CN109888338A - SOFC gas supply fault detection method and equipment based on statistics - Google Patents
SOFC gas supply fault detection method and equipment based on statistics Download PDFInfo
- Publication number
- CN109888338A CN109888338A CN201910125727.5A CN201910125727A CN109888338A CN 109888338 A CN109888338 A CN 109888338A CN 201910125727 A CN201910125727 A CN 201910125727A CN 109888338 A CN109888338 A CN 109888338A
- Authority
- CN
- China
- Prior art keywords
- sofc
- coherent signal
- control limit
- data matrix
- dimensionality reduction
- 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
-
- 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
- Fuel Cell (AREA)
Abstract
The embodiment of the invention provides a kind of, and the SOFC based on statistics supplies fault detection method and equipment.The described method includes: according to the degree of correlation of acquisition signal, determine coherent signal, and input quantity and output quantity are divided to the coherent signal, coherent signal after being divided normalizes the data matrix of the coherent signal after the division, and carries out dimensionality reduction to the data matrix after normalization, obtain the normalization data matrix of dimensionality reduction, according to the normalization data matrix of the dimensionality reduction, determines upper control limit and lower control limit, finally obtain Fault Model;The coherent signal that will be acquired in real time inputs the Fault Model, if output result is between the upper control limit and lower control limit, it is determined that SOFC gas supply is normal.SOFC gas supply fault detection method and equipment provided in an embodiment of the present invention based on statistics, may be implemented effective detection of SOFC gas supply fault.
Description
Technical field
The present embodiments relate to technical field of electricity more particularly to a kind of SOFC based on statistics to supply fault detection side
Method and equipment.
Background technique
Solid oxide fuel battery system (SOFC) is a kind of cleaning, high efficiency, noiseless electricity generation system.SOFC system
The operation conditions of system steadily supplies important in inhibiting to electric power.
Traditional SOFC system detection method just for single pile, designs complicated poor universality mostly, and tests
Process is cumbersome, is unfavorable for the integrated disadvantage of test macro.And merely with SOFC system power KLR signal approach only to pile
Failure it is effective, judge SOFC system whether have elevated-temperature seal BOP (Balance of plant, i.e. workshop auxiliary control system
System) there are biggish limitations for failure or other control unit failures.And SOFC system power KLR signal approach needs to acquire electricity
Signal, voltage signal and pile internal driving are flowed, step is complicated, and when temperature fluctuation occurs in system, the signal of acquisition
It but will be influenced by internal system pressure, gas flow rate, and detection system also will receive shadow when internal system fluctuates
It rings.When the outside of detection system exists, when interfering excessive, interference signal can cover fault-signal, cause to misrepresent deliberately and fail to report, can not
Ensure the timely and accurately detection of failure.Therefore, finding one kind can realize in real-time working condition to SOFC gas supply fault
The method effectively detected, just become industry technical problem urgently to be resolved.
Summary of the invention
In view of the above-mentioned problems existing in the prior art, the embodiment of the invention provides a kind of, and the SOFC based on statistics supplies event
Hinder detection method and equipment.
In a first aspect, the embodiment provides a kind of, the SOFC based on statistics supplies fault detection method, comprising:
According to the degree of correlation of acquisition signal, coherent signal is determined, and input quantity and output quantity are divided to the coherent signal, divided
Coherent signal afterwards normalizes the data matrix of the coherent signal after the division, and to the data matrix after normalization into
Row dimensionality reduction obtains the normalization data matrix of dimensionality reduction, according to the normalization data matrix of the dimensionality reduction, determines upper control limit and control
Lower limit processed, finally obtains Fault Model;The coherent signal that will be acquired in real time inputs the Fault Model, if output
As a result between the upper control limit and lower control limit, it is determined that SOFC gas supply is normal;Wherein, the SOFC is soild oxide
Fuel cell system, the output result are statistical value.
Further, the determining coherent signal, and input quantity and output quantity are divided to the coherent signal, correspondingly,
The input quantity that coherent signal marks off, comprising: methane supply amount, reforming combustion room methane supply amount, Reformer air supply amount,
Bypass air supply amount, deionized water supply amount and discharge current amount.
Further, the determining coherent signal, and input quantity and output quantity are divided to the coherent signal, correspondingly,
The output quantity that coherent signal marks off, comprising: the temperature value of reformer, the temperature value of air heat exchanger, exhaust gas combustion chamber
The real-time voltage value of temperature value and pile.
Further, described and to after normalization data matrix carry out dimensionality reduction, obtain the normalization data matrix of dimensionality reduction,
Include:
Wherein, X'M, nFor the data matrix after normalization;WithFor pivot weight matrix and load matrix;
WithFor residual error weight matrix and load matrix;K is the dimension after dimensionality reduction;M is sampling number;N is measurand number.
Further, the k is according to X'm,nCovariance matrix obtain, comprising:
Wherein, λiFor with X'm,nThe relevant characteristic value of covariance matrix, and λ1>λ2>...>λn>0。
Further, the normalization data matrix according to the dimensionality reduction, determines upper control limit and lower control limit, packet
It includes:
Zm=(1- ω) * Zm-1+ωXm
Xm=(X'm,1+X'm,2+···+X'm,n-1+X'm,n)/n
Wherein, ω is weighted factor, and ω ∈ (0,1];ZmFor statistical value;Objective is the desired value of residual error;C is
Control bounds coefficient;θ0For the standard deviation of residual error;UCL is upper control limit;LCL is lower control limit;XmFor the number after normalization
According to the mean value of matrix.
Further, the SOFC based on statistics supplies fault detection method, further includes: the correlation that will be acquired in real time
Signal inputs the Fault Model, if output result is greater than the upper control limit or is less than the lower control limit, it is determined that
SOFC supplies failure.
Second aspect, the embodiment provides a kind of, and the SOFC based on statistics supplies fault detection means, comprising:
Fault Model obtains module, for the degree of correlation according to acquisition signal, determines coherent signal, and to the phase
OFF signal divides input quantity and output quantity, the coherent signal after being divided, by the data square of the coherent signal after the division
Battle array normalization, and dimensionality reduction is carried out to the data matrix after normalization, the normalization data matrix of dimensionality reduction is obtained, according to the dimensionality reduction
Normalization data matrix, determine upper control limit and lower control limit, finally obtain Fault Model;
Fault detection module, the coherent signal for that will acquire in real time, inputs the Fault Model, if output result
Between the upper control limit and lower control limit, it is determined that SOFC gas supply is normal;
Wherein, the SOFC is solid oxide fuel battery system, and the output result is statistical value.
The third aspect, the embodiment provides a kind of electronic equipment, comprising:
At least one processor;And
At least one processor being connect with processor communication, in which:
Memory is stored with the program instruction that can be executed by processor, and the instruction of processor caller is able to carry out first party
SOFC gas supply failure inspection in the various possible implementations in face provided by any possible implementation based on statistics
Survey method.
Fourth aspect, the embodiment provides a kind of non-transient computer readable storage medium, non-transient calculating
Machine readable storage medium storing program for executing stores computer instruction, and computer instruction makes the various possible realization sides of computer execution first aspect
SOFC in formula provided by any possible implementation based on statistics supplies fault detection method.
SOFC gas supply fault detection method and equipment provided in an embodiment of the present invention based on statistics, by solid oxidation
The signal of object fuel cell system SOFC is for statistical analysis, therefrom extracts the characteristic information in relation to influencing gas supply status,
The dimension of Judging fault is reduced, the operation trend of SOFC system index is excavated, in conjunction with machine learning, realizes that SOFC gas supplies
Answer effective detection of failure.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to do a simple introduction, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is that the SOFC provided in an embodiment of the present invention based on statistics supplies fault detection method flow chart;
Fig. 2 is gas supply fault detection entirety schematic diagram provided in an embodiment of the present invention;
Fig. 3 is gas supply fault detection effect diagram provided in an embodiment of the present invention;
Fig. 4 is that the SOFC provided in an embodiment of the present invention based on statistics supplies fault detection means structural schematic diagram;
Fig. 5 is the entity structure schematic diagram of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.In addition,
Technical characteristic in each embodiment or single embodiment provided by the invention can mutual any combination, to form feasible skill
Art scheme, but must be based on can be realized by those of ordinary skill in the art, when the combination of technical solution occur it is mutual
Contradiction or when cannot achieve, it will be understood that the combination of this technical solution is not present, also not the present invention claims protection scope
Within.
The embodiment of the invention provides a kind of, and the SOFC based on statistics supplies fault detection method, referring to Fig. 1, this method packet
It includes:
101, it according to the degree of correlation of acquisition signal, determines coherent signal, and input quantity and defeated is divided to the coherent signal
Output, the coherent signal after being divided normalize the data matrix of the coherent signal after the division, and to normalization after
Data matrix carry out dimensionality reduction, obtain the normalization data matrix of dimensionality reduction, according to the normalization data matrix of the dimensionality reduction, determine
Upper control limit and lower control limit, finally obtain Fault Model;
102, the coherent signal that will be acquired in real time inputs the Fault Model, if output result is in the control
Between limit and lower control limit, it is determined that SOFC gas supply is normal.
Wherein, the SOFC is solid oxide fuel battery system, and the output result is statistical value.
On the basis of the above embodiments, the SOFC gas supply fault detection side based on statistics provided in the embodiment of the present invention
Method, the determining coherent signal, and input quantity and output quantity are divided to the coherent signal, correspondingly, coherent signal marks off
Input quantity, comprising: methane supply amount, reforming combustion room methane supply amount, Reformer air supply amount, bypass air supply
Amount, deionized water supply amount and discharge current amount.
On the basis of the above embodiments, the SOFC gas supply fault detection side based on statistics provided in the embodiment of the present invention
Method, the determining coherent signal, and input quantity and output quantity are divided to the coherent signal, correspondingly, coherent signal marks off
Output quantity, comprising: the temperature value of reformer, the temperature value of air heat exchanger, the temperature value of exhaust gas combustion chamber and pile
Real-time voltage value.
On the basis of the above embodiments, the SOFC gas supply fault detection side based on statistics provided in the embodiment of the present invention
Method, it is described and to after normalization data matrix carry out dimensionality reduction, obtain the normalization data matrix of dimensionality reduction, comprising:
Wherein, X'm,nFor the data matrix after normalization;WithFor pivot weight matrix and load matrix;
WithFor residual error weight matrix and load matrix;K is the dimension after dimensionality reduction;M is sampling number;N is measurand number.
On the basis of the above embodiments, the SOFC gas supply fault detection side based on statistics provided in the embodiment of the present invention
Method, the k is according to X'm,nCovariance matrix obtain, comprising:
Wherein, λiFor with X'm,nThe relevant characteristic value of covariance matrix, and λ1>λ2>...>λn>0。
On the basis of the above embodiments, the SOFC gas supply fault detection side based on statistics provided in the embodiment of the present invention
Method, the normalization data matrix according to the dimensionality reduction, determines upper control limit and lower control limit, comprising:
Zm=(1- ω) * Zm-1+ωXm
Xm=(X'm,1+X'm,2+···+X'm,n-1+X'm,n)/n
Wherein, ω is weighted factor, and ω ∈ (0,1];ZmFor statistical value;Objective is the desired value of residual error;C is
Control bounds coefficient;θ0For the standard deviation of residual error;UCL is upper control limit;LCL is lower control limit;XmFor the number after normalization
According to the mean value of matrix.
On the basis of the above embodiments, the SOFC gas supply fault detection side based on statistics provided in the embodiment of the present invention
Method, further includes: the coherent signal that will be acquired in real time inputs the Fault Model, if output result is greater than in the control
Limit is less than the lower control limit, it is determined that SOFC supplies failure.
SOFC provided in an embodiment of the present invention based on statistics supplies fault detection method, by solid oxide fuel
The signal of battery system SOFC is for statistical analysis, therefrom extracts the characteristic information in relation to influencing gas supply status, and reduction is sentenced
The dimension of other failure excavates the operation trend of SOFC system index, in conjunction with machine learning, realizes SOFC gas supply fault
Effective detection.
For the essence for the elaboration technical solution of the present invention being more clear, on the basis of the above embodiments, intend proposing
The embodiment of one entirety shows the overall picture of technical solution of the present invention on the whole.It should be noted that the whole implementation example is only
It is not limiting the scope of the invention, this field merely to technological essence of the invention is further embodied
Technical staff is on the basis of each embodiment of the invention, and by combination technique feature, what is obtained any meets the technology of the present invention
The combined technical solution of scheme essence, if can actual implementation, within the protection domain of this patent..
Sample collection is as shown in Fig. 2, whole system is divided into 1. data predictions;2.PCA model training;3.EWMA model is tested
Card, a total of three part.The historical data format of SOFC system operation are as follows: each signal data is with time series according to input
The mode tissue of output pair.The SOFC signal data of acquisition has: cathode air supply amount, bypass air supply amount, reforming combustion
Fuel feed, reforming reaction fuel feed deionized water supply amount, SOFC stack temperature, fuel-air heat exchange temperature,
Air heat exchanger temperature value, exhaust gas combustion chamber temperature value, reformer temperature, discharge current amount, discharge voltage and power, methane supply
To amount, reforming combustion room methane supply amount, Reformer air supply amount, the temperature value of reformer and the real-time voltage of pile
Value.
The correlation in above-mentioned acquisition signal between every two signal is calculated, according to resulting related coefficient, by the degree of correlation
Variable greater than 0.9 retains one.Signal is after relevant treatment, in above-mentioned variable, the correlation of discharge current amount and power
More than 0.9, the two retains one;Every two between fuel-air heat exchange temperature, air heat exchanger temperature and SOFC stack temperature
A related coefficient is all larger than 0.9, only retains one.Therefore it is left 10 variable signals, divides input quantity and defeated to it respectively
Output.
Input is methane supply amount, reforming combustion room methane supply amount, Reformer air supply amount, bypass air supply
Amount, deionized water supply amount, discharge current amount export the temperature value for reformer, the temperature value of air heat exchanger, tail gas combustion
Burn the temperature value of room and the real-time voltage value of pile;So far the data prediction in Fig. 2 is completed.By 80% conduct of whole samples
Training sample, remaining 20% is used as test sample.
The data matrix X of acquisitionm,nIn m be sampling number, n be measurand number.Before carrying out pivot analysis, because same
The dimension that one variable uses is different, need to be to Xm,nIt is normalized, to eliminate the influence of practical dimension, i.e., by each variable
It subtracts after its mean value divided by its standard deviation (so far completing the matrix normalization in Fig. 2).Treated, and matrix is denoted as X'm,n, PCA
By matrix X' after pretreatmentm,nBe decomposed into (i.e. load matrix) k (k≤min { m, n }) to the vector product of vector andAnd one
Residual matrix Em,n:
Wherein, estimated valueResidual matrix WithRespectively indicate pivot power
Weight matrix and load matrix,WithResidual error weight matrix and load matrix are respectively represented, and k is expressed as host element
Number.
K value also illustrates that former observation data matrix intends the dimension after dimensionality reduction, and optimal value can be according to the accumulative ratio of equation
It obtains, it may be assumed that
Wherein eigenvalue λi(i ∈ [1, n]) and X'm,nCovariance matrix it is related, amplitude λ1>λ2>...>λn>0。
According to the data after dimensionality reduction, EWMA (i.e. EWMA control figure) calculation formula is substituted into:
Zm=(1- ω) * Zm-1+ωXm
Wherein, ω (ω ∈ (0,1]) is weighted factor, for determining the mean value X of Current observation valuemWeight Xm=(X'm,1
+X'm,2+···+X'm,n-1+X'm,n)/n。
The EWMA value of current data can be obtained.
Wherein, Objective is the desired value of residual error, and c is the control bounds coefficient of EWMA, θ0It is the standard of residual error
Difference.UCL is the abbreviation of upper control limit, is for upper control limit;LCL is the abbreviation of low control limit,
It is for lower control limit.
If statistical value ZmGreater than UCL or it is less than LCL, then observation should be considered as fault detection task
Abnormal observed value, it is meant that detect failure.As EWMA value (Zm) positioned at when controlling in limit, it is believed that current SOFC system operated
Journey is in normal operating conditions.Specifically, two steps are segmented into Fig. 2 to be judged.If ZmValue be judged as it is no it is out of control (
EWMA model Qualify Phase), the pretreated part of returned data re-executes new SOFC signal data pretreatment.If ZmIt is worth quilt
Be determined as it is out of control, then can also pass into next layer threshold vector judgement, if controlled after being loaded with new threshold vector by EWMA
After the calculating of drawing, still it is determined as out of control, then carries out fault warning, and it is faulty for exporting failure detection result;By
After the calculating of EWMA control figure, if it is determined that then exporting failure detection result is fault-free to be no longer out of control.
When actually detected, the sample data acquired in real time is successively input to pca model and EWMA model, training is completed
Afterwards, it is taken in control bound, if being considered as system within control line range and being in normal condition, conversely, system
Failure occurs.
The SOFC based on statistics that whole implementation example of the invention provides supplies fault detection method, and detection effect is as schemed
It include: that point 304 occurs for lower control limit 301, upper control limit 302, EWMA curve 303 and failure shown in 3, in Fig. 3.Wherein, horizontal axis
For time (unit is the second), the longitudinal axis is EWMA value.As seen from Figure 3, EWMA curve 303 has in initial segment and vibrates in short-term, warp
After crossing adjustment, solid oxide fuel battery system enters the normal condition of failure-free operation, in solid oxide fuel cell
It when being about 10000 seconds when system is run to, breaks down, i.e., failure occurs to break down at point 304, subsequently enters failure operation
Segment, and over time, fault level can be higher and higher, at 24000 seconds, rises to from malfunction grade 1
Malfunction grade 2.
The optimized integration of each embodiment of the present invention is the processing that sequencing is carried out by the equipment with processor function
It realizes.Therefore engineering in practice, can be by the technical solution of each embodiment of the present invention and its function package at various moulds
Block.Based on this reality, on the basis of the various embodiments described above, the embodiment provides a kind of based on statistics
SOFC supplies fault detection means, which is used to execute the SOFC gas supply failure inspection based on statistics in above method embodiment
Survey method.Referring to fig. 4, which includes:
Fault Model obtains module 401, for the degree of correlation according to acquisition signal, determines coherent signal, and to institute
It states coherent signal and divides input quantity and output quantity, the coherent signal after being divided, by the number of the coherent signal after the division
Dimensionality reduction is carried out according to matrix normalization, and to the data matrix after normalization, the normalization data matrix of dimensionality reduction is obtained, according to described
The normalization data matrix of dimensionality reduction, determines upper control limit and lower control limit, finally obtains Fault Model;
Fault detection module 402, the coherent signal for that will acquire in real time, inputs the Fault Model, if output
As a result between the upper control limit and lower control limit, it is determined that SOFC gas supply is normal;
Wherein, the SOFC is solid oxide fuel battery system, and the output result is statistical value.
SOFC provided in an embodiment of the present invention based on statistics supplies fault detection means, is obtained using Fault Model
Module and fault detection module, Cong Zhongti for statistical analysis by the signal to solid oxide fuel battery system SOFC
The characteristic information in relation to influencing gas supply status is taken, the dimension of Judging fault is reduced, excavates the fortune of SOFC system index
Row trend realizes effective detection of SOFC gas supply fault in conjunction with machine learning.
The method of the embodiment of the present invention is to rely on electronic equipment to realize, therefore it is necessary to do one to relevant electronic equipment
Lower introduction.Based on this purpose, the embodiment provides a kind of electronic equipment, as shown in figure 5, the electronic equipment includes:
At least one processor (processor) 501, communication interface (Communications Interface) 504, at least one deposits
Reservoir (memory) 502 and communication bus 503, wherein at least one processor 501, communication interface 504, at least one storage
Device 502 completes mutual communication by communication bus 503.At least one processor 501 can call at least one processor
Logical order in 502, to execute following method: according to the degree of correlation of acquisition signal, determining coherent signal, and to the correlation
Signal divides input quantity and output quantity, the coherent signal after being divided, by the data matrix of the coherent signal after the division
Normalization, and dimensionality reduction is carried out to the data matrix after normalization, the normalization data matrix of dimensionality reduction is obtained, according to the dimensionality reduction
Normalization data matrix determines upper control limit and lower control limit, finally obtains Fault Model;The correlation letter that will be acquired in real time
Number, the Fault Model is inputted, if output result is between the upper control limit and lower control limit, it is determined that SOFC gas supply
Normally;Wherein, the SOFC is solid oxide fuel battery system, and the output result is statistical value.
In addition, the logical order in above-mentioned at least one processor 502 can be real by way of SFU software functional unit
Now and when sold or used as an independent product, it can store in a computer readable storage medium.Based in this way
Understanding, the technical solution of the present invention substantially portion of the part that contributes to existing technology or the technical solution in other words
Dividing can be embodied in the form of software products, which is stored in a storage medium, including several
Instruction is used so that a computer equipment (can be personal computer, server or the network equipment etc.) executes the present invention
The all or part of the steps of each embodiment the method.For example, according to the degree of correlation of acquisition signal, determine related letter
Number, and input quantity and output quantity are divided to the coherent signal, the coherent signal after being divided, by the correlation after the division
The data matrix of signal normalizes, and carries out dimensionality reduction to the data matrix after normalization, obtains the normalization data matrix of dimensionality reduction,
According to the normalization data matrix of the dimensionality reduction, determines upper control limit and lower control limit, finally obtain Fault Model;It will be real
When the coherent signal that acquires, input the Fault Model, if output result between the upper control limit and lower control limit,
Then determine that SOFC gas supply is normal;Wherein, the SOFC is solid oxide fuel battery system, and the output result is statistics
Value.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), deposits at random
The various media that can store program code such as access to memory (RAM, Random Access Memory), magnetic or disk.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features;
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (10)
1. a kind of SOFC based on statistics supplies fault detection method characterized by comprising
According to the degree of correlation of acquisition signal, coherent signal is determined, and input quantity and output quantity are divided to the coherent signal, obtain
Coherent signal after division normalizes the data matrix of the coherent signal after the division, and to the data square after normalization
Battle array carries out dimensionality reduction, obtains the normalization data matrix of dimensionality reduction, according to the normalization data matrix of the dimensionality reduction, determines upper control limit
And lower control limit, finally obtain Fault Model;
The coherent signal that will be acquired in real time inputs the Fault Model, if output result is in the upper control limit and control
Between lower limit, it is determined that SOFC gas supply is normal;
Wherein, the SOFC is solid oxide fuel battery system, and the output result is statistical value.
2. the SOFC according to claim 1 based on statistics supplies fault detection method, which is characterized in that the determining phase
OFF signal, and input quantity and output quantity are divided to the coherent signal, correspondingly, the input quantity that coherent signal marks off, comprising:
Methane supply amount, reforming combustion room methane supply amount, Reformer air supply amount, bypass air supply amount, deionized water
Supply amount and discharge current amount.
3. the SOFC according to claim 1 based on statistics supplies fault detection method, which is characterized in that the determining phase
OFF signal, and input quantity and output quantity are divided to the coherent signal, correspondingly, the output quantity that coherent signal marks off, comprising:
The real-time voltage value of the temperature value of reformer, the temperature value of air heat exchanger, the temperature value of exhaust gas combustion chamber and pile.
4. SOFC according to claim 1 based on statistics supplies fault detection method, which is characterized in that described and to returning
Data matrix after one change carries out dimensionality reduction, obtains the normalization data matrix of dimensionality reduction, comprising:
Wherein, X'm,nFor the data matrix after normalization;WithFor pivot weight matrix and load matrix;With
For residual error weight matrix and load matrix;K is the dimension after dimensionality reduction;M is sampling number;N is measurand number.
5. SOFC according to claim 4 based on statistics supplies fault detection method, which is characterized in that the k according to
X'm,nCovariance matrix obtain, comprising:
Wherein, λiFor with X'm,nThe relevant characteristic value of covariance matrix, and λ1>λ2>...>λn>0。
6. the SOFC according to claim 5 based on statistics supplies fault detection method, which is characterized in that described according to institute
The normalization data matrix for stating dimensionality reduction, determines upper control limit and lower control limit, comprising:
Zm=(1- ω) * Zm-1+ωXm
Xm=(X'm,1+X'm,2+···+X'm,n-1+X'm,n)/n
Wherein, ω is weighted factor, and ω ∈ (0,1];ZmFor statistical value;Objective is the desired value of residual error;C is control side
Boundary's range factor;θ0For the standard deviation of residual error;UCL is upper control limit;LCL is lower control limit;XmFor the data matrix after normalization
Mean value.
7. the SOFC according to claim 1 based on statistics supplies fault detection method, which is characterized in that further include:
The coherent signal that will be acquired in real time inputs the Fault Model, if output result is greater than the upper control limit or small
In the lower control limit, it is determined that SOFC supplies failure.
8. a kind of SOFC based on statistics supplies fault detection means characterized by comprising
Fault Model obtains module, for the degree of correlation according to acquisition signal, determines coherent signal, and to the related letter
Number dividing input quantity and output quantity, the coherent signal after being divided returns the data matrix of the coherent signal after the division
One changes, and carries out dimensionality reduction to the data matrix after normalization, the normalization data matrix of dimensionality reduction is obtained, according to returning for the dimensionality reduction
One changes data matrix, determines upper control limit and lower control limit, finally obtains Fault Model;
Fault detection module, the coherent signal for that will acquire in real time, inputs the Fault Model, if output result is in institute
It states between upper control limit and lower control limit, it is determined that SOFC gas supply is normal;
Wherein, the SOFC is solid oxide fuel battery system, and the output result is statistical value.
9. a kind of electronic equipment characterized by comprising
At least one processor, at least one processor, communication interface and bus;Wherein,
The processor, memory, communication interface complete mutual communication by the bus;
The memory is stored with the program instruction that can be executed by the processor, and the processor calls described program instruction,
To execute method as described in any one of claim 1 to 7.
10. a kind of non-transient computer readable storage medium, which is characterized in that the non-transient computer readable storage medium is deposited
Computer instruction is stored up, the computer instruction makes the computer execute the method as described in any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910125727.5A CN109888338B (en) | 2019-02-20 | 2019-02-20 | SOFC (solid oxide fuel cell) gas supply fault detection method and equipment based on statistics |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910125727.5A CN109888338B (en) | 2019-02-20 | 2019-02-20 | SOFC (solid oxide fuel cell) gas supply fault detection method and equipment based on statistics |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109888338A true CN109888338A (en) | 2019-06-14 |
CN109888338B CN109888338B (en) | 2021-11-09 |
Family
ID=66928554
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910125727.5A Active CN109888338B (en) | 2019-02-20 | 2019-02-20 | SOFC (solid oxide fuel cell) gas supply fault detection method and equipment based on statistics |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109888338B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110783608A (en) * | 2019-10-12 | 2020-02-11 | 华中科技大学 | Method for processing faults of solid oxide fuel cell system |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101344789A (en) * | 2008-09-03 | 2009-01-14 | 天津市纽普兰环保发展有限公司 | Pneumatic conveying remote diagnosis control system |
CN101728556A (en) * | 2008-10-31 | 2010-06-09 | 通用汽车环球科技运作公司 | Method for remedial action in the event of the failure of the primary air flow measurement device in a fuel cell system |
CN104462846A (en) * | 2014-12-22 | 2015-03-25 | 山东鲁能软件技术有限公司 | Intelligent device failure diagnosis method based on support vector machine |
CN107991881A (en) * | 2017-12-20 | 2018-05-04 | 东南大学 | A kind of solid oxide fuel cell non-linear inhibition method based on multiple model predictive control |
KR20180080790A (en) * | 2017-01-05 | 2018-07-13 | 현대자동차주식회사 | Device for valve failure diagnosis and emergency driving of fuel cell air supply system |
WO2018136915A1 (en) * | 2017-01-23 | 2018-07-26 | Nrg Systems, Inc. | System and methods of novelty detection using non-parametric machine learning |
CN108615917A (en) * | 2018-04-11 | 2018-10-02 | 华中科技大学 | A kind of fault detection system and method for solid oxide fuel battery system |
JP2018181455A (en) * | 2017-04-05 | 2018-11-15 | 大阪瓦斯株式会社 | Solid oxide fuel cell system |
CN109101702A (en) * | 2018-07-23 | 2018-12-28 | 山东科技大学 | A kind of fault detection method based on time-constrain rarefaction representation and Feature Dimension Reduction |
-
2019
- 2019-02-20 CN CN201910125727.5A patent/CN109888338B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101344789A (en) * | 2008-09-03 | 2009-01-14 | 天津市纽普兰环保发展有限公司 | Pneumatic conveying remote diagnosis control system |
CN101728556A (en) * | 2008-10-31 | 2010-06-09 | 通用汽车环球科技运作公司 | Method for remedial action in the event of the failure of the primary air flow measurement device in a fuel cell system |
CN104462846A (en) * | 2014-12-22 | 2015-03-25 | 山东鲁能软件技术有限公司 | Intelligent device failure diagnosis method based on support vector machine |
KR20180080790A (en) * | 2017-01-05 | 2018-07-13 | 현대자동차주식회사 | Device for valve failure diagnosis and emergency driving of fuel cell air supply system |
WO2018136915A1 (en) * | 2017-01-23 | 2018-07-26 | Nrg Systems, Inc. | System and methods of novelty detection using non-parametric machine learning |
JP2018181455A (en) * | 2017-04-05 | 2018-11-15 | 大阪瓦斯株式会社 | Solid oxide fuel cell system |
CN107991881A (en) * | 2017-12-20 | 2018-05-04 | 东南大学 | A kind of solid oxide fuel cell non-linear inhibition method based on multiple model predictive control |
CN108615917A (en) * | 2018-04-11 | 2018-10-02 | 华中科技大学 | A kind of fault detection system and method for solid oxide fuel battery system |
CN109101702A (en) * | 2018-07-23 | 2018-12-28 | 山东科技大学 | A kind of fault detection method based on time-constrain rarefaction representation and Feature Dimension Reduction |
Non-Patent Citations (2)
Title |
---|
COSTAMAGNA, PAOLA ET AL: ""Data-driven techniques for fault diagnosis in power generation plants based on solid oxide fuel cells "", 《ENERGY CONVERSION AND MANAGEMENT》 * |
WU XIAOJUAN ET AL: ""Fault Diagnosis of Solid Oxide Fuel Cell Based on a Supervised Self-Organization Map Model"", 《JOURNAL OF FUEL CELL SCIENCE AND TECHNOLOGY》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110783608A (en) * | 2019-10-12 | 2020-02-11 | 华中科技大学 | Method for processing faults of solid oxide fuel cell system |
Also Published As
Publication number | Publication date |
---|---|
CN109888338B (en) | 2021-11-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111652496B (en) | Running risk assessment method and device based on network security situation awareness system | |
Yue et al. | Proton exchange membrane fuel cell system prognostics and decision-making: Current status and perspectives | |
Aydin et al. | Using LSTM networks to predict engine condition on large scale data processing framework | |
Rotondo et al. | Robust fault diagnosis of proton exchange membrane fuel cells using a Takagi-Sugeno interval observer approach | |
WO2020046286A1 (en) | Integrated cybersecurity risk assessment and state monitoring for electrical power grid | |
JP7460864B2 (en) | Method and apparatus for performing state classification of power grid assets | |
CN111709447A (en) | Power grid abnormality detection method and device, computer equipment and storage medium | |
CN107239876B (en) | Management method and system for aging life cycle of I & C equipment of nuclear power plant | |
CN116087787A (en) | Battery fault judging method and system based on principal component analysis method | |
CN115392037A (en) | Equipment fault prediction method, device, equipment and storage medium | |
CN114707834A (en) | Alarm reminding method and device and storage medium | |
CN116505034A (en) | Safety management method and system for hydrogen fuel cell system | |
Duan | Dynamic Bayesian monitoring and detection for partially observable machines under multivariate observations | |
CN117668706A (en) | Method and device for isolating memory faults of server, storage medium and electronic equipment | |
CN109888338A (en) | SOFC gas supply fault detection method and equipment based on statistics | |
CN117117258B (en) | Fault monitoring method and device for hydrogen fuel cell system | |
Chen et al. | Data-driven modeling and fault diagnosis for fuel cell vehicles using deep learning | |
CN117092445A (en) | Fault detection method and system of power distribution system based on big data | |
CN105759217B (en) | Online fault diagnosis method for lead-acid storage battery pack based on measurable data | |
CN112685904A (en) | Method and system for determining whole life cycle reliability of flexible direct current transmission system | |
CN113486553A (en) | Complex equipment reliability analysis method based on Thiessen polygon area division | |
CN112667707B (en) | Method, device, computer equipment and storage medium for processing table code data | |
Vasquez et al. | Chronicle based alarm management in startup and shutdown stages | |
Huang et al. | Dynamic plant-wide process monitoring based on distributed slow feature analysis with inter-unit dissimilarity | |
Guo et al. | A Study on Prediction of the Remaining Useful Life of PEMFC Based on Data-driven CNN-BILSTM |
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 |