CN109214089A - A kind of degree of membership appraisal procedure of bridge structural health monitoring index - Google Patents
A kind of degree of membership appraisal procedure of bridge structural health monitoring index Download PDFInfo
- Publication number
- CN109214089A CN109214089A CN201811042774.5A CN201811042774A CN109214089A CN 109214089 A CN109214089 A CN 109214089A CN 201811042774 A CN201811042774 A CN 201811042774A CN 109214089 A CN109214089 A CN 109214089A
- Authority
- CN
- China
- Prior art keywords
- degree
- achievement data
- membership
- health monitoring
- function
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000011156 evaluation Methods 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000036244 malformation Effects 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000000052 comparative effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Theoretical Computer Science (AREA)
- Civil Engineering (AREA)
- Structural Engineering (AREA)
- Computational Mathematics (AREA)
- Architecture (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to the methods that the degree of membership in bridge structural health monitoring field more particularly to a kind of pair of bridge structural health monitoring is assessed.To solve the problems, such as that existing bridge health monitoring system can not reasonably be evaluated according to evaluation criterion or specification using structure technology situation of the health monitoring index to bridge, the present invention proposes a kind of degree of membership appraisal procedure of bridge structural health monitoring index: acquisition and achievement data x；To x progress theoretical calculation and given step scale and to the degree of membership divided rank of x；The parameter for calculating the subordinating degree function of x, determines x corresponding subordinating degree function in different degree of membership grades；X is updated in subordinating degree function, x being subordinate to angle value and carrying out normalized in different brackets is calculated, obtains the point value of evaluation of x；Degree of membership grade belonging to x is found in the degree of membership table of grading of x.The degree of membership appraisal procedure of bridge structural health monitoring index of the present invention can assess the uncertain health monitoring index of all standards of grading.
Description
Technical field
The present invention relates to bridge structural health monitoring field more particularly to the degrees of membership of a kind of pair of bridge structural health monitoring
The method assessed.
Background technique
Existing bridge health monitoring system usually utilizes strain transducer, displacement sensor, temperature sensor, wind
The equipment such as fast instrument are monitored bridge, to obtain achievement data related with bridge health, such as: structural internal force, structure become
Shape, structure temperature gradient, wind load etc..It is this kind of to pass through compared with traditional evaluation index obtained using artificial detection means
The achievement data related with bridge health that sensor monitors has following distinguishing feature:
1, it is a series of time series data, and changes in a certain range；
2, without corresponding metrics evaluation benchmark.
It can be seen that due in existing bridge structure technology state evaluating standard or specification, not for the strong of bridge
The evaluation criterion of health monitoring index, therefore existing bridge health monitoring system can not utilize health prison according to evaluation criterion or specification
Index is surveyed reasonably to evaluate the structure technology situation of bridge.
Summary of the invention
To solve existing bridge health monitoring system health monitoring index pair can not be utilized according to evaluation criterion or specification
The problem of structure technology situation of bridge is reasonably evaluated, the present invention propose a kind of person in servitude of bridge structural health monitoring index
Category degree appraisal procedure, this method comprises the following steps:
Step S1, acquisition achievement data x related with bridge structure health；
Step S2, theoretical calculation is carried out to the achievement data x, gives step scale according to the calculated results and to institute
The degree of membership divided rank for stating achievement data x obtains the degree of membership table of grading of the achievement data x；
Step S3, the parameter of the subordinating degree function of the achievement data x is calculated, and determines the achievement data x in difference
Degree of membership grade when corresponding subordinating degree function；
Step S4, the achievement data x is updated in the subordinating degree function, calculates the achievement data x not
It is subordinate to angle value when ad eundem, and be subordinate to angle value of the achievement data x in different brackets is normalized, obtains
The point value of evaluation of the achievement data x；
Step S5, it according to the point value of evaluation of the achievement data x, is looked into the degree of membership table of grading of the achievement data x
Degree of membership grade belonging to the achievement data x out.
The degree of membership appraisal procedure of bridge structural health monitoring index of the present invention, calculated result rationally, accurately, and can operate
Property strong (being realized convenient for programming).In the system that the health to structure especially bridge structure is monitored, it can promote on a large scale,
To assess the uncertain health monitoring index of all standards of grading.
Preferably, in the step S1, the achievement data x can be structural internal force, malformation, the knot of monitored bridge
Structure temperature gradient, wind load or tower top vertical deflection.
Preferably, in the step S2, the step scale includes a1、a2And a3, obtained degree of membership table of grading includes
A, tetra- grades of B, C and D, and when grade is A, the corresponding index section the achievement data x are as follows: x > a1；When grade is B, institute
State the corresponding index section achievement data x are as follows: a2< x≤a1；When grade is C, the corresponding index section the achievement data x are as follows:
a3< x≤a2；When grade is D, the corresponding index section the achievement data x are as follows: x < a3。
Preferably, in the step S3, the parameter of the subordinating degree function of the achievement data x includes a, b, c, d and σ.
Preferably, in the step S4, the point value of evaluation of the achievement data x is obtained using fuzzy inference rule.Into
One step, in the step S4, first with the first subordinating degree function to the maximum value x of the achievement data x1With average value x2
Carry out Fuzzy processing, first subordinating degree function are as follows:
Blurring result is made inferences further according to fuzzy inference rule, obtains inference conclusion, the fuzzy inference rule
Are as follows:
Rule1: μIt is small(x1)、μIt is small(x2), then the conclusion of fuzzy reasoning function mu (y) preferably, is denoted as μIt is good(y)；
Rule2: μIt is small(x1)、μIn(x2), then the conclusion of fuzzy reasoning function mu (y) preferably, is denoted as μIt is good(y)；
Rule3: μIt is small(x1)、μGreatly(x2), then the conclusion of fuzzy reasoning function mu (y) is general, is denoted as μGenerally(y)；
Rule4: μIn(x1)、μIt is small(x2), then the conclusion of fuzzy reasoning function mu (y) preferably, is denoted as μIt is good(y)；
Rule5: μIn(x1)、μIn(x2), then the conclusion of fuzzy reasoning function mu (y) is general, is denoted as μGenerally(y)；
Rule6: μIn(x1)、μGreatly(x2), then the conclusion of fuzzy reasoning function mu (y) is poor, is denoted as μDifference(y)；
Rule7: μGreatly(x1)、μIt is small(x2), then the conclusion of fuzzy reasoning function mu (y) is general, is denoted as μGenerally(y)；
Rule8: μGreatly(x1)、μIn(x2), then the conclusion of fuzzy reasoning function mu (y) is poor, is denoted as μDifference(y)；
Rule9: μGreatly(x1)、μGreatly(x2), then the conclusion of fuzzy reasoning function mu (y) is poor, is denoted as μDifference(y)；
And
De-fuzzy processing finally is carried out to the inference conclusion using centre of area method, obtains point value of evaluation.
Preferably, in the maximum value x to the achievement data x1With average value x2When being blurred result progress fuzzy reasoning,
Compare the maximum value x of the achievement data x1With average value x2The corresponding mould under each rule in the fuzzy inference rule
The size of inference function μ (y) value is pasted, and lesser conduct ω is taken to export, is successively denoted as: ω1、ω2、ω3、ω4、ω5、ω6、
ω7、ω8And ω9；The domain [0,100] of the corresponding fuzzy reasoning function mu (y) of rule each in the fuzzy inference rule is drawn
It is divided into n parts, and calculates the value of corresponding fuzzy reasoning function mu (y)；Respectively to the ω and μ (y) under corresponding fuzzy inference rule
Value be compared, take lesser value as μ (yn) output, obtain the matrix that size is 9*n:And using the maximum value in the matrix in 9 elements of each column as finally
Output, is successively denoted as: μAlways(y1), μAlways(y2) ... ..., μAlways(yn), and according toCarry out de-fuzzy
Processing.
Detailed description of the invention
Fig. 1 is the blurring Framework for Reasoning that uses in the degree of membership appraisal procedure of bridge structural health monitoring index of the present invention
Figure；
Fig. 2 is the monitoring data curve graph of the tower top vertical deflection of Changjiang River Bridge Shanghai PM62.
Specific embodiment
In the following, being carried out specifically in conjunction with degree of membership appraisal procedure of the Fig. 1 and 2 to bridge structural health monitoring index of the present invention
It is bright.
Specific step is as follows for the degree of membership appraisal procedure of bridge structural health monitoring index of the present invention:
Firstly, acquisition achievement data x related with bridge structure health, such as: the structural internal force of monitored bridge, structure
Deformation, structure temperature gradient, wind load or tower top vertical deflection.When acquiring achievement data related with bridge structure health,
Sensor can be used to be acquired, so that the precision of collected achievement data is higher, and then assessment result precision can be improved.
Then, theoretical calculation is carried out to achievement data x, gives step scale a according to the calculated results1、a2And a3, and
To the degree of membership divided rank of achievement data x, achievement data x degree of membership table of grading as shown in Table 1 is obtained.
Table 1: the degree of membership table of grading of achievement data x
| Grade | D | C | B | A |
| Index section | X < a3 | a3< x≤a2 | a2< x≤a1 | X > a1 |
Step scale can search relevant criterion, specification is obtained, or calculated by theoretical model according to specific targets
It arrives.For example, " Urban Bridge maintenance technology can be looked into when index to be assessed is the crack that pier reinforcing bar wheel coagulates soil in Urban Bridge
Standard " table 5.3.2 in CJJ 99-2017, a can be obtained1=0.40, a2=0.25, a3=0.20, thus by being assessed in this
The degree of membership grade classification of index is 4 grades.
Then, the parameter of the subordinating degree function of parameter data x, and determine achievement data x in different degrees of membership etc.
Corresponding subordinating degree function when grade, for example, corresponding subordinating degree function is μ when the degree of membership grade of achievement data x is DD
(x)；When the degree of membership grade of achievement data x is C, corresponding subordinating degree function is μC(x)；When the degree of membership of achievement data x
When grade is B, corresponding subordinating degree function is μB(x)；When the degree of membership grade of achievement data x is A, corresponding degree of membership letter
Number is μA(x).Wherein, the parameter of the subordinating degree function of achievement data x includes a, b, c, d and σ.
Then, achievement data x is updated in subordinating degree function, calculates achievement data x being subordinate in different brackets
Angle value, and be subordinate to angle value of the achievement data x in different brackets is normalized, obtain the assessment point of achievement data x
Value.Specifically, the point value of evaluation of the achievement data x is obtained using fuzzy inference rule:
Using the first subordinating degree function to the maximum value x of achievement data x1With average value x2Carry out Fuzzy processing, wherein
First subordinating degree function are as follows:
Blurring result is made inferences according to the fuzzy inference rule in fuzzy inference rule library, obtains inference conclusion,
Fuzzy inference rule library is as shown in table 2.
Table 2: fuzzy inference rule library
According to table 2,
Rule1: μIt is small(x1)、μIt is small(x2), then the conclusion of fuzzy reasoning function mu (y) preferably, is denoted as μIt is good(y)；
Rule2: μIt is small(x1)、μIn(x2), then the conclusion of fuzzy reasoning function mu (y) preferably, is denoted as μIt is good(y)；
Rule3: μIt is small(x1)、μGreatly(x2), then the conclusion of fuzzy reasoning function mu (y) is general, is denoted as μGenerally(y)；
Rule4: μIn(x1)、μIt is small(x2), then the conclusion of fuzzy reasoning function mu (y) preferably, is denoted as μIt is good(y)；
Rule5: μIn(x1)、μIn(x2), then the conclusion of fuzzy reasoning function mu (y) is general, is denoted as μGenerally(y)；
Rule6: μIn(x1)、μGreatly(x2), then the conclusion of fuzzy reasoning function mu (y) is poor, is denoted as μDifference(y)；
Rule7: μGreatly(x1)、μIt is small(x2), then the conclusion of fuzzy reasoning function mu (y) is general, is denoted as μGenerally(y)；
Rule8: μGreatly(x1)、μIn(x2), then the conclusion of fuzzy reasoning function mu (y) is poor, is denoted as μDifference(y)；
Rule9: μGreatly(x1)、μGreatly(x2), then the conclusion of fuzzy reasoning function mu (y) is poor, is denoted as μDifference(y)；
And
De-fuzzy processing is carried out to inference conclusion using centre of area method, obtains point value of evaluation.
In the maximum value x to achievement data x1With average value x2When being blurred result progress fuzzy reasoning, specific operation process
It is as follows:
The first step, the maximum value x of Comparative indices data x1With average value x2In fuzzy inference rule library under each rule
The size of corresponding fuzzy reasoning function mu (y) value, and lesser conduct ω is taken to export, it is successively denoted as: ω1、ω2、ω3、ω4、
ω5、ω6、ω7、ω8And ω9；
Second step, by the domain [0,100] of the corresponding fuzzy reasoning function mu (y) of rule each in fuzzy inference rule library
N parts are divided into, and calculates the value of corresponding fuzzy reasoning function mu (y)；Respectively to the ω and μ under corresponding fuzzy inference rule
(y) value is compared, and takes lesser value as μ (yn) output, obtain the matrix that size is 9*n:And using the maximum value in the matrix in 9 elements of each column as finally
Output, is successively denoted as: μAlways(y1), μAlways(y2) ... ..., μAlways(yn), and according toCarry out de-fuzzy
Processing.
Finally, finding achievement data x in the degree of membership table of grading of achievement data x according to the point value of evaluation of achievement data x
Affiliated degree of membership grade.
In the following, for using the tower top vertical deflection of Changjiang River Bridge Shanghai PM62 as achievement data, that is, evaluation object, verifying
The Evaluated effect of the degree of membership appraisal procedure of bridge structural health monitoring index of the present invention.
Firstly, carrying out long term monitoring using tower top vertical deflection of the sensor to Changjiang River Bridge Shanghai PM62, and with wherein
One month monitoring data (altogether include 43200 data), the curve graph of the monitoring data is as shown in Figure 2.
Then, according to " Highway bridge technique status assessment standard " JTG/T H21-2011, in conjunction with Changjiang River Bridge Shanghai
The actual conditions of PM62, and theoretical calculation and loading test data are referred to, determine the degree of membership etc. of the tower top vertical deflection of PM62
Grade table is as shown in table 3.
Table 3: the degree of membership table of grading of the tower top vertical deflection of Changjiang River Bridge Shanghai PM62
Finally, the degree of membership appraisal procedure of bridge structural health monitoring index through the invention, finally obtains PM62 tower top
The point value of evaluation of vertical deflection is 87.64.
And current bridge maintenance is utilized to evaluate related specifications, it can not be to the tower top of collected Changjiang River Bridge Shanghai PM62
The monitoring data of vertical deflection are judged, point value of evaluation is provided.
Claims (7)
1. a kind of degree of membership appraisal procedure of bridge structural health monitoring index, which is characterized in that this method comprises the following steps:
Step S1, acquisition achievement data x related with bridge structure health；
Step S2, theoretical calculation is carried out to the achievement data x, gives step scale according to the calculated results and to the finger
The degree of membership divided rank for marking data x, obtains the degree of membership table of grading of the achievement data x；
Step S3, the parameter of the subordinating degree function of the achievement data x is calculated, and determines the achievement data x in different persons in servitude
Corresponding subordinating degree function when category degree grade；
Step S4, the achievement data x is updated in the subordinating degree function, calculates the achievement data x different etc.
It is subordinate to angle value when grade, and be subordinate to angle value of the achievement data x in different brackets is normalized, obtains described
The point value of evaluation of achievement data x；
Step S5, according to the point value of evaluation of the achievement data x, institute is found in the degree of membership table of grading of the achievement data x
State degree of membership grade belonging to achievement data x.
2. the degree of membership appraisal procedure of bridge structural health monitoring index according to claim 1, which is characterized in that described
In step S1, the achievement data x can for the structural internal force of monitored bridge, malformation, structure temperature gradient, wind load or
Tower top vertical deflection.
3. the degree of membership appraisal procedure of bridge structural health monitoring index according to claim 1 or 2, which is characterized in that
In the step S2, the step scale includes a1、a2And a3, obtained degree of membership table of grading includes A, B, C and D tetra- etc.
Grade, and when grade is A, the corresponding index section the achievement data x are as follows: x > a1；When grade is B, x pairs of the achievement data
The index section answered are as follows: a2< x≤a1；When grade is C, the corresponding index section the achievement data x are as follows: a3< x≤a2；Deng
When grade is D, the corresponding index section the achievement data x are as follows: x < a3。
4. the degree of membership appraisal procedure of bridge structural health monitoring index according to claim 3, which is characterized in that in institute
It states in step S3, the parameter of the subordinating degree function of the achievement data x includes a, b, c, d and σ.
5. the degree of membership appraisal procedure of bridge structural health monitoring index according to claim 4, which is characterized in that in institute
It states in step S4, the point value of evaluation of the achievement data x is obtained using fuzzy inference rule.
6. the degree of membership appraisal procedure of bridge structural health monitoring index according to claim 5, which is characterized in that in institute
It states in step S4, first with the first subordinating degree function to the maximum value x of the achievement data x1With average value x2It carries out at blurring
Reason, first subordinating degree function are as follows:
Blurring result is made inferences further according to fuzzy inference rule, obtains inference conclusion, the fuzzy inference rule are as follows:
Rule1: μIt is small(x1)、μIt is small(x2), then the conclusion of fuzzy reasoning function mu (y) preferably, is denoted as μIt is good(y)；
Rule2: μIt is small(x1)、μIn(x2), then the conclusion of fuzzy reasoning function mu (y) preferably, is denoted as μIt is good(y)；
Rule3: μIt is small(x1)、μGreatly(x2), then the conclusion of fuzzy reasoning function mu (y) is general, is denoted as μGenerally(y)；
Rule4: μIn(x1)、μIt is small(x2), then the conclusion of fuzzy reasoning function mu (y) preferably, is denoted as μIt is good(y)；
Rule5: μIn(x1)、μIn(x2), then the conclusion of fuzzy reasoning function mu (y) is general, is denoted as μGenerally(y)；
Rule6: μIn(x1)、μGreatly(x2), then the conclusion of fuzzy reasoning function mu (y) is poor, is denoted as μDifference(y)；
Rule7: μGreatly(x1)、μIt is small(x2), then the conclusion of fuzzy reasoning function mu (y) is general, is denoted as μGenerally(y)；
Rule8: μGreatly(x1)、μIn(x2), then the conclusion of fuzzy reasoning function mu (y) is poor, is denoted as μDifference(y)；
Rule9: μGreatly(x1)、μGreatly(x2), then the conclusion of fuzzy reasoning function mu (y) is poor, is denoted as μDifference(y)；
And
De-fuzzy processing finally is carried out to the inference conclusion using centre of area method, obtains point value of evaluation.
7. the degree of membership appraisal procedure of bridge structural health monitoring index according to claim 6, which is characterized in that right
The maximum value x of the achievement data x1With average value x2When being blurred result progress fuzzy reasoning, the achievement data x's
Maximum value x1With average value x2In the fuzzy inference rule under each rule corresponding fuzzy reasoning function mu (y) value it is big
It is small, and lesser conduct ω is taken to export, it is successively denoted as: ω1、ω2、ω3、ω4、ω5、ω6、ω7、ω8And ω9；It will be described fuzzy
The domain [0,100] of the corresponding fuzzy reasoning function mu (y) of each rule is divided into n parts in inference rule, and calculates corresponding
The value of fuzzy reasoning function mu (y)；The value of ω and μ (y) under corresponding fuzzy inference rule are compared respectively, taken lesser
Value is used as μ (yn) output, obtain the matrix that size is 9*n:And with this
Maximum value in matrix in 9 elements of each column is successively denoted as: μ as final outputAlways(y1), μAlways(y2) ... ..., μAlways(yn), and
According toCarry out de-fuzzy processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811042774.5A CN109214089A (en) | 2018-09-07 | 2018-09-07 | A kind of degree of membership appraisal procedure of bridge structural health monitoring index |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811042774.5A CN109214089A (en) | 2018-09-07 | 2018-09-07 | A kind of degree of membership appraisal procedure of bridge structural health monitoring index |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109214089A true CN109214089A (en) | 2019-01-15 |
Family
ID=64986546
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811042774.5A Pending CN109214089A (en) | 2018-09-07 | 2018-09-07 | A kind of degree of membership appraisal procedure of bridge structural health monitoring index |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109214089A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110986873A (en) * | 2019-11-30 | 2020-04-10 | 西南交通大学 | Method for acquiring early warning index of service state of high-speed railway engineering |
| CN113420966A (en) * | 2021-06-08 | 2021-09-21 | 煤炭科学研究总院 | Method and device for acquiring bridge environment score |
-
2018
- 2018-09-07 CN CN201811042774.5A patent/CN109214089A/en active Pending
Non-Patent Citations (2)
| Title |
|---|
| DANHUI BAN等: "The application of a fuzzy inference system and analytical hierarchy process based online evaluation framework to the Donghai Bridge Health Monitoring System", 《SMART STRUCTURES AND SYSTEMS》 * |
| 罗艳利: "基于《公路桥梁技术状况评定标准》的长大桥梁在线评估体系", 《城市道桥与防洪》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110986873A (en) * | 2019-11-30 | 2020-04-10 | 西南交通大学 | Method for acquiring early warning index of service state of high-speed railway engineering |
| CN110986873B (en) * | 2019-11-30 | 2022-02-08 | 西南交通大学 | Method for acquiring early warning index of service state of high-speed railway engineering |
| CN113420966A (en) * | 2021-06-08 | 2021-09-21 | 煤炭科学研究总院 | Method and device for acquiring bridge environment score |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109765053B (en) | Rolling bearing fault diagnosis method using convolutional neural network and kurtosis index | |
| CN110175434B (en) | Railway fastener system damage detection method based on convolutional neural network | |
| CN104751229B (en) | Bearing fault diagnosis method capable of recovering missing data of back propagation neural network estimation values | |
| CN110361176A (en) | A kind of intelligent failure diagnosis method for sharing neural network based on multitask feature | |
| CN108257114A (en) | A kind of transmission facility defect inspection method based on deep learning | |
| CN108173708A (en) | Anomalous traffic detection method, device and storage medium based on incremental learning | |
| CN102663264B (en) | Semi-supervised synergistic evaluation method for static parameter of health monitoring of bridge structure | |
| CN111505424A (en) | Large experimental device power equipment fault diagnosis method based on deep convolutional neural network | |
| CN107909564A (en) | A kind of full convolutional network image crack detection method based on deep learning | |
| CN106555788A (en) | Application of the deep learning based on Fuzzy Processing in hydraulic equipment fault diagnosis | |
| Dackermann et al. | Identification of member connectivity and mass changes on a two-storey framed structure using frequency response functions and artificial neural networks | |
| CN112200237B (en) | Time sequence monitoring data abnormality diagnosis method for structural health monitoring system | |
| CN110827260B (en) | Cloth defect classification method based on LBP characteristics and convolutional neural network | |
| CN109491338A (en) | A kind of relevant method for diagnosing faults of multimode procedure quality based on sparse GMM | |
| DE102021124047A1 (en) | Open quantity fault diagnosis method for high speed EMU bearings | |
| CN102158486A (en) | Method for rapidly detecting network invasion | |
| WO2021114320A1 (en) | Wastewater treatment process fault monitoring method using oica-rnn fusion model | |
| CN107832789A (en) | Characteristic weighing k nearest neighbor method for diagnosing faults based on the conversion of average influence Value Data | |
| CN109214089A (en) | A kind of degree of membership appraisal procedure of bridge structural health monitoring index | |
| CN114118138A (en) | Bearing composite fault diagnosis method based on multi-label field self-adaptive model | |
| CN114429152A (en) | Rolling bearing fault diagnosis method based on dynamic index antagonism self-adaption | |
| CN109242093A (en) | A kind of method for evaluating reliability of the motor in electric automobile based on fuzzy neural network | |
| CN109584208A (en) | A kind of method of inspection for industrial structure defect intelligent recognition model | |
| CN109657122A (en) | A kind of Academic Teams' important member's recognition methods based on academic big data | |
| CN109164794A (en) | Multivariable industrial process Fault Classification based on inclined F value SELM |
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: 20190115 |
|
| RJ01 | Rejection of invention patent application after publication |