CN109888338B - SOFC (solid oxide fuel cell) gas supply fault detection method and equipment based on statistics - Google Patents

SOFC (solid oxide fuel cell) gas supply fault detection method and equipment based on statistics Download PDF

Info

Publication number
CN109888338B
CN109888338B CN201910125727.5A CN201910125727A CN109888338B CN 109888338 B CN109888338 B CN 109888338B CN 201910125727 A CN201910125727 A CN 201910125727A CN 109888338 B CN109888338 B CN 109888338B
Authority
CN
China
Prior art keywords
sofc
supply
fault detection
control limit
data matrix
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
Application number
CN201910125727.5A
Other languages
Chinese (zh)
Other versions
CN109888338A (en
Inventor
李曦
吴肖龙
许元武
仲小博
赵东琦
邓忠华
付晓薇
蒋建华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huazhong University of Science and Technology
Ezhou Institute of Industrial Technology Huazhong University of Science and Technology
Original Assignee
Huazhong University of Science and Technology
Ezhou Institute of Industrial Technology Huazhong University of Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Huazhong University of Science and Technology, Ezhou Institute of Industrial Technology Huazhong University of Science and Technology filed Critical Huazhong University of Science and Technology
Priority to CN201910125727.5A priority Critical patent/CN109888338B/en
Publication of CN109888338A publication Critical patent/CN109888338A/en
Application granted granted Critical
Publication of CN109888338B publication Critical patent/CN109888338B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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 statistical-based SOFC gas supply fault detection method and device. The method comprises the following steps: determining a relevant signal according to the correlation degree of an acquired signal, dividing the input quantity and the output quantity of the relevant signal to obtain a divided relevant signal, normalizing a data matrix of the divided relevant signal, reducing the dimension of the normalized data matrix to obtain a dimension-reduced normalized data matrix, determining an upper control limit and a lower control limit according to the dimension-reduced normalized data matrix, and finally obtaining a fault detection model; and inputting the relevant signals acquired in real time into the fault detection model, and determining that the SOFC is normally supplied with gas if the output result is between the upper control limit and the lower control limit. The SOFC gas supply fault detection method and device based on statistics can realize effective detection of SOFC gas supply faults.

Description

SOFC (solid oxide fuel cell) gas supply fault detection method and equipment based on statistics
Technical Field
The embodiment of the invention relates to the technical field of electricity, in particular to a statistical-based SOFC gas supply fault detection method and device.
Background
A solid oxide fuel cell System (SOFC) is a clean, high efficiency, noise-free power generation system. The operation conditions of SOFC systems are of great importance for a smooth supply of electrical power.
Most of the traditional SOFC system test methods only aim at a single galvanic pile, and have the defects of complex design, poor universality, complicated test process and inconvenience for integration of a test system. And the SOFC system is only effective to the faults of the galvanic pile by using a current signal analysis method of the SOFC system, and whether the SOFC system has the faults of a high-temperature sealed BOP (Balance of plant) or other control units has larger limitation. The SOFC system current signal analysis method needs to collect current signals, voltage signals and internal resistance of a galvanic pile, the steps are complex, the collected signals are influenced by the internal pressure and the gas flow rate of the system when the temperature of the system fluctuates, and the detection system is influenced when the temperature of the system fluctuates. When the external part of the detection system has excessive interference, the interference signal can cover the fault signal, so that false report and missing report are caused, and timely and accurate detection of the fault cannot be guaranteed. Therefore, finding a method capable of effectively detecting the SOFC gas supply fault in real-time working conditions is an urgent technical problem in the industry.
Disclosure of Invention
In order to solve the above problems in the prior art, embodiments of the present invention provide a statistical-based SOFC gas supply fault detection method and apparatus.
In a first aspect, an embodiment of the present invention provides a statistical-based SOFC gas supply fault detection method, including: determining a relevant signal according to the correlation degree of an acquired signal, dividing the input quantity and the output quantity of the relevant signal to obtain a divided relevant signal, normalizing a data matrix of the divided relevant signal, reducing the dimension of the normalized data matrix to obtain a dimension-reduced normalized data matrix, determining an upper control limit and a lower control limit according to the dimension-reduced normalized data matrix, and finally obtaining a fault detection model; inputting the relevant signals acquired in real time into the fault detection model, and determining that the SOFC supplies normal air if the output result is between the upper control limit and the lower control limit; wherein, the SOFC is a solid oxide fuel cell system, and the output result is a statistic value.
Further, the determining a correlation signal and dividing the input quantity and the output quantity into the correlation signal, and accordingly, dividing the input quantity into the correlation signal, includes: methane supply, reformer air supply, bypass air supply, deionized water supply, and discharge current amount.
Further, the determining a correlation signal and dividing the input quantity and the output quantity into the correlation signal, and accordingly dividing the output quantity into the correlation signal, includes: the temperature value of the reformer, the temperature value of the air heat exchanger, the temperature value of the tail gas combustion chamber and the real-time voltage value of the galvanic pile.
Further, the performing dimension reduction on the normalized data matrix to obtain a dimension-reduced normalized data matrix includes:
Figure BDA0001973518510000021
Figure BDA0001973518510000022
Figure BDA0001973518510000023
wherein, X'm，nThe normalized data matrix is obtained;
Figure BDA0001973518510000024
and
Figure BDA0001973518510000025
the principal component weight matrix and the load matrix are used;
Figure BDA0001973518510000026
and
Figure BDA0001973518510000027
the residual error weight matrix and the load matrix are obtained; k is the dimensionality after dimensionality reduction; m is the sampling frequency; and n is the number of measurement variables.
Further, k is according to X'm,nThe covariance matrix of (a) is obtained, including:
Figure BDA0001973518510000028
wherein λ isiIs of and X'm,nIs a covariance matrix of1>λ2>...>λn>0。
Further, the determining an upper control limit and a lower control limit according to the dimension-reduced normalized data matrix includes:
Zm＝(1-ω)*Zm-1+ωXm
Xm＝(X'm,1+X'm,2+···+X'm,n-1+X'm,n)/n
Figure BDA0001973518510000029
Figure BDA0001973518510000031
where ω is a weighting factor and ω ∈ (0, 1)]；ZmIs a statistical value; objective is the expected value of the residual; c is a control boundary range coefficient; theta0Is the standard deviation of the residual error; UCL is the upper control limit; LCL is the lower control limit; xmIs the mean of the normalized data matrix.
Further, the statistical-based SOFC gas supply fault detection method further includes: and inputting the related signals acquired in real time into the fault detection model, and determining the SOFC gas supply fault if the output result is greater than the upper control limit or less than the lower control limit.
In a second aspect, an embodiment of the present invention provides a statistical-based SOFC gas supply failure detection apparatus, including:
the fault detection model acquisition module is used for determining related signals according to the correlation degree of the acquired signals, dividing input quantity and output quantity of the related signals to obtain divided related signals, normalizing the data matrix of the divided related signals, reducing dimensions of the normalized data matrix to obtain a dimension-reduced normalized data matrix, determining an upper control limit and a lower control limit according to the dimension-reduced normalized data matrix, and finally acquiring a fault detection model;
the fault detection module is used for inputting relevant signals acquired in real time into the fault detection model, and if the output result is between the upper control limit and the lower control limit, determining that the SOFC is normally supplied with gas;
wherein, the SOFC is a solid oxide fuel cell system, and the output result is a statistic value.
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, and the processor calls the program instructions to execute the statistical-based SOFC gas supply failure detection method provided by any one 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 for causing a computer to perform the statistical-based SOFC gas supply failure detection method provided in any one of the various possible implementations of the first aspect.
According to the SOFC gas supply fault detection method and device based on statistics, provided by the embodiment of the invention, the SOFC signal of the solid oxide fuel cell system is subjected to statistical analysis, the characteristic information about the influence on the gas supply state is extracted, the variable dimension for judging the fault is reduced, the operation trend of SOFC system indexes is excavated, and the effective detection of the SOFC gas supply fault is realized by combining machine learning.
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 to the drawings required for the description of the embodiments or the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flowchart of a statistical-based SOFC gas supply fault detection method according to an embodiment of the present invention;
FIG. 2 is an overall schematic diagram of the gas supply fault detection provided by the embodiment of the invention;
FIG. 3 is a schematic diagram illustrating an air supply failure detection effect according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a SOFC gas supply fault detection device based on statistics according to an embodiment of the present invention;
fig. 5 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention. In addition, technical features of various embodiments or individual embodiments provided by the invention can be arbitrarily combined with each other to form a feasible technical solution, but must be realized by a person skilled in the art, and when the technical solution combination is contradictory or cannot be realized, the technical solution combination is not considered to exist and is not within the protection scope of the present invention.
The embodiment of the invention provides a statistical-based SOFC gas supply fault detection method, and referring to FIG. 1, the method comprises the following steps:
101. determining a relevant signal according to the correlation degree of an acquired signal, dividing the input quantity and the output quantity of the relevant signal to obtain a divided relevant signal, normalizing a data matrix of the divided relevant signal, reducing the dimension of the normalized data matrix to obtain a dimension-reduced normalized data matrix, determining an upper control limit and a lower control limit according to the dimension-reduced normalized data matrix, and finally obtaining a fault detection model;
102. and inputting the relevant signals acquired in real time into the fault detection model, and determining that the SOFC is normally supplied with gas if the output result is between the upper control limit and the lower control limit.
Wherein, the SOFC is a solid oxide fuel cell system, and the output result is a statistic value.
On the basis of the foregoing embodiments, the SOFC gas supply failure detection method based on statistics provided in the embodiments of the present invention determines the relevant signal, and divides the relevant signal into the input amount and the output amount, and accordingly, the divided input amount of the relevant signal includes: methane supply, reformer air supply, bypass air supply, deionized water supply, and discharge current amount.
On the basis of the foregoing embodiments, the SOFC gas supply failure detection method based on statistics provided in the embodiments of the present invention, where the determining of the relevant signal and the dividing of the relevant signal into the input amount and the output amount are performed, and accordingly, the divided output amount of the relevant signal includes: the temperature value of the reformer, the temperature value of the air heat exchanger, the temperature value of the tail gas combustion chamber and the real-time voltage value of the galvanic pile.
On the basis of the foregoing embodiment, the SOFC gas supply fault detection method based on statistics provided in the embodiment of the present invention, where the dimension reduction is performed on the normalized data matrix to obtain a dimension-reduced normalized data matrix, includes:
Figure BDA0001973518510000051
Figure BDA0001973518510000052
Figure BDA0001973518510000053
wherein, X'm,nThe normalized data matrix is obtained;
Figure BDA0001973518510000054
and
Figure BDA0001973518510000055
the principal component weight matrix and the load matrix are used;
Figure BDA0001973518510000056
and
Figure BDA0001973518510000057
the residual error weight matrix and the load matrix are obtained; k is the dimensionality after dimensionality reduction; m is the sampling frequency; and n is the number of measurement variables.
On the basis of the foregoing embodiment, in the SOFC gas supply fault detection method based on statistics provided in the embodiment of the present invention, k is according to X'm,nThe covariance matrix of (a) is obtained, including:
Figure BDA0001973518510000061
wherein λ isiIs of and X'm,nIs a covariance matrix of1>λ2>...>λn>0。
On the basis of the foregoing embodiment, the statistical-based SOFC gas supply fault detection method provided in the embodiment of the present invention determines, according to the dimension-reduced normalized data matrix, an upper control limit and a lower control limit, including:
Zm＝(1-ω)*Zm-1+ωXm
Xm＝(X'm,1+X'm,2+···+X'm,n-1+X'm,n)/n
Figure BDA0001973518510000062
Figure BDA0001973518510000063
where ω is a weighting factor and ω ∈ (0, 1)]；ZmIs a statistical value; objective is the expected value of the residual; c is a control boundary range coefficient; theta0Is the standard deviation of the residual error; UCL is the upper control limit; LCL is the lower control limit; xmIs the mean of the normalized data matrix.
On the basis of the foregoing embodiment, the SOFC gas supply fault detection method based on statistics provided in the embodiment of the present invention further includes: and inputting the related signals acquired in real time into the fault detection model, and determining the SOFC gas supply fault if the output result is greater than the upper control limit or less than the lower control limit.
According to the SOFC gas supply fault detection method based on statistics, provided by the embodiment of the invention, through carrying out statistics analysis on signals of the SOFC of the solid oxide fuel cell system, characteristic information about the influence on the gas supply state is extracted, the variable dimension for judging the fault is reduced, the operation trend of SOFC system indexes is excavated, and the effective detection of the SOFC gas supply fault is realized by combining machine learning.
In order to more clearly illustrate the essence of the technical solution of the present invention, on the basis of the above-mentioned embodiments, an overall embodiment is proposed, which shows the overall view of the technical solution of the present invention. It should be noted that the whole embodiment is only for further embodying the technical essence of the present invention, and is not intended to limit the scope of the present invention, and those skilled in the art can obtain any combination type technical solution meeting the essence of the technical solution of the present invention by combining technical features based on the various embodiments of the present invention, and as long as the combined technical solution can be practically implemented, the combined technical solution is within the scope of the present patent.
Sample collection as shown in fig. 2, the whole system is divided into 1, data preprocessing; training a PCA model; EWMA model validation, three parts total. The historical data format for the SOFC system operation is: each piece of signal data is organized in a time series in a pattern of input-output pairs. The SOFC signal data collected include: cathode air supply, bypass air supply, reforming combustion fuel supply, reforming reaction fuel supply, deionized water supply, SOFC stack temperature, fuel air heat exchanger temperature, tail gas combustor temperature, reformer temperature, amount of discharge current, discharge voltage and power, methane supply, reforming combustor methane supply, reformer air supply, reformer temperature, and stack real-time voltage.
And calculating the correlation between every two signals in the acquired signals, and keeping one variable with the correlation degree larger than 0.9 according to the obtained correlation coefficient. After the signals are subjected to correlation processing, the correlation between the discharge current and the power in the variables exceeds 0.9, and one of the discharge current and the power is reserved; and the correlation coefficients of every two among the temperature of the fuel-air heat exchanger, the temperature of the air heat exchanger and the temperature of the SOFC stack are all larger than 0.9, and only one of the correlation coefficients is reserved. Thus, 10 variable signals are left, for which the input amount and the output amount are divided, respectively.
The temperature value of the reformer, the temperature value of the air heat exchanger, the temperature value of the tail gas combustor and the real-time voltage value of the electric pile are output; this completes the data preprocessing in fig. 2. 80% of all samples were used as training samples and the remaining 20% were used as test samples.
Collected data matrix Xm,nM in (1) is the sampling times, and n is the number of measurement variables. Before principal component analysis, X is required to be analyzed due to different dimensions of the same variablem,nNormalization is performed to eliminate the effect of the actual dimension by subtracting the mean value of each variable and dividing by the standard deviation (to this point, the matrix normalization in fig. 2 is completed). The processed matrix is denoted as X'm,nMatrix X 'after PCA Pre-treatment'm,nDecomposed as (i.e., loading the matrix) the sum of the vector products of k (k ≦ min { m, n }) versus the vector
Figure BDA0001973518510000071
And a residual matrix Em,n：
Figure BDA0001973518510000072
Wherein the estimated value
Figure BDA0001973518510000073
Residual matrix
Figure BDA0001973518510000074
Figure BDA0001973518510000075
And
Figure BDA0001973518510000076
respectively representing a principal component weight matrix and a load matrix,
Figure BDA0001973518510000077
and
Figure BDA0001973518510000078
respectively representing a residual weight matrix and a load matrix, and k is represented as the number of main elements.
The k value also represents the dimension of the original observation data matrix after dimension reduction, and the optimal value can be obtained according to the accumulative proportion of an equation, namely:
Figure BDA0001973518510000081
wherein the characteristic value lambdai(i∈[1，n]) And X'm,nOf the covariance matrix of (a), amplitude lambda1>λ2>...>λn>0。
Substituting the data after dimensionality reduction into an EWMA (EWMA control chart) calculation formula:
Zm＝(1-ω)*Zm-1+ωXm
wherein ω (ω ∈ (0, 1)]) As a weighting factor, for determining the mean value X of the current observationmWeight X ofm＝(X'm,1+X'm,2+···+X'm,n-1+X'm,n)/n。
The EWMA value of the current data can be obtained.
Figure BDA0001973518510000082
Figure BDA0001973518510000083
Where Objective is the desired value of the residual, c is the control boundary Range coefficient of the EWMA, θ0Is the standard deviation of the residual. UCL is an abbreviation for upper control limit, which is the upper control limit; LCL is an abbreviation for low control limit, which is the lower control limit.
If the statistical value ZmGreater than the UCL or less than the LCL, then the observations should be treated as anomalous observations for the fault detection task, meaning that a fault is detected. When EWMA value (Z)m) And when the SOFC system is within the control limit, the current SOFC system is considered to be in a normal working state in the operation process. Specifically, the judgment can be made in two steps in fig. 2. If Z ismThe value is judged not to be out of control (in the EWMA model verification stage), and the new SOFC signal data preprocessing is executed again after the data preprocessing part returns. If Z ismIf the value is judged to be out of control, the threshold vector judgment of the next layer can be entered, and if the threshold vector judgment is loadedAfter the new threshold vector is calculated and the EWMA control chart is calculated, if the situation is still judged to be out of control, a fault alarm is carried out, and a fault detection result is output to be a fault; and after calculation of the EWMA control chart, if the EWMA control chart is judged not to be out of control, outputting a fault detection result as no fault.
During actual detection, sample data acquired in real time are input into the PCA model and the EWMA model in sequence, after training is completed, the sample data are brought into upper and lower control limits, if the sample data are within the range of a control line, the system is considered to be in a normal state, otherwise, system faults occur.
The SOFC gas supply fault detection method based on statistics provided by the overall embodiment of the present invention has a detection effect as shown in fig. 3, where fig. 3 includes: a lower control limit 301, an upper control limit 302, an EWMA curve 303, and a fault occurrence point 304. Wherein the horizontal axis is time (in seconds) and the vertical axis is the EWMA value. As can be seen from fig. 3, the EWMA curve 303 oscillates in a short time in the initial segment, and after adjustment, the sofc system enters a normal state of fault-free operation, and when the sofc system operates for about 10000 seconds, a fault occurs, i.e., a fault occurs at the fault occurrence point 304, and then enters a fault operation segment, and the fault level increases with time, and at 24000 seconds, the fault level is raised from the fault level 1 to the fault level 2.
The implementation basis of the various embodiments of the present invention is realized by programmed processing performed by a device having a processor function. Therefore, in engineering practice, the technical solutions and functions thereof of the embodiments of the present invention can be packaged into various modules. Based on this reality, on the basis of the foregoing embodiments, embodiments of the present invention provide a statistics-based SOFC gas supply failure detection apparatus, which is used for executing the statistics-based SOFC gas supply failure detection method in the foregoing method embodiments. Referring to fig. 4, the apparatus includes:
a fault detection model obtaining module 401, configured to determine a relevant signal according to a correlation degree of an acquired signal, divide an input quantity and an output quantity of the relevant signal to obtain a divided relevant signal, normalize a data matrix of the divided relevant signal, perform dimension reduction on the normalized data matrix to obtain a dimension-reduced normalized data matrix, determine an upper control limit and a lower control limit according to the dimension-reduced normalized data matrix, and finally obtain a fault detection model;
a fault detection module 402, configured to input a relevant signal acquired in real time into the fault detection model, and determine that the SOFC gas supply is normal if an output result is between the upper control limit and the lower control limit;
wherein, the SOFC is a solid oxide fuel cell system, and the output result is a statistic value.
According to the SOFC gas supply fault detection device based on statistics, provided by the embodiment of the invention, the fault detection model acquisition module and the fault detection module are adopted, the signals of the SOFC of the solid oxide fuel cell system are subjected to statistical analysis, the characteristic information about the influence on the gas supply state is extracted, the variable dimension for judging the fault is reduced, the operation trend of the SOFC system index is excavated, and the effective detection of the SOFC gas supply fault is realized by combining machine learning.
The method of the embodiment of the invention is realized by depending on the electronic equipment, so that the related electronic equipment is necessarily introduced. To this end, an embodiment of the present invention provides an electronic apparatus, 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 through the communication bus 503. The at least one processor 501 may call logic instructions in the at least one memory 502 to perform the following method: determining a relevant signal according to the correlation degree of an acquired signal, dividing the input quantity and the output quantity of the relevant signal to obtain a divided relevant signal, normalizing a data matrix of the divided relevant signal, reducing the dimension of the normalized data matrix to obtain a dimension-reduced normalized data matrix, determining an upper control limit and a lower control limit according to the dimension-reduced normalized data matrix, and finally obtaining a fault detection model; inputting the relevant signals acquired in real time into the fault detection model, and determining that the SOFC supplies normal air if the output result is between the upper control limit and the lower control limit; wherein, the SOFC is a solid oxide fuel cell system, and the output result is a statistic value.
Furthermore, the logic instructions in the at least one memory 502 may be implemented in software functional units and stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. Examples include: determining a relevant signal according to the correlation degree of an acquired signal, dividing the input quantity and the output quantity of the relevant signal to obtain a divided relevant signal, normalizing a data matrix of the divided relevant signal, reducing the dimension of the normalized data matrix to obtain a dimension-reduced normalized data matrix, determining an upper control limit and a lower control limit according to the dimension-reduced normalized data matrix, and finally obtaining a fault detection model; inputting the relevant signals acquired in real time into the fault detection model, and determining that the SOFC supplies normal air if the output result is between the upper control limit and the lower control limit; wherein, the SOFC is a solid oxide fuel cell system, and the output result is a statistic value. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present 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 solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (8)

1. A statistical-based SOFC gas supply fault detection method is characterized by comprising the following steps:
determining a relevant signal according to the correlation degree of an acquired signal, dividing the input quantity and the output quantity of the relevant signal to obtain a divided relevant signal, normalizing a data matrix of the divided relevant signal, reducing the dimension of the normalized data matrix to obtain a dimension-reduced normalized data matrix, determining an upper control limit and a lower control limit according to the dimension-reduced normalized data matrix, and finally obtaining a fault detection model;
inputting the relevant signals acquired in real time into the fault detection model, and determining that the SOFC supplies normal air if the output result is between the upper control limit and the lower control limit;
wherein, the SOFC is a solid oxide fuel cell system, and the output result is a statistical value;
the acquiring signals comprises: a cathode air supply, a bypass air supply, a reforming combustion fuel supply, a reforming reaction fuel supply, a deionized water supply, a SOFC stack temperature, a fuel air heat exchanger temperature, an air heat exchanger temperature value, a tail gas combustor temperature value, a reformer temperature, a discharge current amount, a discharge voltage and power, a methane supply, a reforming combustor methane supply, a reformer air supply, a reformer temperature value, and a stack real-time voltage value;
the determining the relevant signal according to the correlation degree of the acquired signal comprises:
calculating the correlation between every two signals in the collected signals, and determining a correlation signal according to the obtained correlation coefficient;
dividing the input quantity and the output quantity of the relevant signal, wherein the corresponding divided input quantity of the relevant signal comprises the following steps: a supply of methane, a supply of reformer air, a supply of bypass air, a supply of deionized water, and an amount of discharge current;
the output quantity divided by the correlation signal comprises: the temperature value of the reformer, the temperature value of the air heat exchanger, the temperature value of the tail gas combustion chamber and the real-time voltage value of the galvanic pile.
2. The SOFC gas supply fault detection method based on statistics as recited in claim 1, wherein the dimension reduction is performed on the normalized data matrix to obtain a dimension-reduced normalized data matrix, comprising:
Figure FDA0003238088400000011
Figure FDA0003238088400000012
Figure FDA0003238088400000021
wherein, X'm,nThe normalized data matrix is obtained;
Figure FDA0003238088400000022
and
Figure FDA0003238088400000023
the principal component weight matrix and the load matrix are used;
Figure FDA0003238088400000024
and
Figure FDA0003238088400000025
the residual error weight matrix and the load matrix are obtained; k is the dimensionality after dimensionality reduction; m is the sampling frequency; and n is the number of measurement variables.
3. The statistical-based SOFC gas supply fault detection method of claim 2, wherein k is according to X'm,nThe covariance matrix of (a) is obtained, including:
Figure FDA0003238088400000026
wherein λ isiIs of and X'm,nIs a covariance matrix of1>λ2>...>λn>0。
4. The statistical-based SOFC gas supply fault detection method of claim 3, wherein determining an upper control limit and a lower control limit from the reduced-dimension normalized data matrix comprises:
Zm＝(1-ω)*Zm-1+ωXm
Xm＝(X'm,1+X'm,2+…+X'm,n-1+X'm,n)/n
Figure FDA0003238088400000027
Figure FDA0003238088400000028
where ω is a weighting factor and ω ∈ (0, 1)]；ZmIs a statistical value; objective is the expected value of the residual; c is a control boundary range coefficient; theta0Is the standard deviation of the residual error; UCL is the upper control limit; LCL is the lower control limit; xmIs the mean of the normalized data matrix.
5. The statistical-based SOFC gas supply fault detection method of claim 1, further comprising:
and inputting the related signals acquired in real time into the fault detection model, and determining the SOFC gas supply fault if the output result is greater than the upper control limit or less than the lower control limit.
6. A SOFC gas supply fault detection device based on statistics, characterized by includes:
the fault detection model acquisition module is used for determining related signals according to the correlation degree of the acquired signals, dividing input quantity and output quantity of the related signals to obtain divided related signals, normalizing the data matrix of the divided related signals, reducing dimensions of the normalized data matrix to obtain a dimension-reduced normalized data matrix, determining an upper control limit and a lower control limit according to the dimension-reduced normalized data matrix, and finally acquiring a fault detection model;
the fault detection module is used for inputting relevant signals acquired in real time into the fault detection model, and if the output result is between the upper control limit and the lower control limit, determining that the SOFC is normally supplied with gas;
wherein, the SOFC is a solid oxide fuel cell system, and the output result is a statistical value;
the acquiring signals comprises: a cathode air supply, a bypass air supply, a reforming combustion fuel supply, a reforming reaction fuel supply, a deionized water supply, a SOFC stack temperature, a fuel air heat exchanger temperature, an air heat exchanger temperature value, a tail gas combustor temperature value, a reformer temperature, a discharge current amount, a discharge voltage and power, a methane supply, a reforming combustor methane supply, a reformer air supply, a reformer temperature value, and a stack real-time voltage value;
the determining the relevant signal according to the correlation degree of the acquired signal comprises:
calculating the correlation between every two signals in the collected signals, and determining a correlation signal according to the obtained correlation coefficient;
dividing the input quantity and the output quantity of the relevant signal, wherein the corresponding divided input quantity of the relevant signal comprises the following steps: a supply of methane, a supply of reformer air, a supply of bypass air, a supply of deionized water, and an amount of discharge current;
the output quantity divided by the correlation signal comprises: the temperature value of the reformer, the temperature value of the air heat exchanger, the temperature value of the tail gas combustion chamber and the real-time voltage value of the galvanic pile.
7. An electronic device, comprising:
at least one processor, at least one memory, a communication interface, and a bus; wherein the content of the first and second substances,
the processor, the memory and the communication interface complete mutual communication through the bus;
the memory stores program instructions executable by the processor, the processor calling the program instructions to perform the method of any of claims 1 to 5.
8. A non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform the method of any one of claims 1-5.
CN201910125727.5A 2019-02-20 2019-02-20 SOFC (solid oxide fuel cell) gas supply fault detection method and equipment based on statistics Active CN109888338B (en)

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 CN109888338A (en) 2019-06-14
CN109888338B true 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)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110783608B (en) * 2019-10-12 2021-02-09 华中科技大学 Method for processing faults of solid oxide fuel cell system

Family Cites Families (9)

* Cited by examiner, † Cited by third party
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
US8623564B2 (en) * 2008-10-31 2014-01-07 GM Global Technology Operations LLC Method for remedial action in the event of the failure of the primary air flow measurement device in a fuel cell system
CN104462846B (en) * 2014-12-22 2017-11-10 山东鲁能软件技术有限公司 A kind of equipment fault intelligent diagnosing method based on SVMs
KR102286838B1 (en) * 2017-01-05 2021-08-05 현대자동차주식회사 Device for valve failure diagnosis and emergency driving of fuel cell air supply system
US20190377325A1 (en) * 2017-01-23 2019-12-12 Nrg Systems, Inc. System and methods of novelty detection using non-parametric machine learning
JP6827357B2 (en) * 2017-04-05 2021-02-10 大阪瓦斯株式会社 Solid oxide fuel cell system
CN107991881B (en) * 2017-12-20 2021-01-05 东南大学 Solid oxide fuel cell nonlinear suppression method based on multi-model predictive control
CN108615917B (en) * 2018-04-11 2020-08-18 华中科技大学 Fault detection system and method for solid oxide fuel cell system
CN109101702B (en) * 2018-07-23 2023-05-12 山东科技大学 Fault detection method based on time constraint sparse representation and feature dimension reduction

Also Published As

Publication number Publication date
CN109888338A (en) 2019-06-14

Similar Documents

Publication Publication Date Title
CN107633354B (en) Comprehensive evaluation method for running state health degree of station direct current system
CN106709651B (en) Electric power system security evaluation system based on risk theory
CN110046182A (en) A kind of huge hydroelectric power plant's intelligent alarm threshold setting method and system
CN109742788B (en) New energy power station grid-connected performance evaluation index correction method
CN110472871B (en) Investigation method for managing line loss abnormal reasons
EP3215832A1 (en) Method and apparatus for monitoring and diagnosing electrochemical devices based on automatic electrochemical impedance identification
CN107527134A (en) A kind of distribution transformer state evaluating method and device based on big data
CN115800272A (en) Power grid fault analysis method, system, terminal and medium based on topology identification
CN108565852A (en) A kind of Contingency screening and ranking method of the bulk power grid Voltage Stability Evaluation of three progress step by step
CN109888338B (en) SOFC (solid oxide fuel cell) gas supply fault detection method and equipment based on statistics
CN111967620A (en) Photovoltaic module diagnosis method, device, equipment and readable storage medium
CN116125361A (en) Voltage transformer error evaluation method, system, electronic equipment and storage medium
CN113406524A (en) Inconsistent fault diagnosis method and system for power battery system
CN111628195A (en) Fuel cell stack real-time state identification method based on logic reasoning
ul Hassan et al. Online static security assessment for cascading failure using stacked De-noising Auto-encoder
CN115759820B (en) Loss assessment calculation method, system and storage medium for photovoltaic power station
WO2021017284A1 (en) Cortex-learning-based anomaly detection method and apparatus, terminal device, and storage medium
Jalalat et al. Optimal location of voltage sags monitors by determining the vulnerable area of network buses
CN112039074B (en) Online safety and stability emergency control strategy mode word generation method
CN116304763B (en) Power data pre-analysis method, system, equipment and medium
CN114298495A (en) Power grid reliability evaluation method based on fine-grained data driving
CN114336612A (en) Power loss calculation method for power station and fault equipment thereof and related application equipment
CN117368824A (en) Current transformer fault diagnosis method, electronic equipment and storage medium
CN117423868A (en) Method, device, equipment and medium for judging hydrogen-air mutual strings of fuel cell stacks
CN117766821A (en) Method and device for evaluating health state of fuel cell system based on multiple monitoring parameters

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