CN102073015A - Spectrum analysis-based online fault diagnosis method of proton exchange membrane fuel cell - Google Patents
Spectrum analysis-based online fault diagnosis method of proton exchange membrane fuel cell Download PDFInfo
- Publication number
- CN102073015A CN102073015A CN2009101991138A CN200910199113A CN102073015A CN 102073015 A CN102073015 A CN 102073015A CN 2009101991138 A CN2009101991138 A CN 2009101991138A CN 200910199113 A CN200910199113 A CN 200910199113A CN 102073015 A CN102073015 A CN 102073015A
- Authority
- CN
- China
- Prior art keywords
- fault diagnosis
- diagnosis method
- line fault
- model
- fuel cell
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Fuel Cell (AREA)
Abstract
The invention discloses a spectrum analysis-based online fault diagnosis method of a proton exchange membrane fuel cell. The method comprises the following steps of: 1) selecting a model; 2) sampling needed data from a fuel cell system and the model; and 3) performing spectrum analysis and relevant analysis on acquired data so as to perform fault recognition and alarming. The method has a simple algorithm and a small calculated amount, on line calculation is realized easily, a system fault can be judged in time, and the method is suitable for fault early warning of a fuel cell system and particularly has wide application prospect in a small-sized fuel cell system.
Description
Technical field
The present invention relates to the on-line fault diagnosis method of a kind of Proton Exchange Membrane Fuel Cells (PEMFC) based on spectrum analysis.
Background technology
Proton Exchange Membrane Fuel Cells has under the normal temperature startup fast, generating efficiency height, pollution-free, advantage such as noise is little, has broad application prospects at aspects such as vehicle power power supply, compact power, emergency power pacies.PEMFC is a complicated nonlinear systems, need an efficient complicated controller guaranteeing its normal work, and fault diagnosis is a part indispensable in the entire controller, and it is the importance that guarantees the normal stable operation of whole PEMFC system.
At present, at the method for diagnosing faults of PEMFC system mainly contain fault diagnosis based on neural network, based on robust Fault diagnosis of nonlinear state observer etc., the algorithm more complicated of these methods, calculated amount is big, be applicable to larger fuel cell system, for example be used as the PEMFC of vehicle power source etc.In the existing industrial technology, fault diagnosis generally is divided into two steps: modelling and Fault Identification, and wherein very extensive for the former research, but less for the latter.
Summary of the invention
Technical matters to be solved by this invention provides the on-line fault diagnosis method of a kind of Proton Exchange Membrane Fuel Cells based on spectrum analysis (PEMFC).This method is based on the basis of existing known models carries out the Fault Identification Study on Technology, and it is simple to have an algorithm, and calculated amount is little, is suitable for online fault detect and early warning, and wide future in engineering applications is arranged.
Because fuel cell system is in operational process, concern that right and wrong are permanent between each parameters of reason passing in time such as various outsides or inner degeneration, therefore, the model that the present invention chooses has the characteristics of online adaptive.
For achieving the above object, the present invention realizes by the following technical solutions:
The on-line fault diagnosis method of described Proton Exchange Membrane Fuel Cells based on spectrum analysis may further comprise the steps:
1) chooses model.
2) desired data of from fuel cell system and model, sampling.
3) data of gathering are carried out analysis of spectrum and Fault Identification and warning are carried out in correlation analysis.
Above-mentioned selected model has the online adaptive characteristics.
The input signal of above-mentioned selected model is identical with the input signal of detected system.
Described data sampling signal is the peroxide ratio or the output voltage of detected system and model.
By zero-meanization, removal abnormal data, elimination trend term above-mentioned sampled signal is carried out the data pre-service.
Calculate the power spectrum density of described model and detected system respectively by Fast Fourier Transform (FFT).
Two power spectrum densities are carried out cross-correlation analysis, get related coefficient ρ
Xy(0≤| ρ
Xy|≤1).
According to determined differentiation failure criterion, work as ρ
Xy<ρ
The xy standardThe time, system breaks down, and reports to the police.In general, as | ρ
Xy|, represent that two signals are that highly linear is relevant, i.e. this system's non-fault at>0.8 o'clock.
ρ described in the present invention
The xy standardBe defined as follows:
At first to fuel cell system artificial several small faults are set, then to its sample, one group of related coefficient when correlation analysis obtains system small fault is arranged
Get this group data mean value, promptly as the ρ that differentiates fault
The xy standard
Algorithm of the present invention is simple, and calculated amount is little, realize easily online, and can whether fault be made judgement to system timely, be applicable to the fault pre-alarming of fuel cell system, especially, wide application prospect is arranged for the less fuel cell system of scale.
Description of drawings
Fig. 1 is the system architecture diagram of fuel cell of the present invention.
Embodiment
Embodiment 1
As shown in Figure 1, be the structured flowchart of fuel cell system of the present invention.
At the fault type that will detect, the first step is chosen " system emulation journal " Vol.16, No.5, and May.2004, the Proton Exchange Membrane Fuel Cells based on the neural technology of adaptive fuzzy of people such as the Wei Dong of Shanghai Communications University report is a model.Make the input signal of this selected model and detected PEMFC system identical.
Second step was moved above-mentioned selected model and detected system simultaneously, and the peroxide of selecting detected system and model than or output voltage as sampled signal.
The 3rd step, at first carry out the data pre-service for two groups of data that above-mentioned sampling obtains, comprise zero-meanization, remove abnormal data, eliminate trend term etc., and then carry out power spectrumanalysis respectively.And power spectrum density carried out smoothing processing, to reduce error, improve the precision (need to gather abundant data, and in time data are upgraded) that spectrum is estimated.At last, the power spectrum of model and detected system is carried out cross-correlation analysis, obtain related coefficient ρ
Xy, with the discrimination standard ρ of defined
The xy standardCompare, if ρ
Xy<ρ
The xy standard, then illustrative system breaks down, and carries out fault pre-alarming, and system is in time quit work.
Claims (8)
1. the on-line fault diagnosis method based on the Proton Exchange Membrane Fuel Cells of spectrum analysis is characterized in that, may further comprise the steps:
1) chooses model;
2) desired data of from fuel cell system and model, sampling;
3) data of gathering are carried out analysis of spectrum and Fault Identification and warning are carried out in correlation analysis.
2. on-line fault diagnosis method according to claim 1 is characterized in that described model has online adaptive.
3. on-line fault diagnosis method according to claim 1 is characterized in that, the input signal of described model is identical with the input signal of detected system.
4. on-line fault diagnosis method according to claim 1 is characterized in that, described data sampling signal is the peroxide ratio or the output voltage of detected system and model.
5. according to each described on-line fault diagnosis method of claim 1 to 4, it is characterized in that, described sampled signal is carried out the data pre-service by zero-meanization, removal abnormal data, elimination trend term.
6. according to each described on-line fault diagnosis method of claim 1 to 4, it is characterized in that, calculate the power spectrum density of described model and detected system by Fast Fourier Transform (FFT) respectively.
7. on-line fault diagnosis method according to claim 6 is characterized in that, two power spectrum densities are carried out cross-correlation analysis, gets related coefficient ρ
Xy
8. on-line fault diagnosis method according to claim 7 is characterized in that, according to determined differentiation failure criterion, works as ρ
Xy<ρ
The xy standardThe time, system breaks down, and reports to the police.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2009101991138A CN102073015A (en) | 2009-11-20 | 2009-11-20 | Spectrum analysis-based online fault diagnosis method of proton exchange membrane fuel cell |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2009101991138A CN102073015A (en) | 2009-11-20 | 2009-11-20 | Spectrum analysis-based online fault diagnosis method of proton exchange membrane fuel cell |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102073015A true CN102073015A (en) | 2011-05-25 |
Family
ID=44031633
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2009101991138A Pending CN102073015A (en) | 2009-11-20 | 2009-11-20 | Spectrum analysis-based online fault diagnosis method of proton exchange membrane fuel cell |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102073015A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113422088A (en) * | 2021-06-28 | 2021-09-21 | 太原理工大学 | Hydrogen fuel cell air supply system and decoupling control method thereof |
CN113467423A (en) * | 2021-07-01 | 2021-10-01 | 中山大学 | PEMFC fault diagnosis method and system based on cloud platform |
-
2009
- 2009-11-20 CN CN2009101991138A patent/CN102073015A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113422088A (en) * | 2021-06-28 | 2021-09-21 | 太原理工大学 | Hydrogen fuel cell air supply system and decoupling control method thereof |
CN113422088B (en) * | 2021-06-28 | 2023-02-17 | 太原理工大学 | Hydrogen fuel cell air supply system and decoupling control method thereof |
CN113467423A (en) * | 2021-07-01 | 2021-10-01 | 中山大学 | PEMFC fault diagnosis method and system based on cloud platform |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Gu et al. | Data-based flooding fault diagnosis of proton exchange membrane fuel cell systems using LSTM networks | |
Wang et al. | Recent advances and summarization of fault diagnosis techniques for proton exchange membrane fuel cell systems: A critical overview | |
CN110579709B (en) | Fault diagnosis method for proton exchange membrane fuel cell for tramcar | |
Liu et al. | Short-term prognostics of PEM fuel cells: A comparative and improvement study | |
CN112330165B (en) | Power grid transient stability evaluation method and system based on feature separation type neural network | |
CN108344947A (en) | A kind of fuel cell diagnostic method of non-intrusion type | |
CN113011481B (en) | Electric energy meter function abnormality assessment method and system based on decision tree algorithm | |
CN111652479B (en) | Data driving method for dynamic security assessment of power system | |
CN112069727B (en) | Intelligent transient stability evaluation system and method with high reliability for power system | |
Hua et al. | Lifespan prediction for proton exchange membrane fuel cells based on wavelet transform and echo state network | |
CN115453356B (en) | Power equipment operation state monitoring and analyzing method, system, terminal and medium | |
CN110112442B (en) | Fuel cell system control method and device | |
CN113547919B (en) | Remote fault monitoring method and system for fuel cell vehicle | |
Wu et al. | Fault detection and assessment for solid oxide fuel cell system gas supply unit based on novel principal component analysis | |
CN108847679B (en) | Wind generating set and subsynchronous oscillation identification method, device and system for wind generating set | |
CN116956215A (en) | Fault diagnosis method and system for transmission system | |
CN106056305A (en) | Power generation system reliability rapid assessment method based on state clustering | |
CN108646573B (en) | A kind of closed-loop system stability margin of data-driven determines method | |
CN109635430A (en) | Grid power transmission route transient signal monitoring method and system | |
CN102073015A (en) | Spectrum analysis-based online fault diagnosis method of proton exchange membrane fuel cell | |
CN116565354A (en) | Fault grading diagnosis early warning method, system and equipment for electrochemical energy storage system | |
Tingting et al. | Early warning method for power station auxiliary failure considering large-scale operating conditions | |
CN116150666B (en) | Energy storage system fault detection method and device and intelligent terminal | |
Zhang et al. | Fault diagnosis of wind turbine generator system based on PMI-LSSVM | |
CN109976316B (en) | Fault-related variable selection method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20110525 |