Method and system for diagnosing unsmooth exhaust of cooling path of fuel cell

Abstract

The invention relates to a method and a system for diagnosing unsmooth exhaust of a fuel cell cooling path, and belongs to the technical field of fuel cell diagnosis. The method comprises the steps that fuel cell anode parameters are collected through a sensor, and a hydrogen path pressure prediction value is obtained through dynamic equation calculation and processing by combining the number of single cells of an electric pile; cathode parameters and cooling path pressure data are collected, and oxygen path and cooling path pressure prediction values are obtained through the prediction model; calculating the pressure difference according to the pressure predicted values, further determining the maximum pressure difference, obtaining the water pump regulation rotating speed through a proportional formula, controlling the water pump to operate by the intelligent terminal according to the maximum pressure difference, and determining the current fluctuation range; and collecting real-time current data according to a preset frequency, judging whether the current data exceed the range or not, and if yes, executing judgment and exhaust procedures. Automatic diagnosis and gas discharge of unsmooth exhaust of the cooling path for the fuel cell are realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of fuel cell diagnosis, and particularly relates to a method and system for diagnosing unsmooth exhaust of a fuel cell cooling circuit. Background Art

[0002] During the operation of a fuel cell, effective cooling is required to maintain a suitable working temperature. During after-sales maintenance, due to uneven technical capabilities of after-sales personnel, after adding coolant, the gas in the cooling circuit is not completely exhausted, which may cause many problems, such as reduced cooling efficiency, local overheating, system pressure fluctuations, and cavitation of the water pump, seriously affecting the performance and lifespan of the fuel cell. Currently, there is no effective measure to monitor whether the cooling circuit is fully exhausted, and it is difficult to accurately and real-time detect the exhaust condition and take effective measures in a timely manner. Summary of the Invention

[0003] To solve the above problems existing in the prior art, the present invention provides a method and system for diagnosing unsmooth exhaust of a fuel cell cooling circuit,

[0004] The object of the present invention can be achieved by the following technical solutions:

[0005] Collect relevant parameters of the fuel cell anode through sensors, obtain the number of single cells of the stack, calculate the real-time hydrogen path pressure data according to the relevant parameters of the fuel cell anode and the number of single cells of the stack through the dynamic equation of the hydrogen supply system, add a time stamp to the real-time hydrogen path pressure data to obtain the sequential hydrogen path pressure data, store the sequential hydrogen path pressure data to obtain a hydrogen path pressure data sequence, and calculate the hydrogen path pressure prediction value according to the hydrogen path pressure data sequence through a hydrogen pressure prediction model;

[0006] Collect relevant parameters of the fuel cell cathode and cooling circuit pressure data through sensors, add a time stamp to the relevant parameters of the fuel cell cathode and the cooling circuit pressure data to obtain the sequential relevant parameters of the fuel cell cathode and the sequential cooling circuit pressure data, store the sequential relevant parameters of the fuel cell cathode and the sequential cooling circuit pressure data to obtain a cathode relevant parameter sequence and a cooling circuit pressure sequence, calculate the cathode relevant parameter prediction value and the cooling circuit pressure prediction value according to the cathode relevant parameter sequence and the cooling circuit pressure sequence through a prediction model, and calculate the oxygen path pressure prediction value according to the cathode relevant parameter prediction value through a cathode supply pipeline air pressure model;

[0007] Calculate the first pressure difference and the second pressure difference based on the predicted value of the hydrogen path pressure, the predicted value of the oxygen path pressure, and the predicted value of the cooling path pressure. Determine the maximum pressure difference based on the first pressure difference and the second pressure difference, and calculate the adjusted rotation speed of the water pump through a proportional formula according to the maximum pressure difference. The intelligent terminal controls the operation of the water pump according to the adjusted rotation speed of the water pump, and collects the first working current set and the second working current set of the water pump through a current sensor, and determines the current fluctuation range according to the first working current set and the second working current set;

[0008] Preset the sampling frequency, collect the real-time current data of the water pump through the current sensor according to the sampling frequency, and judge whether the real-time current data exceeds the current fluctuation range. If yes, execute the judgment program to obtain a judgment result, and execute the exhaust program according to the judgment result; if not, do nothing.

[0009] Specifically, the dynamic equation expression of the hydrogen supply system is:

[0010]

[0011] Where Y is the real-time pressure data of the hydrogen path, R is the hydrogen gas constant, T st is the stack temperature, V an is the volume of the anode and the diffusion layer, m 1 is the mass flow rate of hydrogen at the anode inlet, m 3 is the mass flow rate of hydrogen at the anode outlet, m 2 is the molar mass of hydrogen, F is the Faraday constant, i is the stack current, and n is the number of single cells in the stack.

[0012] Specifically, the calculation expression of the hydrogen pressure prediction model is:

[0013]

[0014] Where Y (k) is the predicted value of the hydrogen path pressure, Y (k-1) is the time-series hydrogen path pressure data at the k-1 moment, K vl is the regulating valve gain, T vl is the valve time constant, U (k-2) is the valve control signal at the k-2 moment, Z is the proportional coefficient, b (k) is the disturbance quantity at the k moment, R is the hydrogen gas constant, T st is the stack temperature, V an is the volume of the anode and the diffusion layer, and k represents the time variable.

[0015] Specifically, the specific calculation steps of the prediction model include:

[0016] Calculate the cathode-related parameter outliers and cooling path pressure outliers through the C-means clustering algorithm based on the cathode-related parameter sequence and the cooling path pressure sequence, and remove the cathode-related parameter outliers and the cooling path pressure outliers to obtain the relevant parameter cleaning sequence and the pressure cleaning sequence;

[0017] Fill in the missing values of the relevant parameter cleaning sequence and the pressure cleaning sequence through the mean imputation method to obtain the relevant parameter filling sequence and the pressure filling sequence, perform data reduction on the relevant parameter filling sequence and the pressure filling sequence through the discrete cosine transform to obtain the relevant parameter reduction sequence and the pressure reduction sequence, and normalize the relevant parameter reduction sequence and the pressure reduction sequence to obtain the normalized parameter sequence and the normalized pressure sequence;

[0018] Calculate the cathode-related parameter prediction value and the cooling path pressure prediction value through the Transform model based on the normalized parameter sequence and the normalized pressure sequence.

[0019] Specifically, the calculation of the oxygen path pressure prediction value through the cathode supply pipeline air pressure model based on the cathode-related parameter prediction value includes:

[0020] The cathode-related parameter prediction values include the outlet flow prediction value, the air flow prediction value entering the stack, the atmospheric temperature prediction value, the atmospheric pressure prediction value, and the air compressor efficiency prediction value;

[0021] First, calculate the predicted air compressor gas outlet temperature through the gas outlet temperature state equation based on the atmospheric temperature prediction value, the atmospheric pressure prediction value, and the air compressor efficiency prediction value;

[0022] The expression of the gas outlet temperature state equation is:

[0023]

[0024] where, T c (k) is the predicted air compressor gas outlet temperature at time k, T a (k) is the predicted atmospheric temperature at time k, n cp (k) is the air compressor efficiency prediction value at time k, p s (k - 1) is the oxygen path pressure value at time k - 1, p a (k) is the predicted atmospheric pressure at time k, and n is the compression process index;

[0025] Calculate the oxygen path pressure prediction value through the air pipeline air pressure state equation based on the predicted air compressor gas outlet temperature, the outlet flow prediction value, and the air flow prediction value;

[0026] The expression of the air pipeline air pressure state equation is as follows:

[0027]

[0028] where P s is the predicted value of the oxygen path pressure, R is the oxygen gas constant, and T c is the predicted value of the air compressor gas outlet temperature, M a is the molar mass of air, V s is the volume of the intake pipeline, W cp is the predicted value of the outlet flow rate, and W in is the predicted value of the air flow rate entering the fuel cell stack.

[0029] Specifically, the judgment results obtained by executing the judgment program include:

[0030] The judgment results include abnormal exhaust and normal exhaust;

[0031] Collect the pressure value of the coolant entering the stack through the pressure sensor, preset a pressure threshold, and judge whether the pressure value of the coolant entering the stack is greater than the pressure value of the intake stack. If yes, output the judgment result as abnormal exhaust; if no, output the judgment result as normal exhaust.

[0032] Specifically, the exhaust program executed according to the judgment result includes:

[0033] If the judgment result is normal exhaust, do nothing; if the judgment result is abnormal exhaust, execute the exhaust step;

[0034] The exhaust step includes:

[0035] Step 1: The intelligent terminal generates an adaptive signal to control the thermostat to the large circulation mode, preset a first operation duration, and control the water pump to operate according to the first operation duration;

[0036] Step 2: Preset a second operation duration, the intelligent terminal generates an adaptive signal to control the thermostat to the small circulation mode, and control the water pump to operate according to the second operation duration;

[0037] Step 3: Count the number of cycles, preset a cycle threshold, and judge whether the number of cycles is less than the cycle threshold. If yes, repeat steps 1-3; if no, stop the exhaust step.

[0038] Specifically, the proportional calculation formula is:

[0039]

[0040] Wherein, n is the adjusted speed of the water pump, R is the radius of the cooling circuit pipeline, p is the maximum pressure difference, M is the hydrodynamic viscosity, L is the length of the cooling pipeline, and K is the proportionality coefficient of the water pump flow rate and speed.

[0041] A diagnosis strategy and filling system for unsmooth exhaust of a cooling circuit for a fuel cell, comprising: a hydrogen circuit pressure prediction module, an oxygen circuit pressure prediction module, a current fluctuation calculation module, and a response module;

[0042] The hydrogen circuit pressure prediction module is used to collect relevant parameters of the anode of the fuel cell through a sensor, obtain the number of single cells of the stack, calculate the real-time pressure data of the hydrogen circuit according to the relevant parameters of the anode of the fuel cell and the number of single cells of the stack through the dynamic equation of the hydrogen supply system, add a time stamp to the real-time pressure data of the hydrogen circuit to obtain the time-series hydrogen circuit pressure data, store the time-series hydrogen circuit pressure data to obtain the hydrogen circuit pressure data sequence, and calculate the hydrogen circuit pressure prediction value according to the hydrogen circuit pressure data sequence through the hydrogen pressure prediction model;

[0043] The oxygen circuit pressure prediction module is used to collect relevant parameters of the cathode of the fuel cell and the cooling circuit pressure data through a sensor, add a time stamp to the relevant parameters of the cathode of the fuel cell and the cooling circuit pressure data to obtain the time-series relevant parameters of the cathode of the fuel cell and the time-series cooling circuit pressure data, store the time-series relevant parameters of the cathode of the fuel cell and the time-series cooling circuit pressure data to obtain the cathode relevant parameter sequence and the cooling circuit pressure sequence, calculate the cathode relevant parameter prediction value and the cooling circuit pressure prediction value according to the cathode relevant parameter sequence and the cooling circuit pressure sequence through the prediction model, and calculate the oxygen circuit pressure prediction value according to the cathode relevant parameter prediction value through the cathode supply pipeline air pressure model;

[0044] The current fluctuation calculation module is used to calculate a first pressure difference and a second pressure difference according to the hydrogen circuit pressure prediction value, the oxygen circuit pressure prediction value, and the cooling circuit pressure prediction value, determine the maximum pressure difference according to the first pressure difference and the second pressure difference, calculate the adjusted speed of the water pump according to the maximum pressure difference through the proportional formula, the intelligent terminal controls the operation of the water pump according to the adjusted speed of the water pump, and collects the first working current set and the second working current set of the water pump through the current sensor, and determines the current fluctuation range according to the first working current set and the second working current set;

[0045] The response module is used to preset a sampling frequency, collect the real-time current data of the water pump through the current sensor according to the sampling frequency, judge whether the real-time current data exceeds the current fluctuation range, if so, execute a judgment program to obtain a judgment result, and execute an exhaust program according to the judgment result; if not, do nothing.

[0046] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the fuel cell cooling path exhaust blockage diagnosis method and system as described above.

[0047] A storage medium containing computer-executable instructions, which are used to execute the fuel cell cooling path exhaust blockage diagnosis method and system as described above when executed by a computer processor.

[0048] The beneficial effects of the present invention are as follows:

[0049] (1) Precise pressure monitoring and prediction: By collecting relevant parameters of the anode and cathode of the fuel cell and pressure data of the cooling path, and through complex calculations and model predictions, the pressure prediction values of the hydrogen path, oxygen path, and cooling path can be accurately obtained, providing a data basis for the precise judgment of the system operation state.

[0050] (2) Intelligent water pump control: Calculate the pressure difference based on each pressure prediction value, and then determine the adjusted speed of the water pump to achieve intelligent control of the water pump, ensure the efficient and stable operation of the cooling system, and improve the working performance of the fuel cell.

[0051] (3) Fault diagnosis and early warning: Monitor the working current of the water pump through a current sensor, set the current fluctuation range and judge it in real time, and can detect abnormalities in a timely manner. When the real-time current exceeds the range, execute the judgment and exhaust procedures to effectively diagnose the problem of blocked exhaust in the cooling path and ensure the safe and stable operation of the fuel cell system. Description of the Drawings

[0052] For the convenience of those skilled in the art to understand, the present invention will be further described below with reference to the drawings.

[0053] Figure 1 It is a schematic flow chart of a fuel cell cooling path exhaust blockage diagnosis method and system of the present invention. Detailed Embodiment

[0054] To further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following describes in detail the specific embodiments, structures, features, and their effects of the present invention with reference to the drawings and preferred embodiments.

[0055] Please refer to Figure 1 , a fuel cell cooling path exhaust blockage diagnosis method and system;

[0056] Collect relevant parameters of the fuel cell anode through sensors, obtain the number of single cells in the stack, calculate the real-time pressure data of the hydrogen path according to the dynamic equation of the hydrogen supply system based on the relevant parameters of the fuel cell anode and the number of single cells in the stack, add a timestamp to the real-time pressure data of the hydrogen path to obtain the time-series hydrogen path pressure data, store the time-series hydrogen path pressure data to obtain the hydrogen path pressure data sequence, and calculate the predicted value of the hydrogen path pressure according to the hydrogen path pressure data sequence through the hydrogen pressure prediction model;

[0057] Collect relevant parameters of the fuel cell cathode and the cooling path pressure data through sensors, add timestamps to the relevant parameters of the fuel cell cathode and the cooling path pressure data to obtain the time-series relevant parameters of the fuel cell cathode and the time-series cooling path pressure data, store the time-series relevant parameters of the fuel cell cathode and the time-series cooling path pressure data to obtain the cathode relevant parameter sequence and the cooling path pressure sequence, calculate the predicted value of the cathode relevant parameter and the predicted value of the cooling path pressure according to the cathode relevant parameter sequence and the cooling path pressure sequence through the prediction model, and calculate the predicted value of the oxygen path pressure according to the predicted value of the cathode relevant parameter through the cathode supply pipeline air pressure model;

[0058] Calculate the first pressure difference and the second pressure difference according to the predicted value of the hydrogen path pressure, the predicted value of the oxygen path pressure, and the predicted value of the cooling path pressure, determine the maximum pressure difference according to the first pressure difference and the second pressure difference, calculate the adjusted speed of the water pump according to the maximum pressure difference through the proportional formula, the intelligent terminal controls the operation of the water pump according to the adjusted speed of the water pump, and collects the first working current set and the second working current set of the water pump through the current sensor, and determines the current fluctuation range according to the first working current set and the second working current set;

[0059] Preset the sampling frequency, collect the real-time current data of the water pump through the current sensor according to the sampling frequency, judge whether the real-time current data exceeds the current fluctuation range, if yes, execute the judgment program to obtain the judgment result, and execute the exhaust program according to the judgment result; if no, do nothing.

[0060] In this embodiment, the first pressure difference is the difference between the predicted value of the cooling path pressure and the predicted value of the oxygen path pressure, and the second pressure difference is the difference between the predicted value of the hydrogen path pressure and the predicted value of the cooling path pressure.

[0061] Specifically, the relevant parameters of the fuel cell anode include the stack temperature data, the mass flow rate of hydrogen at the anode inlet, the mass flow rate of hydrogen at the anode outlet, and the stack current, and the relevant parameters of the fuel cell cathode include the flow rate at the outlet of the air compressor, the air flow rate entering the stack, the atmospheric temperature data, the atmospheric pressure data, and the efficiency of the air compressor.

[0062] Specifically, the dynamic equation expression of the hydrogen supply system is as follows:

[0063]

[0064] Where Y is the real-time pressure data of the hydrogen path, R is the hydrogen gas constant, T st is the temperature of the fuel cell stack, V an is the volume of the anode and the diffusion layer, m 1 is the mass flow rate of hydrogen at the anode inlet, m 3 is the mass flow rate of hydrogen at the anode outlet, m 2 is the molar mass of hydrogen, F is the Faraday constant, i is the current of the fuel cell stack, and n is the number of single cells of the fuel cell stack.

[0065] Specifically, the calculation expression of the hydrogen pressure prediction model is:

[0066]

[0067] Where Y (k) is the predicted value of the hydrogen path pressure, Y (k-1) is the time-series hydrogen path pressure data at the k-1 moment, K vl is the regulating valve gain, T vl is the valve time constant, U (k-2) is the valve control signal at the k-2 moment, Z is the proportionality coefficient, b (k) is the disturbance quantity at the k moment, R is the hydrogen gas constant, T st is the temperature of the fuel cell stack, V an is the volume of the anode and the diffusion layer, and k represents the time variable.

[0068] Specifically, the specific calculation steps of the prediction model include:

[0069] Calculating the cathode-related parameter outliers and the cooling path pressure outliers through the C-means clustering algorithm according to the cathode-related parameter sequence and the cooling path pressure sequence, and removing the cathode-related parameter outliers and the cooling path pressure outliers to obtain the related parameter cleaning sequence and the pressure cleaning sequence;

[0070] Performing missing value filling on the related parameter cleaning sequence and the pressure cleaning sequence through the mean imputation method to obtain the related parameter filling sequence and the pressure filling sequence, performing data reduction on the related parameter filling sequence and the pressure filling sequence through the discrete cosine transform to obtain the related parameter reduction sequence and the pressure reduction sequence, and normalizing the related parameter reduction sequence and the pressure reduction sequence to obtain the normalized parameter sequence and the normalized pressure sequence;

[0071] The predicted values of the cathode-related parameters and the predicted values of the cooling path pressure are calculated by a Transform model based on the normalized parameter sequence and the normalized pressure sequence.

[0072] Specifically, the calculation of the predicted value of the oxygen path pressure from the predicted value of the cathode-related parameters through the cathode supply pipeline air pressure model includes:

[0073] The predicted values of the cathode-related parameters include the predicted value of the outlet flow rate, the predicted value of the air flow rate entering the fuel cell stack, the predicted value of the atmospheric temperature, the predicted value of the atmospheric pressure, and the predicted value of the air compressor efficiency;

[0074] First, the predicted value of the air compressor gas outlet temperature is calculated by the gas outlet temperature state equation based on the predicted value of the atmospheric temperature, the predicted value of the atmospheric pressure, and the predicted value of the air compressor efficiency;

[0075] The expression of the gas outlet temperature state equation is:

[0076]

[0077] where, T c (k) is the predicted value of the air compressor gas outlet temperature at time k, T a (k) is the predicted value of the atmospheric temperature at time k, n cp (k) is the predicted value of the air compressor efficiency at time k, p s (k - 1) is the oxygen path pressure value at time k - 1, p a (k) is the predicted value of the atmospheric pressure at time k, and n is the compression process exponent;

[0078] The predicted value of the oxygen path pressure is calculated by the air pipeline air pressure state equation based on the predicted value of the air compressor gas outlet temperature, the predicted value of the outlet flow rate, and the predicted value of the air flow rate;

[0079] The expression of the air pipeline air pressure state equation is:

[0080]

[0081] where, P s is the predicted value of the oxygen path pressure, R is the oxygen gas constant, T c is the predicted value of the air compressor gas outlet temperature, M a is the molar mass of air, V s is the volume of the intake pipeline, W cp is the predicted value of the outlet flow rate, W in is the predicted value of the air flow rate entering the fuel cell stack.

[0082] Specifically, the first working current set is the working current sequence of the water pump collected by a current sensor according to a preset sampling frequency and sampling duration when the thermostat is in the large circulation operation; the second working current set is the working current sequence of the water pump collected by the current sensor according to a preset sampling frequency and sampling duration when the thermostat is in the small circulation operation.

[0083] Specifically, the execution of the judgment program to obtain the judgment result includes:

[0084] The judgment result includes abnormal exhaust and normal exhaust;

[0085] Collect the coolant inlet reactor pressure value through a pressure sensor, preset a pressure threshold, and judge whether the coolant inlet reactor pressure value is greater than the inlet reactor pressure value. If yes, output the judgment result as abnormal exhaust; if no, output the judgment result as normal exhaust.

[0086] Specifically, the execution of the exhaust program according to the judgment result includes:

[0087] If the judgment result is normal exhaust, do nothing; if the judgment result is abnormal exhaust, execute the exhaust steps;

[0088] The exhaust steps include:

[0089] Step 1: The intelligent terminal generates an adaptive signal to control the thermostat to adjust to the large circulation mode, preset a first operation duration, and control the water pump to operate according to the first operation duration;

[0090] Step 2: Preset a second operation duration, the intelligent terminal generates an adaptive signal to control the thermostat to adjust to the small circulation mode, and control the water pump to operate according to the second operation duration;

[0091] Step 3: Count the number of cycles, preset a cycle threshold, and judge whether the number of cycles is less than the cycle threshold. If yes, repeat Steps 1 - 3; if no, stop the exhaust steps.

[0092] Specifically, the proportional calculation formula is:

[0093]

[0094] Where n is the adjusted rotational speed of the water pump, R is the radius of the coolant pipeline, p is the maximum pressure difference, M is the fluid dynamic viscosity, L is the length of the cooling pipeline, and K is the proportional coefficient of the water pump flow rate to the rotational speed.

[0095] A diagnosis strategy and filling system for poor exhaust of the cooling circuit of a fuel cell, including: a hydrogen circuit pressure prediction module, an oxygen circuit pressure prediction module, a current fluctuation measurement module, and a response module;

[0096] The hydrogen circuit pressure prediction module is used to collect fuel cell anode-related parameters through sensors, obtain the number of single cells in the stack, calculate the real-time hydrogen circuit pressure data according to the fuel cell anode-related parameters and the number of single cells in the stack through the hydrogen supply system dynamic equation, add a timestamp according to the real-time hydrogen circuit pressure data to obtain time-series hydrogen circuit pressure data, store the time-series hydrogen circuit pressure data to obtain a hydrogen circuit pressure data sequence, and calculate the hydrogen circuit pressure prediction value according to the hydrogen circuit pressure data sequence through the hydrogen pressure prediction model;

[0097] The oxygen circuit pressure prediction module is used to collect fuel cell cathode related parameters and cooling circuit pressure data through sensors, add timestamps according to the fuel cell cathode related parameters and the cooling circuit pressure data to obtain time-series fuel cell cathode related parameters and time-series cooling circuit pressure data, store the time-series fuel cell cathode related parameters and time-series cooling circuit pressure data to obtain cathode related parameter sequence and cooling circuit pressure sequence, calculate cathode related parameter prediction values ​​and cooling circuit pressure prediction values ​​through a prediction model according to the cathode related parameter sequence and the cooling circuit pressure sequence, and calculate the oxygen circuit pressure prediction value through a cathode supply pipeline air pressure model according to the cathode related parameter prediction value;

[0098] The current fluctuation measurement module is used to calculate the first pressure difference and the second pressure difference according to the predicted value of the hydrogen line pressure, the predicted value of the oxygen line pressure, and the predicted value of the cooling line pressure, determine the maximum pressure difference according to the first pressure difference and the second pressure difference, calculate the water pump adjustment speed according to the maximum pressure difference through a proportional formula, the intelligent terminal controls the operation of the water pump according to the water pump adjustment speed, and collects the first working current set and the second working current set of the water pump through the current sensor, and determines the current fluctuation range according to the first working current set and the second working current set;

[0099] The response module is used to preset a sampling frequency, collect real-time current data of the water pump through the current sensor according to the collection frequency, and judge whether the real-time current data exceeds the current fluctuation range. If yes, execute the judgment program to obtain the judgment result, and execute the exhaust program according to the judgment result; if not, do not do anything.

[0100] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method and system for diagnosing poor exhaust in a fuel cell cooling path as described above are implemented.

[0101] A storage medium containing computer-executable instructions, which are used to execute the fuel cell cooling circuit exhaust blockage diagnosis method and system as described above when executed by a computer processor.

[0102] The computer storage medium of the embodiments of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may, for example, but not be limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage medium include: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0103] The computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries the computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0104] The program code contained on a computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber cable, RF, etc., or any suitable combination of the foregoing. The computer program code for performing the operations of the present invention can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., by using an Internet service provider to connect through the Internet).

[0105] As described above, the above are only the preferred embodiments of the present invention, and do not impose any form of limitation on the present invention. Although the present invention has been disclosed above with the preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to the equivalent embodiments by using the above-disclosed technical content within the scope of the technical solution of the present invention. However, as long as it does not depart from the content of the technical solution of the present invention, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A method for diagnosing poor exhaust in a fuel cell cooling path, characterized in that: include: Collecting fuel cell anode-related parameters through sensors to obtain the number of single cells in the stack, calculating the real-time pressure data of the hydrogen path according to the fuel cell anode-related parameters and the number of single cells in the stack through the hydrogen supply system dynamic equation, adding a timestamp to the real-time pressure data of the hydrogen path to obtain time-series hydrogen path pressure data, storing the time-series hydrogen path pressure data to obtain a hydrogen path pressure data sequence, and calculating the hydrogen path pressure prediction value according to the hydrogen path pressure data sequence through a hydrogen pressure prediction model; Collect fuel cell cathode related parameters and cooling path pressure data through sensors, add timestamps according to the fuel cell cathode related parameters and the cooling path pressure data to obtain time-series fuel cell cathode related parameters and time-series cooling path pressure data, store the time-series fuel cell cathode related parameters and time-series cooling path pressure data to obtain cathode related parameter sequence and cooling path pressure sequence, calculate cathode related parameter prediction values ​​and cooling path pressure prediction values ​​through prediction models according to the cathode related parameter sequence and the cooling path pressure sequence, and calculate oxygen path pressure prediction values ​​through cathode supply pipeline air pressure model according to the cathode related parameter prediction values; A first pressure difference and a second pressure difference are calculated according to the predicted value of the hydrogen line pressure, the predicted value of the oxygen line pressure, and the predicted value of the cooling line pressure, a maximum pressure difference is determined according to the first pressure difference and the second pressure difference, a water pump adjustment speed is calculated according to the maximum pressure difference by a proportional formula, the intelligent terminal controls the operation of the water pump according to the water pump adjustment speed, and collects a first working current set and a second working current set of the water pump through a current sensor, and determines a current fluctuation range according to the first working current set and the second working current set; A sampling frequency is preset, and real-time current data of the water pump is collected through the current sensor according to the collection frequency, and it is judged whether the real-time current data exceeds the current fluctuation range. If yes, a judgment program is executed to obtain a judgment result, and an exhaust program is executed according to the judgment result; If not, no action will be taken.

2. The method and system for diagnosing poor exhaust in a fuel cell cooling path according to claim 1, characterized in that: The dynamic equation expression of the hydrogen supply system is: Among them, Y is the real-time pressure data of hydrogen path, R is the hydrogen gas constant, T st is the stack temperature, V an is the volume of the anode and diffusion layer, m1 is the hydrogen mass flow rate at the anode inlet, m3 is the hydrogen mass flow rate at the anode outlet, m2 is the molar mass of hydrogen, F is the Faraday constant, i is the stack current, and n is the number of cells in the stack.

3. According to the fuel cell cooling path exhaust blockage diagnosis method of claim 1, the calculation expression of the hydrogen pressure prediction model is: in, Y (k) is the predicted value of hydrogen line pressure, Y (k-1) is the time series hydrogen line pressure data at time k-1, K vl To adjust the valve gain, T vl is the valve time constant, U (k-2) is the valve control signal at time k-2, Z is the proportional coefficient, b (k) is the disturbance at time k, R is the hydrogen gas constant, T st is the stack temperature, V an is the volume of anode and diffusion layer, and k is the time variable.

4. According to the method for diagnosing poor exhaust in a fuel cell cooling path according to claim 1, the specific calculation steps of the prediction model include: According to the cathode related parameter sequence and the cooling path pressure sequence, a cathode related parameter abnormal value and a cooling path pressure abnormal value are calculated by a C-means clustering algorithm, and the cathode related parameter abnormal value and the cooling path pressure abnormal value are eliminated to obtain a related parameter cleaning sequence and a pressure cleaning sequence; According to the relevant parameter cleaning sequence and the pressure cleaning sequence, missing values ​​are filled by the mean interpolation method to obtain a relevant parameter filling sequence and a pressure filling sequence; according to the relevant parameter filling sequence and the pressure filling sequence, data reduction is performed by discrete cosine transform to obtain a relevant parameter reduction sequence and a pressure regulation sequence; according to the relevant parameter reduction sequence and the pressure regulation sequence, normalization is performed to obtain a normalized parameter sequence and a normalized pressure sequence; The cathode-related parameter prediction value and the cooling path pressure prediction value are obtained by calculating the normalized parameter sequence and the normalized pressure sequence through the Transform model.

5. According to the fuel cell cooling path exhaust blockage diagnosis method of claim 1, the oxygen path pressure prediction value is calculated by the cathode supply pipeline pressure model according to the cathode related parameter prediction value, comprising: The cathode-related parameter prediction values ​​include the outlet flow prediction value, the air flow into the fuel cell stack prediction value, the atmospheric temperature prediction value, the atmospheric pressure prediction value, and the air compressor efficiency prediction value; Firstly, the predicted value of the air compressor gas outlet temperature is calculated by the gas outlet temperature state equation according to the predicted value of the atmospheric temperature, the predicted value of the atmospheric pressure, and the predicted value of the air compressor efficiency; The gas outlet temperature state equation is expressed as: Among them, T c (k) is the predicted value of the air compressor gas outlet temperature at time k, T a (k) is the predicted value of atmospheric temperature at time k, n cp (k) is the predicted value of air compressor efficiency at time k, p s (k-1) is the oxygen circuit pressure value at time k-1, p a (k) is the predicted value of atmospheric pressure at time k, and n is the compression process index; The predicted value of the oxygen line pressure is calculated by using the air pipeline pressure state equation according to the predicted value of the air compressor gas outlet temperature, the predicted value of the outlet flow rate, and the predicted value of the air flow rate; The air duct pressure state equation is expressed as: Among them, P s is the predicted value of oxygen line pressure, R is the oxygen gas constant, T c is the predicted value of the air compressor gas outlet temperature, M a is the molar mass of air, V s is the volume of the intake pipe, W cp is the predicted value of the export flow, W in It is the predicted value of air flow entering the fuel cell stack.

6. The method for diagnosing poor exhaust in a fuel cell cooling path according to claim 1, wherein the executing a judgment procedure to obtain a judgment result comprises: The judgment result includes abnormal exhaust and normal exhaust; The pressure sensor is used to collect the stack pressure value of the cooling path, and a pressure threshold is preset to determine whether the stack pressure value of the cooling path is greater than the stack pressure value. If yes, the determination result is output as exhaust abnormality; If not, the judgment result is outputted as normal exhaust. Specifically, executing the exhaust procedure according to the judgment result includes: If the judgment result is that the exhaust is normal, no processing is performed; if the judgment result is that the exhaust is abnormal, the exhaust step is performed; The exhaust step comprises: Step 1: The intelligent terminal generates an adaptive signal to control the thermostat to be adjusted to a large circulation mode, presets a first operating time, and controls the operation of the water pump according to the first operating time; Step 2: Preset a second operating time, the intelligent terminal generates an adaptive signal to control the thermostat to be adjusted to a small circulation mode, and controls the operation of the water pump according to the second operating time; Step 3: Count the number of cycles, preset a cycle threshold, and determine whether the number of cycles is less than the cycle threshold. If yes, repeat steps 1 to 3; if no, stop the exhaust step.

7. According to the fuel cell cooling path exhaust blockage diagnosis method of claim 1, the ratio calculation formula is: in, n is the water pump adjustment speed, R is the radius of the cooling pipe, p is the maximum pressure difference, M is the fluid dynamic viscosity, L is the cooling pipe length, and K is the water pump flow speed proportional coefficient.

8. A fuel cell cooling path exhaust blockage diagnosis strategy and filling system, characterized in that: Including: hydrogen circuit pressure prediction module, oxygen circuit pressure prediction module, current fluctuation measurement module, response module; The hydrogen circuit pressure prediction module is used to collect fuel cell anode-related parameters through sensors, obtain the number of single cells in the stack, calculate the real-time hydrogen circuit pressure data according to the fuel cell anode-related parameters and the number of single cells in the stack through the hydrogen supply system dynamic equation, add a timestamp according to the real-time hydrogen circuit pressure data to obtain time-series hydrogen circuit pressure data, store the time-series hydrogen circuit pressure data to obtain a hydrogen circuit pressure data sequence, and calculate the hydrogen circuit pressure prediction value according to the hydrogen circuit pressure data sequence through the hydrogen pressure prediction model; The oxygen circuit pressure prediction module is used to collect fuel cell cathode related parameters and cooling circuit pressure data through sensors, add timestamps according to the fuel cell cathode related parameters and the cooling circuit pressure data to obtain time-series fuel cell cathode related parameters and time-series cooling circuit pressure data, store the time-series fuel cell cathode related parameters and time-series cooling circuit pressure data to obtain cathode related parameter sequence and cooling circuit pressure sequence, calculate cathode related parameter prediction values ​​and cooling circuit pressure prediction values ​​through a prediction model according to the cathode related parameter sequence and the cooling circuit pressure sequence, and calculate the oxygen circuit pressure prediction value through a cathode supply pipeline air pressure model according to the cathode related parameter prediction value; The current fluctuation measurement module is used to calculate the first pressure difference and the second pressure difference according to the predicted value of the hydrogen line pressure, the predicted value of the oxygen line pressure, and the predicted value of the cooling line pressure, determine the maximum pressure difference according to the first pressure difference and the second pressure difference, calculate the water pump adjustment speed according to the maximum pressure difference through a proportional formula, the intelligent terminal controls the operation of the water pump according to the water pump adjustment speed, and collects the first working current set and the second working current set of the water pump through the current sensor, and determines the current fluctuation range according to the first working current set and the second working current set; The response module is used to preset a sampling frequency, collect the real-time current data of the water pump through the current sensor according to the collection frequency, judge whether the real-time current data exceeds the current fluctuation range, and if yes, execute a judgment program to obtain a judgment result, and execute an exhaust program according to the judgment result; If not, no action will be taken.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method for diagnosing poor exhaust in a fuel cell cooling path as described in any one of claims 1 to 7 is implemented.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to execute the fuel cell cooling path exhaust blockage diagnosis method as described in any one of claims 1-7 when executed by a computer processor.

Images