energy in the future due to their high efficiency and zero emission characteristics. The core key to their high-efficiency and stable operation lies in the precise stoichiometry control of hydrogen supply on the anode side. Hydrogen stoichiometry refers to the ratio of hydrogen flow supplied to the anode to the actual hydrogen flow consumed by the electrochemical reaction of the stack. Maintaining an appropriate and stable stoichiometry is crucial for ensuring cell performance, improving hydrogen utilization, and prolonging the life of the stack.

[0003] However, the existing mainstream hydrogen stoichiometry control method has significant technical bottlenecks and challenges. The current widely used method is a combination of load current-based feedforward and simple pressure or flow feedback control. This method can work in steady-state conditions, but in dynamic conditions, especially when the load current changes sharply, it shows serious hysteresis and insufficient control accuracy, and has one-sidedness and hysteresis. Therefore, it is necessary to develop a method and system for precisely controlling the hydrogen stoichiometry of a fuel cell. SUMMARY

[0004] To overcome the above shortcomings, the present application provides a method and system for precisely controlling the hydrogen stoichiometry of a fuel cell, aiming to improve the one-sidedness and hysteresis of the traditional method in the prior art which only relies on a single load current or pressure signal for control.

[0005] In a first aspect, the present application provides a method for precisely controlling the hydrogen stoichiometry of a fuel cell, comprising:

[0006] S1, real-time acquisition of the load current of the fuel cell, acquisition of the anode inlet pressure and the anode outlet pressure through pressure sensors arranged at the anode gas inlet and outlet, and acquisition of the stack temperature;

[0007] by injecting a high-frequency alternating disturbance signal into the stack and measuring its voltage and current response to calculate the high-frequency resistance value;

[0008] S2, calculating the anode inlet and outlet pressure difference according to the anode inlet pressure and the anode outlet pressure, and inputting the high-frequency resistance value and the anode inlet and outlet pressure difference into a preset fusion calculation model to calculate an anode health state value representing the comprehensive state of the anode;

[0009] Comparing the actual anode health state value with a target health state value, and the difference between them is the health state error;

[0010] S3. Calculate the instantaneous rate of change of the load current, and input the real-time value of the load current and its instantaneous rate of change into a feedforward calculation model to generate a hydrogen flow feedforward compensation amount to cope with load changes.

[0011] S4. The anode health status value is compared with a preset target value to obtain the deviation, and the deviation is input to a parameter adjustable PID controller.

[0012] The hydrogen flow feedforward compensation is superimposed on the output of the PID controller to generate a hydrogen flow control command.

[0013] S5. Drive the actuator in the hydrogen supply system according to the hydrogen flow control command to adjust the hydrogen flow rate supplied to the fuel cell.

[0014] The step of obtaining the stack temperature in S1 includes:

[0015] The temperature sensor collects a simulated temperature signal representing the operating temperature of the fuel cell stack in real time.

[0016] The temperature simulation signal is filtered and converted from analog to digital to obtain and output a digital stack temperature value for use by the fusion calculation model.

[0017] The step in S1 to calculate the high-frequency resistance value includes:

[0018] A high-frequency AC disturbance signal with a preset frequency and amplitude is injected into the fuel cell stack, and the voltage and current response of the stack to this signal are measured.

[0019] Based on the voltage and current response, the high-frequency resistance value of the fuel cell at the preset frequency is calculated using an impedance analysis algorithm.

[0020] The steps in S1 to obtain the anode inlet and outlet pressures include:

[0021] Analog signals of the anode inlet pressure and anode outlet pressure are simultaneously collected by pressure sensors installed at the anode inlet and outlet respectively.

[0022] The analog signal is conditioned and converted from analog to digital to obtain a digitized pressure value, which provides input for calculating the pressure difference between the anode inlet and outlet.

[0023] The fusion calculation model in S2 is a nonlinear function model, and the steps for calculating the anode health state value using the nonlinear function model include:

[0024] The high-frequency resistance value, the anode inlet and outlet pressure difference, the load current, and the stack temperature are used as input variables.

[0025] The input variables are weighted and fused using a pre-defined nonlinear function model;

[0026] The model or mapping table is used to calculate and output the anode health status value, and the error between the anode health status value and the actual health status value is predicted.

[0027] The feedforward calculation model in S3 includes:

[0028] The load current is differentiated in real time to obtain the instantaneous rate of change;

[0029] Perform the following calculation: Hydrogen flow feedforward compensation = Load current × Rate of change × Feedforward coefficient.

[0030] The PID controller parameter adjustment steps of S4 include:

[0031] Establish a mapping table between the anode health status error value and the PID parameters;

[0032] When the anode health status value is lower than the preset threshold, the proportional coefficient and integral coefficient are automatically increased.

[0033] The feedforward compensation and the PID output are weighted and superimposed to generate the hydrogen flow control command.

[0034] The step of adjusting the hydrogen flow rate supplied to the fuel cell in S5 includes:

[0035] Convert hydrogen flow control commands into duty cycle signals or analog voltage signals;

[0036] Drive proportional valve or hydrogen injector actuator;

[0037] The flow rate of hydrogen supplied to the anode of the fuel cell is regulated by the actuator.

[0038] It also includes fault handling, the fault handling steps of which include:

[0039] Continuously monitor the anode health status value;

[0040] Determine whether the anode health status value remains below a preset fault threshold for an extended period of time.

[0041] When the judgment conditions are met, a first-level forced anode purging operation is triggered.

[0042] In the high-frequency resistance measurement, the high-frequency resistance is obtained by injecting a high-frequency AC disturbance signal into the fuel cell stack and measuring its response. The frequency range of the high-frequency AC disturbance signal is 1 kHz to 10 kHz, and the amplitude of the high-frequency AC disturbance signal is less than 5% of the rated voltage of the fuel cell stack.

[0043] Secondly, the present invention provides the following technical solution: a system for precisely controlling the hydrogen metering ratio of a fuel cell, comprising:

[0044] The dynamic parameter acquisition module is used to acquire the load current of the fuel cell in real time, obtain the anode inlet pressure and anode outlet pressure through pressure sensors set at the anode inlet and outlet, obtain the stack temperature, and calculate the high-frequency resistance value by injecting a high-frequency AC disturbance signal into the stack and measuring its voltage and current response.

[0045] The differential pressure and state fusion module is used to calculate the differential pressure between the anode inlet and outlet based on the anode inlet pressure and the anode outlet pressure, and input the high-frequency resistance value and the differential pressure between the anode inlet and outlet into a preset fusion calculation model to calculate an anode health state value that characterizes the comprehensive state inside the anode.

[0046] The actual anode health status value is compared with a preset target health status value that represents the optimal operating state of the anode, and the difference is the health status error.

[0047] The predictive feedforward calculation module is used to calculate the instantaneous rate of change of the load current, and input the real-time value of the load current and the instantaneous rate of change into a feedforward calculation model to generate a hydrogen flow feedforward compensation amount to cope with load changes.

[0048] The collaborative control module is used to compare the anode health status value with a preset target value to obtain the deviation, and input the deviation to a parameter-adjustable PID controller, wherein the control parameters of the PID controller are dynamically adjusted according to the anode health status value; at the same time, the hydrogen flow feedforward compensation amount is superimposed with the output of the PID controller to generate a hydrogen flow control command.

[0049] The instruction execution module is used to drive the actuator in the hydrogen supply system according to the hydrogen flow control instruction, so as to adjust the hydrogen flow rate supplied to the fuel cell.

[0050] The present invention has the following beneficial effects:

[0051] 1. In this invention, by creating an integrated diagnostic parameter—the anode health status value—precise perception and forward-looking judgment of the internal state of the fuel cell are achieved. By deeply integrating multi-source heterogeneous information such as high-frequency resistance, anode voltage difference, current, and temperature, a comprehensive index is generated that fully and quantitatively reflects the anode water content, gas concentration, and flow channel patency. This lays a reliable foundation for subsequent precise control.

[0052] 2. This invention constructs a control architecture that intelligently coordinates predictive feedforward and adaptive feedback, fundamentally solving the hydrogen starvation problem under dynamic operating conditions. By utilizing the load current change rate for predictive feedforward, hydrogen flow is compensated in advance before hydrogen starvation occurs; simultaneously, the feedback controller can adjust its own strategy in real time based on the AHS value, proactively enhancing control when conditions are unfavorable. This collaborative mechanism of feedforward responding to sudden changes, feedback ensuring accuracy, and adaptation improving robustness ensures that the system can respond quickly and maintain the optimal metering ratio when facing complex load changes, significantly improving the transient performance and lifespan of the fuel cell stack.

[0053] 3. This invention transforms complex electrochemical state management into a highly efficient, reliable, and easily engineerable closed-loop system. The entire scheme forms an automated closed loop of multi-source sensing, intelligent fusion, predictive decision-making, and adaptive execution. This not only overcomes the limitations of traditional methods relying on complex offline diagnostics or coarse empirical models, achieving precise online, real-time, and fully automated control, but also features a clear system architecture with well-defined functions for each module, which can be implemented using standard hardware and software modules. This provides crucial technical support for the high reliability and large-scale commercial application of fuel cell systems. Attached Figure Description

[0054] Figure 1 This is a flowchart of a method and system for precisely controlling the hydrogen metering ratio in a fuel cell, as proposed in this invention.

[0055] Figure 2 This is a system architecture diagram of a precise control system for hydrogen metering ratio in a fuel cell proposed in this invention. Detailed Implementation

[0056] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] Example 1

[0058] In a first embodiment of the present invention, the present invention provides a method for precisely controlling the hydrogen metering ratio of a fuel cell, such as... Figure 1 As shown, the process includes the following steps: S1, real-time acquisition of the load current of the fuel cell, acquisition of the anode inlet pressure and anode outlet pressure by pressure sensors set at the anode inlet and outlet, and acquisition of the stack temperature;

[0059] The high-frequency resistance value is calculated by injecting a high-frequency AC disturbance signal into the fuel cell stack and measuring its voltage and current response.

[0060] S2. Calculate the pressure difference between the anode inlet and outlet based on the anode inlet pressure and the anode outlet pressure, and input the high-frequency resistance value and the pressure difference between the anode inlet and outlet into a preset fusion calculation model to calculate an anode health status value that characterizes the overall internal state of the anode.

[0061] The actual anode health status value is compared with a target health status value, and the difference is the health status error.

[0062] S3. Calculate the instantaneous rate of change of the load current, and input the real-time value of the load current and its instantaneous rate of change into a feedforward calculation model to generate a hydrogen flow feedforward compensation amount to cope with load changes.

[0063] S4. The anode health status value is compared with a preset target value to obtain the deviation, and the deviation is input to a parameter adjustable PID controller.

[0064] The hydrogen flow feedforward compensation is superimposed on the output of the PID controller to generate a hydrogen flow control command.

[0065] S5. Drive the actuator in the hydrogen supply system according to the hydrogen flow control command to adjust the hydrogen flow rate supplied to the fuel cell.

[0066] Further, the step of obtaining the stack temperature in S1 includes:

[0067] The temperature sensor collects a simulated temperature signal representing the stack's operating temperature in real time.

[0068] The temperature simulation signal is filtered and converted from analog to digital to obtain and output a digital stack temperature value for use by the fusion calculation model.

[0069] Specifically, the temperature sensor is connected to the signal acquisition unit of the control system via wires. The PT100 sensor typically uses a constant current source drive or a Wheatstone bridge circuit to convert changes in its resistance value into changes in voltage. The analog voltage signal output by the sensor first passes through an RC low-pass filter circuit to suppress high-frequency electromagnetic interference from the vehicle environment or power devices, preventing signal distortion. This conditioned analog signal is then converted into a digital quantity that can be processed by the microprocessor. The filtered analog voltage signal is then sent to the microcontroller's built-in or external analog-to-digital converter (ADC). The ADC's reference voltage should be stable, and its resolution is recommended to be no less than 12 bits to ensure a temperature measurement resolution on the order of 0.1°C. In the software program, the voltage value is first converted into a preliminary temperature value based on the ADC's sampled value and the sensor's calibration table. Subsequently, this temperature value is processed by a software filtering algorithm to further smooth the data and eliminate occasional pulse interference. Finally, the processed, digitized stack temperature value is stored in a designated memory unit. Ultimately, the digitized stack temperature value is transmitted in real time via a data bus or memory sharing and used by the fusion calculation model in step S2 as one of the key compensation variables for calculating the anode health status value.

[0070] Furthermore, the step of calculating the high-frequency resistance value in S1 includes:

[0071] The step in S1 to calculate the high-frequency resistance value includes:

[0072] A high-frequency AC disturbance signal with a preset frequency and amplitude is injected into the fuel cell stack, and the voltage and current response of the stack to this signal are measured.

[0073] Based on the voltage and current response, the high-frequency resistance value of the fuel cell at the preset frequency is calculated using an impedance analysis algorithm.

[0074] Specifically, in high-frequency resistance measurement, the high-frequency resistance is obtained by injecting a high-frequency AC disturbance signal into the fuel cell stack and measuring its response. The frequency range of the high-frequency AC disturbance signal is 1kHz to 10kHz, and the amplitude of the high-frequency AC disturbance signal is less than 5% of the fuel cell stack's rated voltage. A preset sine wave digital sequence is generated by the digital signal processor of the main control microcontroller or a dedicated direct digital frequency synthesizer module. The frequency of this sequence is precisely set within the range of 1kHz to 10kHz, as this frequency band is most sensitive to changes in the water content of the proton exchange membrane and the concentration of reactant gases on the anode catalyst surface. The signal amplitude is strictly limited, with the corresponding current amplitude typically not exceeding 2% of the fuel cell stack's rated current or the voltage amplitude not exceeding 5% of the fuel cell stack's rated voltage, to ensure that it is a lossless perturbation to the normal operation of the fuel cell stack. The generated digital sequence is then converted into an analog sine wave by a high-precision digital-to-analog converter. This analog signal is then converted and amplified into an AC current source or voltage source with a certain driving capability by a voltage-to-current conversion circuit or a power operational amplifier. Finally, this signal is safely superimposed onto both ends of the fuel cell stack through a coupling circuit. The coupling circuit typically includes a DC blocking capacitor to prevent the DC component of the disturbance signal from affecting the fuel cell stack. A high-precision differential amplifier is used to acquire the voltage signal from both ends of the fuel cell stack. This amplifier must have high input impedance and high common-mode rejection ratio to accurately extract the millivolt-level AC voltage response superimposed on the hundreds of volts DC bus voltage. A precision sampling resistor is connected in series in the injection loop, and the injected AC current response is indirectly obtained by measuring the voltage drop across this resistor. The voltage and current analog signals are passed through anti-aliasing low-pass filters to filter out high-frequency noise above the Nyquist frequency. Subsequently, the two signals are sent to a multi-channel analog-to-digital converter with synchronous sampling capability for synchronous acquisition, ensuring that the voltage and current samples acquired at the same time have an accurate phase relationship, thus obtaining a discrete-time series. The microprocessor executes an impedance analysis algorithm on the acquired discrete series. This algorithm is an efficient and accurate implementation method based on orthogonal demodulation correlation detection, which is essentially a calculation of the discrete Fourier transform at a single frequency point.

[0075] Furthermore, the step of obtaining the anode inlet and outlet pressures in S1 includes:

[0076] Analog signals of the anode inlet pressure and anode outlet pressure are simultaneously collected by pressure sensors installed at the anode inlet and outlet respectively.

[0077] The analog signal is conditioned and converted from analog to digital to obtain a digitized pressure value, which provides input for calculating the pressure difference between the anode inlet and outlet.

[0078] Specifically, two piezoresistive pressure sensors with the same range and performance parameters are selected, covering the pressure range for normal operation of the fuel cell anode. Before installation, the two sensors must be paired and calibrated to ensure high consistency of their output signals under the same pressure, thereby minimizing pressure difference calculation errors caused by inherent sensor biases. The two pressure sensors are directly installed via mechanical interfaces at the closest points to the inlet and outlet of the anode gas flow channel. The installation location should avoid areas of unstable flow, such as sharp bends in the flow channel and downstream of valves, to ensure that stable static pressure is measured. The sensor diaphragm must be flush with the inner wall of the flow channel to avoid dynamic pressure shocks and measurement lag. The two pressure sensors operate synchronously. Each sensor's integrated Wheatstone bridge outputs a millivolt-level differential voltage signal upon sensing a pressure change, representing the instantaneous absolute values ​​of the inlet and outlet pressures. The sensor's raw output signal is very weak and susceptible to interference, therefore conditioning is necessary; the signal is first amplified by an instrumentation amplifier. The high common-mode rejection ratio (CMRR) of the instrumentation amplifier effectively suppresses common-mode noise. The amplified signal passes through an RC low-pass filter circuit, whose cutoff frequency is set at a frequency much higher than the pressure change frequency but effectively filters out switching power supply noise and electromagnetic interference, thus smoothing the signal and reducing noise. The two conditioned analog voltage signals are sent to the microcontroller's built-in synchronous sampling ADC module or converted by an external synchronous sampling ADC chip. Synchronous sampling is crucial, ensuring that the instantaneous pressure values ​​at the inlet and outlet are captured at the same time. This allows the calculated pressure difference to accurately reflect the transient flow state of the flow channel, avoiding calculation errors introduced by asynchronous sampling under dynamic conditions. The raw digital values ​​obtained from the ADC conversion are first further processed by software algorithms to eliminate occasional pulse interference. Subsequently, based on the pressure-voltage conversion formula established during the calibration phase, the digital values ​​are converted into digitized inlet and outlet pressure values ​​with physical units. This pressure difference value ΔP, along with the high-frequency resistance value, is used as a core input variable in the subsequent fusion calculation model to calculate the anode health status value.

[0079] Furthermore, the fusion calculation model in S2 is a nonlinear function model, and the steps for calculating the anode health state value using the nonlinear function model include:

[0080] The high-frequency resistance value, the anode inlet and outlet pressure difference, the load current, and the stack temperature are used as input variables.

[0081] The input variables are weighted and fused using a pre-defined nonlinear function model;

[0082] The model or mapping table is used to calculate and output the anode health status value, and the error between the anode health status value and the actual health status value is predicted.

[0083] Specifically, in a laboratory environment, a large number of data sets are simultaneously collected under different aging states and operating conditions (including cold start, variable load, and high load) of the fuel cell. Each data set includes: high-frequency resistance value R, anode inlet and outlet pressure difference ΔP, load current I, and stack temperature T. Simultaneously, the hydrogen concentration in the anode exhaust gas is measured using specialized equipment, or the anode state is precisely analyzed using electrochemical impedance spectroscopy. Based on this, an expert assigns a baseline anode health state value to each data set. This value is a normalized value between 0 and 1, where 1 represents the optimal state and 0 represents a severe fault. When the controller is running online, the nonlinear function model calculates the anode health state value according to the following steps: First, it reads the real-time digital values ​​of the high-frequency resistance value R, anode inlet and outlet pressure difference ΔP, load current I, and stack temperature T, which have been preprocessed in the aforementioned steps, from the microprocessor memory. To improve the numerical stability of the model, these input variables are standardized by subtracting their calibration mean and dividing by the calibration standard deviation. The standardized variable values ​​are then substituted into the fixed nonlinear function model. The microprocessor performs a series of multiplication and addition operations to calculate the values ​​of the polynomial and its cross terms, ultimately synthesizing a preliminary AHS value. This preliminary AHS value is then output-limited, strictly constraining it to the physical range of 0 to 1. Finally, the normalized anode health state value is output.

[0084] Furthermore, the feedforward calculation model in S3 includes:

[0085] The load current is differentiated in real time to obtain the instantaneous rate of change;

[0086] Perform the following calculation: Hydrogen flow feedforward compensation = Load current × Rate of change × Feedforward coefficient.

[0087] Specifically, the acquired load current signal is first differentiated in real time, and the instantaneous rate of change (dI / dt) is calculated using the backward difference method; then, the core calculation is performed: the hydrogen flow feedforward compensation amount (Q). ff = Load current (I) × Rate of change (dI / dt) × Feedforward coefficient (K) ff The feedforward coefficient is calibrated through bench tests, and its value is the optimal ratio of the compensation flow rate and the intensity of current change required to prevent hydrogen starvation. Finally, the calculation results are subjected to bidirectional limiting to ensure that the output value is within a safe range, and the compensation amount is finally sent to the control module to achieve advance adjustment.

[0088] Furthermore, the PID controller parameter adjustment step in S4 includes:

[0089] Establish a mapping table between the anode health status error value and the PID parameters;

[0090] When the anode health status value is lower than the preset threshold, the proportional coefficient and integral coefficient are automatically increased.

[0091] The feedforward compensation and the PID output are weighted and superimposed to generate the hydrogen flow control command.

[0092] Specifically, a parameter mapping table is preset in the control system's memory. This table, indexed by the anode health state value, assigns a set of corresponding PID parameters to each AHS range of anode health state value, including the proportional coefficient Kp, integral coefficient Ki, and derivative coefficient Kd. In each control cycle, the control module reads the real-time anode health state value from the state fusion module. PID controller parameter adjustment is achieved through the preset anode health state value-parameter mapping table in memory.

[0093] When AHS > 0.9, the conventional parameter group {Kp1, Ki 1} is used to maintain stability; when 0.7 ≤ AHS ≤ 0.9, it automatically switches to the active parameter group {Kp2, Ki2} (where Kp2 > Kp1, Ki2 > Ki 1) to enhance the control effect; when AHS < 0.7, the strong intervention parameter group {Kp3, Ki 3} (Kp3 > Kp2, Ki 3 > Ki2) is activated to implement rapid correction. The controller monitors the AHS value in real time and calls the corresponding parameters to calculate the feedback quantity. Finally, the feedback quantity is algebraically superimposed with the feedforward compensation quantity to generate the hydrogen flow control command to drive the actuator.

[0094] Furthermore, the step of adjusting the hydrogen flow rate supplied to the fuel cell in S5 includes:

[0095] Convert hydrogen flow control commands into duty cycle signals or analog voltage signals;

[0096] Drive proportional valve or hydrogen injector actuator;

[0097] The flow rate of hydrogen supplied to the anode of the fuel cell is regulated by the actuator.

[0098] Specifically, the instruction execution steps are implemented through the signal conversion and power drive module: First, the digital instruction for hydrogen flow output by the control module is converted into a square wave signal with an adjustable duty cycle through the PWM module of the microcontroller. Then, it is amplified by the power drive circuit and drives the coil of the proportional valve or the electromagnet of the hydrogen injector. Finally, by adjusting the valve opening or the injection pulse width, the linear and precise control of the hydrogen flow supplied to the anode of the fuel cell is achieved.

[0099] Furthermore, it also includes fault handling, the fault handling steps of which include:

[0100] Continuously monitor the anode health status value;

[0101] Determine whether the anode health status value remains below a preset fault threshold for an extended period of time.

[0102] When the judgment conditions are met, a first-level forced anode purging operation is triggered.

[0103] Specifically, the controller reads the anode health status value (AHS) in each operation cycle (10ms). When the AHS value is detected to be continuously lower than the fault threshold of 0.5 for 10 consecutive cycles, the safety logic circuit is triggered to output a drive signal to the anode purge valve for 200ms, forcibly opening the purge valve to discharge the accumulated liquid and impurities in the anode flow channel. At the same time, the controller sends the fault code 0x0A to the host computer to complete the graded safety protection operation.

[0104] Example 2:

[0105] Fuel cell buses are prone to problems during start-stop-acceleration cycles in urban areas during peak hours. To address this issue, this invention provides a system for precisely controlling the hydrogen metering ratio in fuel cells, the structure of which is as follows: Figure 2 As shown. The specific implementation process of this system is as follows:

[0106] The dynamic parameter acquisition module not only collects the anode inlet and outlet pressures through pressure sensors when the bus is heavily loaded and climbing a hill, but also simultaneously injects a high-frequency AC disturbance signal into the fuel cell stack, measures its response, and calculates the high-frequency resistance value.

[0107] The differential pressure and state fusion module addresses the issue that when a bus accelerates rapidly and then suddenly idles, the anode may experience both a rise in differential pressure and impaired membrane hydration. This module can calculate the anode inlet and outlet differential pressure ΔP in real time. ΔP, high-frequency resistance, load current, and stack temperature are simultaneously input into a preset nonlinear fusion calculation model. The model outputs a normalized anode health state value (AHS).

[0108] The predictive feedforward calculation module detects a sharp increase in load current when the bus accelerates away from the station, as the driver presses the accelerator. Traditional feedback control only recognizes the need to add hydrogen after hydrogen is consumed, anode pressure or concentration decreases, or voltage fluctuations occur, by which time hydrogen starvation has already occurred. This module calculates the instantaneous rate of change of load current, dI / dt, in real time. Upon detecting the driver pressing the accelerator, it immediately captures the sharp positive jump in dI / dt and, according to formula Q... ff =I*(dI / dt)*K ff It instantly calculates a positive hydrogen flow feedforward compensation. This action occurs before the anode condition deteriorates due to hydrogen starvation, fundamentally eliminating the risk of instantaneous hydrogen starvation under rapid loading conditions;

[0109] The collaborative control module, unlike traditional PID controllers with fixed parameters, cannot adapt to the significant changes in operating conditions of a bus, from congested idling to smooth cruising. This module receives AHS values ​​from the fusion module. When the AHS value is low, it automatically retrieves a set of more aggressive control parameters from the parameter mapping table, adding a feedforward compensation quantity Q representing future demand. ff The output of the adaptive PID controller, which is responsible for eliminating the current deviation, is superimposed to generate the final hydrogen flow control command. This achieves adaptive control parameters tailored to local conditions and feedforward-feedback coordination that combines near and far-field operations, enabling the system to maintain fast, stable, and precise control performance under all operating conditions.

[0110] The instruction execution module addresses the limitations of traditional actuators, which suffer from slow response and low precision, hindering precise and rapid flow regulation. This module rapidly converts digital instructions from the coordinated control module into physical signals that directly drive the actuators via a high-resolution PWM generator. The power drive circuit amplifies these signals, driving the actuators to precisely execute the commands, achieving millisecond-level, highly linear regulation of hydrogen flow.

[0111] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for precisely controlling the hydrogen metering ratio in a fuel cell, characterized in that, include: S1. Real-time acquisition of the load current of the fuel cell, and acquisition of the anode inlet pressure and anode outlet pressure by pressure sensors set at the anode inlet and outlet, and acquisition of the stack temperature; The high-frequency resistance value is calculated by injecting a high-frequency AC disturbance signal into the fuel cell stack and measuring its voltage and current response. S2. Calculate the pressure difference between the anode inlet and outlet based on the anode inlet pressure and the anode outlet pressure, and input the high-frequency resistance value and the pressure difference between the anode inlet and outlet into a preset fusion calculation model to calculate an anode health status value that characterizes the overall internal state of the anode. The actual anode health status value is compared with a target health status value, and the difference is the health status error. S3. Calculate the instantaneous rate of change of the load current, and input the real-time value of the load current and its instantaneous rate of change into a feedforward calculation model to generate a hydrogen flow feedforward compensation amount to cope with load changes. S4. The anode health status value is compared with a preset target value to obtain the deviation, and the deviation is input to a parameter adjustable PID controller. The hydrogen flow feedforward compensation is superimposed on the output of the PID controller to generate a hydrogen flow control command. S5. Drive the actuator in the hydrogen supply system according to the hydrogen flow control command to adjust the hydrogen flow rate supplied to the fuel cell.

2. The method for precisely controlling the hydrogen metering ratio of a fuel cell according to claim 1, characterized in that, The step of obtaining the stack temperature in S1 includes: The temperature sensor collects a simulated temperature signal representing the operating temperature of the fuel cell stack in real time. The temperature simulation signal is filtered and converted from analog to digital to obtain and output a digital stack temperature value for use by the fusion calculation model.

3. The method for precisely controlling the hydrogen metering ratio of a fuel cell according to claim 1, characterized in that, The step in S1 to calculate the high-frequency resistance value includes: A high-frequency AC disturbance signal with a preset frequency and amplitude is injected into the fuel cell stack, and the voltage and current response of the stack to this signal are measured. Based on the voltage and current response, the high-frequency resistance value of the fuel cell at the preset frequency is calculated using an impedance analysis algorithm.

4. The method for precisely controlling the hydrogen metering ratio of a fuel cell according to claim 1, characterized in that, The steps in S1 to obtain the anode inlet and outlet pressures include: Analog signals of the anode inlet pressure and anode outlet pressure are simultaneously collected by pressure sensors installed at the anode inlet and outlet respectively. The analog signal is conditioned and converted from analog to digital to obtain a digitized pressure value, which provides input for calculating the pressure difference between the anode inlet and outlet.

5. The method for precisely controlling the hydrogen metering ratio of a fuel cell according to claim 1, characterized in that, The fusion calculation model in S2 is a nonlinear function model, and the steps for calculating the anode health state value using the nonlinear function model include: The high-frequency resistance value, the anode inlet and outlet pressure difference, the load current, and the stack temperature are used as input variables. The input variables are weighted and fused using a pre-defined nonlinear function model; The model or mapping table is used to calculate and output the anode health status value, and the error between the anode health status value and the actual health status value is predicted.

6. The method for precisely controlling the hydrogen metering ratio in a fuel cell according to claim 1, characterized in that, The feedforward calculation model in S3 includes: The load current is differentiated in real time to obtain the instantaneous rate of change; Perform the following calculation: Hydrogen flow feedforward compensation = Load current × Rate of change × Feedforward coefficient.

7. The method for precisely controlling the hydrogen metering ratio of a fuel cell according to claim 1, characterized in that, The PID controller parameter adjustment steps of S4 include: Establish a mapping table between the anode health status error value and the PID parameters; When the anode health status value is lower than the preset threshold, the proportional coefficient and integral coefficient are automatically increased. The feedforward compensation and the PID output are weighted and superimposed to generate the hydrogen flow control command.

8. The method for precisely controlling the hydrogen metering ratio of a fuel cell according to claim 1, characterized in that, The step of adjusting the hydrogen flow rate supplied to the fuel cell in S5 includes: Convert hydrogen flow control commands into duty cycle signals or analog voltage signals; Drive proportional valve or hydrogen injector actuator; The flow rate of hydrogen supplied to the anode of the fuel cell is regulated by the actuator.

9. The method for precisely controlling the hydrogen metering ratio of a fuel cell according to claim 1, characterized in that, It also includes fault handling, the fault handling steps of which include: Continuously monitor the anode health status value; Determine whether the anode health status value remains below a preset fault threshold for an extended period of time. When the judgment conditions are met, a first-level forced anode purging operation is triggered.

10. A system for precisely controlling the hydrogen metering ratio in a fuel cell, characterized in that, include: The dynamic parameter acquisition module is used to acquire the load current of the fuel cell in real time, obtain the anode inlet pressure and anode outlet pressure through pressure sensors set at the anode inlet and outlet, obtain the stack temperature, and calculate the high-frequency resistance value by injecting a high-frequency AC disturbance signal into the stack and measuring its voltage and current response. The differential pressure and state fusion module is used to calculate the differential pressure between the anode inlet and outlet based on the anode inlet pressure and the anode outlet pressure, and input the high-frequency resistance value and the differential pressure between the anode inlet and outlet into a preset fusion calculation model to calculate an anode health state value that characterizes the comprehensive state inside the anode. The actual anode health status value is compared with a preset target health status value that represents the optimal operating state of the anode, and the difference is the health status error. The predictive feedforward calculation module is used to calculate the instantaneous rate of change of the load current, and input the real-time value of the load current and the instantaneous rate of change into a feedforward calculation model to generate a hydrogen flow feedforward compensation amount to cope with load changes. The collaborative control module is used to compare the anode health status value with a preset target value to obtain the deviation, and input the deviation to a parameter-adjustable PID controller, wherein the control parameters of the PID controller are dynamically adjusted according to the anode health status value; at the same time, the hydrogen flow feedforward compensation amount is superimposed with the output of the PID controller to generate a hydrogen flow control command. The instruction execution module is used to drive the actuator in the hydrogen supply system according to the hydrogen flow control instruction, so as to adjust the hydrogen flow rate supplied to the fuel cell.

Images