CN110190306A - A kind of on-line fault diagnosis method for fuel cell system - Google Patents
A kind of on-line fault diagnosis method for fuel cell system Download PDFInfo
- Publication number
- CN110190306A CN110190306A CN201910481798.9A CN201910481798A CN110190306A CN 110190306 A CN110190306 A CN 110190306A CN 201910481798 A CN201910481798 A CN 201910481798A CN 110190306 A CN110190306 A CN 110190306A
- Authority
- CN
- China
- Prior art keywords
- fuel cell
- cell system
- fault diagnosis
- data
- real
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M8/00—Fuel cells; Manufacture thereof
- H01M8/04—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
- H01M8/04298—Processes for controlling fuel cells or fuel cell systems
- H01M8/04313—Processes for controlling fuel cells or fuel cell systems characterised by the detection or assessment of variables; characterised by the detection or assessment of failure or abnormal function
- H01M8/04664—Failure or abnormal function
- H01M8/04679—Failure or abnormal function of fuel cell stacks
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M8/00—Fuel cells; Manufacture thereof
- H01M8/04—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
- H01M8/04298—Processes for controlling fuel cells or fuel cell systems
- H01M8/04313—Processes for controlling fuel cells or fuel cell systems characterised by the detection or assessment of variables; characterised by the detection or assessment of failure or abnormal function
- H01M8/04664—Failure or abnormal function
- H01M8/04686—Failure or abnormal function of auxiliary devices, e.g. batteries, capacitors
-
- 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
Abstract
The invention discloses a kind of on-line fault diagnosis methods for fuel cell system, including obtaining Fisrt fault diagnostic model, Fisrt fault diagnostic model is that the real time data and machine learning method based on pile obtain, and the real time data of pile is to test to obtain by pile benchmark test；During operation of fuel cell system, the pile operation data of real-time measurement is obtained, as the input parameter of Fisrt fault diagnostic model, obtains the fault diagnosis result of pile；The second fault diagnosis model is obtained, normal data corresponding with accessory each in fuel cell system is contained in the second fault diagnosis model；The real-time running data for obtaining each accessory in fuel cell system obtains the fault diagnosis result of each accessory as the input parameter of second fault diagnosis model；The present invention increases sensor and test equipment based on existing fuel cell system, without additional, and will not interfere to operation of fuel cell system, and implementation cost is low, easy to spread.
Description
Technical field
The invention belongs to field of fuel cell technology, and in particular to a kind of on-line fault diagnosis for fuel cell system
Method.
Background technique
Fuel cell is a kind of device that the chemical energy of fuel is converted into electric energy, has operational efficiency height, cleaning
It the advantages that pollution-free, low noise, is expected to substitute problem of environmental pollution of traditional heat engine to solve energy resource system.Currently, fuel
Battery starts to promote and apply in fields such as automobile, unmanned plane, stationary power generations, and future has broad application prospects.
Fuel cell system includes pile, air supply system, hydrogen gas feed system, heat management system etc., is a set of multiple
Miscellaneous nonlinear system.It is possible to occur the failures such as dry water logging, film, deficency, short circuit, catalyst poisoning in operational process, to combustion
Material battery performance and service life all have a significant impact.Therefore, on-line checking is carried out to fuel cell system in use, in real time
Its malfunction is assessed, it is most important to guarantee safe and stable operation.On the one hand, failure is found in time and is taken corresponding
Fault recovery measure, avoid more serious failure from occurring, reduce irreversible damage caused by failure, improve system reliability.
On the other hand, accurate positioning failure occurs position determines the reason of fault type and failure occur, and can greatly reduce dimension
Workload when repairing.
Although having proposed pluralities of fuel battery system method for diagnosing faults in the prior art, it is not met by and actually answers
Needs, the main problems are as follows: 1) diagnostic method is proposed just for a kind of fault type mostly, can not directly use
In actual fuel cell system；2) be mostly method for diagnosing faults only for fuel cell pile, but in fact air compressor machine,
The fault detection of the critical components such as hydrogen gas circulating pump is also indispensable；3) diagnostic method is complicated, and implementation cost is high, Wu Fayong
In on-line fault diagnosis.Due to above, a kind of can promote the use of, rule are had not yet been formed in field of fuel cell technology so far
The unified method for diagnosing faults of model.
Summary of the invention
In view of the above-mentioned problems, the present invention proposes a kind of on-line fault diagnosis method for fuel cell system, it can be right
Fuel cell pile carries out real-time online detection, accurate evaluation its malfunction, and diagnosis process quickly, efficiently, can be used for fuel
Battery control system or fuel cell testing device.
In order to achieve the above technical purposes, reach above-mentioned technical effect, the invention is realized by the following technical scheme:
A kind of on-line fault diagnosis method for fuel cell system, comprising the following steps:
Fisrt fault diagnostic model is obtained, the Fisrt fault diagnostic model is real time data and engineering based on pile
Learning method obtains；The real time data of the pile is to test to obtain by pile benchmark test；
During operation of fuel cell system, the pile operation data of real-time measurement is obtained, as first event
Hinder the input parameter of diagnostic model, and then obtains the fault diagnosis result of pile.
Preferably, the acquisition step of the Fisrt fault diagnostic model specifically:
The real-time regular picture floor data and fault condition data of pile are obtained, data set is formed；
The data set is divided into training data subset and verify data subset；
Selected machine learning model；
The machine learning model is trained using the training data subset；
The accuracy of machine learning model is verified using the verify data subset；
The structure that machine learning model is adjusted according to verification result is repeated training and verifying, finally obtains accuracy
Satisfactory Fisrt fault diagnostic model.
Preferably, the learning method of the machine learning model is k nearest neighbor, Bayesian network, support vector machines, artificial mind
Through any one in network or deep learning.
Preferably, using based on gradient descent method, newton during the structure of the adjustment machine learning model
Method, conjugate gradient method or genetic algorithm.
Preferably, the fault diagnosis result of the pile includes water logging, film dry, deficency, short circuit and/or catalyst poisoning.
Preferably, the method also includes following steps:
Obtain the second fault diagnosis model, contained in second fault diagnosis model with it is each auxiliary in fuel cell system
Help the corresponding normal data of component；
The real-time running data for obtaining each accessory in fuel cell system, as the second fault diagnosis mould
The input parameter of type, and then obtain the fault diagnosis result of each accessory.
Preferably, it is described obtain pile real-time running data step and/or obtain fuel cell system in each assisted parts
After the real-time running data of part further include:
Real-Time Filtering is carried out to collected real-time running data, removes the high fdrequency component of time domain data.
Preferably, the real-time running data for obtaining each accessory in fuel cell system, as described the
The input parameter of two fault diagnosis models, and then the fault diagnosis result of each accessory is obtained, specifically:
Obtain the real-time running data of each accessory in fuel cell system；
In the fuel cell system that will acquire in the real-time running data of each accessory and the second fault diagnosis model
Whether existing normal data compares, be more than preset threshold value according to difference, to judge whether accessory occurs
Failure.
Preferably, the accessory includes hydrogen gas circulating pump, air compressor, heat exchanger, water pump, DC/DC boosting turn
Parallel operation；
For hydrogen gas circulating pump, air compressor and water pump, normal data refers to that flow and pressure under different rotating speeds close
It is curve；
For heat exchanger, normal data refers to the relation curve of the coefficient of heat transfer and flow；
For DC/DC boost converter, normal data refers to the relation curve of efficiency and voltage ratio.
Preferably, the real-time running data of the pile include: electric current, voltage, the voltage of each battery unit, cathode and
Gas flow, out temperature, inlet and outlet pressure, inlet and outlet humidity, cooling water flow and/or the cooling water outlet and inlet temperature of anode
Degree；The real-time running data of each accessory includes: hydrogen gas circulating pump revolving speed, inlet and outlet pressure, flow, air compressor
Revolving speed, inlet and outlet pressure, flow, heat exchanger inlet and outlet temperature, flow, pump rotary speed, inlet and outlet pressure, flow, DC/DC boosting
Converter input voltage, output voltage, input power, output power.
Compared with prior art, beneficial effects of the present invention:
(1) method of the invention increases sensor and test without additional based on existing fuel cell system
Equipment, and operation of fuel cell system will not be interfered, implementation cost is low, easy to spread.
(2) method of the invention is capable of the various faults state of real-time detection pile and accessory simultaneously, meets practical
Use demand.
(3) method of the invention constructs fuel cell pile fault diagnosis model using machine learning method, overcomes combustion
Expect battery stack nonlinear characteristic bring technical difficulty, diagnostic method is adaptable, diagnosis accuracy is higher.
(4) present invention is capable of the position of accurate judgement fault type and failure generation, carries out fault recovery for control system
Important reference is provided with maintenance work.
(5) accurate, the perfect fault message that the present invention obtains can provide foundation for fuel cell system optimization design.
Detailed description of the invention
In order that the present invention can be more clearly and readily understood, right below according to specific embodiment and in conjunction with attached drawing
The present invention is described in further detail, in which:
Fig. 1 is the state parameter schematic diagram for needing real-time measurement in an embodiment of the present invention in failure diagnostic process；
Fig. 2 is the stream that the fuel cell pile fault diagnosis model based on machine learning is constructed in an embodiment of the present invention
Cheng Tu；
Fig. 3 is the on-line fault diagnosis method flow diagram of fuel cell system in an embodiment of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to embodiments, to the present invention
It is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not used to
It limits the scope of protection of the present invention.
Application principle of the invention is explained in detail with reference to the accompanying drawing.
Embodiment 1
The embodiment of the invention provides a kind of on-line fault diagnosis methods for fuel cell system, including following step
It is rapid:
Step (1) obtains Fisrt fault diagnostic model, and the Fisrt fault diagnostic model is the real time data based on pile
It is obtained with machine learning method；The real time data of the pile is to test to obtain by pile benchmark test；
During step (2) operation of fuel cell system, the pile operation data of real-time measurement is obtained, as described
The input parameter of Fisrt fault diagnostic model, and then obtain the fault diagnosis result of pile, it is preferable that the failure of the pile is examined
Disconnected result includes water logging, film dry, deficency, short circuit and/or catalyst poisoning.
In a kind of specific embodiment of the embodiment of the present invention, the acquisition step of the Fisrt fault diagnostic model is specific
Are as follows:
A carries out benchmark test experiment for fuel cell pile, obtains real-time regular picture floor data and the event of pile
Hinder floor data, forms data set；In the actual process, it shall be guaranteed that the data in data set are enough；As shown in Figure 1, institute
Stating floor data includes following parameter:
1. electric current；
2. voltage；
3. monolithic voltage: the voltage of i.e. each battery unit；
4. anodic gas state parameter: flow, out temperature, inlet and outlet pressure, inlet and outlet humidity；
5. cathode gas state parameter: flow, out temperature, inlet and outlet pressure, inlet and outlet humidity；
6. cooling water state parameter: flow, out temperature；
Since the parameter of above-mentioned real-time measurement is all the data that fuel cell system itself needs to acquire in real time.Therefore,
Fuel cell system method for diagnosing faults of the present invention, will not be to fuel without introducing additional sensor and measuring device
Battery system operation interferes, and implementation cost is low；
It is described for fuel cell pile carry out benchmark test experiment be divided into two parts, specifically: first is that different temperatures,
Accidental conditions under pressure, damp condition measure；Second is that pile failure caused by artificial, records under malfunction
Fuel cell system state parameter.In experimentation, fuel cell pile state parameter shown in FIG. 1 is measured, and marks
Remember the corresponding malfunction of every group of state parameter, forms set of data samples；
Data set is divided into two parts by B: a part is used for the training process of machine learning model, referred to as training data
Collection；Another part is used for the verification process of machine learning model, becomes verify data subset；
C selectes machine learning model；Preferably, the learning method of the machine learning model is k nearest neighbor, Bayesian network
Any one in network, support vector machines, artificial neural network or deep learning, referring specifically to Fig. 2；It is with artificial neural network
Example, it is thus necessary to determine that input layer, hidden layer, the number of nodes of output layer and the number of plies, number of nodes, that is, malfunction of output layer
Quantity；
D is trained the machine learning model using the training data subset；In training process, constantly basis
The process that training data subset is adjusted the state of machine learning model is taken in machine learning model building process
Between longest process.After the completion of training process, machine learning model can be good at the fault characteristic for being fitted fuel cell pile,
Pile fault type can be accurately calculated according to the input parameter of training data subset；Influence the factor master of the accuracy of model
Have: whether the condition range of fuel cell pile benchmark test experiment sufficiently wide, selection of training dataset whether suitable, machine
Whether the type of device learning method is suitable；
E verifies the accuracy of machine learning model using the verify data subset, i.e., machine learning model is instructed
After practicing process, using the fuel cell system state parameter of verify data subset as input parameter, the machine completed with training
Device learning model carries out fuel cell pile diagnosis.Whether it is coincide according to the malfunction of diagnostic result and validation data set,
Assess the accuracy of machine learning model；
F adjusts the structure of machine learning model according to verification result, and training and verifying is repeated, finally obtains accuracy
Satisfactory Fisrt fault diagnostic model；Preferably, it is described adjustment machine learning model structure during using
Based on gradient descent method, Newton method, conjugate gradient method or genetic algorithm, specifically:
If machine learning model model Qualify Phase accuracy not up to be expected, need to machine learning model into
Row adjustment, iterates to obtain accurate fuel cell pile fault diagnosis model.Adjustment is divided into three levels:
Firstly, adjustment model training method；
If the accuracy of model can't reach expected, adjust machine learning model after adjusting model training method
Structure or replacement machine learning method；
It still cannot reach expected model accuracy by above step, fuel cell pile benchmark test can be supplemented
Experiment, with more training samples come training machine learning model.
In a kind of preferred embodiment of the embodiment of the present invention, after the real-time running data step for obtaining pile
Further include:
Real-Time Filtering is carried out to the real-time running data of the pile got, the high-frequency data of time domain data is removed, prevents
Interference signal influences fault diagnosis result, and hardware filtering can be used by implementing filtering technique, can also use software filtering.
Embodiment 2
Based on identical inventive concept, as shown in figure 3, the embodiment of the present invention the difference from embodiment 1 is that: the method
It is further comprising the steps of:
Obtain the second fault diagnosis model, contained in second fault diagnosis model with it is each auxiliary in fuel cell system
Help the corresponding normal data of component；
The real-time running data for obtaining each accessory in fuel cell system, as the second fault diagnosis mould
The input parameter of type, and then obtain the fault diagnosis result of each accessory；In actual application, the fuel cell
System monitors each state parameter of pile and each accessory simultaneously.
In a kind of specific embodiment of the embodiment of the present invention, the accessory includes hydrogen gas circulating pump, air pressure
Contracting machine, heat exchanger, water pump, DC/DC boost converter；
The real-time running data of each accessory includes following parameter: hydrogen gas circulating pump revolving speed, inlet and outlet pressure, stream
Amount, air compressor revolving speed, inlet and outlet pressure, flow, heat exchanger inlet and outlet temperature, flow, pump rotary speed, inlet and outlet pressure,
Flow, DC/DC boost converter input voltage, output voltage, input power, output power；
For hydrogen gas circulating pump, air compressor and water pump, normal data refers to that flow and pressure under different rotating speeds close
It is curve；For heat exchanger, normal data refers to the relation curve of the coefficient of heat transfer and flow；For DC/DC boost converter, mark
Quasi- data refer to the relation curve of efficiency and voltage ratio；
The input parameter as second fault diagnosis model, and then the failure for obtaining each accessory is examined
It is disconnected as a result, specifically: the real-time running data of each accessory and the second fault diagnosis in the fuel cell system that will acquire
Whether existing normal data compares in model, be more than preset threshold value according to difference, to judge that accessory is
It is no to break down；More specifically:
For hydrogen gas circulating pump, air compressor, water pump: according to real-time revolving speed and flow, being looked on standard performance curve
Corresponding inlet and outlet pressure ratio is ask, is compared with the pressure ratio of real-time measurement；
For heat exchanger: according to real-time traffic, the corresponding coefficient of heat transfer is obtained according to standard performance data difference, and it is real-time
The coefficient of heat transfer of measurement is compared；
For DC/DC boost converter: according to real-time input voltage and output voltage, being obtained according to standard performance data interpolation
To corresponding energy conversion efficiency, it is compared with the energy conversion efficiency of real-time measurement.
When the difference of the real-time measuring data of each accessory and normal data is more than preset threshold value, illustrate assisted parts
Part breaks down.
It is described to obtain each accessory in fuel cell system in a kind of specific embodiment of the embodiment of the present invention
After real-time running data further include:
Real-Time Filtering is carried out to collected real-time running data, removes the high-frequency data of time domain data, prevents interference from believing
Number influence fault diagnosis result.Hardware filtering can be used by implementing filtering technique, can also use software filtering.
The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this
The principle of invention, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these changes
Change and improvement all fall within the protetion scope of the claimed invention.The claimed scope of the invention by appended claims and its
Equivalent thereof.
Claims (10)
1. a kind of on-line fault diagnosis method for fuel cell system, which comprises the following steps:
Fisrt fault diagnostic model is obtained, the Fisrt fault diagnostic model is based on the real time data of pile and machine learning side
Method obtains；The real time data of the pile is to test to obtain by pile benchmark test；
During operation of fuel cell system, the pile operation data of real-time measurement is obtained, is examined as the Fisrt fault
The input parameter of disconnected model, and then obtain the fault diagnosis result of pile.
2. a kind of on-line fault diagnosis method for fuel cell system according to claim 1, it is characterised in that: institute
State the acquisition step of Fisrt fault diagnostic model specifically:
The real-time regular picture floor data and fault condition data of pile are obtained, data set is formed；
The data set is divided into training data subset and verify data subset；
Selected machine learning model；
The machine learning model is trained using the training data subset；
The accuracy of machine learning model is verified using the verify data subset；
The structure that machine learning model is adjusted according to verification result is repeated training and verifying, finally obtains accuracy and meet
It is required that Fisrt fault diagnostic model.
3. a kind of on-line fault diagnosis method for fuel cell system according to claim 2, it is characterised in that: institute
The learning method for stating machine learning model is k nearest neighbor, Bayesian network, support vector machines, artificial neural network or deep learning
In any one.
4. a kind of on-line fault diagnosis method for fuel cell system according to claim 2, it is characterised in that: institute
It states during the structure of adjustment machine learning model using based on gradient descent method, Newton method, conjugate gradient method or something lost
Propagation algorithm.
5. a kind of on-line fault diagnosis method for fuel cell system described in any one of -4 according to claim 1,
Be characterized in that: the fault diagnosis result of the pile includes water logging, film dry, deficency, short circuit and/or catalyst poisoning.
6. a kind of on-line fault diagnosis method for fuel cell system according to claim 1, it is characterised in that: institute
It is further comprising the steps of to state method:
The second fault diagnosis model is obtained, is contained in second fault diagnosis model and assisted parts each in fuel cell system
The corresponding normal data of part；
The real-time running data for obtaining each accessory in fuel cell system, as second fault diagnosis model
Parameter is inputted, and then obtains the fault diagnosis result of each accessory.
7. a kind of on-line fault diagnosis method for fuel cell system according to claim 6, it is characterised in that: institute
State obtain pile real-time running data step and/or obtain fuel cell system in each accessory real-time running data it
Afterwards further include:
Real-Time Filtering is carried out to collected real-time running data, removes the high fdrequency component of time domain data.
8. a kind of on-line fault diagnosis method for fuel cell system according to claim 6, it is characterised in that: institute
The real-time running data for obtaining each accessory in fuel cell system is stated, as the defeated of second fault diagnosis model
Enter parameter, and then obtain the fault diagnosis result of each accessory, specifically:
Obtain the real-time running data of each accessory in fuel cell system；
Have in the real-time running data of each accessory and the second fault diagnosis model in the fuel cell system that will acquire
Normal data compare, whether be more than preset threshold value according to difference, to judge whether accessory breaks down.
9. a kind of on-line fault diagnosis method for fuel cell system according to claim 8, it is characterised in that: institute
Stating accessory includes hydrogen gas circulating pump, air compressor, heat exchanger, water pump, DC/DC boost converter；
For hydrogen gas circulating pump, air compressor and water pump, normal data refers to flow and pressure dependence song under different rotating speeds
Line；
For heat exchanger, normal data refers to the relation curve of the coefficient of heat transfer and flow；
For DC/DC boost converter, normal data refers to the relation curve of efficiency and voltage ratio.
10. a kind of on-line fault diagnosis method for fuel cell system according to claim 6, it is characterised in that:
The real-time running data of the pile include: electric current, voltage, the voltage of each battery unit, cathode and anode gas flow,
Out temperature, inlet and outlet pressure, inlet and outlet humidity, cooling water flow and/or cooling water outlet and inlet temperature；Each assisted parts
The real-time running data of part includes: hydrogen gas circulating pump revolving speed, inlet and outlet pressure, flow, air compressor revolving speed, inlet and outlet pressure
Power, flow, heat exchanger inlet and outlet temperature, flow, pump rotary speed, inlet and outlet pressure, flow, DC/DC boost converter input electricity
Pressure, output voltage, input power, output power.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910481798.9A CN110190306B (en) | 2019-06-04 | 2019-06-04 | Online fault diagnosis method for fuel cell system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910481798.9A CN110190306B (en) | 2019-06-04 | 2019-06-04 | Online fault diagnosis method for fuel cell system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110190306A true CN110190306A (en) | 2019-08-30 |
| CN110190306B CN110190306B (en) | 2022-08-05 |
Family
ID=67720217
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910481798.9A Active CN110190306B (en) | 2019-06-04 | 2019-06-04 | Online fault diagnosis method for fuel cell system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110190306B (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110632519A (en) * | 2019-09-30 | 2019-12-31 | 潍柴动力股份有限公司 | Fuel cell fault diagnosis method and apparatus |
| CN111029624A (en) * | 2019-12-12 | 2020-04-17 | 东风汽车集团有限公司 | System and method for on-line monitoring and recovering water state of fuel cell |
| CN111220913A (en) * | 2020-02-24 | 2020-06-02 | 上海捷氢科技有限公司 | Diagnostic device and diagnostic method for fuel cell stack system |
| CN111765102A (en) * | 2020-05-26 | 2020-10-13 | 稳力(广东)科技有限公司 | Fault diagnosis and protection system of air compressor for fuel cell system |
| CN111856299A (en) * | 2020-07-29 | 2020-10-30 | 中国联合网络通信集团有限公司 | Method, device and equipment for determining power supply state |
| CN112026524A (en) * | 2020-09-16 | 2020-12-04 | 浙江吉利控股集团有限公司 | Fault diagnosis and processing method and system for fuel cell vehicle |
| CN112133941A (en) * | 2020-10-10 | 2020-12-25 | 西南交通大学 | Rapid fault diagnosis method for locomotive proton exchange membrane fuel cell system |
| CN112186226A (en) * | 2020-09-24 | 2021-01-05 | 同济大学 | Fuel cell monomer gas deficiency diagnosis method |
| CN112946497A (en) * | 2020-12-04 | 2021-06-11 | 广东电网有限责任公司 | Storage battery fault diagnosis method and device based on fault injection deep learning |
| CN112993337A (en) * | 2019-12-14 | 2021-06-18 | 中国科学院大连化学物理研究所 | Water management fault diagnosis system suitable for fuel cell attenuation process |
| CN113561853A (en) * | 2021-06-08 | 2021-10-29 | 北京科技大学 | Online fault diagnosis method and device for fuel cell system |
| CN113659175A (en) * | 2021-10-19 | 2021-11-16 | 潍柴动力股份有限公司 | Self-diagnosis method and device for fuel cell stack and electronic equipment |
| CN114094150A (en) * | 2020-06-29 | 2022-02-25 | 中国科学院大连化学物理研究所 | Method for predicting optimal operation condition of flow battery cell stack based on machine learning |
| CN114843560A (en) * | 2022-05-19 | 2022-08-02 | 上海捷氢科技股份有限公司 | Method and device for diagnosing water flooding fault of fuel cell system |
| CN115000456A (en) * | 2022-05-12 | 2022-09-02 | 亿创氢能源科技(张家港)有限公司 | Short-circuit test method for electric pile in fuel cell system |
| CN115476734A (en) * | 2022-09-20 | 2022-12-16 | 中国汽车工程研究院股份有限公司 | Fuzzy reasoning based water management fault diagnosis method for fuel cell system |
| WO2023000985A1 (en) * | 2021-07-22 | 2023-01-26 | 中国第一汽车股份有限公司 | Method and apparatus for predicting remaining life of fuel cell |
| CN116231010A (en) * | 2023-05-10 | 2023-06-06 | 北京新研创能科技有限公司 | Fault diagnosis method and system for hydrogen fuel cell system |
| CN116505034A (en) * | 2023-06-28 | 2023-07-28 | 北京新研创能科技有限公司 | Safety management method and system for hydrogen fuel cell system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107180983A (en) * | 2017-05-16 | 2017-09-19 | 华中科技大学 | A kind of SOFC pile method for diagnosing faults and system |
| CN108344947A (en) * | 2018-01-11 | 2018-07-31 | 西南交通大学 | A kind of fuel cell diagnostic method of non-intrusion type |
-
2019
- 2019-06-04 CN CN201910481798.9A patent/CN110190306B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107180983A (en) * | 2017-05-16 | 2017-09-19 | 华中科技大学 | A kind of SOFC pile method for diagnosing faults and system |
| CN108344947A (en) * | 2018-01-11 | 2018-07-31 | 西南交通大学 | A kind of fuel cell diagnostic method of non-intrusion type |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110632519A (en) * | 2019-09-30 | 2019-12-31 | 潍柴动力股份有限公司 | Fuel cell fault diagnosis method and apparatus |
| CN111029624A (en) * | 2019-12-12 | 2020-04-17 | 东风汽车集团有限公司 | System and method for on-line monitoring and recovering water state of fuel cell |
| CN111029624B (en) * | 2019-12-12 | 2021-06-01 | 东风汽车集团有限公司 | System and method for on-line monitoring and recovering water state of fuel cell |
| CN112993337B (en) * | 2019-12-14 | 2022-05-17 | 中国科学院大连化学物理研究所 | Water management fault diagnosis system suitable for fuel cell attenuation process |
| CN112993337A (en) * | 2019-12-14 | 2021-06-18 | 中国科学院大连化学物理研究所 | Water management fault diagnosis system suitable for fuel cell attenuation process |
| CN111220913A (en) * | 2020-02-24 | 2020-06-02 | 上海捷氢科技有限公司 | Diagnostic device and diagnostic method for fuel cell stack system |
| CN111765102A (en) * | 2020-05-26 | 2020-10-13 | 稳力(广东)科技有限公司 | Fault diagnosis and protection system of air compressor for fuel cell system |
| CN111765102B (en) * | 2020-05-26 | 2021-04-30 | 稳力(广东)科技有限公司 | Fault diagnosis and protection system of air compressor for fuel cell system |
| CN114094150B (en) * | 2020-06-29 | 2023-11-17 | 中国科学院大连化学物理研究所 | Machine learning-based flow battery pile optimal operation condition prediction method |
| CN114094150A (en) * | 2020-06-29 | 2022-02-25 | 中国科学院大连化学物理研究所 | Method for predicting optimal operation condition of flow battery cell stack based on machine learning |
| CN111856299A (en) * | 2020-07-29 | 2020-10-30 | 中国联合网络通信集团有限公司 | Method, device and equipment for determining power supply state |
| CN112026524A (en) * | 2020-09-16 | 2020-12-04 | 浙江吉利控股集团有限公司 | Fault diagnosis and processing method and system for fuel cell vehicle |
| CN112186226A (en) * | 2020-09-24 | 2021-01-05 | 同济大学 | Fuel cell monomer gas deficiency diagnosis method |
| CN112186226B (en) * | 2020-09-24 | 2021-05-11 | 同济大学 | Fuel cell monomer gas deficiency diagnosis method |
| CN112133941A (en) * | 2020-10-10 | 2020-12-25 | 西南交通大学 | Rapid fault diagnosis method for locomotive proton exchange membrane fuel cell system |
| CN112946497A (en) * | 2020-12-04 | 2021-06-11 | 广东电网有限责任公司 | Storage battery fault diagnosis method and device based on fault injection deep learning |
| CN113561853A (en) * | 2021-06-08 | 2021-10-29 | 北京科技大学 | Online fault diagnosis method and device for fuel cell system |
| WO2023000985A1 (en) * | 2021-07-22 | 2023-01-26 | 中国第一汽车股份有限公司 | Method and apparatus for predicting remaining life of fuel cell |
| CN113659175A (en) * | 2021-10-19 | 2021-11-16 | 潍柴动力股份有限公司 | Self-diagnosis method and device for fuel cell stack and electronic equipment |
| CN113659175B (en) * | 2021-10-19 | 2022-04-05 | 潍柴动力股份有限公司 | Self-diagnosis method and device for fuel cell stack and electronic equipment |
| CN115000456A (en) * | 2022-05-12 | 2022-09-02 | 亿创氢能源科技(张家港)有限公司 | Short-circuit test method for electric pile in fuel cell system |
| CN114843560A (en) * | 2022-05-19 | 2022-08-02 | 上海捷氢科技股份有限公司 | Method and device for diagnosing water flooding fault of fuel cell system |
| CN115476734A (en) * | 2022-09-20 | 2022-12-16 | 中国汽车工程研究院股份有限公司 | Fuzzy reasoning based water management fault diagnosis method for fuel cell system |
| CN115476734B (en) * | 2022-09-20 | 2023-05-23 | 中国汽车工程研究院股份有限公司 | Fuzzy reasoning-based fuel cell system water management fault diagnosis method |
| CN116231010A (en) * | 2023-05-10 | 2023-06-06 | 北京新研创能科技有限公司 | Fault diagnosis method and system for hydrogen fuel cell system |
| CN116505034A (en) * | 2023-06-28 | 2023-07-28 | 北京新研创能科技有限公司 | Safety management method and system for hydrogen fuel cell system |
| CN116505034B (en) * | 2023-06-28 | 2023-09-15 | 北京新研创能科技有限公司 | Safety management method and system for hydrogen fuel cell system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110190306B (en) | 2022-08-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110190306A (en) | A kind of on-line fault diagnosis method for fuel cell system | |
| CN109726452B (en) | Online proton exchange membrane fuel cell fault diagnosis method based on impedance spectrum | |
| Yang et al. | On-board diagnosis of soft short circuit fault in lithium-ion battery packs for electric vehicles using an extended Kalman filter | |
| CN104391189B (en) | Large-sized photovoltaic array fault diagnosis localization method based on three-level diagnosis | |
| CN105846780A (en) | Decision tree model-based photovoltaic assembly fault diagnosis method | |
| CN103925155B (en) | The self-adapting detecting method that a kind of Wind turbines output is abnormal | |
| CN113782778B (en) | Electric pile water management regulation and control method and device based on fixed frequency impedance and gas pressure drop | |
| CN113447828B (en) | Lithium battery temperature estimation method and system based on Bayesian neural network | |
| CN110970679B (en) | Battery pack temperature sensor rationality diagnosis method based on thermal symmetry | |
| CN104767482A (en) | Method for diagnosing aging and short circuit of photovoltaic module online | |
| CN213583883U (en) | Thermal management test system for vehicle hydrogen fuel cell | |
| CN112331888A (en) | Fuel cell stack simulator based on simulation model | |
| CN116629120A (en) | Heat dissipation evaluation method and system for dry type power transformer | |
| CN113611900A (en) | Membrane dry fault diagnosis method of proton exchange membrane fuel cell | |
| Peng et al. | Generalized spatial–temporal fault location method for solid oxide fuel cells using LSTM and causal inference | |
| Huang et al. | Correlation analysis and prediction of PEM fuel cell voltage during start-stop operation based on real-world driving data | |
| CN112448005B (en) | Temperature fault-tolerant control method for failure of fuel cell engine stack-out temperature sensor | |
| CN113128005A (en) | Power grid node clustering and frequency safety analysis method and system based on dynamic characteristics | |
| CN112051082A (en) | Fault diagnosis method in operation of heat exchanger of heat supply system | |
| CN113571742A (en) | Fault diagnosis method and device for fuel cell thermal management system | |
| Dong et al. | Design of PHM test verification method and system for aviation electrical system | |
| CN112234940B (en) | Inverter output power abnormity early warning method considering power limit and operation efficiency | |
| Xia et al. | Fast Fault Diagnosis for Proton Exchange Membrane Fuel Cells based on an Electrochemical Impedance Spectroscopy Measurement | |
| CN117668739B (en) | Hydroelectric generating set fault diagnosis method and system based on characteristic samples | |
| CN117117258B (en) | Fault monitoring method and device for hydrogen fuel cell system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230904 Address after: No. 1-251, No. 129, South Section of Hanguang Road, Yanta District, Xi'an City, Shaanxi Province, 710000 Patentee after: Zhao Guilan Address before: 215300 Room 315, Room A3, Room 268 Dengyun Road, Yushan Town, Kunshan City, Suzhou City, Jiangsu Province Patentee before: Kunshan Zhihydrogen Information Technology Co.,Ltd. |