CN107153748A - Based on weighting core pivot element analysis（WKPCA）Rotary kiln method for diagnosing faults - Google Patents
Based on weighting core pivot element analysis（WKPCA）Rotary kiln method for diagnosing faults Download PDFInfo
- Publication number
- CN107153748A CN107153748A CN201710426287.8A CN201710426287A CN107153748A CN 107153748 A CN107153748 A CN 107153748A CN 201710426287 A CN201710426287 A CN 201710426287A CN 107153748 A CN107153748 A CN 107153748A
- Authority
- CN
- China
- Prior art keywords
- rotary kiln
- core pivot
- weighting
- core
- variable
- 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
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000004458 analytical method Methods 0.000 title claims abstract description 32
- 238000001514 detection method Methods 0.000 claims abstract description 19
- 239000011159 matrix material Substances 0.000 claims abstract description 10
- 102000008297 Nuclear Matrix-Associated Proteins Human genes 0.000 claims abstract description 9
- 108010035916 Nuclear Matrix-Associated Proteins Proteins 0.000 claims abstract description 9
- 210000000299 nuclear matrix Anatomy 0.000 claims abstract description 9
- 230000007257 malfunction Effects 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims abstract description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 10
- 238000003745 diagnosis Methods 0.000 abstract description 6
- 238000002405 diagnostic procedure Methods 0.000 abstract description 2
- 239000004568 cement Substances 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 8
- 239000002994 raw material Substances 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 5
- 239000000463 material Substances 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000002912 waste gas Substances 0.000 description 3
- BVKZGUZCCUSVTD-UHFFFAOYSA-L Carbonate Chemical compound [O-]C([O-])=O BVKZGUZCCUSVTD-UHFFFAOYSA-L 0.000 description 2
- 238000001354 calcination Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- BVKZGUZCCUSVTD-UHFFFAOYSA-N carbonic acid Chemical compound OC(O)=O BVKZGUZCCUSVTD-UHFFFAOYSA-N 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001311 chemical methods and process Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 210000003739 neck Anatomy 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000001172 regenerating effect Effects 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Muffle Furnaces And Rotary Kilns (AREA)
Abstract
Rotary kiln method for diagnosing faults disclosed by the invention based on weighting core pivot element analysis, its step is：Gather the training sample data under normal condition and pre-process, the data after processing are mapped to higher dimensional space, nuclear matrix is obtained；The characteristic value and eigenmatrix of nuclear matrix are calculated, kernel pivot model is set up, obtains the core pivot variable under normal condition；The density fonction of each core pivot variable under normal condition is calculated using Density Estimator function；SPE controls limit and T are calculated according to core pivot variable2Control limit；The detection sample data under malfunction is gathered in real time and is pre-processed；Bring each core pivot variable for detecting sample into corresponding density fonction, obtain the weighted value of each core pivot variable, set up weight matrix；SPE statistics and T are calculated according to the core pivot variable after weighting2Statistic, with obtain before control limit be compared, whether decision-making system breaks down.The diagnostic method that the present invention is provided, rationally there is provided the accuracy of fault diagnosis for its step.
Description
Technical field
The present invention relates to process control technology field, more particularly to the rotary kiln fault diagnosis based on weighting core pivot element analysis
Method.
Background technology
Cement is widely used in civilian, industrial, water conservancy and traffic as one of basic raw material of the development of the national economy
Etc. engineering, cement industry has become the important symbol of national economy social development levels and comprehensive strength.New type nonaqueous cement
Production technology be using suspended preheater and predecomposition technology as core, using modern scientific theory and technology, using computer and
Its network information technology carries out the complex art of manufacture of cement, with high-quality, efficient, energy-saving and environmental protection and sustainable development etc.
Feature.
Nsp kiln is made up of preheater, dore furnace, rotary kiln, four subsystems of efficient cooler, mainly undertakes cement
The preheating of clinker burning process, decompose, burn till, cooling down each phased mission.Wherein nsp kiln stable operation is that production status is good
Good important symbol, so ensureing that normally operation is highly important to nsp kiln.Although nsp kiln is equipped with computer behaviour
Action control system, has the advantages that time saving, timely and is difficult error, also have many diagnostic methods to apply the event in cement rotary kiln
In barrier diagnosis, but for current technology level, some places need for human assistance completion, it is therefore desirable to improve back
The OBD technology of rotary kiln.
Pivot analysis (PCA) is a kind of multivariate statistical method, in many necks such as management, data statistics, process detections
Domain is widely used, and the basic thought of its algorithm is exactly to become multiple linear correlation variable compressions for minority is incoherent
Amount, by reducing data dimension, removes data invalid to fault diagnosis in information, chooses quantity less as far as possible and can wrap
Data containing most of effective information.
The advantage of the algorithm is need not there is deep understanding to the structure and operation mechanism of system, and can drop
Low data dimension, by it is invalid, include the few data of effective information and reject, simplify data, reduce the calculating during diagnosis
Amount.Pivot analysis has successful application in the application of chemical process, but the application in cement rotary kiln field is few.Especially
When being that small fault occurs for system, the method based on pivot analysis or core pivot element analysis can not be supervised accurately and timely to system
Survey, the stable operation to nsp kiln brings certain hidden danger.
The content of the invention
The purpose of the present invention is that there is provided the rotary kiln based on weighting core pivot element analysis (WKPCA) for above-mentioned technical problem
Method for diagnosing faults, its step rationally, is assigned higher in the detection on the basis of Weighted Kernel pca method to fault data
Weight, its fault signature is amplified, can occur small fault when more effectively be monitored, improve
The validity of rotary kiln malfunction monitoring.
Technical scheme
Examined in order to solve the above technical problems, the present invention provides the rotary kiln failure based on weighting core pivot element analysis (WKPCA)
Disconnected method, specifically includes following steps：
Data are done normalization pretreatment, after processing by the training sample data under S1, collection rotary kiln normal condition
Sample data is mapped to higher dimensional space, obtains nuclear matrix；
S2, calculates the characteristic value and eigenmatrix of nuclear matrix, sets up kernel pivot model, obtain under rotary kiln normal condition
Core pivot variable；
S3, the density fonction of each core pivot variable under normal condition is calculated using Density Estimator function；
S4, SPE controls limit and T are calculated according to core pivot variable2Control limit；
S5, pretreatment is normalized in data by the detection sample data under collection rotary kiln malfunction in real time；
S6, brings each core pivot variable of each group of detection sample into corresponding density fonction, obtains each core pivot
The weighted value of variable, sets up weight matrix；
S7, SPE statistics and T are calculated according to the core pivot variable after weighting2Statistic, with the control that obtains before limit into
Row compares, and determines whether to break down；
S8, if system prompt breaks down, determines that position occurs for rotary kiln failure using contribution plot method.
Further, the pivot t of the higher dimensional spaceiFor
Further, in step s3, the Density Estimator function isKernel function is adopted
Use gaussian kernel function.
Further, in step s 6, the weighted value isWherein, α is density threshold,
Further, in step s 8, the contribution plot based on SPE is calculated,
Further, in step s 8, it is described to be based on T2Contribution plot calculate,
Beneficial effect of the present invention：
The rotary kiln method for diagnosing faults based on weighting core pivot element analysis (WKPCA) that the present invention is provided, its step is reasonable,
Assign higher weight on the basis of Weighted Kernel pca method in the detection to fault data, its fault signature is put
Greatly, it more accurately can effectively be monitored when occurring small fault, improve the validity of rotary kiln malfunction monitoring.
Brief description of the drawings
By the detailed description made in conjunction with the following drawings, above-mentioned advantage of the invention will be apparent and be easier reason
Solution, these accompanying drawings are schematical, are not intended to limit the present invention, wherein：
Fig. 1 is the flow chart of the present invention based on weighting core pivot element analysis method for diagnosing faults；
Fig. 2 is precalcining kiln cement calcination process schematic diagram；
Fig. 3 is the SPE and T of one embodiment based on pivot analysis method for diagnosing faults2Count spirogram；
Fig. 4 is the SPE and T of one embodiment based on weighting core pivot element analysis method for diagnosing faults2Count spirogram；
Fig. 5 is based on SPE and T of each variable to trouble point in weighting core pivot element analysis2Contribution plot；
Fig. 6 is the SPE and T of second embodiment based on pivot analysis method for diagnosing faults2Count spirogram；
Fig. 7 is the SPE and T of second embodiment based on weighting core pivot element analysis method for diagnosing faults2Count spirogram.
Embodiment
With reference to specific embodiments and the drawings, the rotary kiln failure of the present invention based on weighting core pivot element analysis is examined
Disconnected method is described in detail.
The embodiment recorded herein is the specific embodiment of the present invention, and the design for illustrating the present invention is
It is explanatory and exemplary, it should not be construed as the limitation to embodiment of the present invention and the scope of the invention.Except the reality recorded herein
Exception is applied, those skilled in the art can also be based on the application claims and specification disclosure of that using aobvious and easy
The other technical schemes seen, these technical schemes include any obviously replacing using to making for the embodiment recorded herein
The technical scheme changed and changed.
The rotary kiln method for diagnosing faults based on weighting core pivot element analysis (WKPCA) that the present invention is provided, its flow chart, such as
Shown in Fig. 1, it specifically includes following steps：
Data are done normalization pretreatment, after processing by the training sample data under S1, collection rotary kiln normal condition
Sample data is mapped to higher dimensional space, obtains nuclear matrix；
Specifically, core pivot element analysis (KPCA) algorithm is that it can be more preferable in directly improving that pca method is carried out
Adaptation nonlinear situation processing, in the analysis in face of nonlinear data, can more be applicable.
The concept of kernel function is introduced in core pivot, it is assumed that there is a function in luv space and meetWhereinFor φ (i) in higher dimensional space and φ (j) inner product, then function K is called
Kernel function.
The calculating process of this method is similar to pivot analysis, is all to obtain feature sky by finding the characteristic vector of variance matrix
Between in pivot.But before Eigenvalues Decomposition is carried out, first have to input matrix being mapped in higher dimensional space, set first
Determine input sample X ∈ Rn, input matrix is mapped to the variance matrix in high-dimensional feature space, feature space using Nonlinear Mapping
For
The characteristic vector for solving the variance matrix obtains pivot in feature space, and its characteristic value and characteristic vector are as follows
Have for all nonzero eigenvalues
That is characteristic vector ν can be regarded asLinear combination.It is simultaneously rightInner product is asked to can obtain：
Kernel function is updated in formula, above formula is subjected to abbreviation, equation below is obtained
Wherein, α=[α1,α2,…αl]T, nuclear matrix K is with Kj,kFor the matrix of element.
S2, calculates the characteristic value and eigenmatrix of nuclear matrix, sets up kernel pivot model, obtain under rotary kiln normal condition
Core pivot variable；
The process for calculating pivot number is consistent with the choosing method of pivot in pca method, then calculates higher dimensional space
Pivot tiFor
After the core pivot for obtaining higher dimensional space, further it is modeled using pca method, obtains core pivot element analysis
Model.
S3, the density fonction of each core pivot variable under normal condition is calculated using Density Estimator function；
In step s3, the Density Estimator function isKernel function uses Gaussian kernel
Function.
Density Estimator function such as formula can be drawn by arranging
S4, SPE controls limit and T are calculated according to core pivot variable2Control limit；
S5, pretreatment is normalized in data by the detection sample data under collection rotary kiln malfunction in real time；
S6, brings each core pivot variable of each group of detection sample into corresponding density fonction, obtains each core pivot
The weighted value of variable, sets up weight matrix；
In step s 6, the weighted value isWherein, α is density threshold,
Specifically, when density estimation value is more than the threshold value, it is believed that data are in normal range (NR), without departing from normal condition, because
It is 1 that this, which assigns weights,.When density estimation value is less than the threshold value, the pivot variable of detection sample deviate from normal condition, and it is estimated
Evaluation is smaller, illustrates bigger to failure contribution degree, therefore assigns weights β.
Some pivot variable deviation normal condition of current detection sample data is bigger, and weights β is also bigger.Pass through weighting
Difference between pivot variable afterwards becomes big, and fault sample data and normal sample data just can be distinguished preferably, be built
Vertical monitoring statisticss amount is also just more efficient.
S7, SPE statistics and T are calculated according to the core pivot variable after weighting2Statistic, with the control that obtains before limit into
Row compares, and determines whether to break down；
S8, if system prompt breaks down, determines that position occurs for rotary kiln failure using contribution plot method.
Specifically, in step s 8, the contribution plot based on SPE is calculated,
It is described to be based on T2Contribution plot calculate,
Fig. 2 is precalcining kiln cement calcination process schematic diagram, and raw material first are from the boosted machine of raw material silo and calcined by rotary kiln
The waste gas of generation enters in suspended preheater C1~C5 jointly, and wherein preheater has heat exchange function and gas-solid separation function, fills
Divide and raw material are heated using the heat in waste gas, subsequently into next stage preheater.Raw material enter calcined by rotary kiln it
It is preceding to be preheated using waste gas.Dore furnace is arranged on before rotary kiln, by the carbonic acid salinity of most heat dissipation during clinker burning
Solution preocess moves to progress in dore furnace, assume responsibility for the carbonate decomposition task carried out originally in rotary kiln, make burning, heat exchange and
Carbonate decomposition process is optimized, and clinker burning technique more attains perfection；And fuel all traditionally will be added by kiln hood
Method, is improved to add from kiln hood on a small quantity, most of to be added from dore furnace, improves the heating power Distribution Pattern in kiln system.
Rotary kiln is made up of cylinder, wheel belt, support roller, gear wheel, transmission device and sealing device etc..Material is by preheating
Enter after device and dore furnace in rotary kiln, as kiln body is rotated, material frictionally is taken up, because cylinder has certain oblique
Degree, material can be moved from kiln tail to kiln hood, and the rotation so constantly circulated, material is progressively advanced and calcined, and raw material are in kiln
Interior generation physical-chemical reaction, eventually forms clinker.Finally clinker is cooled down via grate-cooler, with meet clinker conveyor,
The requirement that storage and cement are crushed, and grate-cooler also carries the recovery task for a large amount of heat contents taken out of to clinker discharging, will
These energy regeneratings are reused.
First embodiment：
Emulation experiment is carried out by taking certain large-scale cement rotary kiln for producing 2500t clinkers daily as an example, for whole precalcining system
Fault detect for, it should using the temperature and pressure of each key position be used as detection emphasis.Gone out with the kiln end temperature of variable 1
Exemplified by existing failure, failure 1 is that unexpected rise occurs for kiln end temperature, sets failure and is lighted as system in the 101st sampling at kiln tail
The elevated both phase step fault of generation temperature.It is first according to the criterion selection pivot number that accumulative variance contribution ratio is more than 0.8.
Fault detect is carried out with pca method and Weighted Kernel pca method respectively, SPE and T is calculated2Control limit
And statistic.As can be seen from Figure 3 during fault detect is carried out using PCA methods, abscissa represents sampling instant,
Ordinate represents statistics value, and two dotted lines represent SPE and T2Control limit, curve represents SPE and T2Statistic, when equipment operation
When being in normal condition, SPE and T2Statistic is in below control limit, but after the failure occurs, SPE statistic and T2System
Metering is the display system failure at some moment, but there occurs failure during can not persistently detecting, it is impossible to continuous
Alarm, good monitoring effect can not be played in detection.
In the detection process after adding weight, it is observed that can be once in a while in system normal course of operation from Fig. 4
The situation of wrong report is produced, but is due to SPE statistic and T2Statistic is out of order without display simultaneously, thus while in system
The situation beyond control limit occurs in statistic in normal course of operation, but two statistics are without simultaneously beyond control limit
It will not cause to show the system failure.Start in the 101st sampled point, SPE and T2Statistic is above control limit, and two systems
Metering is continuously detected statistical value and limited beyond control simultaneously, and explanation system breaks down in the process of running, as a result real with emulation
The setting tested is consistent.
As can be drawn from Figure 5, according to weighting core pivot element analysis algorithm, the calculating to contribution rate, the kiln tail temperature of variable 1 are passed through
Degree is in SPE and T2Contribution rate be both greater than its dependent variable, show that the contribution that variable 1 makes in the failure is more than its dependent variable,
It is consistent with the abort situation that sets before, and can continue detection after failure generation to be out of order, do not fail to report,
Situations such as wrong report.
Second embodiment：
Occur temperature drift as trouble point 2 using kiln end temperature, the failure of variable 1 is set to the kiln tail from the k=101 moment
The slowly varying failure of temperature occurs for place, has carried out fault diagnosis test to it using this method, as can be seen from Figure 6 pivot
Analysis is able to detect that drifting fault occurs for temperature, although be able to detect that two statistics exceed control limit, but in k=
115 moment detected failure, it is impossible to send alarm in time.
But 8 moment of the detection method after weighting as can be seen from Figure 7 after temperature is drifted about, that is, k
=108 moment limited with regard to detection statistic well beyond control, detected generation of being out of order, compared with single PCA methods much sooner
It is accurately detected the generation of failure.
The rotary kiln method for diagnosing faults based on weighting core pivot element analysis (WKPCA) that the present invention is provided, its step is reasonable,
Assign higher weight on the basis of Weighted Kernel pca method in the detection to fault data, its fault signature is put
Greatly, it more accurately can effectively be monitored when occurring small fault, improve the validity of rotary kiln malfunction monitoring.
The present invention is not limited to the above-described embodiments, and anyone can draw other various forms under the enlightenment of the present invention
Product, it is every that there is technical side identical or similar to the present application however, make any change in its shape or structure
Case, is within the scope of the present invention.
Claims (6)
1. the rotary kiln method for diagnosing faults based on weighting core pivot element analysis, it is characterised in that comprise the following steps：
Data are done normalization pretreatment, by the sample after processing by the training sample data under S1, collection rotary kiln normal condition
Data are mapped to higher dimensional space, obtain nuclear matrix；
S2, calculates the characteristic value and eigenmatrix of nuclear matrix, sets up kernel pivot model, obtain the core master under rotary kiln normal condition
Metavariable；
S3, the density fonction of each core pivot variable under normal condition is calculated using Density Estimator function；
S4, SPE controls limit and T are calculated according to core pivot variable2Control limit；
S5, pretreatment is normalized in data by the detection sample data under collection rotary kiln malfunction in real time；
S6, brings each core pivot variable of each group of detection sample into corresponding density fonction, obtains each core pivot variable
Weighted value, set up weight matrix；
S7, SPE statistics and T are calculated according to the core pivot variable after weighting2Statistic, with obtain before control limit compared
Compared with determining whether to break down；
S8, if system prompt breaks down, determines that position occurs for rotary kiln failure using contribution plot method.
2. the rotary kiln method for diagnosing faults according to claim 1 based on weighting core pivot element analysis, it is characterised in that described
The pivot ti of higher dimensional space is
3. the rotary kiln method for diagnosing faults according to claim 1 based on weighting core pivot element analysis, it is characterised in that in step
In rapid S3, the Density Estimator function isKernel function uses gaussian kernel function.
4. the rotary kiln method for diagnosing faults according to claim 1 based on weighting core pivot element analysis, it is characterised in that in step
In rapid S6, the weighted value isWherein, α is density threshold,
5. the rotary kiln method for diagnosing faults according to claim 1 based on weighting core pivot element analysis, it is characterised in that in step
In rapid S8, the contribution plot based on SPE is calculated,
6. the rotary kiln method for diagnosing faults according to claim 1 based on weighting core pivot element analysis, it is characterised in that in step
In rapid S8, the contribution plot based on T2 is calculated,
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710426287.8A CN107153748A (en) | 2017-06-07 | 2017-06-07 | Based on weighting core pivot element analysis（WKPCA）Rotary kiln method for diagnosing faults |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710426287.8A CN107153748A (en) | 2017-06-07 | 2017-06-07 | Based on weighting core pivot element analysis（WKPCA）Rotary kiln method for diagnosing faults |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107153748A true CN107153748A (en) | 2017-09-12 |
Family
ID=59795714
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710426287.8A Pending CN107153748A (en) | 2017-06-07 | 2017-06-07 | Based on weighting core pivot element analysis（WKPCA）Rotary kiln method for diagnosing faults |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107153748A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108062565A (en) * | 2017-12-12 | 2018-05-22 | 重庆科技学院 | Double pivots-dynamic kernel principal component analysis method for diagnosing faults based on chemical industry TE processes |
| CN108182302A (en) * | 2017-12-13 | 2018-06-19 | 东北大学 | Incipient fault detection method based on modification cluster semi-supervised kernel pivot analysis |
| CN110209145A (en) * | 2019-05-16 | 2019-09-06 | 浙江大学 | One kind being based on the approximate carbon dioxide absorption tower method for diagnosing faults of nuclear matrix |
| CN110717552A (en) * | 2019-10-23 | 2020-01-21 | 智洋创新科技股份有限公司 | Method for determining visible mechanical continuous alarm of power transmission line channel |
| CN111680725A (en) * | 2020-05-28 | 2020-09-18 | 哈尔滨工业大学 | Gas sensor array multi-fault isolation algorithm based on reconstruction contribution |
| CN113031566A (en) * | 2021-03-09 | 2021-06-25 | 上海海事大学 | PCA (principal component analysis) model fault detection method based on online principal component selection and weighting |
| CN113311803A (en) * | 2021-05-17 | 2021-08-27 | 北京航空航天大学 | On-orbit spacecraft flywheel fault detection method based on kernel principal component analysis |
| CN113390641A (en) * | 2021-07-06 | 2021-09-14 | 上海市东方海事工程技术有限公司 | Intelligent early warning and online diagnosis method and system for equipment faults of wind and smoke system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105022355A (en) * | 2014-04-21 | 2015-11-04 | 东北大学 | Cement rotary kiln intelligent optimization control system |
| CN106017925A (en) * | 2016-05-09 | 2016-10-12 | 北京信息科技大学 | Rotary kiln holder wheel bearing fault diagnosis method based on wavelet packet decomposition |
-
2017
- 2017-06-07 CN CN201710426287.8A patent/CN107153748A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105022355A (en) * | 2014-04-21 | 2015-11-04 | 东北大学 | Cement rotary kiln intelligent optimization control system |
| CN106017925A (en) * | 2016-05-09 | 2016-10-12 | 北京信息科技大学 | Rotary kiln holder wheel bearing fault diagnosis method based on wavelet packet decomposition |
Non-Patent Citations (3)
| Title |
|---|
| QINGCHAO JIANG等: "Improved fault detection in nonlinear chemical processes using WKPCA-SVDD", 《THE KOREAN INSTITUTE OF CHEMICAL ENGINEERS》 * |
| 苏中鲜: "基于时序数据挖掘的工业设备异常检测分析", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
| 韩敏等: "基于加权核独立成分分析的故障检测方法", 《控制与决策》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108062565A (en) * | 2017-12-12 | 2018-05-22 | 重庆科技学院 | Double pivots-dynamic kernel principal component analysis method for diagnosing faults based on chemical industry TE processes |
| CN108182302A (en) * | 2017-12-13 | 2018-06-19 | 东北大学 | Incipient fault detection method based on modification cluster semi-supervised kernel pivot analysis |
| CN110209145A (en) * | 2019-05-16 | 2019-09-06 | 浙江大学 | One kind being based on the approximate carbon dioxide absorption tower method for diagnosing faults of nuclear matrix |
| CN110209145B (en) * | 2019-05-16 | 2020-09-11 | 浙江大学 | Carbon dioxide absorption tower fault diagnosis method based on nuclear matrix approximation |
| CN110717552A (en) * | 2019-10-23 | 2020-01-21 | 智洋创新科技股份有限公司 | Method for determining visible mechanical continuous alarm of power transmission line channel |
| CN111680725A (en) * | 2020-05-28 | 2020-09-18 | 哈尔滨工业大学 | Gas sensor array multi-fault isolation algorithm based on reconstruction contribution |
| CN111680725B (en) * | 2020-05-28 | 2023-05-05 | 哈尔滨工业大学 | Gas sensor array multi-fault isolation algorithm based on reconstruction contribution |
| CN113031566A (en) * | 2021-03-09 | 2021-06-25 | 上海海事大学 | PCA (principal component analysis) model fault detection method based on online principal component selection and weighting |
| CN113311803A (en) * | 2021-05-17 | 2021-08-27 | 北京航空航天大学 | On-orbit spacecraft flywheel fault detection method based on kernel principal component analysis |
| CN113390641A (en) * | 2021-07-06 | 2021-09-14 | 上海市东方海事工程技术有限公司 | Intelligent early warning and online diagnosis method and system for equipment faults of wind and smoke system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107153748A (en) | Based on weighting core pivot element analysis（WKPCA）Rotary kiln method for diagnosing faults | |
| CN106647718B (en) | Nonlinear industrial processes fault detection method based on the slow signature analysis of Bayes's core | |
| CN110309886B (en) | Wireless sensor high-dimensional data real-time anomaly detection method based on deep learning | |
| CN107528823A (en) | A kind of network anomaly detection method based on improved K Means clustering algorithms | |
| CN103853152A (en) | Batch process failure monitoring method based on AR-PCA (Autoregressive Principal Component Analysis) | |
| CN108062565A (en) | Double pivots-dynamic kernel principal component analysis method for diagnosing faults based on chemical industry TE processes | |
| Li et al. | Ensemble model of wastewater treatment plant based on rich diversity of principal component determining by genetic algorithm for status monitoring | |
| CN104777830A (en) | Multi-work-condition process monitoring method based on KPCA (kernel principal component analysis) mixture model | |
| CN104914847A (en) | Industrial process fault diagnosis method based on direction kernel partial least square | |
| CN108803465B (en) | A kind of distributed plug and play fault monitoring method based on closed-loop data driving | |
| CN105607631B (en) | The weak fault model control limit method for building up of batch process and weak fault monitoring method | |
| CN109407652A (en) | Multivariable industrial process fault detection method based on major-minor pca model | |
| CN106950945A (en) | A kind of fault detection method based on dimension changeable type independent component analysis model | |
| CN109144039A (en) | A kind of batch process fault detection method keeping extreme learning machine based on timing extension and neighborhood | |
| Huang et al. | Industrial process modeling and monitoring based on jointly specific and shared dictionary learning | |
| Zhang et al. | A new deep convolutional domain adaptation network for bearing fault diagnosis under different working conditions | |
| Tang et al. | Dual attention bidirectional generative adversarial network for dynamic uncertainty process monitoring and diagnosis | |
| Khan et al. | Advanced statistical and meta-heuristic based optimization fault diagnosis techniques in complex industrial processes: a comparative analysis | |
| Yan et al. | Quality-relevant dynamic process monitoring based on dynamic total slow feature regression model | |
| CN106933097A (en) | A kind of Fault Diagnosis for Chemical Process method based on multi-level optimization PCC SDG | |
| Kaib et al. | Improving kernel PCA-based algorithm for fault detection in nonlinear industrial process through fractal dimension | |
| CN105759787B (en) | A kind of method for diagnosing faults having supervision linear dynamic system model based on switching | |
| CN111914888A (en) | Chemical process monitoring method integrating multi-working-condition identification and fault detection | |
| Sun et al. | An enhanced kernel learning data-driven method for multiple fault detection and identification in industrial systems | |
| CN106970301A (en) | A kind of detecting system based on smart home power supply circuit |
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: 20170912 |
|
| RJ01 | Rejection of invention patent application after publication |