CN109840593B - Method and apparatus for diagnosing solid oxide fuel cell system failure - Google Patents
Method and apparatus for diagnosing solid oxide fuel cell system failure Download PDFInfo
- Publication number
- CN109840593B CN109840593B CN201910081095.7A CN201910081095A CN109840593B CN 109840593 B CN109840593 B CN 109840593B CN 201910081095 A CN201910081095 A CN 201910081095A CN 109840593 B CN109840593 B CN 109840593B
- Authority
- CN
- China
- Prior art keywords
- fuel cell
- solid oxide
- oxide fuel
- neural network
- cell system
- 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.)
- Active
Links
- 239000000446 fuel Substances 0.000 title claims abstract description 89
- 239000007787 solid Substances 0.000 title claims abstract description 74
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000003745 diagnosis Methods 0.000 claims abstract description 67
- 238000003062 neural network model Methods 0.000 claims abstract description 59
- 238000012549 training Methods 0.000 claims abstract description 15
- 210000004027 cell Anatomy 0.000 claims description 69
- 230000006870 function Effects 0.000 claims description 27
- 238000002407 reforming Methods 0.000 claims description 12
- 230000004913 activation Effects 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 9
- 210000002569 neuron Anatomy 0.000 claims description 9
- 238000004088 simulation Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 4
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 abstract description 26
- 239000003345 natural gas Substances 0.000 abstract description 6
- 238000010801 machine learning Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 4
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 description 3
- 238000002485 combustion reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000007789 gas Substances 0.000 description 3
- 239000001257 hydrogen Substances 0.000 description 3
- 229910052739 hydrogen Inorganic materials 0.000 description 3
- 238000010248 power generation Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003487 electrochemical reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000007800 oxidant agent Substances 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 230000001590 oxidative effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- 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 embodiment of the invention provides a method and equipment for diagnosing faults of a solid oxide fuel cell system. Wherein the method comprises the following steps: obtaining a diagnosis sample set according to a solid oxide fuel cell system model, aiming at the diagnosis sample set, obtaining system parameters of a neural network model, and training the neural network model by adopting the system parameters and the diagnosis sample set to obtain a final fault diagnosis model; and collecting working data of the solid oxide fuel cell system in real time, and inputting the working data into the final fault diagnosis model to obtain the fault type of the solid oxide fuel cell system. According to the method and the device for diagnosing the faults of the solid oxide fuel cell system, provided by the embodiment of the invention, the machine learning classification method of the neural network model is adopted to classify and identify the solid oxide fuel cell system with natural gas or methane, so that the fault occurrence condition of the solid oxide fuel cell system can be effectively diagnosed.
Description
Technical Field
The embodiment of the invention relates to the technical field of fuel cells, in particular to a method and equipment for diagnosing faults of a solid oxide fuel cell system.
Background
A Solid Oxide Fuel Cell (SOFC) is a power generation device that directly converts chemical energy stored in fuel and oxidant into electric energy through electrochemical reaction, and is one of the most promising power generation modes at present due to its high efficiency and pollution-free characteristics. However, although some representative SOFC energy companies (mainly electric power supply departments and large automobile manufacturers) and scientific research institutions are becoming more and more sophisticated in technical development level, abundant results are obtained from single cell preparation, pile assembly and system integration operation, and international pile manufacturing technologies are also very mature, some can run for tens of thousands of hours, and system functions are not obviously degraded, but the data are obtained on a constant temperature test bench when the pile is in the optimal working condition. If the SOFC system is intended to be put into commercial use as soon as possible, it must be removed from the constant temperature test station. Therefore, studies on the failure damage phenomenon and failure diagnosis of the SOFC system must be paid attention to.
Although research has been conducted on SOFC systems, research on fault diagnosis of SOFCs is not so much and many are on stacks or single cell sheets. In addition, many scholars have studied systems using pure hydrogen as fuel, but because pure hydrogen is not easily available and has higher cost, the practical future has more application prospect as well as power generation systems with reforming (hydrogen production by partial oxidation reforming of natural gas and methane) using methane, natural gas and the like as fuel. Therefore, in order to remedy the above-mentioned shortcomings, finding a method for performing fault diagnosis on a methane reforming SOFC system with low operation cost is a technical problem of great concern in the industry.
Disclosure of Invention
In view of the foregoing problems in the prior art, embodiments of the present invention provide a method and apparatus for diagnosing a failure in a solid oxide fuel cell system.
In a first aspect, embodiments of the present invention provide a method of diagnosing a solid oxide fuel cell system failure, comprising: obtaining a diagnosis sample set according to a solid oxide fuel cell system model, aiming at the diagnosis sample set, obtaining system parameters of a neural network model, and training the neural network model by adopting the system parameters and the diagnosis sample set to obtain a final fault diagnosis model; and collecting working data of the solid oxide fuel cell system in real time, and inputting the working data into the final fault diagnosis model to obtain the fault type of the solid oxide fuel cell system.
Further, the obtaining a diagnostic sample set according to the solid oxide fuel cell system model includes: and performing simulation on the gas leakage fault and the normal working state of the fuel pipeline of the reforming chamber of the solid oxide fuel cell system model, and taking simulation data and experimental data as the diagnosis sample set.
Further, the obtaining the system parameters of the neural network model for the diagnosis sample set includes: and setting an input layer, an output layer, an hidden layer number, a hidden layer neuron number and an activation function of the neural network model according to the input-output corresponding relation of the diagnosis sample set.
Further, the setting the activation function of the neural network model includes:
wherein f is an activation function; z is the input variable for f.
Further, training the neural network model using the system parameters and the diagnostic sample set includes regularizing the neural network model:
F(w)=αE w +βE d
wherein F is an objective function; e (E) w Is the sum of squares of the connection weights; w (w) j The j-th connection weight value; e (E) d The mean square error of the neural network model response; alpha and beta are parameters of the objective function F.
Further, the α and β include:
wherein ,wMP Minimum value of objective function; gamma is the number of effective parameters of the neural network model.
In a second aspect, embodiments of the present invention provide an apparatus for diagnosing a malfunction of a solid oxide fuel cell system, comprising:
the fault diagnosis model acquisition module is used for acquiring a diagnosis sample set according to the solid oxide fuel cell system model, obtaining system parameters of a neural network model aiming at the diagnosis sample set, and training the neural network model by adopting the system parameters and the diagnosis sample set to obtain a final fault diagnosis model;
and the fault diagnosis execution module is used for collecting working data of the solid oxide fuel cell system in real time, and inputting the working data into the final fault diagnosis model to obtain the fault type of the solid oxide fuel cell system.
In a third aspect, an embodiment of the present invention provides an electronic device, including:
at least one processor; and
at least one memory communicatively coupled to the processor, wherein:
the memory stores program instructions executable by the processor to invoke the program instructions to perform a method of diagnosing a solid oxide fuel cell system failure provided by any of the various possible implementations of the first aspect.
In a fourth aspect, embodiments of the present invention provide a non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform a method of diagnosing a solid oxide fuel cell system failure provided by any of the various possible implementations of the first aspect.
According to the method and the device for diagnosing the faults of the solid oxide fuel cell system, provided by the embodiment of the invention, the machine learning classification method of the neural network model is adopted to classify and identify the solid oxide fuel cell system with natural gas or methane, so that the fault occurrence condition of the solid oxide fuel cell system can be effectively diagnosed.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief description will be given below of the drawings required for the embodiments or the prior art descriptions, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without any inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for diagnosing a solid oxide fuel cell system failure in accordance with an embodiment of the present invention;
FIG. 2 is a schematic diagram of a neural network model according to an embodiment of the present invention;
FIG. 3 is a schematic diagram showing the effect of diagnosing the leakage faults of the fuel pipeline of the reforming chamber according to the embodiment of the invention;
fig. 4 is a schematic structural diagram of an apparatus for diagnosing faults of a solid oxide fuel cell system according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an entity structure of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention. In addition, the technical features of the various embodiments or the single embodiments provided in the present invention may be combined with each other arbitrarily to form a feasible technical solution, but it is necessary to base that a person skilled in the art can implement the solution, and when the combination of the technical solutions contradicts or cannot implement the solution, it should be considered that the combination of the technical solutions does not exist and is not within the scope of protection claimed in the present invention.
An embodiment of the present invention provides a method for diagnosing a fault in a solid oxide fuel cell system, referring to fig. 1, the method includes:
101. obtaining a diagnosis sample set according to a solid oxide fuel cell system model, aiming at the diagnosis sample set, obtaining system parameters of a neural network model, and training the neural network model by adopting the system parameters and the diagnosis sample set to obtain a final fault diagnosis model;
102. and collecting working data of the solid oxide fuel cell system in real time, and inputting the working data into the final fault diagnosis model to obtain the fault type of the solid oxide fuel cell system.
On the basis of the above embodiment, the method for diagnosing a solid oxide fuel cell system fault provided in the embodiment of the present invention, where the obtaining a diagnostic sample set according to a solid oxide fuel cell system model includes: and performing simulation on the gas leakage fault and the normal working state of the fuel pipeline of the reforming chamber of the solid oxide fuel cell system model, and taking simulation data and experimental data as the diagnosis sample set.
On the basis of the above embodiment, the method for diagnosing a solid oxide fuel cell system fault provided in the embodiment of the present invention obtains, for the diagnostic sample set, system parameters of a neural network model, including: and setting an input layer, an output layer, an hidden layer number, a hidden layer neuron number and an activation function of the neural network model according to the input-output corresponding relation of the diagnosis sample set.
On the basis of the foregoing embodiments, the method for diagnosing a fault of a solid oxide fuel cell system provided in the embodiment of the present invention, where the setting of an activation function of a neural network model includes:
wherein f is an activation function; z is the input variable for f.
The standard BP algorithm is based on a gradient descent method, and network weight and threshold gradient are corrected by calculating an objective function. The BP algorithm consists of two parts, namely forward transfer of information and back propagation of errors. BP neural networks typically employ the mean square error (E d ) As a performance index:
wherein n is the total number of training set samples, t p For the expected output value of the p-th training, a p The actual output value for training for group p.
Although the BP network principle is simple, the problems of under fitting, over fitting, local minima and the like inevitably occur, so the invention uses the BP neural network model after Bayesian regularization optimization to carry out fault diagnosis. The neural network model is regularized in order to minimize the training objective function by an optimal weight set. Adding regularization term into objective function can make the connection weight with small effect tend to zero as much as possible, and on the premise of ensuring that the network meets fitting precision, redundant connection weight and neuron are cut off, and the complexity of the network is reduced to obtain better popularization.
Based on the above embodiments, the method for diagnosing a fault of a solid oxide fuel cell system provided in the embodiments of the present invention uses the system parameters and the diagnostic sample set to train the neural network model, including regularizing the neural network model:
F(w)=αE w +βE d
wherein F is an objective function; e (E) w Is the sum of squares of the connection weights; w (w) j The j-th connection weight value; e (E) d The mean square error of the neural network model response; alpha and beta are parameters of the objective function F.
On the basis of the above embodiments, the method for diagnosing a fault of a solid oxide fuel cell system provided in the embodiment of the present invention, the α and β include:
wherein ,wMP Minimum value of objective function; gamma is the number of effective parameters of the neural network model, and the specific expression is as follows:
γ=K-α·Trace(A -1 )
wherein K is the number of connection weights in the neural network model.
The above embodiments of the present invention are described in terms of a reformer chamber fuel conduit leakage failure and normal operating conditions of a solid oxide fuel cell system. The neural network model adopts a four-input two-output mode, and can be seen in fig. 2. In FIG. 2, the leftmost input layer of the neural network model is input with X 1 ,X 2 ,X 3 and X4 Is a signal input to the processor; the middle is an implicit layer comprising a plurality of layers, each neuron (the neurons are shown as circles in the figure) in each layer has a specific connection weight corresponding to the neuron, for example, W ii For the connection weight corresponding to the neuron of the ith row and ith column, W ik The connection weight corresponding to the neuron in the ith row and k column is obtained; the output layer is composed of two outputs, Y 1 and Y2 。
In the present invention, the hidden layer node number n hidden The empirical formula selected is as follows:
wherein ,nhidden Represents the number of hidden layer nodes, n in Represents the number of input layer nodes, n out The number of output layer nodes is represented, and alpha represents a constant with a value ranging from 1 to 10.
According to the method for diagnosing the faults of the solid oxide fuel cell system, provided by the embodiment of the invention, the solid oxide fuel cell system with natural gas or methane is classified and identified by adopting the machine learning classification method of the neural network model, so that the fault occurrence condition of the solid oxide fuel cell system can be effectively diagnosed.
In particular, the practical effect of performing fault diagnosis on the solid oxide fuel cell system in the various embodiments of the present invention may be seen in fig. 3. Fig. 3 includes: a reformer temperature profile 301 when the reformer chamber tube leaks and a reformer temperature profile 302 in normal conditions. The inputs include: combustor outlet temperature, system power, reformer temperature, and output voltage. The output state is: 0 represents the normal working state of the system, and 1 represents the gas leakage fault of the fuel pipeline of the reforming chamber. The hidden layer node is set to 8. After the parameters of the neural network model are set, real-time data of the outlet temperature of the combustion chamber, the power of the system, the temperature of the reformer and the output voltage of the system are passed through the neural network model, and the fault diagnosis is carried out to obtain whether the solid oxide fuel cell system is in a normal state or in a fuel pipeline leakage fault state of the reforming chamber at the moment. As can be seen in particular in fig. 3, over time (approximately over 1400 seconds), the reformer temperature profile 301 for the blow-by of the reformer tube corresponds to a substantially greater combustion chamber temperature than the reformer temperature profile 302 for the normal condition. This means that a large amount of air is mixed in the combustion chamber in the failure state (blow-by state), so that the fuel can be burned more sufficiently.
The implementation basis of the embodiments of the present invention is realized by a device with a processor function to perform programmed processing. Therefore, in engineering practice, the technical solutions and the functions of the embodiments of the present invention can be packaged into various modules. Based on this reality, on the basis of the above embodiments, the embodiments of the present invention provide an apparatus for diagnosing a solid oxide fuel cell system failure, which is used to perform the method for diagnosing a solid oxide fuel cell system failure in the above method embodiments. Referring to fig. 4, the apparatus includes:
the fault diagnosis model obtaining module 401 is configured to obtain a diagnosis sample set according to a solid oxide fuel cell system model, obtain system parameters of a neural network model for the diagnosis sample set, and train the neural network model by adopting the system parameters and the diagnosis sample set to obtain a final fault diagnosis model;
the fault diagnosis execution module 402 is configured to collect working data of the solid oxide fuel cell system in real time, and input the working data to the final fault diagnosis model to obtain a fault type of the solid oxide fuel cell system.
The device for diagnosing the faults of the solid oxide fuel cell system provided by the embodiment of the invention combines the fault diagnosis model acquisition module and the fault diagnosis execution module, and can effectively diagnose the fault occurrence condition of the solid oxide fuel cell system by classifying and identifying the solid oxide fuel cell system with natural gas or methane by adopting a machine learning classification method of a neural network model.
The method of the embodiment of the invention is realized by the electronic equipment, so that the related electronic equipment is necessary to be introduced. To this end, an embodiment of the present invention provides an electronic device, as shown in fig. 5, including: at least one processor (processor) 501, a communication interface (Communications Interface) 504, at least one memory (memory) 502 and a communication bus 503, wherein the at least one processor 501, the communication interface 504, and the at least one memory 502 are in communication with each other via the communication bus 503. The at least one processor 501 may invoke logic instructions in the at least one memory 502 to perform the following method: obtaining a diagnosis sample set according to a solid oxide fuel cell system model, aiming at the diagnosis sample set, obtaining system parameters of a neural network model, and training the neural network model by adopting the system parameters and the diagnosis sample set to obtain a final fault diagnosis model; and collecting working data of the solid oxide fuel cell system in real time, and inputting the working data into the final fault diagnosis model to obtain the fault type of the solid oxide fuel cell system.
Further, the logic instructions in the at least one memory 502 described above may be implemented in the form of software functional units and stored in a computer readable storage medium when sold or used as a stand alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. Examples include: obtaining a diagnosis sample set according to a solid oxide fuel cell system model, aiming at the diagnosis sample set, obtaining system parameters of a neural network model, and training the neural network model by adopting the system parameters and the diagnosis sample set to obtain a final fault diagnosis model; and collecting working data of the solid oxide fuel cell system in real time, and inputting the working data into the final fault diagnosis model to obtain the fault type of the solid oxide fuel cell system. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (6)
1. A method of diagnosing a solid oxide fuel cell system failure, comprising:
obtaining a diagnosis sample set according to a solid oxide fuel cell system model, aiming at the diagnosis sample set, obtaining system parameters of a neural network model, and training the neural network model by adopting the system parameters and the diagnosis sample set to obtain a final fault diagnosis model;
collecting working data of the solid oxide fuel cell system in real time, inputting the working data into the final fault diagnosis model to obtain the fault type of the solid oxide fuel cell system, wherein the neural network model adopts a four-input two-output mode, and input parameters comprise: combustor outlet temperature, system power, reformer temperature, output voltage, output state is: 0 represents the normal working state of the system, 1 represents the gas leakage fault of the fuel pipeline of the reforming chamber, and the hidden layer node is set to be 8;
the obtaining a diagnostic sample set according to the solid oxide fuel cell system model comprises:
performing simulation on the gas leakage fault and the normal working state of the fuel pipeline of the reforming chamber of the solid oxide fuel cell system model, and taking simulation data and experimental data as the diagnosis sample set;
training the neural network model using the system parameters and the diagnostic sample set, including regularizing the neural network model:
wherein F is an objective function; e (E) w Is the sum of squares of the connection weights; w (w) j The j-th connection weight value; e (E) d The mean square error of the neural network model response; and />Parameters for the objective function F;
the said and />Comprising:
wherein ,minimum value of objective function; />The number of effective parameters of the neural network model is expressed as follows:
wherein K is the number of connection weights in the neural network model.
2. The method of diagnosing a solid oxide fuel cell system failure in accordance with claim 1, wherein said deriving system parameters of a neural network model for said diagnostic sample set comprises:
and setting an input layer, an output layer, an hidden layer number, a hidden layer neuron number and an activation function of the neural network model according to the input-output corresponding relation of the diagnosis sample set.
3. The method for diagnosing a solid oxide fuel cell system as recited in claim 2, wherein the setting an activation function of the neural network model includes:
wherein ,is an activation function; z is->Is a variable of the input of (a).
4. An apparatus for diagnosing a solid oxide fuel cell system failure, comprising:
the fault diagnosis model acquisition module is used for acquiring a diagnosis sample set according to the solid oxide fuel cell system model, obtaining system parameters of a neural network model aiming at the diagnosis sample set, and training the neural network model by adopting the system parameters and the diagnosis sample set to obtain a final fault diagnosis model;
the fault diagnosis execution module is used for collecting working data of the solid oxide fuel cell system in real time, inputting the working data into the final fault diagnosis model to obtain a fault type of the solid oxide fuel cell system, wherein the neural network model adopts a four-input two-output mode, and input parameters comprise: combustor outlet temperature, system power, reformer temperature, output voltage, output state is: 0 represents the normal working state of the system, 1 represents the gas leakage fault of the fuel pipeline of the reforming chamber, and the hidden layer node is set to be 8;
the obtaining a diagnostic sample set according to the solid oxide fuel cell system model comprises:
performing simulation on the gas leakage fault and the normal working state of the fuel pipeline of the reforming chamber of the solid oxide fuel cell system model, and taking simulation data and experimental data as the diagnosis sample set;
training the neural network model using the system parameters and the diagnostic sample set, including regularizing the neural network model:
wherein F is an objective function; e (E) w Is the sum of squares of the connection weights; w (w) j The j-th connection weight value; e (E) d The mean square error of the neural network model response; and />Parameters for the objective function F;
the said and />Comprising:
wherein ,minimum value of objective function; />The number of effective parameters of the neural network model is expressed as follows:
wherein K is the number of connection weights in the neural network model.
5. An electronic device, comprising:
at least one processor, at least one memory, a communication interface, and a bus; wherein,
the processor, the memory and the communication interface complete the communication with each other through the bus;
the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the method of any of claims 1-3.
6. A non-transitory computer readable storage medium storing computer instructions that cause the computer to perform the method of any one of claims 1 to 3.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910081095.7A CN109840593B (en) | 2019-01-28 | 2019-01-28 | Method and apparatus for diagnosing solid oxide fuel cell system failure |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910081095.7A CN109840593B (en) | 2019-01-28 | 2019-01-28 | Method and apparatus for diagnosing solid oxide fuel cell system failure |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109840593A CN109840593A (en) | 2019-06-04 |
CN109840593B true CN109840593B (en) | 2023-09-05 |
Family
ID=66884276
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910081095.7A Active CN109840593B (en) | 2019-01-28 | 2019-01-28 | Method and apparatus for diagnosing solid oxide fuel cell system failure |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109840593B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110137547B (en) * | 2019-06-20 | 2022-04-26 | 华中科技大学鄂州工业技术研究院 | Method and device for controlling fuel cell system with reformer, and electronic apparatus |
CN110783608B (en) * | 2019-10-12 | 2021-02-09 | 华中科技大学 | Method for processing faults of solid oxide fuel cell system |
CN111310305B (en) * | 2020-01-19 | 2023-04-25 | 华中科技大学鄂州工业技术研究院 | Method for obtaining oscillation variable of solid oxide fuel cell system |
CN112736268B (en) * | 2020-12-17 | 2022-02-15 | 华中科技大学 | Control optimization method and system for prolonging service life of SOFC (solid oxide fuel cell) system |
CN113945569B (en) * | 2021-09-30 | 2023-12-26 | 河北建投新能源有限公司 | Fault detection method and device for ion membrane |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6391484B1 (en) * | 1999-07-06 | 2002-05-21 | General Motors Corporation | Fuel processor temperature monitoring and control |
EP2214239A1 (en) * | 2009-01-19 | 2010-08-04 | Truma Gerätetechnik GmbH & Co. KG | Device and method for supplying process water for a reformer fuel cell system |
CN103943873A (en) * | 2014-05-19 | 2014-07-23 | 哈尔滨工业大学 | MEMS (Micro-Electromechanical Systems) methanol reforming fuel cell system |
CN104037433A (en) * | 2014-05-30 | 2014-09-10 | 山东省科学院海洋仪器仪表研究所 | Fuel cell monitoring equipment for ocean buoy |
CN105706283A (en) * | 2013-11-06 | 2016-06-22 | 瓦特燃料电池公司 | Integrated gaseous fuel cpox reformer and fuel cell systems, and methods of producing electricity |
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 |
CN107422266A (en) * | 2017-03-15 | 2017-12-01 | 中国电力科学研究院 | A kind of method for diagnosing faults and device of high capacity cell energy-storage system |
-
2019
- 2019-01-28 CN CN201910081095.7A patent/CN109840593B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6391484B1 (en) * | 1999-07-06 | 2002-05-21 | General Motors Corporation | Fuel processor temperature monitoring and control |
EP2214239A1 (en) * | 2009-01-19 | 2010-08-04 | Truma Gerätetechnik GmbH & Co. KG | Device and method for supplying process water for a reformer fuel cell system |
CN105706283A (en) * | 2013-11-06 | 2016-06-22 | 瓦特燃料电池公司 | Integrated gaseous fuel cpox reformer and fuel cell systems, and methods of producing electricity |
CN103943873A (en) * | 2014-05-19 | 2014-07-23 | 哈尔滨工业大学 | MEMS (Micro-Electromechanical Systems) methanol reforming fuel cell system |
CN104037433A (en) * | 2014-05-30 | 2014-09-10 | 山东省科学院海洋仪器仪表研究所 | Fuel cell monitoring equipment for ocean buoy |
CN107422266A (en) * | 2017-03-15 | 2017-12-01 | 中国电力科学研究院 | A kind of method for diagnosing faults and device of high capacity cell energy-storage system |
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 |
Non-Patent Citations (1)
Title |
---|
固体氧化物燃料电池的故障预测;叶倩文;《中国优秀硕士学位论文全文数据库》;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN109840593A (en) | 2019-06-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109840593B (en) | Method and apparatus for diagnosing solid oxide fuel cell system failure | |
CN107180983B (en) | Fault diagnosis method and system for solid oxide fuel cell stack | |
CN110579709B (en) | Fault diagnosis method for proton exchange membrane fuel cell for tramcar | |
Zuo et al. | Data-driven flooding fault diagnosis method for proton-exchange membrane fuel cells using deep learning technologies | |
CN110879377B (en) | Metering device fault tracing method based on deep belief network | |
CN105719062B (en) | A kind of power grid risk considering double probability of malfunction characteristic and weak link appraisal procedure | |
Zhang et al. | Fault diagnosis of proton exchange membrane fuel cell system of tram based on information fusion and deep learning | |
CN112117475A (en) | Fault detection device and method for water management subsystem of fuel cell | |
CN111200141A (en) | Proton exchange membrane fuel cell performance prediction and optimization method based on deep belief network | |
Wang et al. | A deep transfer learning method for system-level fault diagnosis of nuclear power plants under different power levels | |
Won et al. | Hybrid diagnosis method for initial faults of air supply systems in proton exchange membrane fuel cells | |
CN113343581B (en) | Transformer fault diagnosis method based on graph Markov neural network | |
Gao et al. | Real-time long-term voltage stability assessment based on eGBDT for large-scale power system with high renewables penetration | |
CN114048772A (en) | Fault diagnosis method, system and storage medium for fuel cell device | |
CN111091141B (en) | Photovoltaic backboard fault diagnosis method based on layered Softmax | |
CN116562114A (en) | Power transformer fault diagnosis method based on graph convolution neural network | |
Quan et al. | Fault diagnosis in a current sensor and its application to fault-tolerant control for an air supply subsystem of a 50 kW-Grade fuel cell engine | |
Sun et al. | Fault diagnosis method for proton exchange membrane fuel cell system based on digital twin and unsupervised domain adaptive learning | |
Baraldi et al. | A method for estimating the confidence in the identification of nuclear transients by a bagged ensemble of FCM classifiers | |
CN113780537B (en) | Fault diagnosis method and device for proton exchange membrane fuel cell power generation system | |
Li et al. | Multi-time-step and multi-parameter prediction for real-world proton exchange membrane fuel cell vehicles (PEMFCVs) toward fault prognosis and energy consumption prediction | |
CN112507526B (en) | Performance prediction method and system for proton exchange fuel cell system | |
Bao et al. | Physics-Informed Machine Learning with Application to Solid Oxide Fuel Cell System Modeling and Optimization | |
Chen et al. | A coupled and interactive influence of operational parameters for optimizing power output of cleaner energy production systems under uncertain conditions | |
Yuan et al. | Fault classification of proton exchange membrane fuel cell based on convolutional neural network coupled with support vector machine |
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 |