CN110159554A - Centrifugal pump fault diagnostic method based on pivot analysis and sequential probability ratio test - Google Patents
Centrifugal pump fault diagnostic method based on pivot analysis and sequential probability ratio test Download PDFInfo
- Publication number
- CN110159554A CN110159554A CN201910441787.8A CN201910441787A CN110159554A CN 110159554 A CN110159554 A CN 110159554A CN 201910441787 A CN201910441787 A CN 201910441787A CN 110159554 A CN110159554 A CN 110159554A
- Authority
- CN
- China
- Prior art keywords
- centrifugal pump
- ratio test
- probability ratio
- analysis
- sequential probability
- 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
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04D—NON-POSITIVE-DISPLACEMENT PUMPS
- F04D15/00—Control, e.g. regulation, of pumps, pumping installations or systems
- F04D15/0088—Testing machines
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05D—INDEXING SCHEME FOR ASPECTS RELATING TO NON-POSITIVE-DISPLACEMENT MACHINES OR ENGINES, GAS-TURBINES OR JET-PROPULSION PLANTS
- F05D2260/00—Function
- F05D2260/80—Diagnostics
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05D—INDEXING SCHEME FOR ASPECTS RELATING TO NON-POSITIVE-DISPLACEMENT MACHINES OR ENGINES, GAS-TURBINES OR JET-PROPULSION PLANTS
- F05D2260/00—Function
- F05D2260/81—Modelling or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Control Of Non-Positive-Displacement Pumps (AREA)
- Structures Of Non-Positive Displacement Pumps (AREA)
Abstract
The invention discloses a kind of centrifugal pump fault diagnostic method based on pivot analysis and sequential probability ratio test, this method establish model using common impeller and failure impeller, obtain original vibration signal using centrifugal pump vibration signal acquiring system；Then noise reduction is carried out to signal with wavelet package transforms, the characteristic parameter of signal is extracted using temporal analysis；Dimension-reduction treatment is carried out to extracted characteristic parameter using principle component analysis again, chooses the maximum pivot of contribution rate as checking sequence；The operating status that is finally pumped using sequential probability ratio test algorithm come analysis centrifugal simultaneously classifies to failure in conjunction with root mean square algorithm.The present invention is mainly the method for carrying out malfunction diagnosis using pivot analysis and sequential probability ratio test, creates the criterion of classification, and this method has higher validity and accuracy in terms of centrifugal pump fault diagnosis and identification.
Description
Technical field
The invention belongs to technical field of nondestructive testing more particularly to a kind of based on pivot analysis and sequential probability ratio test
Centrifugal pump fault diagnostic method.
Background technique
With scientific and technological progress and economic development, industrial technology is quickly grown, thus to the safety of the equipment of industrial product, can
Requirement by property etc. is also higher and higher, and mechanical equipment can all seriously affect production even if there is failure or shutdown
It can cause casualties.In order to reduce because mechanical equipment fault bring negatively affects, fault diagnosis technology is particularly important.
In recent years, as equipment common in industrial production, centrifugal pump is because it can satisfy big flow, continuously run for a long time
It waits production requirements and is used in the industries such as the petrochemical industry in China universal.In centrifugal pump operational process, impeller failure and axis damage
It is inevitable etc. various failures, may cause casualties and heavy economic losses.Therefore it separates the failure of heart pump and adopts
It takes corresponding measure to be very important through row processing, the diagnosis for complex fault mode is needed to make improvement.
Summary of the invention
The centrifugation based on pivot analysis and sequential probability ratio test that the technical problem to be solved by the invention is to provide a kind of
Failure of pump diagnostic method, creates the criterion of classification, and this method has in terms of centrifugal pump fault diagnosis and identification with higher
Effect property and accuracy.
The technical solution adopted by the present invention to solve the technical problems is: providing a kind of based on pivot analysis and sequential probability
Than the centrifugal pump fault diagnostic method of inspection, this approach includes the following steps, step 1: using standard control impeller and failure leaf
Wheel establishes model, obtains original vibration signal using centrifugal pump vibration signal acquiring system；Step 2: using wavelet package transforms pair
Original signal carries out noise reduction process, and the characteristic parameter of signal is extracted using temporal analysis；Step 3: using principle component analysis pair
Extracted characteristic parameter carries out dimension-reduction treatment, chooses the maximum pivot of contribution rate as checking sequence；Step 4: utilizing sequential
Probability ratio test algorithm carrys out the operating status of analysis centrifugal pump and classifies in conjunction with root mean square algorithm to failure.
According to the above technical scheme, in step 2 noise reduction process and extract signal characteristic parameter specifically, becoming with wavelet packet
It changes after carrying out noise reduction process to original signal, obtain centrifugal pump refers in particular to parameter.
Wavelet package transforms carry out noise reduction process to original signal, and being conducive to being capable of low frequency part and high frequency section to signal
Finer decomposition is all carried out, to improve the time frequency resolution of signal, reduces the amplitude of signal after noise reduction obviously,
And signal curve is also relatively sharp.
According to the above technical scheme, eight kinds of characteristic parameters of four group signal of the centrifugal pump under four kinds of situations, four types are obtained
The impeller of type includes standard control impeller (F1), blade injury impeller (F2), damage of edges impeller (F3) and perforation impeller (F4).
The model of impeller, the model of centrifugal pump are selected, rotating manner and the rotation of centrifugal pump and motor is arranged in the power and revolving speed of motor
Than the placement location of vibrating sensor.In the step 1, according to using standard control impeller and failure impeller to be divided into four types
Type, centrifugal pump vibration signal acquiring system include centrifugal pump, motor, vibrating sensor, data acquisition card and computer, centrifugal pump vibration
Dynamic signal acquiring system determines respectively obtains 4 kinds of original vibration signals under normal condition and fault condition, use S1, S2, S3 respectively
It is indicated with S4.
By using the impeller of four seed types, then by centrifugal pump vibration signal acquiring system respectively determine normal condition and
Original vibration signal S1, S2, S3 and S4 are obtained under fault condition, is compared with four seed types, and the original signal of acquisition is also more
It is handled added with the later period is conducive to wavelet packet analysis.Impeller by four seed types includes normal (F1) blade injury
(F2), (F3) of damage of edges and perforation (F4), convenient for these four modes have clearly difference again can represent well from
The typical fault of heart pump impeller passes through the model of impeller, the model of centrifugal pump, the power and revolving speed of motor, centrifugal pump and motor
Rotating manner and rotation ratio, convenient for confirmation impeller, centrifugal pump and motor model, also indicate that very have generality, pass through vibration
The placement location of dynamic sensor, the original signal that can be more effectively tested with, and keep its accuracy higher.
According to the above technical scheme, characteristic parameter includes mean value, virtual value, standard deviation, kurtosis index, waveform index, peak value
Index, margin index and pulse index.
Mean value, for reflecting the size of signal fluctuation energy；Virtual value, for describing the index of dynamic signal strength；Mark
It is quasi- poor, for describing the wave component of signal；
Kurtosis index, for reacting the shock characteristic in vibration signal；Waveform index, for reflecting that signal deviates Gauss point
The index of cloth degree；Pulse index and peak index have shock-free index for detecting in signal；Margin index, for examining
Survey the wear condition of mechanical equipment.Because each characteristic parameter can reflect certain characteristic of the signal, joined according to feature
Number combines vibration signal, can be with side light centrifugal pump operating status.
According to the above technical scheme, the maximum pivot of contribution rate is chosen in step 3 specifically, using principle component analysis to being mentioned
After the characteristic parameter taken carries out dimension-reduction treatment, according to the height of contribution rate come to treated, principal component carries out descending arrangement, choosing
The first pivot that accumulation contribution rate is more than 85% is selected, as checking sequence.
Dimension-reduction treatment is carried out to extracted characteristic parameter using principle component analysis, simplifies original procedure specificity analysis
Complexity reduces the dimension of data and retains the useful information of the original variable overwhelming majority.Pass through selection accumulation contribution
Rate is more than 85% the first pivot, as checking sequence, is that subsequent inspection is more convenient, improves the efficiency of analysis,
As a result accuracy rate is also very high.
According to the above technical scheme, contribution rate is to retain the amount of useful information in original information.
According to the above technical scheme, specific steps in step 4 are as follows:
Step 41: the checking sequence of selection meets Gaussian Profile, can obtain its mean μ and standard deviation sigma；
Step 42: calculating the joint probability density function P of any two groups of sequencesik(yk)、Pjk(yk)；
Step 43: by probability density function it can be concluded that sequential probability ratio test likelihood ratio Δi,j(YSm)；
Step 44: according to the test criterion of sequential probability ratio test, identifying the state of centrifugal pump；
Step 45: in conjunction with root-mean-square error algorithm, by the mean value of the sequence to be checked under wherein state respectively with other three groups
Three kinds of analyses are combined as sequential probability ratio test parameter and identify the state by the mean value of sequence to be checked.
By joint probability density, keep useful information more accurate, for will not generally be distributed not because of individual factors
It is affected together.By sequential probability ratio test, solve the problems, such as excessively to consider to choose sample number, and do not need pre-
First fixed sample amount reduces frequency in sampling.In sequential probability ratio test likelihood ratio, proposition is more advantageous to reflection inspection with likelihood ratio
The authenticity and reliability of survey.By combining root-mean-square error algorithm with sequential probability ratio test, i.e., passed through generally with three sequences
Rate diagnoses centrifugal pump fault than inspection to verify the validity of sequential probability ratio test algorithm and stability, then with four
Group sequence to be checked compares and analyzes, and more finely can effectively identify centrifugal pump state in which in this way.
According to the above technical scheme, the test criterion for passing through probability ratio test is to compare likelihood ratio and threshold value A, the size of B；It is to be checked
The mean value of sequence is denoted as Y ' by choosing the sequence to be checked of 10 groups of vibration signals under sequence status to be checkedS1(M), wherein M=
1 ..., 10, calculate Y 'S1(M) mean μi。
The beneficial effect comprise that: with wavelet package transforms to signal de-noising, then to the characteristic parameter of extraction
Pivot analysis is carried out, finally applies to sequential probability ratio test in centrifugal pump fault diagnosis.The result shows that wavelet-packet noise reduction is imitated
Fruit is good, and 4 kinds of different failure moulds can be recognized accurately for sequential probability ratio test in the data after pivot analysis processing
Formula.Sequential probability ratio test is combined with root-mean-square error algorithm simultaneously, further various modes are classified, created
The criterion of classification, this method centrifugal pump fault diagnose and identification in terms of with higher validity and accuracy.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples, in attached drawing:
Fig. 1 is the flow diagram of centrifugal pump fault diagnostic method of the embodiment of the present invention based on PCA-SPRT algorithm；
Fig. 2 is centrifugal pump fault diagnostic method of the embodiment of the present invention based on PCA-SPRT algorithm based on sequential probability ratio
The centrifugal pump fault diagnostic flow chart of check algorithm；
Fig. 3 is centrifugal pump fault diagnostic method of the embodiment of the present invention based on PCA-SPRT algorithm based on sequential probability ratio
Examine and combine the centrifugal pump fault diagnostic flow chart of root mean square algorithm；
Fig. 4 is the centrifugal pump signal acquisition of centrifugal pump fault diagnostic method of the embodiment of the present invention based on PCA-SPRT algorithm
System diagram.
Wherein, 1, motor, 2, V-type conveyer belt, 3, vibrating sensor, 4, centrifugal pump, 5, data line, 6, control panel, 7,
Computer.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.
As shown in Figure 1, be the centrifugal pump fault diagnostic method specific embodiment flow diagram based on PCA-SPRT algorithm,
The following steps are included:
S1: establishing experimental model using common impeller and failure impeller, is obtained using centrifugal pump vibration signal acquiring system
Original vibration signal.
When specific, the present invention selects Weir/Warman3/2 CAH centrifugal pump.Impeller is closed, model C2147, by
Motor driven, motor rated power 40HP, revolving speed are 1200 turns.There is a V belt driver between motor and centrifugal pump, passes
Dynamic ratio is 13/6.In order to acquire vibration signal of the centrifugal pump under each state, need that sensor is installed in key position, therefore
Three 3-axis acceleration sensors are separately mounted to upper part of the housing, the top of the bearing in the exit and centrifugal pump of centrifugal pump with
This measures shell, outlet and the Vibration Condition of bearing.Vibration data is taken down notes by signal analyzer and Dell Inspiron9200
The acquisition storage of this computer, is handled by spectrum analyzer later.
Fig. 4 is the centrifugal pump signal acquisition of centrifugal pump fault diagnostic method of the embodiment of the present invention based on PCA-SPRT algorithm
System diagram, wherein motor 1 is connect with V-type conveyer belt 2, and vibrating sensor 3 is arranged on centrifugal pump 4, control panel 6 and computer 7
Directly connected by data line 5.
It checks all components in centrifugal pump, the normal impeller F1 generation of the impeller in centrifugal pump is replaced.It is first turned on import
Then pipeline valve introduces mud into pump, further according to transmission belt transmission ratio set 1200rpm for wheel speed after start
Motor gradually opens large outlet valve after the outlet pressure of pump is higher than operating pressure.Signal analyzer is utilized after pumping stable operation
Experimental data is acquired with data acquisition software.Revolving speed is respectively set to 1400rpm again after one group of data collection finishes,
1600rpm ..., 2600rpm repeat above step and acquire data.
Then impeller F2, F3 and the F4 for successively replacing failure repeat the above steps, and record and store data.
S2: noise reduction process is carried out to original signal with wavelet package transforms, the feature of signal is extracted using temporal analysis
Parameter；
When specific, using wavelet package transforms to centrifugal pump vibration signal carry out noise reduction, first according to vibration signal the characteristics of
And require to be arranged and determine Decomposition order, wherein Decomposition order is 3 layers.Then optimal base is chosen, that is, chooses suitable basic function pair
Signal carries out 3 layers of decomposition, constructs Optimal Wavelet Packet tree, finally chooses suitable threshold value and carries out noise reduction and signal is reconstructed,
Signal after obtaining noise reduction.
This eight parameter indexes are chosen to be calculated.Assuming that xi=[x1, x2... xN] be one group of spatial distribution random mistake
Journey, N=30000.Every group takes 5000 check points, 25001 groups of inspection datas available in this way.Pretreated vibration will be passed through
Signal (n=5000) substitute into formula in calculate separately mean value, virtual value, standard deviation, kurtosis index, waveform index, peak index,
Margin index and pulse index etc. obtain eight kinds of characteristic parameters of four group signal of the centrifugal pump under four kinds of situations, wherein specifically
Formula does not illustrate.
S3: dimension-reduction treatment is carried out to extracted characteristic parameter using principle component analysis, chooses the maximum pivot of contribution rate
As checking sequence；
When specific, this experiment carries out pivot analysis (PCA) processing, data matrix X (the X ∈ of required processing to four groups of data
Rn×m) there are 25001 groups of sample points, 8 variables.The step of carrying out pivot analysis to it is as follows:
1. being standardized first to data matrix X, the matrix after handling is denoted as Xs；
2. calculating XsCovariance matrix
3. calculating the m eigenvalue λ of covariance matrix C1≥λ2≥…λmAnd the corresponding feature vector p of characteristic value1,
p2..., pm；
4. seeking corresponding pivot: ti=Xspi
5. calculating the contribution rate and contribution rate of accumulative total of each pivot:
6. choose contribution rate of accumulative total be more than 85% preceding several pivots as the data matrix after dimensionality reduction.
After handling by pivot analysis, preceding several pivots of the contribution rate of accumulative total higher than 85% include enough useful originals
Beginning information is carried out sequential probability ratio test so selection contribution rate is higher as sequence to be tested.
S4: the operating status that is pumped using sequential probability ratio test algorithm come analysis centrifugal simultaneously combines root mean square algorithm to failure
Classify.
When specific, the maximum sequence of contribution rate is chosen here as checking sequence, is denoted as YSi=[y1...yk], i=1,2,
3,4。
Its mean value and standard deviation are as follows:
Assuming that wherein the probability distribution of one group of sequence to be checked meets just hypothesis Hi: μ=μi；The probability of another group of sequence to be checked
Distribution meets alternative hvpothesis Hj: μ=μj, standard deviation sigma remains unchanged, and the joint probability density function for calculating two groups of sequences is as follows:
Sequential probability ratio test likelihood ratio Δi,j(YSm) calculate it is as follows:
The test criterion of sequential probability ratio test is the size for comparing likelihood ratio Yu threshold value (critical value) A, B, due to above
Likelihood ratio formula is simplified, then threshold value can also simplify a=lnA, b=lnB.To being obtained in the case of four kinds of different faults
Signal Si and Sj, test according to flow chart 2, can identify centrifugation pump operation state.
Then the realization that sequential probability ratio test and root-mean-square error combine passes through the F in centrifugal pump1、F2、F3、F4Four
In the original vibration signal of kind state, 10 groups of signals are extracted respectively, and every group includes 10000 sample points, altogether 40 groups of vibrations letters
Number.Sequence to be checked is taken out according to inspection process, is denoted as Y 'Sm(M), m=1 ..., 4, M=1 ..., 10.According to the stream of flow chart 3
Journey calculates the likelihood ratio Δ of 40 groups of sequences to be checkedi,j(Y′Sm(M)), m=1 ..., 4, M=1 ..., 10.Work as i, when j is determined, shape
Available 10 likelihood ratios of 10 groups of vibration signals under state.The root-mean-square error between this 10 likelihood ratios is first calculated, then
The root-mean-square error under this 10 likelihood ratios and other states between the likelihood ratio of vibration signal is calculated again.Finally, according to inspection
Criterion identifies the various states of centrifugal pump.
It should be understood that for those of ordinary skills, it can be modified or changed according to the above description,
And all these modifications and variations should all belong to the protection domain of appended claims of the present invention.
Claims (8)
1. a kind of centrifugal pump fault diagnostic method based on pivot analysis and sequential probability ratio test, which is characterized in that this method
Include the following steps, step 1: model is established using standard control impeller and failure impeller, using centrifugal pump vibration signal acquisition
System obtains original vibration signal；
Step 2: noise reduction process being carried out to original signal with wavelet package transforms, is joined using the feature that temporal analysis extracts signal
Number；
Step 3: dimension-reduction treatment being carried out to extracted characteristic parameter using principle component analysis, the maximum pivot of contribution rate is chosen and makees
For checking sequence；
Step 4: the operating status that is pumped using sequential probability ratio test algorithm come analysis centrifugal simultaneously combines root mean square algorithm to failure
Classify.
2. the centrifugal pump fault diagnostic method according to claim 1 based on pivot analysis and sequential probability ratio test,
Be characterized in that, in step 2 noise reduction process and extract signal characteristic parameter specifically, with wavelet package transforms to original signal into
After row noise reduction process, obtain centrifugal pump refers in particular to parameter.
3. the centrifugal pump fault diagnostic method according to claim 2 based on pivot analysis and sequential probability ratio test,
It is characterized in that, obtain eight kinds of characteristic parameters of four group signal of the centrifugal pump under four kinds of situations, the impeller of four seed types includes mark
Quasi- control impeller, blade injury impeller, damage of edges impeller and perforation impeller.
4. the centrifugal pump fault diagnostic method according to claim 3 based on pivot analysis and sequential probability ratio test,
Be characterized in that, characteristic parameter include mean value, virtual value, standard deviation, kurtosis index, waveform index, peak index, margin index and
Pulse index.
5. the centrifugal pump fault diagnostic method according to claim 1 or 2 based on pivot analysis and sequential probability ratio test,
It is characterized in that, choosing the maximum pivot of contribution rate in step 3 specifically, using principle component analysis to extracted characteristic parameter
After carrying out dimension-reduction treatment, according to the height of contribution rate come to treated, principal component carries out descending arrangement, selection accumulation contribution rate
The first pivot more than 85%, as checking sequence.
6. the centrifugal pump fault diagnostic method according to claim 5 based on pivot analysis and sequential probability ratio test,
It is characterized in that, contribution rate is to retain the amount of useful information in original information.
7. the centrifugal pump fault diagnostic method according to claim 1 or 2 based on pivot analysis and sequential probability ratio test,
It is characterized in that, in step 4 the specific steps are,
Step 41: the checking sequence of selection meets Gaussian Profile, can obtain its mean μ and standard deviation sigma；
Step 42: calculating the joint probability density function P of any two groups of sequencesik(yk)、Pjk(yk)；
Step 43: by probability density function it can be concluded that sequential probability ratio test likelihood ratio Δi,j(YSm)；
Step 44: according to the test criterion of sequential probability ratio test, identifying the state of centrifugal pump；
Step 45: in conjunction with root-mean-square error algorithm, the mean value of the sequence to be checked under wherein state is to be checked with other three groups respectively
Three kinds of analyses are combined as sequential probability ratio test parameter and identify the state by the mean value of sequence.
8. the centrifugal pump fault diagnostic method according to claim 7 based on pivot analysis and sequential probability ratio test,
It is characterized in that, the test criterion for passing through probability ratio test is to compare likelihood ratio and threshold value A, the size of B；The mean value of sequence to be checked by
The sequence to be checked that 10 groups of vibration signals are chosen under sequence status to be checked, is denoted as Y 'S1(M), wherein M=1 ..., 10, it calculates
Y′S1(M) mean μi。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910441787.8A CN110159554A (en) | 2019-05-24 | 2019-05-24 | Centrifugal pump fault diagnostic method based on pivot analysis and sequential probability ratio test |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910441787.8A CN110159554A (en) | 2019-05-24 | 2019-05-24 | Centrifugal pump fault diagnostic method based on pivot analysis and sequential probability ratio test |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110159554A true CN110159554A (en) | 2019-08-23 |
Family
ID=67632849
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910441787.8A Pending CN110159554A (en) | 2019-05-24 | 2019-05-24 | Centrifugal pump fault diagnostic method based on pivot analysis and sequential probability ratio test |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110159554A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111043050A (en) * | 2019-12-19 | 2020-04-21 | 武汉工程大学 | Fault diagnosis method and system for centrifugal pump |
| CN111810418A (en) * | 2020-06-10 | 2020-10-23 | 武汉工程大学 | Fault detection method and system |
| CN113530850A (en) * | 2021-08-26 | 2021-10-22 | 江苏科技大学 | Centrifugal pump fault diagnosis method based on EAS (electronic article surveillance) and stacked capsule self-encoder |
| CN113640394A (en) * | 2021-07-02 | 2021-11-12 | 武汉工程大学 | Fatigue crack identification method and system |
| CN114279707A (en) * | 2021-12-17 | 2022-04-05 | 哈尔滨工业大学 | Large-scale rotating equipment spindle state feature extraction method based on multi-domain analysis and principal component analysis |
| CN117072460A (en) * | 2023-10-16 | 2023-11-17 | 四川中测仪器科技有限公司 | Centrifugal pump state monitoring method based on vibration data and expert experience |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5658423A (en) * | 1995-11-27 | 1997-08-19 | International Business Machines Corporation | Monitoring and controlling plasma processes via optical emission using principal component analysis |
| CN102313578A (en) * | 2011-08-04 | 2012-01-11 | 广州市香港科大霍英东研究院 | Mechanical seal online monitoring system |
| CN107657351A (en) * | 2017-10-26 | 2018-02-02 | 广州泰阳能源科技有限公司 | A kind of load prediction system based on PLC Yu pivot analysis RBF neural |
| CN108069308A (en) * | 2017-12-05 | 2018-05-25 | 暨南大学 | A kind of electric staircase failure diagnosis method based on sequential probability |
| CN108874741A (en) * | 2018-06-19 | 2018-11-23 | 南京中车浦镇海泰制动设备有限公司 | A kind of relay valve leakage failure detection method based on SPRT algorithm |
-
2019
- 2019-05-24 CN CN201910441787.8A patent/CN110159554A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5658423A (en) * | 1995-11-27 | 1997-08-19 | International Business Machines Corporation | Monitoring and controlling plasma processes via optical emission using principal component analysis |
| CN102313578A (en) * | 2011-08-04 | 2012-01-11 | 广州市香港科大霍英东研究院 | Mechanical seal online monitoring system |
| CN107657351A (en) * | 2017-10-26 | 2018-02-02 | 广州泰阳能源科技有限公司 | A kind of load prediction system based on PLC Yu pivot analysis RBF neural |
| CN108069308A (en) * | 2017-12-05 | 2018-05-25 | 暨南大学 | A kind of electric staircase failure diagnosis method based on sequential probability |
| CN108874741A (en) * | 2018-06-19 | 2018-11-23 | 南京中车浦镇海泰制动设备有限公司 | A kind of relay valve leakage failure detection method based on SPRT algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 黄文健等: "基于PCA与SPRT的机械故障诊断方法研究", 《武汉工程大学学报》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111043050A (en) * | 2019-12-19 | 2020-04-21 | 武汉工程大学 | Fault diagnosis method and system for centrifugal pump |
| CN111810418A (en) * | 2020-06-10 | 2020-10-23 | 武汉工程大学 | Fault detection method and system |
| CN113640394A (en) * | 2021-07-02 | 2021-11-12 | 武汉工程大学 | Fatigue crack identification method and system |
| CN113640394B (en) * | 2021-07-02 | 2023-11-10 | 武汉工程大学 | Fatigue crack identification method and system |
| CN113530850A (en) * | 2021-08-26 | 2021-10-22 | 江苏科技大学 | Centrifugal pump fault diagnosis method based on EAS (electronic article surveillance) and stacked capsule self-encoder |
| CN113530850B (en) * | 2021-08-26 | 2022-10-18 | 江苏科技大学 | Centrifugal pump fault diagnosis method based on ESA and stacked capsule self-encoder |
| CN114279707A (en) * | 2021-12-17 | 2022-04-05 | 哈尔滨工业大学 | Large-scale rotating equipment spindle state feature extraction method based on multi-domain analysis and principal component analysis |
| CN117072460A (en) * | 2023-10-16 | 2023-11-17 | 四川中测仪器科技有限公司 | Centrifugal pump state monitoring method based on vibration data and expert experience |
| CN117072460B (en) * | 2023-10-16 | 2023-12-19 | 四川中测仪器科技有限公司 | Centrifugal pump state monitoring method based on vibration data and expert experience |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110159554A (en) | Centrifugal pump fault diagnostic method based on pivot analysis and sequential probability ratio test | |
| Goumas et al. | Classification of washing machines vibration signals using discrete wavelet analysis for feature extraction | |
| Azizi et al. | Improving accuracy of cavitation severity detection in centrifugal pumps using a hybrid feature selection technique | |
| CN107631867B (en) | A kind of rotating machinery fault intelligent method for classifying based on deep learning | |
| Rapur et al. | Automation of multi-fault diagnosing of centrifugal pumps using multi-class support vector machine with vibration and motor current signals in frequency domain | |
| CN110823576B (en) | Mechanical anomaly detection method based on generation of countermeasure network | |
| CN104616033A (en) | Fault diagnosis method for rolling bearing based on deep learning and SVM (Support Vector Machine) | |
| CN113537328B (en) | Rotary machine fault diagnosis method and device based on deep learning | |
| Sharma et al. | A novel feature extraction method based on weighted multi-scale fluctuation based dispersion entropy and its application to the condition monitoring of rotary machines | |
| Sakthivel et al. | Use of histogram features for decision tree-based fault diagnosis of monoblock centrifugal pump | |
| Galloway et al. | Diagnosis of tidal turbine vibration data through deep neural networks | |
| CN105956514A (en) | Helicopter rotor abnormity detecting method driven by vibration data | |
| CN113283292B (en) | Method and device for diagnosing faults of underwater micro-propeller | |
| Zhang et al. | A novel intelligent method for bearing fault diagnosis based on Hermitian scale-energy spectrum | |
| Peng et al. | RMA-CNN: A residual mixed-domain attention CNN for bearings fault diagnosis and its time-frequency domain interpretability | |
| Lee et al. | Condition monitoring of chain sprocket drive system based on iot device and convolutional neural network | |
| Wu et al. | Condition-based monitoring and novel fault detection based on incremental learning applied to rotary systems | |
| CN114263621A (en) | Test method and system for diagnosing and simulating cavitation fault of centrifugal pump | |
| CN113283028A (en) | Fault diagnosis method for gear of gear box | |
| Gundewar et al. | Rolling element bearing fault diagnosis using supervised learning methods-artificial neural network and discriminant classifier | |
| CN107490477B (en) | The Fault Diagnosis of Gear Case method compared based on frequency spectrum kernel density function correlation | |
| Han et al. | Fault diagnosis of rolling bearings using dual-tree complex wavelet packet transform and time-shifted multiscale range entropy | |
| Lihui et al. | Fault diagnosis of the planetary gearbox based on ssDAG-SVM | |
| Sakthivel et al. | Effect of kernel function in support vector machine for the fault diagnosis of pump | |
| Sakthivel et al. | Decision support system using artificial immune recognition system for fault classification of centrifugal pump |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190823 |
|
| RJ01 | Rejection of invention patent application after publication |