CN109974837A - A kind of Ship Structure damnification recognition method of Process Based - Google Patents
A kind of Ship Structure damnification recognition method of Process Based Download PDFInfo
- Publication number
- CN109974837A CN109974837A CN201910314921.8A CN201910314921A CN109974837A CN 109974837 A CN109974837 A CN 109974837A CN 201910314921 A CN201910314921 A CN 201910314921A CN 109974837 A CN109974837 A CN 109974837A
- Authority
- CN
- China
- Prior art keywords
- damage
- signatures
- srvr
- signal
- damage detection
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H9/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
- G01H9/004—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means using fibre optic sensors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Abstract
The present invention relates to a kind of Ship Structure damnification recognition methods of Process Based, belong to Ship Structure condition monitoring and fault diagnosis field.This method carries out WAVELET PACKET DECOMPOSITION to fiber-optic grating sensor monitoring signals, signatures for damage detection is acquired, is inputted as reliability inference pattern, according to ship damaged structure position, degree of injury setting structure damage type, it is exported as reliability inference pattern, constructs reliability rule base.The activation weight that strictly all rules are calculated according to input value carries out decision according to the reliability of fusion gained damage type, judges structural damage classification belonging to Ship Structure by evidential reasoning algorithm fusion strictly all rules.Objective function training Optimal Parameters set is constructed, the optimized parameter set of inference pattern is obtained.It is online to obtain signatures for damage detection, fusion results are obtained based on optimal inference pattern and carry out decision, judge affiliated structural damage classification.The present invention is able to achieve the high-precision identification of Ship Structure damage.
Description
Technical field
The present invention relates to a kind of Ship Structure damnification recognition methods of Process Based, belong to Ship Structure status monitoring
With fault diagnosis field.
Background technique
Ship is a kind of integrated system of large size, and structure is complicated, and long service is in severe marine environment, and by each
The reciprocation of kind load, such as wind load, ocean current, seaway load, ice load, deep-water pressure load, are also in for platform sometimes
The impacts such as wind, hull collision, explosion, structure itself further suffer from the influence such as environmental corrosion.It is long in these rugged environment load
Under phase effect, along with design or improper use, structure are easy to produce various forms of damages, make under the bearing capacity of structure
Drop occurs disastrous accident, causes huge casualties, economic loss.And as Ship Structure becomes increasing, navigation
Speed is getting faster, and hull is assessed by the experience of crewman by load and has become extremely difficult to damage caused by hull.
Online Ship Structure health monitoring simultaneously provides objective reliable information to the personnel that steer a ship in time, resists ship under sail respectively
Kind risk, becomes urgent problem.
Either the ribbing straddle of the stiffened panel structure of above water craft or submersible, T-type node structure are all hulls
Typical members, and these components usually influence longitudinal strength and the local strength of hull, such as hull transverse bulkhead and deck layer
Junction, ship side and junction of deck layer etc., and various load effect under, welding due to or the strength of materials because
Element, so that junction is easy to appear fracture to T-type structure in length and breadth, therefore the damage identification technique for studying these structures can be ship knot
The health monitoring of structure provides guidance.
Summary of the invention
In view of the deficiencies of the prior art, the present invention proposes a kind of Ship Structure damnification recognition methods of rule-based reasoning.It should
The vibration signal that method is generated by load impactings hulls such as fiber-optic grating sensor monitoring wave, explosions, it is dynamic using fiber grating
State (FBG) demodulator demodulates to obtain detection signal, after WAVELET PACKET DECOMPOSITION, acquires signatures for damage detection and inputs as reliability inference pattern.
It is exported according to ship damaged structure position, degree of injury setting structure damage type as reliability inference pattern, based on given
Input reference is obtained according to the activation weight that input value calculates strictly all rules by evidential reasoning algorithm fusion strictly all rules
Fusion results carry out decision, judge affiliated structural damage classification, then construct objective function training evidence reliability inference pattern
Parameter carries out decision finally by fusion results, judges affiliated structural damage classification.This method passes through fiber-optic grating sensor
Monitoring data can reach the high-precision identification of Ship Structure damage.
A kind of Ship Structure damnification recognition method of Process Based proposed by the present invention, comprising the following steps:
(1) according to ship damaged structure position, set Θ={ F of degree of injury setting Ship Structure damage1,
...Fi,...FN, FiThe i-th class damage in Ship Structure damage Θ, i=1 are represented, 2 ..., N, N are that Ship Structure damages class
Other number.
(2) SRVR is to be able to reflect Ship Structure to damage every class formation damage F in set ΘiSignatures for damage detection, damage
Hurt distinguishing indexes to be defined as follows:
In vessel motion, believed by the vibration that the load impactings hulls such as fiber-optic grating sensor monitoring wave, explosion generate
Number, it demodulates to obtain using fiber grating dynamic demodulation instrument and detects signal, if detection signal is f (t), carried out J layers of wavelet packet
It decomposes, and each node signal is reconstructed, if each node reconstruction signal isThen have:
The energy of each node reconstruction signal may be defined as:
Retain preceding m node signal and thus reconstruction signal after removing the lesser node of energy
It, can be by seeking in order to ensure reconstruction signal retains the major frequency components of original signal f (t) at this timeWith
The related coefficient of f (t), the signal of m node reconstruct is effective before thinking when the two related coefficient is greater than 0.8, if small echo
M node can effectively reconstruct original signal before packet decomposes, and the ratio for remembering that each node reconstruction signal energy accounts for signal gross energy is
Signatures for damage detection can then be defined are as follows:
In formula (5)The reference data of signal gross energy ratio is accounted for for each node reconstruction signal energy, it can be by being good in structure
Vibration signal is repeatedly measured under health state to seek obtained by the average value of each node reconstruction signal energy proportion.
(3) when the N class formation damage in Ship Structure damage set Θ occurs respectively, the damage of every kind of structural damage is obtained
Wound identification sample, every class signatures for damage detection w amount to x=N × w signatures for damage detection sample set as training sample,
It is denoted as F (x)={ SRVR1(x),SRVR2(x),...,SRVRn(x) }, n is the number of fiber-optic grating sensor, SRVRnInput
With reference to value setJnFor reference value number.
(4) rule base is constructed, is made of L rule, the kth rule description in the production rule library of foundation are as follows:
In formula: SRVRnIndicate n-th of signatures for damage detection；Indicate the ginseng of n-th of input variable in kth rule
Value is examined, and is hadL=J1×J2×…×Jn,
(5) by signatures for damage detection sample set { SRVR1(x),SRVR2(x),...,SRVRn(x) } as the defeated of model
Enter, the classification of the damage of the Ship Structure belonging to it gone out by rule base fusion reasoning, the specific steps are as follows:
(5-1) calculates n-th of signatures for damage detection SRVRn(x) corresponding each reference valueDistance, it is as follows
Shown in formula (7)
(5-2) defines n-th of signatures for damage detection SRVRn(x) corresponding each reference valueMatching degree be
(5-3) calculates n-th of signatures for damage detection SRVR according to the formula (8) in step (5-2)n(x) every rules and regulations are activated
Weight then
WhereinFor the i-th signatures for damage detection SRVRi(x) with kth rule under corresponding reference valueMatching
Degree, 0≤rk≤ 1 is the weight of kth evidence, 0≤λi≤ 1 is the reliability of each signatures for damage detection；
(5-4) obtains the activation weight of each rule according to step (5-3)Afterwards, by each rule confidence level mN,k
It is merged, obtained fusion results are denoted asFusion formula is as follows:
The fusion results that (5-5) is obtained according to step (5-4)Decision is carried out, maximum is found out
Confidence level, maximum confidence level isIt can determine whether that the signatures for damage detection sample set belongs to structural damage Fi。
(6) optimization model is constructed based on Euclidean distance, the specific steps are as follows:
(6-1) determines Optimal Parameters set P={ mi,k,rk,λj| i=1,2 ..., N；K=1,2 ..., L；J=1,
2,...,n}；
(6-2) will minimize Euclidean distance as optimization object function,
When signatures for damage detection sample set actually belongs to FiWhen class formation damages,
s.t. 0≤mi,k≤1 (12a)
0≤rk≤1 (12c)
0≤λi≤1 (12d)
Formula (12b)-(12d) indicates the constraint condition that Optimal Parameters need to meet；
(6-3) utilizes GA GAs Toolbox, optimal parameter sets P is obtained, in vessel motion, by fiber grating
Sensor monitors the vibration signal that the load impactings hulls such as wave, explosion generate, and is demodulated using fiber grating dynamic demodulation instrument
To detection signal, signatures for damage detection is calculated, fusion results are obtained according to step (5), carry out decision, judge affiliated ship
Oceangoing ship damage type.
A kind of Ship Structure damnification recognition method of Process Based proposed by the present invention.This method is passed by fiber grating
Sensor monitors the vibration signal that the load impactings hulls such as wave, explosion generate, and demodulates to obtain using fiber grating dynamic demodulation instrument
Detection signal acquires signatures for damage detection after WAVELET PACKET DECOMPOSITION, inputs as reliability inference pattern, is changed according to input value
Range sets input reference, according to ship damaged structure position, degree of injury setting structure damage type as reliability reasoning
Model output, establishes reliability inference pattern.The activation weight that strictly all rules are calculated according to input value, is melted by evidential reasoning algorithm
Strictly all rules are closed, fusion results are obtained, decision is carried out according to the reliability of fusion results, judges affiliated structural damage classification.Structure
Objective function training Optimal Parameters set is built, the optimized parameter set of inference pattern is obtained, obtains signatures for damage detection online, count
The activation weight for calculating strictly all rules obtains fusion results by evidential reasoning algorithm fusion strictly all rules, carries out decision, judgement
Affiliated structural damage classification.The program (translation and compiling environment Matlab) worked out according to the method for the present invention can transport on computers
Row, and the hardware such as combination sensor, data collector form on-line monitoring system, damage prison in real time to Ship Structure to realize
It surveys and diagnoses.
Detailed description of the invention
Fig. 1 is the program flow chart of the method for the present invention；
Fig. 2 is the test set result figure in embodiment of the present invention method.
Specific embodiment
A kind of Ship Structure damnification recognition method of Process Based proposed by the present invention, flow diagram such as Fig. 1 institute
Show, including following steps:
(1) according to ship damaged structure position, set Θ={ F of degree of injury setting Ship Structure damage1,
...Fi,...FN, FiThe i-th class damage in Ship Structure damage Θ, i=1 are represented, 2 ..., N, N are that Ship Structure damages class
Other number.
(2) SRVR is to be able to reflect Ship Structure to damage every class formation damage F in set ΘiSignatures for damage detection, damage
Hurt distinguishing indexes to be defined as follows:
In vessel motion, believed by the vibration that the load impactings hulls such as fiber-optic grating sensor monitoring wave, explosion generate
Number, it demodulates to obtain using fiber grating dynamic demodulation instrument and detects signal, if detection signal is f (t), carried out J layers of wavelet packet
It decomposes, and each node signal is reconstructed, if each node reconstruction signal isThen have:
The energy of each node reconstruction signal may be defined as:
Retain preceding m node signal and thus reconstruction signal after removing the lesser node of energy
It, can be by seeking in order to ensure reconstruction signal retains the major frequency components of original signal f (t) at this timeWith
The related coefficient of f (t), the signal of m node reconstruct is effective before thinking when the two related coefficient is greater than 0.8, if small echo
M node can effectively reconstruct original signal before packet decomposes, and the ratio for remembering that each node reconstruction signal energy accounts for signal gross energy is
Signatures for damage detection can then be defined are as follows:
In formula (5)The reference data of signal gross energy ratio is accounted for for each node reconstruction signal energy, it can be by being good in structure
Vibration signal is repeatedly measured under health state to seek obtained by the average value of each node reconstruction signal energy proportion.
(3) when the N class formation damage in Ship Structure damage set Θ occurs respectively, the damage of every kind of structural damage is obtained
Wound identification sample, every class signatures for damage detection w amount to x=N × w signatures for damage detection sample set as training sample,
It is denoted as F (x)={ SRVR1(x),SRVR2(x),...,SRVRn(x) }, n is the number of fiber-optic grating sensor, SRVRnInput
With reference to value setJnFor reference value number.
(4) rule base is constructed, is made of L rule, the kth rule description in the production rule library of foundation are as follows:
In formula: SRVRnIndicate n-th of signatures for damage detection；Indicate the ginseng of n-th of input variable in kth rule
Value is examined, and is hadL=J1×J2×…×Jn,
(5) by signatures for damage detection sample set { SRVR1(x),SRVR2(x),...,SRVRn(x) } as the defeated of model
Enter, the classification of the damage of the Ship Structure belonging to it gone out by rule base fusion reasoning, the specific steps are as follows:
(5-1) calculates n-th of signatures for damage detection SRVRn(x) corresponding each reference valueDistance, it is as follows
Shown in formula (7)
(5-2) defines n-th of signatures for damage detection SRVRn(x) corresponding each reference valueMatching degree be
(5-3) calculates n-th of signatures for damage detection SRVR according to the formula (8) in step (5-2)n(x) every rules and regulations are activated
Weight then
WhereinFor the i-th signatures for damage detection SRVRi(x) with kth rule under corresponding reference valueMatching
Degree, 0≤rk≤ 1 is the weight of kth evidence, 0≤λi≤ 1 is the reliability of each signatures for damage detection；
(5-4) obtains the activation weight of each rule according to step (5-3)Afterwards, by each rule confidence level mN,k
It is merged, obtained fusion results are denoted asFusion formula is as follows:
The fusion results that (5-5) is obtained according to step (5-4)Decision is carried out, maximum is found out
Confidence level, maximum confidence level isIt can determine whether that the signatures for damage detection sample set belongs to structural damage Fi。
For ease of understanding, it illustrates how to carry out all rules using formula (7)-(10) in step (5) herein
Reasoning fusion, the model of one output of two input, the input/output referencing value setting of model is as shown in table 1, rule base
It is as shown in table 2:
The semantic values and reference value of the input of table 1 and output
2 rule base of table
Such as input is that { 10.5,14.5 } belongs to F1, acquired according to formula (7) It is acquired according to formula (8) It is assumed that rk=1, λ1=λ2=1 acquires each rule according to formula (9)
Activate weight It is obtained according to the confidence level that formula (10) merge each rule
Fusion resultsDecision is carried out to fusion results, confidence level is maximum to be
It can determine whether that the input belongs to F1Class formation damage.
(6) optimization model is constructed based on Euclidean distance, the specific steps are as follows:
(6-1) determines Optimal Parameters set P={ mi,k,rk,λj| i=1,2 ..., N；K=1,2 ..., L；J=1,
2,...,n}；
(6-2) will minimize Euclidean distance as optimization object function,
When signatures for damage detection sample set actually belongs to FiWhen class formation damages,
s.t. 0≤mi,k≤1 (12a)
0≤rk≤1 (12c)
0≤λi≤1 (12d)
Formula (12b)-(12d) indicates the constraint condition that Optimal Parameters need to meet.
(6-3) utilizes GA GAs Toolbox, optimal parameter sets P is obtained, in vessel motion, by fiber grating
Sensor monitors the vibration signal that the load impactings hulls such as wave, explosion generate, and is demodulated using fiber grating dynamic demodulation instrument
To detection signal, signatures for damage detection is calculated, fusion results are obtained according to step (5), carry out decision, judge affiliated ship
Oceangoing ship damage type.
Below in conjunction with attached drawing, the embodiment of the method for the present invention is discussed in detail:
The flow chart of the method for the present invention is as shown in Figure 1, core is: carrying out to fiber-optic grating sensor monitoring signals small
Wave packet decomposes, and acquires signatures for damage detection, inputs as reliability inference pattern, according to ship damaged structure position, damage
Degree setting structure damage type is exported as reliability inference pattern, constructs reliability rule base.All rule are calculated according to input value
Activation weight then carries out decision according to the reliability of fusion gained damage type by evidential reasoning algorithm fusion strictly all rules,
Judge structural damage classification belonging to Ship Structure.Objective function training Optimal Parameters set is constructed, obtains inference pattern most
Excellent parameter sets.It is online to obtain signatures for damage detection, fusion results are obtained based on optimal inference pattern and carry out decision, belonging to judgement
Structural damage classification.
Below in conjunction with certain ship cabin bottom T-type girder construction, each step of the method for the present invention is discussed in detail, passes through experimental data
Verify the performance of the method for the present invention Damage Assessment Method.
1, the collection processing of experimental data
Step (1-2) collection according to the present invention is mounted on two fiber-optic grating sensor monitoring data, root in T-type girder construction
It is different according to the T-type girder construction degree of injury, four classes are splitted data into, acquire signatures for damage detection according to these data, amount to 500
It is a, belong to first kind F1125, belong to the second class F2125, belong to third class F3125 belong to the 4th class F4's
125.Appoint in every one kind and take 100 as training sample, is left 25 and is used as test sample, training sample is 400 total, surveys
Sample sheet is 100 total.
2, the selection of input reference
Step (3) according to the present invention set the signatures for damage detection reference value of first fiber-optic grating sensor as A1=
{ 14,15,16,17,18,19,20,33,34,36,37 } amount to J1=11 reference values；Second fiber-optic grating sensor
Signatures for damage detection refers to value set A2={ 10,11,12,13,14,15,16,20,21,22,23 } amount to J2=11 references
Value.
3, rule base is constructed
Step (4) according to the present invention, the signatures for damage detection SRVR, each SRVR of two fiber-optic grating sensors have 11
Reference value constructs total 121 rules, such as the following table 3.
3 rule base of table
3, training optimization
Step (6) according to the present invention determine Optimal Parameters set, amount to 607, wherein initial rk=1, λ1=λ2=1,
m1,kAnd m2,kFor the confidence level of 3 rule base of table, training is done with 400 groups of data, uses and minimizes Euclidean distance as optimization aim
Function, parameter of the GA genetic algorithm as optimization algorithm, after being optimized.
3, test experiments
Using above-mentioned 100 groups of training datas, the Damage Assessment Method result of decision is obtained according to step (5), is calculating identification just
True rate is 89%, as a result as shown in Fig. 2, having reached desired design precision.
Claims (2)
1. a kind of Ship Structure damnification recognition method of Process Based, it is characterised in that method includes the following steps:
(1) according to ship damaged structure position, set Θ={ F of degree of injury setting Ship Structure damage1,...Fi,
...FN, FiThe i-th class damage in Ship Structure damage Θ, i=1 are represented, 2 ..., N, N are of Ship Structure damage type
Number；
(2) signatures for damage detection SRVR is defined, specifically:
In vessel motion, the vibration signal generated by fiber-optic grating sensor monitors load impact hull uses fiber grating
Dynamic demodulation instrument demodulates to obtain detection signal, if detection signal is f (t), is carried out J layers of WAVELET PACKET DECOMPOSITION, and by each node
Signal reconstruction, if each node reconstruction signal isThen have:
The energy of each node reconstruction signal may be defined as:
Retain preceding m node signal and thus reconstruction signal after removing the lesser node of energy
In order to ensure reconstruction signal retains the major frequency components of original signal f (t) at this time, by seekingWith the phase of f (t)
Relationship number, the signal of m node reconstruct is effective before thinking when the two related coefficient is greater than 0.8；If m before WAVELET PACKET DECOMPOSITION
A node can effectively reconstruct original signal, and the ratio for remembering that each node reconstruction signal energy accounts for signal gross energy is
Then define signatures for damage detection are as follows:
In formula (5)The reference data of signal gross energy ratio is accounted for for each node reconstruction signal energy；
(3) when the N class formation damage in Ship Structure damage set Θ occurs respectively, the damage for obtaining every kind of structural damage is known
Very this, amounts to x=N × w signatures for damage detection sample set as training sample, is denoted as by every class signatures for damage detection w
F (x)={ SRVR1(x),SRVR2(x),...,SRVRn(x) }, n is the number of fiber-optic grating sensor, SRVRnInput reference
Value setJnFor reference value number；
(4) rule base is constructed, is made of L rule, the kth rule description in the production rule library of foundation are as follows:
In formula: SRVRnIndicate n-th of signatures for damage detection；Indicate the reference value of n-th of input variable in kth rule,
And haveL=J1×J2×…×Jn,
(5) by signatures for damage detection sample set { SRVR1(x),SRVR2(x),...,SRVRn(x) } as the input of model, lead to
Cross the classification for the Ship Structure damage that rule base fusion reasoning goes out belonging to it, the specific steps are as follows:
(5-1) calculates n-th of signatures for damage detection SRVRn(x) corresponding each reference valueDistance, such as following formula (7)
It is shown
(5-2) defines n-th of signatures for damage detection SRVRn(x) corresponding each reference valueMatching degree be
(5-3) calculates n-th of signatures for damage detection SRVR according to the formula (8) in step (5-2)n(x) power of every rule is activated
Weight
WhereinFor the i-th signatures for damage detection SRVRi(x) with kth rule under corresponding reference valueMatching degree, 0
≤rk≤ 1 is the weight of kth evidence, 0≤λi≤ 1 is the reliability of each signatures for damage detection；
(5-4) obtains the activation weight of each rule according to step (5-3)Afterwards, by each rule confidence level mN,kIt carries out
Fusion, obtained fusion results are denoted asFusion formula is as follows:
The fusion results that (5-5) is obtained according to step (5-4)Decision is carried out, maximum set is found out
Reliability, maximum confidence level areIt can determine whether that the signatures for damage detection sample set belongs to structural damage Fi。
2. a kind of Ship Structure damnification recognition method of Process Based according to claim 1, it is characterised in that: also
Including constructing optimization model based on Euclidean distance, the specific steps are as follows:
(6-1) determines Optimal Parameters set P={ mi,k,rk,λj| i=1,2 ..., N；K=1,2 ..., L；J=1,2 ...,
n}；
(6-2) will minimize Euclidean distance as optimization object function,
When signatures for damage detection sample set actually belongs to FiWhen class formation damages,
s.t. 0≤mi,k≤1 (12a)
0≤rk≤1 (12c)
0≤λi≤1 (12d)
Formula (12b)-(12d) indicates the constraint condition that Optimal Parameters need to meet；
(6-3) utilizes GA GAs Toolbox, optimal parameter sets P is obtained, in vessel motion, by optical fiber grating sensing
Device monitors load impacts the vibration signal that hull generates, and demodulates to obtain detection signal using fiber grating dynamic demodulation instrument, calculate
Signatures for damage detection is obtained, fusion results are obtained according to step (5), carry out decision, judge affiliated ship damage type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910314921.8A CN109974837B (en) | 2019-04-18 | 2019-04-18 | Ship structure damage identification method based on rule reasoning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910314921.8A CN109974837B (en) | 2019-04-18 | 2019-04-18 | Ship structure damage identification method based on rule reasoning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109974837A true CN109974837A (en) | 2019-07-05 |
| CN109974837B CN109974837B (en) | 2022-05-20 |
Family
ID=67085250
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910314921.8A Active CN109974837B (en) | 2019-04-18 | 2019-04-18 | Ship structure damage identification method based on rule reasoning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109974837B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110850206A (en) * | 2019-11-13 | 2020-02-28 | 武汉理工大学 | Inverter capacitor aging fault diagnosis method based on confidence rule reasoning |
| CN111912612A (en) * | 2020-07-16 | 2020-11-10 | 中国特种设备检测研究院 | Method and system for monitoring damage of gas cylinder of long-tube trailer |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105203130A (en) * | 2015-10-13 | 2015-12-30 | 哈尔滨工程大学 | Information fusion based fault diagnosis method for vessel integrated navigation system |
| CN109115491A (en) * | 2018-10-16 | 2019-01-01 | 杭州电子科技大学 | A kind of evidence fusion method of Electrical Propulsion Ship shafting propulsion system mechanical fault diagnosis |
| CN109615228A (en) * | 2018-12-12 | 2019-04-12 | 杭州电子科技大学 | Railway transportation risk probability calculation method based on mixing heuristic rule system |
-
2019
- 2019-04-18 CN CN201910314921.8A patent/CN109974837B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105203130A (en) * | 2015-10-13 | 2015-12-30 | 哈尔滨工程大学 | Information fusion based fault diagnosis method for vessel integrated navigation system |
| CN109115491A (en) * | 2018-10-16 | 2019-01-01 | 杭州电子科技大学 | A kind of evidence fusion method of Electrical Propulsion Ship shafting propulsion system mechanical fault diagnosis |
| CN109615228A (en) * | 2018-12-12 | 2019-04-12 | 杭州电子科技大学 | Railway transportation risk probability calculation method based on mixing heuristic rule system |
Non-Patent Citations (2)
| Title |
|---|
| XINPING YAN 等: "Intelligent wear mode identification system for marine diesel engines based on multi-level belief rule base methodology", 《MEASUREMENT SCIENCE AND TECHNOLOGY》 * |
| 徐晓健 等: "基于证据推理规则的船舶柴油机磨损类型辨识研究", 《摩擦学学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110850206A (en) * | 2019-11-13 | 2020-02-28 | 武汉理工大学 | Inverter capacitor aging fault diagnosis method based on confidence rule reasoning |
| CN111912612A (en) * | 2020-07-16 | 2020-11-10 | 中国特种设备检测研究院 | Method and system for monitoring damage of gas cylinder of long-tube trailer |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109974837B (en) | 2022-05-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104050329B (en) | A kind of method for detecting Collision Risk Index | |
| Prabowo et al. | Advanced development of sensors’ roles in maritime-based industry and research: From field monitoring to high-risk phenomenon measurement | |
| EP3330171A2 (en) | Apparatus for predicting a power consumption of a maritime vessel | |
| Longo et al. | Phase-averaged PIV for the nominal wake of a surface ship in regular head waves | |
| Vakilabadi et al. | Experimental study on heave and pitch motion characteristics of a wave-piercing trimaran | |
| CN109974837A (en) | A kind of Ship Structure damnification recognition method of Process Based | |
| CN111599130A (en) | Environmental risk early warning system for marine rescue | |
| Gaidai et al. | Lifetime assessment for container vessels | |
| Troesch et al. | Modern nonlinear dynamical analysis of vertical plane motion of planing hulls | |
| Jiao et al. | A review of large-scale model at-sea measurements for ship hydrodynamics and structural loads | |
| Mintu et al. | Ice accretion for ships and offshore structures. Part 2–Compilation of data | |
| Kong et al. | Full-scale identification of ice load on ship hull by least square support vector machine method | |
| CN113868910A (en) | Method for evaluating structure fatigue accumulation damage probability under random repeated collision of ice-ship | |
| Thomas | Wave slam response of large high-speed catamarans | |
| Han et al. | Mapping the landscape of ship berthing research: A bibliometric analysis and literature review over two decades | |
| Kuo et al. | A review of intact ship stability research and criteria | |
| Tiwari et al. | Experimental investigation on the effects of froude number on manoeuvring characteristic of a research vessel | |
| CN111553559B (en) | Unmanned ship comprehensive capacity testing method, device and system | |
| Kose et al. | An expert system for monitoring dynamic stability of small craft | |
| Themelis | Probabilistic assessment of ship dynamic stability in waves | |
| Roberton | Residual life assessment of composite structures: with application to all weather lifeboats | |
| Zhao et al. | Sea Ice Type and Thickness Identification Based on Vibration Sensor Networks and Machine Learning | |
| Gebrezgabir et al. | Slam and wave load response reconstruction in high speed catamarans using transmissibility on full scale sea trials | |
| Islam et al. | Applicability of Current Statutory Rules for Stability Requirements of Bangladesh Inland Passenger Vessels | |
| Olivieri et al. | Froude number and scale effects and Froude number 0.35 wave elevations and mean-velocity measurements for bow and shoulder wave breaking of surface combatant DTMB 5415 |
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 |