CN112559964B - Weight coefficient-based flight control fault probability calculation method - Google Patents
Weight coefficient-based flight control fault probability calculation method Download PDFInfo
- Publication number
- CN112559964B CN112559964B CN202011363326.2A CN202011363326A CN112559964B CN 112559964 B CN112559964 B CN 112559964B CN 202011363326 A CN202011363326 A CN 202011363326A CN 112559964 B CN112559964 B CN 112559964B
- Authority
- CN
- China
- Prior art keywords
- fault
- probability
- data
- calculation
- expert
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Algebra (AREA)
- Evolutionary Biology (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of fault diagnosis, in particular to a calculation method for flight control fault probability based on weight coefficients, wherein an expert knowledge base provides expert calculation data to a fault probability calculation module, and a fault database provides statistical data to the fault probability calculation module; and the fault probability calculation module performs weighted calculation on the expert calculation fault probability and the statistical database according to the expert calculation data and the statistical data to obtain the expert calculation and statistical data weighted fault probability of each fault reason corresponding to the fault. By the aid of the calculation method, the fault probability corresponding to each fault reason and based on the weight coefficient self-adaptive adjustment algorithm can be automatically given, and the problem of low fault positioning accuracy can be effectively solved.
Description
Technical Field
The invention relates to the technical field of fault diagnosis, in particular to a calculation method for flight control fault probability based on a weight coefficient.
Background
The flight control computer of the fly-by-wire flight control system has a self-detection function in the flight control computer, and when the aircraft flight control system has a fault, the flight control computer can detect the fault and record the fault for the ground service maintenance personnel of the aircraft to carry out flight control fault diagnosis. At present, when an airplane has a flight control fault, a ground service maintainer uses flight control ground maintenance equipment to read a fault code recorded by a flight control computer, and then a related technical expert analyzes the fault code to judge a possible fault reason. However, due to the limitation of the self fault detection capability of the airplane, the probability of each fault reason can not be determined only by confirming which reason the fault may be caused by through the fault code, so that the fault cannot be accurately positioned, the troubleshooting efficiency is low, and the waste of manpower and material resources is caused.
Disclosure of Invention
In order to solve the technical problems, the invention provides a calculation method for flight control fault probability based on a weight coefficient, which automatically gives the fault probability corresponding to each fault reason and based on a weight coefficient self-adaptive adjustment algorithm, and can effectively solve the problem of low fault positioning accuracy.
The invention is realized by adopting the following technical scheme:
a flight control fault probability calculation method based on weight coefficients is characterized by comprising the following steps: the system comprises a fault probability calculation module, an expert knowledge base module and a fault database module; the method specifically comprises the following steps:
a. after a flight control system of the airplane breaks down, the expert knowledge base provides expert calculation data to the failure probability calculation module, and the failure database provides statistical data to the failure probability calculation module;
b. and the fault probability calculation module receives data provided by the expert knowledge base module and the fault database module, and performs weighted calculation on the expert calculation fault probability and the statistical database to obtain the expert calculation and statistical data weighted fault probability of each fault reason corresponding to the fault.
The step b of performing weighted calculation on the expert calculation fault probability and the statistical database specifically comprises the following steps:
b1judging whether the weight system self-adaptive adjustment is met or not by the fault probability calculation module according to the statistical data of the statistical database; if not, go to step b2If yes, go to step b3；
b2Setting different interval ranges according to the quantity of the fault data, and setting different fault manual setting weight coefficients according to the different interval ranges; the fault probability calculation module judges the range of the fault data in the fault database, and calculates the weighted fault probability by manually setting a weight coefficient according to the corresponding fault:
Nx＝Nx1*ix+Nx2*(1-ix)，
wherein x is the number of the interval range, NxTo weight the failure probability, Nx1To estimate the probability, N, for the expertx2To count the probability, ixSetting a weight coefficient for manual work;
b3setting different interval ranges for the number of the fault data, judging which interval range the number of the fault data is in the data fault database by the fault probability calculation module, and setting different weight coefficient intervals I for the different interval rangesx(a-b, b > a), calculating the absolute value of the error between the weighted fault probability and the standard statistical probability under different weight coefficients, selecting the weight coefficient corresponding to the minimum absolute value of the error as the optimal adaptive weight coefficient, and calculating the weighted fault probability by the fault probability calculation module through the optimal adaptive weight coefficient:
LAD1＝min(∣Nx1*a％+Nx2*(1-a％)-Nx3)∣、∣Nx1*(a+1)％+Nx2*(1-(a+1)％)-Nx3)∣、…、∣Nx1*b％+Nx2*(1-b％)-Nx3)∣)
ix＝LADx(Ix)
Nx＝Nx1*ix+Nx2*(1-ix)，
wherein x is the number of the interval range, NxTo weight the failure probability, Nx1To estimate the probability, N, for the expertx2Is a phase statistical probability, Nx3Is a standard statistical probability sum ixAnd the optimal weight coefficient is self-adaptive.
The more fault data stored in the fault database, the smaller the weight of the weighted fault probability of the expert calculation probability is, and the larger the weight of the weighted fault probability of the fault statistical data is.
Step b1The method specifically comprises the following steps: and judging whether the number of any fault in the database reaches a preset value.
Said step b2And b3In the method, a fault probability calculation module judges data faultsThe method for determining the range of the fault data quantity in the database comprises the following steps: and comparing the fault data quantity with the interval range in sequence.
The expert knowledge base module is used for storing the fault probability calculated by the expert of each fault reason.
And the fault database module is used for storing the actual fault reason of the flight control fault.
Compared with the prior art, the invention has the beneficial effects that:
1. the flight control fault codes recorded by the flight control computer are weighted in a segmented mode according to the fault data amount stored in the fault database, when the fault data amount meets a certain requirement, the weight coefficient is adjusted in a self-adaptive mode, the weighted fault probability of each fault reason based on statistical data is automatically given, and the positioning accuracy rate of the flight control fault is greatly improved.
2. The more fault data stored in the fault database, the smaller the weight of the fault probability calculated by the expert on the weighted fault probability, the larger the weight of the fault statistical data on the weighted fault probability, and the higher the fault positioning accuracy.
3. And the fault probability calculation module calculates the error absolute value between the predicted fault probability and the standard value under different weight coefficients according to the existing fault statistical data serving as the standard value, selects the weight coefficient corresponding to the minimum error absolute value as the optimal self-adaptive adjustment weight coefficient to predict the fault probability, and is convenient to improve the accuracy of fault positioning.
Drawings
The invention will be described in further detail with reference to the following description taken in conjunction with the accompanying drawings and detailed description, in which:
FIG. 1 is a schematic flow chart of the present invention.
Detailed Description
Example 1
As a basic implementation mode of the invention, the invention comprises a calculation method based on the weight coefficient flight control fault probability, which comprises a fault probability calculation module, an expert knowledge base module and a fault database module; the method specifically comprises the following steps:
a. after a flight control system of the airplane breaks down, the expert knowledge base provides expert calculation data to the failure probability calculation module, and the failure database provides statistical data to the failure probability calculation module;
b. and the fault probability calculation module receives data provided by the expert knowledge base module and the fault database module, and performs weighted calculation on the expert calculation fault probability and the statistical database to obtain the expert calculation and statistical data weighted fault probability of each fault reason corresponding to the fault.
Example 2
As a better implementation mode of the invention, the invention comprises a calculation method based on weight coefficient flight control fault probability, which comprises a fault probability calculation module, an expert knowledge base module and a fault database module; the method specifically comprises the following steps:
a. after a flight control system of the airplane breaks down, the expert knowledge base provides expert calculation data to the failure probability calculation module, and the failure database provides statistical data to the failure probability calculation module;
b. and the fault probability calculation module receives data provided by the expert knowledge base module and the fault database module, and performs weighted calculation on the expert calculation fault probability and the statistical database to obtain the expert calculation and statistical data weighted fault probability of each fault reason corresponding to the fault.
The step b of performing weighted calculation on the expert calculation fault probability and the statistical database specifically comprises the following steps:
b1judging whether the weight system self-adaptive adjustment is met or not by the fault probability calculation module according to the statistical data of the statistical database; if not, go to step b2If yes, go to step b3. Wherein, whether the weight system self-adaptive adjustment is satisfied is judged according to the statistical data of the statistical database: and judging whether any fault in the database reaches a preset value, wherein the preset value can be set according to the actual situation and can be generally 50 times or more.
b2Setting different interval ranges according to different areas according to the number of the fault dataSetting different fault manual setting weight coefficients within the interval range; the fault probability calculation module judges the range of the fault data in the data fault database, and the corresponding fault manual setting weight coefficient corresponds to a manual setting weight calculation formula:
Nx＝Nx1*ix+Nx2*(1-ix)，
wherein x is the number of the interval range, NxTo weight the failure probability, Nx1To estimate the probability, N, for the expertx2Is statistical probability sum ixSetting a weight coefficient for manual work;
b3setting different section ranges for the number of the fault data, and setting different weight coefficient sections I for the different section rangesx(a-b, b > a), the fault probability calculation module judges in which range the fault data quantity in the data fault database is located, calculates the error absolute value between the weighted fault probability and the standard statistical probability under different weight coefficients, selects the weight coefficient corresponding to the minimum error absolute value as the optimal adaptive weight coefficient, and calculates the weighted fault probability through the optimal adaptive weight coefficient:
LAD1＝min(∣Nx1*a％+Nx2*(1-a％)-Nx3)∣、∣Nx1*(a+1)％+Nx2*(1-(a+1)％)-Nx3)∣、…、∣Nx1*b％+Nx2*(1-b％)-Nx3)∣)
ix＝LADx(Ix)
Nx＝Nx1*ix+Nx2*(1-ix)，
wherein x is the number of the interval range, NxTo weight the failure probability, Nx1To estimate the probability, N, for the expertx2Is a phase statistical probability, Nx3Is a standard statistical probability sum ixAnd the optimal weight coefficient is self-adaptive.
Example 3
As the best implementation mode of the invention, the invention comprises a calculation method based on the weight coefficient flight control fault probability, which mainly comprises a fault probability calculation module, an expert knowledge base module and a fault database module. And the fault probability calculation module is used for calculating the expert calculation and statistical data weighted fault probability of each fault reason corresponding to the flight control fault according to the data provided by the expert knowledge base module and the fault database module. The expert knowledge base module is used for storing the fault probability calculated by the expert of each fault reason. And the fault database module is used for storing the actual fault reason of the flight control fault. The more fault data stored in the fault database, the smaller the weight of the fault probability calculated by the expert on the weighted fault probability is, and the larger the weight of the fault statistical data on the weighted fault probability is.
The calculation method specifically comprises the following steps:
a. after a flight control system of the airplane breaks down, the expert knowledge base provides expert calculation data to the failure probability calculation module, and the failure database provides statistical data to the failure probability calculation module;
b. and the fault probability calculation module receives data provided by the expert knowledge base module and the fault database module, and performs weighted calculation on the expert calculation fault probability and the statistical database to obtain the expert calculation and statistical data weighted fault probability of each fault reason corresponding to the fault.
The step b of performing weighted calculation on the expert calculation fault probability and the statistical database specifically comprises the following steps:
b1judging whether the weight system self-adaptive adjustment is met or not by the fault probability calculation module according to the statistical data of the statistical database; if not, go to step b2If yes, go to step b3. The criterion for judging whether the weight system self-adaptive adjustment is satisfied is whether any fault number in the database reaches a preset value, the preset value is set according to actual conditions, and the value in the embodiment is 50.
b2For the number of the specific fault data, different section ranges are set, and in this embodiment, section 1, section 2, and section 3 may be set, where section 1 may be 3549, interval 2 may be 20-34, and interval 3 may be 10-19. And setting different artificial setting weight coefficients of the faults according to different interval ranges. The more fault data stored in the fault database, the smaller the weight of the weighted fault probability of the expert calculation probability is, and the larger the weight of the weighted fault probability of the fault statistical data is. And the fault probability calculation module performs weighted calculation on the expert calculation fault probability and the statistical database.
The weighting calculation method specifically comprises the following steps:
b21judging whether the quantity of the fault data in the data fault database is within the range of the interval 1 by the fault probability calculation module, if not, entering the step b22(ii) a If yes, the fault probability calculation module sets a weight coefficient 1 corresponding to a fault probability weight calculation formula 1 through fault manual work: n is a radical of1＝N11*i1+N12*(1-i1) Wherein N is11Calculating probability, N, for the expert12Is statistical probability, i1For manual setting of a weight coefficient of 1 (20%), N1In order to weight the failure probability, the manually set weighting factor 1 is also preset, and the set weighting factor is larger according to the more failure data recorded by the failure database.
b22Judging the number of fault data in the data fault database is within the range of the interval 2, if not, entering the step b23(ii) a If yes, the fault probability calculation module sets a weight coefficient 2 corresponding to a fault probability weight calculation formula 2 through fault manual work: n is a radical of2＝N21*i2+N22*(1-i2) Wherein N is21Calculating probability, N, for the expert22Is statistical probability, i2Manually set the weighting coefficients 2 (50%) and N2Is a weighted failure probability.
b23Judging the number of fault data in the data fault database is in the range of the section 3, if not, entering the step b24(ii) a If yes, the fault probability calculation module sets a weight coefficient 3 corresponding to a fault probability weight calculation formula 3 through fault manual: n is a radical of3＝N31*i3+N32*(1-i3) Wherein，N31Calculating probability, N, for the expert32Is statistical probability, i3Manually set the weighting coefficients 3 (80%) and N3Is a weighted failure probability.
b24And ending.
b3For the number of the specific fault data, different section ranges are set, and the specific process refers to the right part of the specification in fig. 1, wherein the section ranges include a section 4, a section 5 and a section 6, and the section ranges respectively correspond to the ranges of the section 1, the section 2 and the section 3, namely, the section 4 can be 35-49, the section 5 can be 20-34, and the section 6 can be 10-19. Setting different weight coefficient intervals I for different interval rangesx(a-b, b > a), wherein a can be 5% and b 35%.
The fault probability calculation module calculates the error absolute value between the weighted fault probability and the standard statistical probability under different weight coefficients, selects the weight coefficient corresponding to the minimum error absolute value as the optimal self-adaptive weight coefficient to carry out fault prediction, and the specific method comprises the following steps:
b31judging whether the quantity of the fault data in the data fault database is within the range of 4 by the fault probability calculation module, if not, entering the step b32(ii) a If yes, the fault probability calculation module calculates the optimal self-adaptive weight coefficient i4Correspondingly solving the probability weight of the fault, formula 1:
LAD4＝min(∣N41*5％+N42*(1-5％)-N43)∣、∣N41*6％+N42*(1-6％)-N43)∣、…、∣N41*35％+N42*(1-35％)-N43)∣)
I4＝LAD4(I4)
N4＝N41*i4+N42*(1-i4)；
wherein N is41Calculating probability, N, for the expert42Is a phase statistical probability, N43As standard statistical probability, LAD4Is the minimum absolute value deviation, I4Is a weight coefficient (5-35%) i4The self-adaptive weight coefficient (5-35%) and N are optimal4Weighting the failure probability;
b32judging the number of fault data in the data fault database is within the range of 5, if not, entering the step b33(ii) a If yes, the fault probability calculation module calculates the optimal self-adaptive weight coefficient i5Correspondingly solving a fault probability weight calculation formula 2:
LAD5＝min(∣N51*35％+N52*(1-35％)-N53)∣、∣N51*36％+N52*(1-36％)-N53)∣、…、∣N51*65％+N52*(1-65％)-N53)∣)
I5＝LAD5(I5) Is composed of
N5＝N51*i5+N52*(1-i5)；
Wherein N is51Calculating probability, N, for the expert52Is a phase statistical probability, N53As standard statistical probability, LAD5Is the minimum absolute value deviation, I5Is a weight coefficient (35-65%) i5The weight coefficient (35-65%) and N are adaptive to the optimal5Weighting the failure probability;
b33judging the number of fault data in the data fault database is within the range of 6, if not, entering the step b34(ii) a If yes, the fault probability calculation module calculates the optimal self-adaptive weight coefficient i6And correspondingly solving the fault probability weight calculation formula 3:
LAD6＝min(∣N61*65％+N62*(1-65％)-N63)∣、∣N61*66％+N62*(1-66％)-N63)∣、…、∣N61*95％+N62*(1-95％)-N63)∣)
I6＝LAD6(I6)
N6＝N61*i6+N62*(1-i6)；
wherein N is61To be specially designedFamily calculation probability, N62Is a phase statistical probability, N63As standard statistical probability, LAD6Is the minimum absolute value deviation, I6Is a weight coefficient (65-95%)6The optimal adaptive weight coefficient (65-95%) and N6Weighting the failure probability;
b34and ending.
In summary, after reading the present disclosure, those skilled in the art should make various other modifications without creative efforts according to the technical solutions and concepts of the present disclosure, which are within the protection scope of the present disclosure.
Claims (6)
1. A flight control fault probability calculation method based on weight coefficients is characterized by comprising the following steps: the system comprises a fault probability calculation module, an expert knowledge base module and a fault database module; the method specifically comprises the following steps:
a. after a flight control system of the airplane breaks down, the expert knowledge base provides expert calculation data to the failure probability calculation module, and the failure database provides statistical data to the failure probability calculation module;
b. the fault probability calculation module receives data provided by the expert knowledge base module and the fault database module, and carries out weighted calculation on the expert calculation fault probability and the statistical database to obtain the expert calculation and statistical data weighted fault probability of each fault reason corresponding to the fault;
the step b of performing weighted calculation on the expert calculation fault probability and the statistical database specifically comprises the following steps:
b1judging whether the weight system self-adaptive adjustment is met or not by the fault probability calculation module according to the statistical data of the statistical database; if not, go to step b2If yes, go to step b3；
b2Setting different interval ranges according to the quantity of the fault data, and setting different fault manual setting weight coefficients according to the different interval ranges; the fault probability calculation module judges the range of the fault data in the fault database, and the fault probability calculation module compares the fault data with the range of the section in which the fault data is positionedManually setting a weight coefficient for calculating the weighted fault probability according to the faults:
Nx=Nx1*ix+Nx2*（1-ix），
wherein x is the number of the interval range, NxTo weight the failure probability, Nx1To estimate the probability, N, for the expertx2To count the probability, ixSetting a weight coefficient for manual work;
b3setting different section ranges for the number of the fault data, and setting different weight coefficient sections I for the different section rangesx(a-b, b > a), the fault probability calculation module judges in which range the fault data quantity in the data fault database is located, calculates the error absolute value between the weighted fault probability and the standard statistical probability under different weight coefficients, selects the weight coefficient corresponding to the minimum error absolute value as the optimal adaptive weight coefficient, and calculates the weighted fault probability through the optimal adaptive weight coefficient:
LAD1=min（∣Nx1*a%+Nx2*（1-a%）-Nx3）∣、∣Nx1*（a+1）%+Nx2*（1-（a+1）%）-Nx3）∣、…、∣Nx1*b%+Nx2*（1-b%）-Nx3）∣）
ix=LADx（Ix）
Nx=Nx1*ix+Nx2*（1-ix），
wherein x is the number of the interval range, NxTo weight the failure probability, Nx1To estimate the probability, N, for the expertx2Is a phase statistical probability, Nx3Is a standard statistical probability sum ixAnd the optimal weight coefficient is self-adaptive.
2. The flight control fault probability calculation method based on the weight coefficient as claimed in claim 1, wherein: the more fault data stored in the fault database, the smaller the weight of the expert calculation probability in the weighted fault probability is, and the larger the weight of the fault statistical data in the weighted fault probability is.
3. The flight control fault probability calculation method based on the weight coefficient as claimed in claim 1, wherein: step b1The method specifically comprises the following steps: and judging whether the number of any fault in the database reaches a preset value.
4. The flight control fault probability calculation method based on the weight coefficient as claimed in claim 2, wherein: said step b2And b3The method for judging the range of the fault data quantity in the data fault database by the fault probability calculation module comprises the following steps: and comparing the fault data quantity with the interval range in sequence.
5. The method for calculating flight control fault probability based on the weight coefficient according to claim 1 or 4, characterized in that: the expert knowledge base module is used for storing the fault probability calculated by the expert of each fault reason.
6. The flight control fault probability calculation method based on the weight coefficient as claimed in claim 5, wherein: and the fault database module is used for storing the actual fault reason of the flight control fault.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011363326.2A CN112559964B (en) | 2020-11-27 | 2020-11-27 | Weight coefficient-based flight control fault probability calculation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011363326.2A CN112559964B (en) | 2020-11-27 | 2020-11-27 | Weight coefficient-based flight control fault probability calculation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112559964A CN112559964A (en) | 2021-03-26 |
| CN112559964B true CN112559964B (en) | 2022-05-10 |
Family
ID=75046565
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011363326.2A Active CN112559964B (en) | 2020-11-27 | 2020-11-27 | Weight coefficient-based flight control fault probability calculation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112559964B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113485305B (en) * | 2021-07-28 | 2023-04-07 | 成都飞机工业（集团）有限责任公司 | Aircraft outwork fault diagnosis system and method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107145475A (en) * | 2017-05-16 | 2017-09-08 | 国网四川省电力公司电力科学研究院 | A kind of bushing shell for transformer probability of malfunction computational methods based on Fuzzy-valued |
| CN109034368A (en) * | 2018-06-22 | 2018-12-18 | 北京航空航天大学 | A kind of complex device Multiple Fault Diagnosis Method based on DNN |
| CN111708798A (en) * | 2020-06-30 | 2020-09-25 | 浙江运达风电股份有限公司 | Wind turbine generator fault diagnosis and processing method and system |
| CN111798146A (en) * | 2020-07-09 | 2020-10-20 | 中国第一汽车股份有限公司 | Method for evaluating performance of fuel cell engine |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7539597B2 (en) * | 2001-04-10 | 2009-05-26 | Smartsignal Corporation | Diagnostic systems and methods for predictive condition monitoring |
| US20050096950A1 (en) * | 2003-10-29 | 2005-05-05 | Caplan Scott M. | Method and apparatus for creating and evaluating strategies |
-
2020
- 2020-11-27 CN CN202011363326.2A patent/CN112559964B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107145475A (en) * | 2017-05-16 | 2017-09-08 | 国网四川省电力公司电力科学研究院 | A kind of bushing shell for transformer probability of malfunction computational methods based on Fuzzy-valued |
| CN109034368A (en) * | 2018-06-22 | 2018-12-18 | 北京航空航天大学 | A kind of complex device Multiple Fault Diagnosis Method based on DNN |
| CN111708798A (en) * | 2020-06-30 | 2020-09-25 | 浙江运达风电股份有限公司 | Wind turbine generator fault diagnosis and processing method and system |
| CN111798146A (en) * | 2020-07-09 | 2020-10-20 | 中国第一汽车股份有限公司 | Method for evaluating performance of fuel cell engine |
Non-Patent Citations (2)
| Title |
|---|
| "A fault diagnosis model based on weighted extension neural network for turbo-generator sets on small samples with noise";Tichun WANG 等;《Chinese Journal of Aeronautics》;20201013;第33卷(第10期);第2757-2769页 * |
| "测试性验证试验中的故障样本综合加权分配方法";张西山 等;《计算机测量与控制》;20150125;第23卷(第1期);第139-142页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112559964A (en) | 2021-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11916380B2 (en) | Maintaining connectivity information for meters and transformers located in a power distribution network | |
| KR102434460B1 (en) | Apparatus for re-learning predictive model based on machine learning and method using thereof | |
| US8650060B2 (en) | Plan execution control apparatus, plan execution control method, and plan execution control program | |
| CN112559964B (en) | Weight coefficient-based flight control fault probability calculation method | |
| US20250111383A1 (en) | Methods and internet of things (iot) systems for smart gas emergency safety simulation based on government regulation | |
| CN102800029B (en) | Risk probability evaluation method for same-tower multi-circuit power transmission line | |
| CN118735208B (en) | A scenario-adaptive fault repair scheduling method and system | |
| CN110287543B (en) | Method for predicting service life of relay protection device | |
| CN117805688B (en) | A digital monitoring method, device and medium for power transmission and transformation engineering | |
| CN109919394B (en) | Method for predicting residual life of power transformer | |
| CN110334728A (en) | A fault warning method and device for industrial Internet | |
| CN110867906B (en) | An identification method of power grid topology relationship based on power balance index | |
| US20250148430A1 (en) | Methods, internet of things (iot) systems, and mediums for pipeline repair based on smart gas | |
| CN114779747A (en) | Vehicle fault cause determination system and method | |
| CN106789646A (en) | Service transmission path determines method and device | |
| CN119398530A (en) | A multi-dimensional planning method and system for distribution network considering extreme natural disasters | |
| CN114062842B (en) | A cable monitoring method and terminal | |
| CN113627732A (en) | Power failure maintenance automatic identification overlapping maintenance pre-estimation risk method | |
| JP5513348B2 (en) | Lightning strike prediction apparatus, method and program | |
| KR20240140214A (en) | Adaptive maintenance scheduling method and apparatus for PCS system | |
| CN114910740B (en) | Low-voltage distribution network fault warning and fault location method, equipment, medium and system based on edge computing | |
| CN116341837A (en) | Intelligent gas call center work order creation method, internet of things system and medium | |
| US11010694B2 (en) | Optimally deploying utility repair assets to minimize power outages during major weather events | |
| CN109783945B (en) | Non-precise failure model construction method based on gamma-generalized inverse Weibull distribution | |
| CN114014120B (en) | Elevator brake performance prediction method, device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |