CN117973853A - Dynamic FMEA (failure mode and effect analysis) management method based on fusion analysis method - Google Patents
Dynamic FMEA (failure mode and effect analysis) management method based on fusion analysis method Download PDFInfo
- Publication number
- CN117973853A CN117973853A CN202410094054.2A CN202410094054A CN117973853A CN 117973853 A CN117973853 A CN 117973853A CN 202410094054 A CN202410094054 A CN 202410094054A CN 117973853 A CN117973853 A CN 117973853A
- Authority
- CN
- China
- Prior art keywords
- fault
- fmea
- data
- analysis
- equipment
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 40
- 238000011058 failure modes and effects analysis Methods 0.000 title claims abstract description 30
- 238000007726 management method Methods 0.000 title claims abstract description 17
- 230000004927 fusion Effects 0.000 title claims abstract description 14
- 238000001514 detection method Methods 0.000 claims abstract description 26
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 238000005259 measurement Methods 0.000 claims abstract description 10
- 238000004364 calculation method Methods 0.000 claims abstract description 6
- 238000007621 cluster analysis Methods 0.000 claims abstract description 5
- 238000011156 evaluation Methods 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 9
- 238000012423 maintenance Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000000034 method Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 4
- 238000005336 cracking Methods 0.000 claims description 3
- 230000007547 defect Effects 0.000 claims description 3
- 230000003647 oxidation Effects 0.000 claims description 3
- 238000007254 oxidation reaction Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000003449 preventive effect Effects 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 abstract description 3
- 230000005611 electricity Effects 0.000 abstract description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 abstract description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a dynamic FMEA management method based on a fusion analysis method, which comprises the steps of constructing an FMEA fault mode library, defining a risk factor dictionary library comprising severity, incidence and detection degree, constructing a fault incidence measurement model, and finally calculating a risk priority number RPN; the invention combines various analysis algorithms such as a trend analysis method, a Weibull model, a fast Fourier transform and a cluster analysis model, so that the fault occurrence degree measurement model improves the accuracy and the efficiency; a fault mode library is defined aiming at hydropower industry specifications, and a knowledge base is provided for dynamic FMEA; aiming at the water and electricity industry specification, the grade division of the severity, the occurrence degree and the detection degree of the fault mode is defined, and a basis is provided for calculating the risk priority; the dynamic FMEA management is realized, the fault occurrence degree and the risk priority number can be intelligently and automatically calculated, the possible development trend of the fault occurrence degree and the risk priority number can be predicted according to the calculation result, and different-level alarms can be sent out.
Description
Technical Field
The invention relates to the field of industrial Internet hydropower, in particular to a dynamic FMEA (field programmable effect enhanced analysis) management method based on a fusion analysis method.
Background
The existing fault analysis and risk assessment method based on the FMEA principle often lacks an intelligent and automatic dynamic management function, and in the actual condition that production equipment does not stop rotating for 24 hours, workers hardly find faults and related risks in time; in addition, the prior art is not combined with a fault incidence model based on data driving, and lacks support of actual production data, so that the system is not objective enough and does not conform to the running condition of actual equipment, and therefore, a dynamic FMEA management method based on a fusion analysis method is required to be designed to solve the problems.
Disclosure of Invention
The invention aims to provide a dynamic FMEA management method based on a fusion analysis method, which combines a machine learning and analysis algorithm model with an FMEA principle to realize intelligent and automatic calculation of fault occurrence and risk priority; the method can automatically identify the fault mode, forecast the possible development trend and evaluate the influence of the fault mode on the system risk, and once the fault is detected or the risk is evaluated, the system can send out corresponding alarms and provide corresponding fault removal suggestions.
In order to achieve the technical effects, the technical scheme of the invention is as follows:
a dynamic FMEA management method based on a fusion analysis method comprises the following steps:
s1, constructing an FMEA fault mode library, wherein the fault mode is defined as a mode that equipment fails to meet or provide expected functions;
s2, defining a risk factor dictionary library, wherein the risk factors comprise severity, occurrence degree and detection degree, and maintaining relevant basic fault mode data, severity, occurrence degree and detection degree criterion data and corresponding relations thereof; defining a plurality of measure libraries, including a preventive measure library, a detection measure library and a maintenance measure library, wherein the measure libraries provide suggestions and measures for the final FMEA result;
s3, constructing a fault occurrence degree measurement model;
s301, acquiring equipment maintenance data, test detection data and equipment operation data from a data source, wherein the data is used as a data base of a fault occurrence degree measure model;
S302, preprocessing data according to an analysis algorithm to correspond to a format required by the analysis algorithm; combining a plurality of analysis algorithms, carrying out fault occurrence degree calculation in multiple dimensions from different aspects;
S303, data normalization: carrying out normalization processing on the result dimension calculated by each analysis algorithm through some data normalization algorithms, and processing the data to the middle of 1-10 as a final fault occurrence degree measurement result;
S4, calculating a risk priority number RPN;
and S5, searching corresponding suggestions and measures in a measure library according to the risk priority number of the fault mode to form a final fault report.
Preferably, in step S1, the failure mode includes component cracking, component deformation, and component oxidation.
Preferably, in step S2, the severity is an evaluation of the degree of influence of the failure mode of the equipment or the equipment component; the occurrence degree is the evaluation of the occurrence frequency of the failure modes of the equipment and the equipment parts; the detection measure is an evaluation of the extent to which the device and device components detect the cause of the fault or the failure mode.
Preferably, in step S302, the plurality of analysis algorithms includes trend analysis, weibull model, fast fourier transform and cluster analysis model.
Preferably, in step S4, the method for calculating the risk priority number RPN is as follows:
RPN = S×O×D;
wherein S is the severity of the failure mode, O is the occurrence, and D is the detection;
The risk priority RPN is used to measure possible equipment defects, with larger values indicating higher risk of potential equipment problems.
The dynamic FMEA management method based on the fusion analysis method has the advantages that:
1, the invention combines various analysis algorithms such as a trend analysis method, a Weibull model, a fast Fourier transform and a cluster analysis model, so that the fault occurrence degree measurement model improves the accuracy and the efficiency;
2, the invention defines a fault mode library aiming at the water and electricity industry standard and provides a knowledge base for dynamic FMEA;
3, aiming at the water and electricity industry specification, the invention defines the grade division of the severity, the occurrence degree and the detection degree of the fault mode, and provides a basis for calculating the risk priority number;
The invention realizes dynamic FMEA management, can intelligently and automatically calculate the fault occurrence degree and risk priority, predicts the trend of possible development according to the calculation result, and sends out different-level alarms;
5, the invention predicts the fault occurrence probability in multiple aspects and multiple angles, greatly improves the efficiency and the accuracy, and solves the problems that the fault analysis method based on the FMEA principle on the market at present is not combined with the fault occurrence rate model based on data driving, lacks support of actual production data, is not objective enough and does not accord with the running condition of actual equipment.
Drawings
FIG. 1 is a schematic flow chart of the present invention;
FIG. 2 is a schematic flow chart of the present invention for constructing a failure rate prediction model.
Detailed Description
Embodiment one:
as shown in fig. 1, a dynamic FMEA management method based on a fusion analysis method includes the following steps:
s1, constructing an FMEA fault mode library, wherein the fault mode is defined as a mode that equipment fails to meet or provide expected functions;
s2, defining a risk factor dictionary library, wherein the risk factors comprise severity, occurrence degree and detection degree, and maintaining relevant basic fault mode data, severity, occurrence degree and detection degree criterion data and corresponding relations thereof; defining a plurality of measure libraries, including a preventive measure library, a detection measure library and a maintenance measure library, wherein the measure libraries provide suggestions and measures for the final FMEA result;
s3, as shown in FIG. 2, constructing a fault occurrence degree measurement model;
s301, acquiring equipment maintenance data, test detection data and equipment operation data from a data source, wherein the data is used as a data base of a fault occurrence degree measure model;
S302, preprocessing data according to an analysis algorithm to correspond to a format required by the analysis algorithm; combining a plurality of analysis algorithms, carrying out fault occurrence degree calculation in multiple dimensions from different aspects;
S303, data normalization: carrying out normalization processing on the result dimension calculated by each analysis algorithm through some data normalization algorithms, and processing the data to the middle of 1-10 as a final fault occurrence degree measurement result;
S4, calculating a risk priority number RPN;
and S5, searching corresponding suggestions and measures in a measure library according to the risk priority number of the fault mode to form a final fault report.
Preferably, in step S1, the failure mode includes component cracking, component deformation, and component oxidation.
Preferably, in step S2, the severity is an evaluation of the degree of influence of the failure mode of the equipment or the equipment component; the occurrence degree is the evaluation of the occurrence frequency of the failure modes of the equipment and the equipment parts; the detection measure is an evaluation of the extent to which the device and device components detect the cause of the fault or the failure mode.
Preferably, in step S302, the plurality of analysis algorithms includes trend analysis, weibull model, fast fourier transform and cluster analysis model.
Preferably, in step S4, the method for calculating the risk priority number RPN is as follows:
RPN = S×O×D;
wherein S is the severity of the failure mode, O is the occurrence, and D is the detection;
The risk priority RPN is used to measure possible equipment defects, with larger values indicating higher risk of potential equipment problems.
Embodiment two:
take the oil leakage fault of the oil groove device in the bearing as an example.
Step one: when the system performs oil leakage fault detection of the oil tank, a fault mode library is searched for a fault mode of oil leakage of the oil tank.
Step two: and inquiring the severity level and the detection level corresponding to the fault mode. The severity level was 6 and the detection level was 4.
Step three: constructing a fault occurrence degree measurement model, and acquiring operation data of oil groove deduction equipment: and (5) carrying related data such as oil level of the oil groove, thrust bush temperature, oil density and the like into a Weibull distribution model to obtain a result with a value of 0.6.
Step four: and (3) because the range of the severity and the detection degree is 0-10, the result of the occurrence degree in the step three needs to be multiplied by 10, and the normalized occurrence degree can be obtained, namely the occurrence degree is 6.
Step five: the risk priority is obtained by multiplying the severity in the second step, the detection degree and the normalized occurrence degree in the fourth step, i.e., 6x4x6=144.
Step six: and searching corresponding suggestions and measures in a measure library according to the risk priority number of the fault mode to form a final fault report.
The above embodiments are merely preferred embodiments of the present application, and should not be construed as limiting the present application, and the embodiments and features of the embodiments of the present application may be arbitrarily combined with each other without collision. The protection scope of the present application is defined by the claims, and the protection scope includes equivalent alternatives to the technical features of the claims. I.e., equivalent replacement modifications within the scope of this application are also within the scope of the application.
Claims (5)
1. The dynamic FMEA management method based on the fusion analysis method is characterized by comprising the following steps of:
s1, constructing an FMEA fault mode library, wherein the fault mode is defined as a mode that equipment fails to meet or provide expected functions;
s2, defining a risk factor dictionary library, wherein the risk factors comprise severity, occurrence degree and detection degree, and maintaining relevant basic fault mode data, severity, occurrence degree and detection degree criterion data and corresponding relations thereof; defining a plurality of measure libraries, including a preventive measure library, a detection measure library and a maintenance measure library, wherein the measure libraries provide suggestions and measures for the final FMEA result;
s3, constructing a fault occurrence degree measurement model;
s301, acquiring equipment maintenance data, test detection data and equipment operation data from a data source, wherein the data is used as a data base of a fault occurrence degree measure model;
S302, preprocessing data according to an analysis algorithm to correspond to a format required by the analysis algorithm; combining a plurality of analysis algorithms, carrying out fault occurrence degree calculation in multiple dimensions from different aspects;
S303, data normalization: carrying out normalization processing on the result dimension calculated by each analysis algorithm through some data normalization algorithms, and processing the data to the middle of 1-10 as a final fault occurrence degree measurement result;
S4, calculating a risk priority number RPN;
and S5, searching corresponding suggestions and measures in a measure library according to the risk priority number of the fault mode to form a final fault report.
2. The fusion analysis method-based dynamic FMEA management method of claim 1, wherein: in step S1, failure modes include component cracking, component deformation, and component oxidation.
3. The fusion analysis method-based dynamic FMEA management method of claim 1, wherein: in step S2, the severity is an evaluation of the degree of influence of the failure mode of the equipment and the equipment components; the occurrence degree is the evaluation of the occurrence frequency of the failure modes of the equipment and the equipment parts; the detection measure is an evaluation of the extent to which the device and device components detect the cause of the fault or the failure mode.
4. The fusion analysis method-based dynamic FMEA management method of claim 1, wherein: in step S302, a variety of analysis algorithms include trend analysis, weibull models, fast Fourier transforms, and cluster analysis models.
5. The fusion analysis method-based dynamic FMEA management method of claim 1, wherein: in step S4, the method for calculating the risk priority number RPN is as follows:
RPN = S×O×D;
wherein S is the severity of the failure mode, O is the occurrence, and D is the detection;
The risk priority RPN is used to measure possible equipment defects, with larger values indicating higher risk of potential equipment problems.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410094054.2A CN117973853A (en) | 2024-01-23 | 2024-01-23 | Dynamic FMEA (failure mode and effect analysis) management method based on fusion analysis method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410094054.2A CN117973853A (en) | 2024-01-23 | 2024-01-23 | Dynamic FMEA (failure mode and effect analysis) management method based on fusion analysis method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117973853A true CN117973853A (en) | 2024-05-03 |
Family
ID=90845140
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410094054.2A Pending CN117973853A (en) | 2024-01-23 | 2024-01-23 | Dynamic FMEA (failure mode and effect analysis) management method based on fusion analysis method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117973853A (en) |
-
2024
- 2024-01-23 CN CN202410094054.2A patent/CN117973853A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109524139B (en) | Real-time equipment performance monitoring method based on equipment working condition change | |
KR102455338B1 (en) | Defect detection method and apparatus, model training method and apparatus, and device and storage medium | |
CN108445410A (en) | A kind of method and device of monitoring accumulator group operating status | |
Juuso et al. | Intelligent scaling of features in fault diagnosis | |
US20120253694A1 (en) | Method and apparatus for judging status of mechanical system | |
CN115469176A (en) | Digital twin power grid risk assessment system based on data model | |
CN113204919B (en) | Method and device for predicting state of main transformer conservator based on digital twinning and electronic equipment | |
CN117270514A (en) | Production process whole-flow fault detection method based on industrial Internet of things | |
CN113758604B (en) | Method, device, equipment and storage medium for detecting running state of electrical equipment | |
CN112734201B (en) | Multi-equipment overall quality evaluation method based on expected failure probability | |
CN117331790A (en) | Machine room fault detection method and device for data center | |
CN117973853A (en) | Dynamic FMEA (failure mode and effect analysis) management method based on fusion analysis method | |
CN110794683A (en) | Wind power gear box state evaluation method based on deep neural network and kurtosis characteristics | |
CN114837902B (en) | Health degree evaluation method, system, equipment and medium for wind turbine generator | |
CN114527331B (en) | Capacitor analysis method and system | |
RU2668852C1 (en) | Method and system of accounting residual operation life of turbo-aggregate components | |
Hu et al. | Degradation assessment of bearing fault using SOM network | |
Sun et al. | Research on condition monitoring of key components in wind turbine based on cointegration analysis | |
CN110874088B (en) | Monitoring method of ship key equipment system based on multi-dimensional vector model | |
CN117851956B (en) | Electromechanical equipment fault diagnosis method, system and terminal based on data analysis | |
CN117272844B (en) | Method and system for predicting service life of distribution board | |
CN110927488B (en) | Transformer running state monitoring method based on membership function | |
CN117454121B (en) | Data analysis processing method and system based on power plant safety precaution | |
Qi et al. | Prognostics of rolling element bearings based on entropy indicators and particle filtering | |
CN117348541A (en) | Method and system for monitoring health faults of industrial Internet equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination |