CN117542237A - Fuel cell system fault diagnosis training platform based on man-machine interaction - Google Patents
Fuel cell system fault diagnosis training platform based on man-machine interaction Download PDFInfo
- Publication number
- CN117542237A CN117542237A CN202311343383.8A CN202311343383A CN117542237A CN 117542237 A CN117542237 A CN 117542237A CN 202311343383 A CN202311343383 A CN 202311343383A CN 117542237 A CN117542237 A CN 117542237A
- Authority
- CN
- China
- Prior art keywords
- fuel cell
- fault
- hydrogen
- fault diagnosis
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000000446 fuel Substances 0.000 title claims abstract description 153
- 238000003745 diagnosis Methods 0.000 title claims abstract description 74
- 230000003993 interaction Effects 0.000 title claims abstract description 67
- 238000012549 training Methods 0.000 title claims abstract description 31
- 238000012544 monitoring process Methods 0.000 claims abstract description 19
- 230000004044 response Effects 0.000 claims abstract description 8
- 238000011835 investigation Methods 0.000 claims abstract description 6
- 239000001257 hydrogen Substances 0.000 claims description 77
- 229910052739 hydrogen Inorganic materials 0.000 claims description 77
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 claims description 63
- 239000000110 cooling liquid Substances 0.000 claims description 33
- 230000008439 repair process Effects 0.000 claims description 32
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 28
- 239000007789 gas Substances 0.000 claims description 26
- 238000007689 inspection Methods 0.000 claims description 21
- 239000007788 liquid Substances 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 17
- 150000002431 hydrogen Chemical class 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 11
- 230000001276 controlling effect Effects 0.000 claims description 11
- 238000005516 engineering process Methods 0.000 claims description 10
- 239000012528 membrane Substances 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 7
- 239000002826 coolant Substances 0.000 claims description 7
- 238000004806 packaging method and process Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 5
- 238000011217 control strategy Methods 0.000 claims description 5
- 230000014509 gene expression Effects 0.000 claims description 5
- 230000036541 health Effects 0.000 claims description 5
- 230000020169 heat generation Effects 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 5
- 230000036571 hydration Effects 0.000 claims description 4
- 238000006703 hydration reaction Methods 0.000 claims description 4
- 230000001105 regulatory effect Effects 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 4
- 238000007599 discharging Methods 0.000 claims description 3
- 238000010926 purge Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 abstract description 7
- 238000000605 extraction Methods 0.000 abstract description 3
- 230000008901 benefit Effects 0.000 abstract description 2
- 238000000034 method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000033228 biological regulation Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000015654 memory Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000010287 polarization Effects 0.000 description 2
- 206010013496 Disturbance in attention Diseases 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 208000028659 discharge Diseases 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B9/00—Simulators for teaching or training purposes
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B23/00—Models for scientific, medical, or mathematical purposes, e.g. full-sized devices for demonstration purposes
- G09B23/06—Models for scientific, medical, or mathematical purposes, e.g. full-sized devices for demonstration purposes for physics
- G09B23/18—Models for scientific, medical, or mathematical purposes, e.g. full-sized devices for demonstration purposes for physics for electricity or magnetism
- G09B23/188—Models for scientific, medical, or mathematical purposes, e.g. full-sized devices for demonstration purposes for physics for electricity or magnetism for motors; for generators; for power supplies; for power distribution
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/30—Hydrogen technology
- Y02E60/50—Fuel cells
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Algebra (AREA)
- Power Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Fuel Cell (AREA)
Abstract
The invention discloses a human-computer interaction-based fuel cell system fault diagnosis training platform, which comprises a fuel cell multi-dimensional online monitoring system, a fuel cell system dynamic model, a fuel cell fault diagnosis system and a human-computer interaction system, and has both a fuel cell system fault diagnosis and a fault diagnosis training teaching working mode; the fault diagnosis training platform of the fuel cell system has two working modes, and when the fuel cell system works normally, man-machine interaction system can be used for carrying out man-made active obstacle setting; when the fuel cell system fails, the system failure can be automatically detected, judged, positioned and repaired, or the failure state is kept to wait for manual investigation and solution, so that the functions of on-line practical training and on-site teaching are realized. The practical training platform for fault diagnosis of the fuel cell system has the advantages of high response speed of a dynamic model, strong fault characteristic signal extraction and identification capability, intelligent man-machine interaction and the like.
Description
Technical Field
The invention belongs to the technical field of fuel cells, and relates to a fuel cell system fault diagnosis training platform based on man-machine interaction.
Technical Field
Hydrogen energy carries an important mission to achieve the goal of "two carbons", and fuel cells are an important carrier for hydrogen energy utilization. In terms of reliability and durability of the fuel cell system, the problems of low reliability, insufficient dynamic response performance, fast performance decay, low service life and the like still exist at present. Most of the current fuel cell fault diagnosis systems are limited in function to display of parameters and states and simple alarming, lack of extraction and identification capability of fault characteristic signals and lack of functions of fault detection, judgment, positioning and recovery. When a fault alarm occurs, the fault diagnosis system can only be operated by a self-shutdown or load-down command to avoid damage to the fuel cell system caused by the fault, and the reliability, dynamic response performance and service life of the fuel cell system are difficult to ensure by the processing mode, so that the real fault diagnosis and prediction purposes can not be achieved. And the existing fuel cell fault diagnosis system does not have a practical training teaching function.
The practical training system proposed by the practical training system (CN 202020431450.7) of the fuel cell consists of the fuel cell, a hydrogen cylinder, a monitoring module and a controller, wherein the practical training function is limited to signal display, and the intelligent setting and processing of the shown signals can not be performed.
A fuel cell fault diagnosis method, device and storage medium (CN 109830714A) are used for determining a state area where a fuel cell is positioned through a relation curve of ohmic resistance of a proton exchange membrane of the fuel cell and water content of the fuel cell, and accurately estimating the water content of the fuel cell in different modes. The invention only provides a diagnosis method aiming at one fault type, the method is complex and low in speed, the fault cannot be accurately positioned, and the on-line dynamic fault diagnosis is difficult to realize.
Disclosure of Invention
In order to overcome the technical defects, the invention provides a fuel cell system fault diagnosis training platform based on man-machine interaction.
The invention is realized at least by one of the following technical schemes:
a fuel cell system fault diagnosis training platform based on man-machine interaction comprises a fuel cell multi-dimensional online monitoring system, a fuel cell system dynamic model, a fuel cell fault diagnosis system and a man-machine interaction system;
the fuel cell multi-dimensional on-line monitoring system inputs the monitored and collected running state data into a fuel cell system dynamic model, so that the running state of the fuel cell and the dynamic response characteristics of each component of the system are accurately simulated, the fuel cell fault diagnosis system judges whether the running of the fuel cell system is normal in real time, and when the system breaks down and the on-line monitoring system needs to actively set faults and manually repair faults in a training teaching scene, a man-machine interaction system is used for executing repair operation, and the operation result is monitored and fed back in real time by the fuel cell multi-dimensional on-line monitoring system.
Further, the dynamic model of the fuel cell system comprises a galvanic pile model, a hydrogen system model, an air system model, an exhaust gas treatment system model and a water heat management system model;
the galvanic pile model comprises a flow field model, a membrane hydration model, a voltage model and a heat generation model;
the hydrogen system model comprises a high-pressure hydrogen storage tank, a filter, a pressure reducing valve, a hydrogen inlet valve, a first flowmeter, a hydrogen stacking electromagnetic valve and a hydrogen sensor for detecting the temperature and pressure of hydrogen stacking, which are connected in sequence; the hydrogen sensor is connected with an anode inlet of the fuel cell stack;
the air system model comprises an air filter, an air check valve, an air compressor, a second flowmeter, an air humidifier, an air pile-in electromagnetic valve and an air sensor for detecting the air pile-in temperature and pressure, which are connected in sequence; the air sensor is connected with the cathode inlet of the fuel cell stack;
the tail gas treatment system model comprises a hydrogen circulating pump, a first gas-liquid separator, a tail gas exhaust treatment electromagnetic valve, a second gas-liquid separator, a back pressure valve, a cathode outlet electromagnetic valve and a tail gas mixing chamber; one branch of the second gas-liquid separator is sequentially connected with the cathode outlet electromagnetic valve and the tail gas mixing chamber through a back pressure valve, the other branch returns air between the stack electromagnetic valve and the air sensor through a tail gas treatment electromagnetic valve, and the tail gas mixing chamber is provided with a hydrogen concentration sensor; one branch of the first gas-liquid separator is connected with the tail gas mixing chamber through an anode outlet electromagnetic valve, and the other branch returns hydrogen to the space between the stack electromagnetic valve and the hydrogen sensor through a hydrogen circulating pump for tail hydrogen discharging circulation;
the water thermal management system model comprises a thermostat, a cooling liquid heat exchanger, a cooling liquid circulating pump, a sensor for detecting the temperature and pressure of the cooling liquid entering the pile, and a radiator; the input end of the thermostat, the cooling liquid heat exchanger, the cooling liquid circulating pump, the sensor for detecting the temperature and the pressure of the cooling liquid entering the stack and the fuel cell stack are sequentially connected; the radiator is arranged in parallel with the cooling liquid heat exchanger.
Further, the multi-dimensional online monitoring system of the fuel cell comprises a lower management system, wherein the lower management system comprises a fuel cell main control board and a pile inspection module;
the fuel cell main control board comprises a data processing module, a start-stop logic and state switching module, a system performance analysis module, an air system control module, a hydrogen system control module, a water thermal management system control module and a data packaging module;
the start-stop logic and state switching module completes the execution flow of the relevant relay through the information of the pile inspection module, the sensor information and the state code to realize the start-stop, purging, idling and normal work logic switching;
the system performance analysis module calculates output power, hydrogen consumption and efficiency according to real-time data acquired by the sensor, and compares the output power, the hydrogen consumption and the efficiency with theoretical data to estimate the health state;
the air system control module is responsible for controlling an air system, and cooperatively controlling the air compressor and the throttle valve according to the information of the air sensor, the fault information of the air system, the system target power, the target rotating speed of the air compressor, the target flow and the target pressure;
the hydrogen system control module is responsible for controlling the hydrogen system, and cooperatively controlling the regulating valve, the circulating pump and the pressure reducing valve according to the information of the hydrogen sensor, the fault information of the hydrogen system and the target power of the system;
the water heat management system control module is responsible for controlling the heat of the system, and cooperatively controls the radiator, the cooling liquid circulating pump and the cooling liquid heat exchanger according to the water heat management sensing information, the heat management fault information and the data of the electric pile inspection module;
the data packaging module sends the sensor information, the relay information, the electric pile inspection module information and the performance information to the LabVIEW upper computer through a communication protocol.
Further, the framework of the fuel cell fault diagnosis system comprises a lower management system, a fault diagnosis module and a LabVIEW upper computer;
the application layer software of the lower management system divides the fault diagnosis strategy into a pile fault, a hydrogen system fault, an air system fault, a water heat management system fault, a control system fault and an electromagnetic compatibility fault according to the subsystem where the fault is located;
the fault diagnosis module judges whether faults occur or not and corresponding fault positions through sensor information, stack inspection module data and state code analysis, and sends the fault positions, fault grades and corresponding operation signals to each module to be uploaded to the LabVIEW upper computer.
Further, the fuel cell fault diagnosis system monitors and analyzes signals of sensors or actuators related to the operation state of the fuel cell, quantitatively analyzes the operation states of the single cells, the electric stacks and the auxiliary systems, and diagnoses the position and the severity of the fault of the fuel cell system.
Further, the fuel cell fault diagnosis system comprises a status code of each subsystem fault, the faults of each component are reflected in the status code, meanwhile, the grade of the faults is judged, shutdown inspection is carried out on the corresponding faults, and the faults with lower fault grades are processed and repaired in a specific actuator control strategy; the fault repair mode can be selected from two modes, namely automatic repair and manual repair.
Further, the man-machine interaction system comprises a man-machine interaction module, a multi-channel interaction technology module and a mobile interface module.
Further, the man-machine interaction module dynamically displays the performance parameter curve change of the fuel cell system through a visual man-machine interaction interface; the man-machine interaction interface can display the influence of system faults on the working state of the fuel cell in real time.
Further, the multi-channel interaction technology module is used for communicating with the fuel cell system and performing fault investigation, diagnosis and repair through interaction modes of voice, gestures, eyes and expressions of a user based on the multi-channel interaction technology.
Further, the user accesses the system data at any time through the mobile interface module to grasp important information, and performs fault diagnosis and repair of the fuel cell system.
Compared with the prior art, the invention has the following advantages:
1. the dynamic model has high response speed. The fuel cell online monitoring platform provided by the invention can accurately monitor various data in the running process of a fuel cell system, and can effectively improve the dynamic response performance of the system. Meanwhile, the model parameters on which the dynamic model depends can be mostly measured on line, and accurate system dynamic performance analysis can be performed in real time.
2. The fault characteristic signal has strong extraction and identification capability. The fault diagnosis system provided by the invention has stronger self-learning and self-organizing capabilities, the operation parameters of the electric pile and the auxiliary system are accurately measured and finely managed and controlled through the sensor and the actuator, the operation states of the single cell, the electric pile and the auxiliary system are quantitatively analyzed and researched, the faults of each component can be represented in the state code, and the grade of the faults is judged.
3. Human-computer interaction is intelligent. The user can access the system data at any time through the visual man-machine interaction interface to master important information, and simultaneously, the user can communicate with the fuel cell system and perform fault investigation, diagnosis and repair by using natural interaction modes such as voice, gestures, eye spirit, expression and the like.
Drawings
FIG. 1 is a working schematic diagram of a practical training platform for fault diagnosis of a fuel cell system based on man-machine interaction;
FIG. 2 is a schematic diagram of a dynamic model of a fuel cell system according to the present invention;
FIG. 3 is a schematic diagram of a fuel cell fault diagnosis system according to the present invention;
FIG. 4 is a schematic diagram of a man-machine interaction system according to the present invention;
the device comprises a high-pressure hydrogen storage tank, 2, a filter, 3, a pressure reducing valve, 4, a hydrogen inlet valve, 5, a first flowmeter, 6, a hydrogen inlet solenoid valve, 7, a hydrogen sensor for detecting the temperature and the pressure of the hydrogen inlet, 8, a hydrogen circulating pump, 9, a first gas-liquid separator, 10, an anode outlet solenoid valve, 11, an air filter, 12, an air check valve, 13, an air compressor, 14, a second flowmeter, 15, an air humidifier, 16, an air inlet solenoid valve, 17, an air sensor for detecting the temperature and the pressure of the air inlet, 18, a tail gas processing solenoid valve, 19, a second gas-liquid separator, 20, a back pressure valve, 21, a cathode outlet solenoid valve, 22, a tail gas mixing chamber, 23, a hydrogen concentration sensor, 24, a thermostat, 25, a coolant heat exchanger, 26, a coolant circulating pump, 27, a sensor for detecting the temperature and the pressure of the coolant inlet, 28, a radiator, 29, a sensor for detecting the internal temperature of the electric pile, 30 and a fuel cell pile.
Detailed Description
For a further understanding of the invention, the invention is further described below with reference to the drawings. However, the scope of the present invention is not limited to the following examples.
As shown in fig. 1, the invention provides a practical training platform for fault diagnosis of a fuel cell system based on man-machine interaction, which comprises a multi-dimensional online monitoring system of the fuel cell, a dynamic model of the fuel cell system, a fault diagnosis system of the fuel cell and a man-machine interaction system, and has the working modes of fault diagnosis of the fuel cell system and practical training teaching of the fault diagnosis. The fuel cell multidimensional online detection system inputs the monitored and collected operation data such as pressure, temperature, humidity, flow, conductivity and the like into a fuel cell system dynamic model, and the fuel cell system dynamic model accurately simulates the operation state of the fuel cell and the dynamic response characteristics of each component part of the system by researching the relation among the dynamic characteristics of multiple physical quantities, the operation parameters, the operation working conditions and the electrochemical performances in the system, and the fuel cell fault diagnosis system judges whether the operation of the fuel cell system is normal or not in real time. When the system fails, the fuel cell fault diagnosis system analyzes the faults from the aspects and the cause mechanism of the faults of the fuel cell, classifies the faults according to the occurrence positions of the faults, and judges the fault level. If the fault is automatically repaired, the fuel cell fault diagnosis system automatically processes and repairs according to the state code and the fault severity level; when the fault is required to be actively set or repaired manually, a user executes repair operation through a man-machine interaction system, and the operation result is monitored and fed back in real time by a multi-dimensional online detection system of the fuel cell.
The hardware design framework of the fuel cell multi-dimensional on-line monitoring system comprises a lower management system; the hardware design architecture adopts a distributed architecture;
the lower management system comprises a fuel cell main control board and a pile inspection module;
the pile inspection module is responsible for monitoring a certain number of single cells, including acquisition and pretreatment of single cell parameters (voltage, temperature, humidity, pressure, etc.). The pretreatment of the data is data cleaning, and the main steps comprise: selecting a subset, renaming column names, deleting repeated values, processing missing values, processing consistency, processing data ordering and processing abnormal values. The preprocessing of the embodiment specifically comprises the steps of single cell parameter selection, column name renaming, duplicate value deletion, missing value processing, unification processing, data sorting processing and abnormal value processing.
The fuel cell main control board comprises hardware such as a power supply, communication, a relay, control, a sensor and the like, is used for acquiring system operation parameters (pressure, temperature, humidity, flow, conductivity, liquid level, total pile parameters and the like), realizes hydrogen pressure regulation through a regulating valve, realizes air flow regulation through an air compressor, realizes temperature and humidity regulation through a pump, a radiator, a heater and the like, and specifically comprises a data processing module, a start-stop logic and state switching module, a system performance analysis module, a fault diagnosis module, an air system control module, a hydrogen system control module, a water thermal management system control module and a data packaging module;
the data processing module is mainly used for sorting data of some related parameter data sets (data sets of pressure, temperature, humidity, flow, conductivity, liquid level, stack overall parameters and the like), carrying out data result collection once every 1 minute, executing a machine learning algorithm, deducing the real-time performance of the fuel cell according to the existing acquisition parameters and carrying out parameter interpolation within a time interval (1 minute).
The start-stop logic and state switching module completes the execution flow of the relevant relay through the information of the pile inspection module, the sensor information and the state code to realize the start-stop, purging, idling and normal work logic switching.
The system performance analysis module calculates output power, hydrogen consumption and efficiency according to real-time data acquired by the sensor, and compares the output power, the hydrogen consumption and the efficiency with theoretical data to estimate the health state; the system performance analysis module is essentially a comparison module, and if the data of output power, hydrogen consumption, efficiency and the like are within the theoretical range, the health is judged, and vice versa. Based on how far these data deviate from theoretical overall, the less the deviation, the higher the score, and the better the state of health of the battery estimate.
The air system control module is responsible for air system control, and cooperatively controls the air compressor and the throttle valve according to air path sensing information, fault information of the air system, system target power, target rotating speed of the air compressor, target flow and target pressure.
The hydrogen system control module is responsible for hydrogen system control, and cooperatively controls the regulating valve, the circulating pump and the pressure reducing valve according to hydrogen gas path sensing information, fault information of the hydrogen system and system target power.
The water heat management system control module is responsible for controlling the heat of the system, and cooperatively controls the radiator, the cooling liquid circulating pump and the cooling liquid heat exchanger according to the water heat management sensing information, the heat management fault information and the data of the electric pile inspection module.
The data packaging module sends the sensor information, the relay information, the electric pile inspection module information, the fault diagnosis module information and the performance information to the LabVIEW upper computer through a communication protocol (TTL or RS 232).
As a preferred embodiment, the software design architecture of the fuel cell multidimensional online monitoring system comprises an embedded real-time operating system, a main control board bottom layer software and a main control board application layer software;
the embedded real-time operating system is responsible for task scheduling, task communication and memory management, and if the task needs to be executed, the real-time operating system can immediately execute the task.
The bottom software of the main control board is responsible for tasks such as the creation of an embedded real-time operating system environment, driving configuration, event task management and the like, and tasks necessary for realizing functions are created on three layers of an operating system, a data interface and an application layer algorithm, and priorities and memories are distributed according to the importance and the calculated amount of the tasks.
The application layer software of the main control board depends on the bottom layer data and is responsible for the control algorithm and state scheduling (on-off strategy, control of each actuator and fault diagnosis strategy) of all upper layer functions of the system, so that the safe and efficient operation of the fuel cell system is ensured.
As shown in fig. 2, the fuel cell system dynamic model includes a galvanic pile model, a hydrogen system model, an air system model, an exhaust gas treatment system model, and a hydrothermal management system model;
the galvanic pile model comprises a flow field model, a membrane hydration model, a voltage model and a heat generation model; the flow field model comprises anode and cathode flow channels and is used for solving the distribution of speed, pressure, substance concentration and the like in the battery flow field; the membrane hydration model comprises a proton exchange membrane and is used for solving the water content and the distribution of the water content in the proton exchange membrane; the voltage model is used for solving balance potential, active polarization loss, resistance loss, concentration loss and final output voltage of the battery voltage; the heat generation model is used for solving the heat generation and distribution of the battery.
The hydrogen system model comprises a high-pressure hydrogen storage tank 1, a filter 2, a pressure reducing valve 3, a hydrogen inlet valve 4, a first flowmeter 5, a hydrogen stacking electromagnetic valve 6 and a hydrogen sensor 7 for detecting the temperature and pressure of the hydrogen stacking; the hydrogen sensor 7 is connected with an anode inlet of the fuel cell stack 30;
the air system model comprises an air filter 11, an air check valve 12, an air compressor 13, a second flowmeter 14, an air humidifier 15, an air in-pile solenoid valve 16 and an air sensor 17 for detecting the temperature and pressure of the in-pile air, which are connected in sequence; the air sensor 17 is connected with the cathode inlet of the fuel cell stack 30;
the tail gas treatment system model comprises a hydrogen circulating pump 8, a first gas-liquid separator 9, a tail gas discharge treatment electromagnetic valve 18, a second gas-liquid separator 19, a back pressure valve 20, a cathode outlet electromagnetic valve 21 and a tail gas mixing chamber 22; a branch of the second gas-liquid separator 19 and the back pressure valve 20 is sequentially connected with the cathode outlet electromagnetic valve 21 and the tail gas mixing chamber 22, the tail gas mixing chamber 22 is provided with the hydrogen concentration sensor 23, and the other branch returns air to the space between the stack electromagnetic valve 16 and the air sensor 17 through the tail gas treatment electromagnetic valve 18; one branch of the first gas-liquid separator 9 is connected with the tail gas mixing chamber 22 through the anode outlet electromagnetic valve 10, and the other branch returns hydrogen to the space between the stack electromagnetic valve 6 and the hydrogen sensor 7 through the hydrogen circulating pump 8 for tail hydrogen discharging circulation;
the hydrothermal management system model comprises a thermostat 24, a cooling liquid heat exchanger 25, a cooling liquid circulating pump 26, a sensor 27 for detecting the temperature and pressure of the cooling liquid entering the pile, and a radiator 28; the input end of the thermostat 24, the cooling liquid heat exchanger 25, the cooling liquid circulating pump 26, the sensor 27 for detecting the temperature and pressure of the cooling liquid entering the stack and the fuel cell stack 30 are connected in sequence; the radiator 28 is arranged in parallel with the coolant heat exchanger 25.
The framework of the fuel cell fault diagnosis system comprises a lower management system, a fault diagnosis module and a LabVIEW upper computer, wherein the fault diagnosis module judges whether a fault occurs or not and the corresponding fault position through sensor information, stack inspection module data and state code analysis, and sends the fault position, the fault grade and the corresponding operation signals to each module to be applied to upload to the LabVIEW upper computer.
Specifically, the fault diagnosis module captures signals, state parameters, process parameters and change characteristic parameters of sensors (actuators) closely related to the running state of the fuel cell through the pile inspection module and the fuel cell main control board, monitors and analyzes the signals, state parameters, process parameters and change characteristic parameters, and evaluates the target running states (target power, target pressure, target flow and the like) of the single cell and the pile. If the real-time state parameter is not in the given normal range, diagnosing the fault of the fuel cell system, judging the position of the system and parts where the fault occurs according to the position of the parameter in the dynamic model of the fuel cell system, and comprehensively considering the relative amplitude exceeding the normal range and the reduction condition of the output power of the fuel cell to determine the severity. The different degree of failure of each component in each system failure corresponds one-to-one to the design status code. The greater the relative amplitude of the monitored parameter outside the normal range, the more the fuel cell output power drops, the more serious the fault and the higher the fault level.
The application layer software of the lower management system divides the fault diagnosis strategy into a pile fault, a hydrogen system fault, an air system fault, a water heat management system fault, a control system fault and an electromagnetic compatibility fault according to the corresponding system where the fault is located; the method comprises the steps of including a status code of each subsystem fault, showing faults of each component in the status code, judging the level of the faults, performing shutdown inspection on corresponding faults, and processing and repairing the faults with lower fault levels in a specific actuator control strategy; the fault repair mode can be selected from two modes, namely automatic repair and manual repair.
The lower management system monitors and analyzes signals of sensors or actuators related to the operation state of the fuel cell, quantitatively analyzes the operation states of the single cells, the electric stacks and the auxiliary systems, and diagnoses the position and the severity of the fault of the fuel cell system.
As one example, the fault diagnosis module classifies fault classes into two stages according to fault severity. For high-level serious faults, shutdown inspection is needed, and minor faults with lower fault levels are processed and repaired in a specific actuator control strategy. The fault repair mode has two modes of closed loop feedback automatic repair and manual repair which can be selected. Automatic repair corrects the fault by adjusting the deviation parameter to within the normal range.
The man-machine interaction system comprises a man-machine interaction module, a multi-channel interaction technology module and a mobile interface module, and the performance parameter curve change of the fuel cell system is dynamically displayed through a visual man-machine interaction interface; the man-machine interaction interface can display the influence of system faults on the working state of the fuel cell in real time.
The multi-channel interaction technology module is based on the multi-channel interaction technology, and a user communicates with the fuel cell system and performs fault investigation, diagnosis and repair in a natural interaction mode such as voice, gestures, eye, expression and the like.
Take as an example the failure of the coolant circulation pump 26 in the hydrothermal management system.
When the fuel cell system works normally, a user performs artificial active obstacle setting on the fuel cell system through the man-machine interaction module, namely, the cooling liquid circulating pump 26 in the water thermal management system is set to be faulty.
The fuel cell multidimensional online monitoring system accurately measures and finely manages and controls the operation parameters of the fuel cell stack 30 and each component of the system through high-precision and high-sensitivity sensors and actuators, and realizes quantitative analysis on the operation states of single cells, stacks and auxiliary systems.
The operation data of each component of the fuel cell system measured by the multi-dimensional online monitoring system of the fuel cell is input into a dynamic model of the fuel cell system, and a man-machine interaction interface displays the working state and characteristics of the fuel cell system when the cooling liquid circulating pump 26 in the dynamic model fails, namely, the cooling liquid circulating pump 26 fails, the cooling liquid stops flowing, and as the fuel cell stack 30 continuously works and generates heat, the temperature inside the fuel cell stack 30 rises to accelerate the evaporation of liquid water in the cell, so that the content of membrane water is reduced, the resistance is increased, the ohmic polarization is increased, and the working voltage of the cell is reduced.
The fuel cell fault diagnosis system compares the fuel cell running state data with the target parameter range in real time, when the temperature parameter, the output voltage and the membrane water content parameter exceed the normal range values, the fuel cell fault diagnosis system diagnoses the fault of the cooling liquid circulating pump 26 in the hydro-thermal management system, feeds back the corresponding state code, and judges the fault as serious fault according to the change amplitude of the temperature relative to the reference temperature, the change amplitude of the membrane water content relative to the reference water content and the descending degree of the output voltage, and belongs to high fault grade.
According to the status code of the system fault fed back by the fuel cell fault diagnosis system, the man-machine interaction interface displays that the cooling liquid circulating pump 26 in the hydrothermal management system is in fault, and at the moment, the shutdown check can be manually selected or the automatic processing and repair can be selected in a specific actuator control strategy.
The fault repair mode has two modes of closed loop feedback automatic repair and manual repair which can be selected. In order to achieve the purpose of practical training teaching, in this embodiment, the fault repair mode selects manual repair.
The visualized man-machine interaction interface displays information of the cooling liquid circulating pump (26), the fault severity degree, the working state and the characteristics of the fuel cell system when the fault occurs and the like in the water heat management system to a user. The user can refer to the information displayed by the man-machine interaction interface to check the running state of each component of the fuel cell system.
Based on the multi-channel interaction technology, a user communicates with the fuel cell system through natural interaction modes such as voice, gestures, eye, expression and the like, and performs fault investigation, diagnosis and repair. In this embodiment, the interaction mode is a gesture.
According to the working state and the characteristics of the fuel cell system displayed in real time by the man-machine interaction interface, the cooling liquid circulating pump 26 in the water heat management system can be judged to be in fault, and the information fed back by the fuel cell fault diagnosis system is kept consistent. The user performs a reset operation on the coolant circulation pump 26 in the fuel cell system through a gesture at the man-machine interaction interface, and the fuel cell system resumes normal operation.
While the invention has been described in terms of specific embodiments, it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the invention are desired to be protected by the following claims.
Claims (10)
1. A fuel cell system fault diagnosis practical training platform based on man-machine interaction is characterized in that: the system comprises a fuel cell multi-dimensional online monitoring system, a fuel cell system dynamic model, a fuel cell fault diagnosis system and a man-machine interaction system;
the fuel cell multi-dimensional on-line monitoring system inputs the monitored and collected running state data into a fuel cell system dynamic model, so that the running state of the fuel cell and the dynamic response characteristics of each component of the system are accurately simulated, the fuel cell fault diagnosis system judges whether the running of the fuel cell system is normal in real time, and when the system breaks down and the on-line monitoring system needs to actively set faults and manually repair faults in a training teaching scene, a man-machine interaction system is used for executing repair operation, and the operation result is monitored and fed back in real time by the fuel cell multi-dimensional on-line monitoring system.
2. The human-computer interaction-based fuel cell system fault diagnosis training platform as claimed in claim 1, wherein: the dynamic model of the fuel cell system comprises a galvanic pile model, a hydrogen system model, an air system model, a tail gas treatment system model and a water heat management system model;
the galvanic pile model comprises a flow field model, a membrane hydration model, a voltage model and a heat generation model;
the hydrogen system model comprises a high-pressure hydrogen storage tank (1), a filter (2), a pressure reducing valve (3), a hydrogen inlet valve (4), a first flowmeter (5), a hydrogen stacking electromagnetic valve (6) and a hydrogen sensor (7) for detecting the temperature and pressure of hydrogen stacking; the hydrogen sensor (7) is connected with an anode inlet of the fuel cell stack (30);
the air system model comprises an air filter (11), an air check valve (12), an air compressor (13), a second flowmeter (14), an air humidifier (15), an air pile-in electromagnetic valve (16) and an air sensor (17) for detecting the air pile-in temperature and pressure, which are connected in sequence; the air sensor (17) is connected with a cathode inlet of the fuel cell stack (30);
the tail gas treatment system model comprises a hydrogen circulating pump (8), a first gas-liquid separator (9), a tail gas exhaust treatment electromagnetic valve (18), a second gas-liquid separator (19), a back pressure valve (20), a cathode outlet electromagnetic valve (21) and a tail gas mixing chamber (22); one branch of the second gas-liquid separator (19) is sequentially connected with a cathode outlet electromagnetic valve (21) and a tail gas mixing chamber (22) through a back pressure valve (20), the other branch returns air between a pile inlet electromagnetic valve (16) and an air sensor (17) through a tail gas exhaust treatment electromagnetic valve (18), and a hydrogen concentration sensor (23) is arranged on the tail gas mixing chamber (22); one branch of the first gas-liquid separator (9) is connected with the tail gas mixing chamber (22) through the anode outlet electromagnetic valve (10), and the other branch returns hydrogen to the space between the stack electromagnetic valve (6) and the hydrogen sensor (7) through the hydrogen circulating pump (8) for tail hydrogen discharging circulation;
the water thermal management system model comprises a thermostat (24), a cooling liquid heat exchanger (25), a cooling liquid circulating pump (26), a sensor (27) for detecting the temperature and pressure of the cooling liquid entering the pile, and a radiator (28); the input end of the thermostat (24), the cooling liquid heat exchanger (25), the cooling liquid circulating pump (26), the sensor (27) for detecting the temperature and the pressure of the cooling liquid entering the stack and the fuel cell stack (30) are connected in sequence; the radiator (28) is arranged in parallel with the coolant heat exchanger (25).
3. The human-computer interaction-based fuel cell system fault diagnosis training platform as claimed in claim 2, wherein: the fuel cell multidimensional on-line monitoring system comprises a lower management system, wherein the lower management system comprises a fuel cell main control board and a pile inspection module;
the fuel cell main control board comprises a data processing module, a start-stop logic and state switching module, a system performance analysis module, an air system control module, a hydrogen system control module, a water thermal management system control module and a data packaging module;
the start-stop logic and state switching module completes the execution flow of the relevant relay through the information of the pile inspection module, the sensor information and the state code to realize the start-stop, purging, idling and normal work logic switching;
the system performance analysis module calculates output power, hydrogen consumption and efficiency according to real-time data acquired by the sensor, and compares the output power, the hydrogen consumption and the efficiency with theoretical data to estimate the health state;
the air system control module is responsible for controlling an air system, and cooperatively controlling the air compressor and the throttle valve according to the information of the air sensor, the fault information of the air system, the system target power, the target rotating speed of the air compressor, the target flow and the target pressure;
the hydrogen system control module is responsible for controlling the hydrogen system, and cooperatively controlling the regulating valve, the circulating pump and the pressure reducing valve according to the information of the hydrogen sensor, the fault information of the hydrogen system and the target power of the system;
the water heat management system control module is responsible for controlling the heat of the system, and cooperatively controls the radiator, the cooling liquid circulating pump and the cooling liquid heat exchanger according to the water heat management sensing information, the heat management fault information and the data of the electric pile inspection module;
the data packaging module sends the sensor information, the relay information, the electric pile inspection module information and the performance information to the LabVIEW upper computer through a communication protocol.
4. The human-computer interaction-based fuel cell system fault diagnosis training platform as claimed in claim 1, wherein: the framework of the fuel cell fault diagnosis system comprises a lower management system, a fault diagnosis module and a LabVIEW upper computer;
the application layer software of the lower management system divides the fault diagnosis strategy into a pile fault, a hydrogen system fault, an air system fault, a water heat management system fault, a control system fault and an electromagnetic compatibility fault according to the subsystem where the fault is located;
the fault diagnosis module judges whether faults occur or not and corresponding fault positions through sensor information, stack inspection module data and state code analysis, and sends the fault positions, fault grades and corresponding operation signals to each module to be uploaded to the LabVIEW upper computer.
5. The human-computer interaction-based fuel cell system fault diagnosis training platform according to any one of claims 1 to 4, wherein the training platform is characterized in that: the fuel cell fault diagnosis system monitors and analyzes signals of sensors or actuators related to the operation state of the fuel cell, quantitatively analyzes the operation states of single cells, stacks and auxiliary systems, and diagnoses the position and severity of the fault of the fuel cell system.
6. The human-computer interaction-based fuel cell system fault diagnosis training platform as claimed in claim 5, wherein: the fuel cell fault diagnosis system comprises a state code of each subsystem fault, wherein the faults of each component are reflected in the state code, meanwhile, the grade of the faults is judged, shutdown inspection is carried out on the corresponding faults, and the faults with lower fault grades are processed and repaired in a specific actuator control strategy; the fault repair mode can be selected from two modes, namely automatic repair and manual repair.
7. The human-computer interaction-based fuel cell system fault diagnosis training platform as claimed in claim 1, wherein: the man-machine interaction system comprises a man-machine interaction module, a multi-channel interaction technology module and a mobile interface module.
8. The human-computer interaction-based fuel cell system fault diagnosis training platform as claimed in claim 7, wherein: the man-machine interaction module dynamically displays the change of the performance parameter curve of the fuel cell system through a visual man-machine interaction interface; the man-machine interaction interface can display the influence of system faults on the working state of the fuel cell in real time.
9. The human-computer interaction-based fuel cell system fault diagnosis training platform as claimed in claim 7, wherein: the multi-channel interaction technology module is used for communicating with the fuel cell system and performing fault investigation, diagnosis and repair through interaction modes of voice, gestures, eyes and expressions of a user based on the multi-channel interaction technology.
10. The human-computer interaction-based fuel cell system fault diagnosis training platform as claimed in claim 7, wherein: the user accesses the system data at any time through the mobile interface module to master important information, and performs fault diagnosis and repair of the fuel cell system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311343383.8A CN117542237A (en) | 2023-10-17 | 2023-10-17 | Fuel cell system fault diagnosis training platform based on man-machine interaction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311343383.8A CN117542237A (en) | 2023-10-17 | 2023-10-17 | Fuel cell system fault diagnosis training platform based on man-machine interaction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117542237A true CN117542237A (en) | 2024-02-09 |
Family
ID=89794683
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311343383.8A Pending CN117542237A (en) | 2023-10-17 | 2023-10-17 | Fuel cell system fault diagnosis training platform based on man-machine interaction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117542237A (en) |
-
2023
- 2023-10-17 CN CN202311343383.8A patent/CN117542237A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108344947A (en) | A kind of fuel cell diagnostic method of non-intrusion type | |
| CN107180983B (en) | Fault diagnosis method and system for solid oxide fuel cell stack | |
| JP7364832B2 (en) | System and method for distributed fault management in fuel cell systems | |
| CN110165259A (en) | Monitoring method and device, the system of the operating status of battery | |
| KR102632527B1 (en) | System and method for fault diagnosis of fuel cell energy management system based on digital twin | |
| Zhao et al. | Faults diagnosis for PEM fuel cell system based on multi-sensor signals and principle component analysis method | |
| CN111640970B (en) | CAN bus-based fuel cell engine upper computer monitoring method | |
| CN109447236A (en) | A kind of method for diagnosing faults of hybrid vehicle heat management system | |
| CN102097636A (en) | Fault diagnosis device and method of fuel cell system | |
| CN213275898U (en) | Modularized fuel cell detection system | |
| CN209312921U (en) | A kind of fuel cell system | |
| CN102593488A (en) | Unattended fuel cell testing system | |
| EP4428962A1 (en) | Fuel cell vehicle, and hydrogen discharge valve/drain valve fault diagnosis method and apparatus | |
| CN118089287B (en) | Water chiller energy efficiency optimizing system based on intelligent algorithm | |
| CN117032120A (en) | Integrated intelligent cloud control system and control method for air compression station | |
| CN117542237A (en) | Fuel cell system fault diagnosis training platform based on man-machine interaction | |
| CN117766815A (en) | Automatic generation method of all-vanadium redox flow battery operation and maintenance strategy based on knowledge graph | |
| CN202633439U (en) | Unattended fuel cell test system | |
| CN113849988B (en) | Energy storage system | |
| CN115933437A (en) | Semi-physical simulation test system development method for fuel cell controller | |
| CN115332582A (en) | Low-temperature starting control system for fuel cell | |
| Zhu et al. | On the hazards of proton exchange membrane (PEM) water electrolysis systems using system theoretic process analysis (STPA) | |
| Mpelogianni et al. | Proactive Building Energy Management based on Fuzzy Logic and Expert Intelligence | |
| CN110333708A (en) | Based on the associated diagnosis control method of Hydraulic Power Unit technical water supply water pressure data, system, storage medium and terminal | |
| CN113707915B (en) | Water management control method and device for fuel cell stack |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |