CN109145951A - A kind of tunnel lining structure duty status evaluation method based on Bayesian network - Google Patents
A kind of tunnel lining structure duty status evaluation method based on Bayesian network Download PDFInfo
- Publication number
- CN109145951A CN109145951A CN201810811112.3A CN201810811112A CN109145951A CN 109145951 A CN109145951 A CN 109145951A CN 201810811112 A CN201810811112 A CN 201810811112A CN 109145951 A CN109145951 A CN 109145951A
- Authority
- CN
- China
- Prior art keywords
- bayesian network
- tunnel
- lining
- node
- disease damage
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 33
- 201000010099 disease Diseases 0.000 claims abstract description 51
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 51
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000001514 detection method Methods 0.000 claims abstract description 11
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000006073 displacement reaction Methods 0.000 claims description 4
- 230000006866 deterioration Effects 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 2
- 230000035515 penetration Effects 0.000 claims description 2
- 235000015170 shellfish Nutrition 0.000 claims description 2
- 238000012360 testing method Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000007812 deficiency Effects 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010224 classification analysis Methods 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000003012 network analysis Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
Abstract
The tunnel lining structure duty status evaluation method based on Bayesian network that the invention discloses a kind of.This method the following steps are included: determine the typical disease damage type and its feature during tunnel military service first, the bayesian network structure of tunnel lining structure duty status evaluation is determined using bayesian network structure learning TAN method and expertise knowledge, each node diagnostic is determined according to detection data and expertise, and each node diagnostic prior probability is carried out using the parameter learning EM method and statistical data of Bayesian network and is determined.Then according to actual tunnel liner structure Service Environment and on-site test data, the evaluation result of tunnel duty status is obtained using Bayesian network reasoning from logic.Bayesian network that the present invention establishes can objectively describe tunnel-liner service state and reliability it can be considered that influencing each other between interrelated factor, has fully demonstrated the systematicness of tunnel lining structure.
Description
Technical field
The invention belongs to technical field of highway traffic, and in particular to a kind of tunnel lining structure clothes based on Bayesian network
Use as a servant status evaluation method.
Background technique
By the end of the year 2016, China's operation vcehicular tunnel total kilometrage has reached 14039.7km, the vcehicular tunnel fortune of enormous amount
Safety management is sought, is the work that Current Highway administrative department attaches great importance to.Wherein, operation tunnel duty status evaluation is important ring
One of section, and evaluation result will directly affect Tunnel Repair Maintenance Decision making, therefore, effective and reasonable evaluation method be taken to examine
Disconnected tunnel duty status, it has also become the project paid close attention in the industry.
In the Process of Comprehensive Assessment of vcehicular tunnel duty status, the parameter of input model is more, and diagnostic result is closer
Actual state, evaluation result are more accurate.If all information can be obtained, evaluation result is the most reliable.But because of the practical clothes in tunnel
Complex is used as a servant, the condition limitation of detection device and economic factor, detection data is often all not complete enough, the classification of these data
The accuracy of evaluation result is directly affected with quantity.General evaluation method mostly just considers single-factor influence, could not consider
Disease is multifactor to influence each other, and evaluation procedure direct basis detection data could not form complete appraisement system.The evaluation of this paper
Method, using Bayesian network, it is contemplated that influencing each other between all kinds of factors, simultaneously because the building of Bayesian network, energy
It is enough that factor of evaluation probability is dynamically adjusted, to tunnel military service shape according to data screening and Bayesian learning according to newest detection data
Condition carries out dynamic evaluation.
Summary of the invention
It is an object of the invention to consider it is multifactor influence each other and disease factor dynamic change, provide a kind of based on pattra leaves
The tunnel lining structure duty status evaluation method of this network mentions for the operation highway tunnel lining Disease Processing under complex environment
For real-time foundation and guidance.
To realize the above-mentioned technical purpose, scheme provided by the invention is: a kind of tunnel-liner knot based on Bayesian network
Structure duty status evaluation method, comprising the following steps:
(1) determine the node and type of Bayesian network: Bayesian network node corresponds respectively to each variable in model, needs
Each variable and its correlation are determined according to network analysis, and the type of node, node are distinguished according to variable property
Type mainly includes destination node, evidence node and intermediate node.According to tunnel lining structure disease damage properties study achievement, determine
Variable factors relevant to tunnel lining structure duty status distinguish according to variable property the type of node as node,
Wherein destination node is tunnel-liner duty status, and disease damage type is as child node, that is, evidence node, including Lining Crack, lining
Build displacement or deformation, lining cutting back cavity, lining thickness deficiency, lining cutting deterioration, lining cutting conquassation or peeling and lining cutting percolating water；It is right
Disease damage type carries out the disease damage feature that describes of feature as father node i.e. intermediate node, wherein the disease damage feature of Lining Crack
It include: fracture length, fracture width, the penetration of fracture and crack location；Lining displacement or the disease damage feature of deformation include: deformation speed
Rate and headroom are insufficient；The disease damage feature of lining cutting back cavity includes: empty length and empty depth；The insufficient disease damage of lining thickness
Feature includes: lining cutting thickness thinning ratio and thinning area；The disease damage feature of lining cutting deterioration includes strength of lining ratio；Lining cutting conquassation or
The disease damage feature of peeling includes: that diameter and lining cutting peeling depth are peeled off in lining cutting；The disease damage feature of lining cutting percolating water includes: percolating water
Position and leakage water flow.Grade classification is carried out to each disease damage feature, as shown in table 1.
Each disease damage feature level of table 1 divides table
According to tunnel-liner disease damage research achievement, child node is divided into three-level by security implication degree, respectively " serious ", " one
As " and " slight ", it respectively corresponds and jeopardizes tunnel and normally operate, need artificially to reinforce and need to monitor, observation, tunnel-liner is taken
Labour status evaluation result is divided into level Four, respectively " 1 grade ", " 2 grades ", " 3 grades ", " 4 grades " correspond to " good ", " preferable ", " general ",
" poor ", specific divided rank are as shown in table 2.
2 tunnel-liner duty status evaluation result hierarchical table of table
(2) it determines bayesian network structure: according to tunnel lining structure disease damage feature, extending simple shellfish in conjunction with expertise and tree
This network method for calculation of leaf establishes the bayesian network structure model of tunnel lining structure duty status evaluation；Bayesian network is
One directed acyclic graph (Directed Acyclic Graph, DAG), by representing the node of variable and connecting having for these nodes
It is constituted to side, directed edge is directed toward child node by father node, is indicated with single lined arrows " → ".It inquires to understand to grasp Xiang expert and leads to tunnel
Logical relation between the correlative factor of road lining cutting disease damage, and the causality between each node is tentatively established, it is formed such as Fig. 2 institute
Show bayesian network structure model.
(3) Bayesian network parameters learn: detection data and environmental information during being on active service according to tunnel lining structure,
Using the parametric learning method or probabilistic method of expectation maximization, the Prior Probability of father node disease damage feature is determined,
Can according to actual count to detection data amount select the suitable method to determine Prior Probability, it is more for data volume
Situation can choose the parametric learning method of expectation maximization, and the few situation of data volume, which can be counted directly, to be obtained, each grade disease
The Prior Probability of feature is damaged equal to the ratio between the disease damage characteristic of each grade and total disease damage number.
Wherein the basic thought of expectation maximization algorithm is to provide an initial parameter value S (0), then constantly corrects it,
Maximize its maximum likelihood probability value, i.e. maximization E (lnP (Y | S)), Y is whole training samples, from current estimated value S
To next estimated value S(t)Need two steps:
Step 1 expectation computing, when calculating Observable training sample D and current S, the probability distribution expectation of data set Y are as follows:
Step 2 maximizes, and maximizes current function Q (S(t)| S), make function maximum by maximal possibility estimation:
Wherein D is the data set of observation, and Z is the data set that do not observe, whole training data Y=D ∪ Z.
Further according to Prior Probability determine father node for the conditional probability of child node, conditional probability by father node priori
The weight that probability value and father node influence every level-one child node determines that this weight is determined according to detection expert analysis mode.
(4) it the probability inference of Bayesian network: according to Prior Probability and conditional probability obtained in step (3), uses
The bayesian network structure model reasoning established in step (2) carries out tunnel lining structure duty status overall merit.
Beneficial effects of the present invention:
(1) Bayesian network is evaluated based on the tunnel-liner disease damage that a large amount of tunnel disease damage research achievement is established, sufficiently reflected
Tunnel be on active service during disease damage type the relationship that influences each other, reflection tunnel it is multifactor between influence each other；
(2) prior probability that Bayesian network father node is determined based on EM learning method and a large amount of tunnel statistical data, using general
Rate come reflect disease damage for the influence degree of tunnel-liner, the Tunnel testing data that process adequately utilizes, description sufficiently put
The reliability in tunnel has been reflected, it is more scientific objective.
Detailed description of the invention
Fig. 1 is flow chart of the invention；
Fig. 2 is that bayesian network structure figure is evaluated in tunnel-liner
Fig. 3 is the Bayesian network and Prior Probability distribution map in embodiment；
Fig. 4 is the Bayesian network evaluation result figure in embodiment.
Specific embodiment
Elaborate with reference to the accompanying drawing to the embodiment of the present invention: embodiment is based on the technical solution of the present invention
Under implemented, give detailed embodiment, but protection scope of the present invention embodiment not limited to the following.
As shown in Figure 1, a kind of tunnel lining structure duty status evaluation method based on Bayesian network, it is first determined tunnel
Typical disease damage type and its feature during road is on active service carry out disease damage feature based on the special knowledge of tunnel research achievement and family
Classification and statistical analysis, then determine tunnel-liner knot using bayesian network structure learning TAN method and expertise knowledge
The bayesian network structure of structure duty status evaluation is evaluated purpose and on-site test data according to actual tunnel liner structure, is adopted
It is combined with the parameter learning EM method of statistical data and Bayesian network, determines the Prior Probability of each father node, finally adopt
The evaluation result of tunnel duty status is obtained with Bayesian network reasoning from logic.The bayesian network structure model wherein established is such as
Shown in Fig. 2, then according to this model tunnel specific lining cutting duty status is evaluated in conjunction with specific detection data.
Embodiment 1: it according to the detection data of certain tunnel lining structure, is carried out according to disease damage type and disease damage classification
Statistics, obtains the statistical probability of each father node, i.e. Prior Probability.The Prior Probability of each grade disease damage feature is equal to
The ratio between the disease damage number of each grade disease damage feature and total disease damage number.It is specific as follows:
(1) Tunnel Lining Cracks
Certain tunnel statistics shows that tunnel shares at crack 375.Crack of the fracture length less than 1m shares 54；Crack is long
Degree is more than or equal to crack of the 1m less than 2.5m and shares 144；Fracture length is more than or equal to crack of the 2.5m less than 5m and shares 145
Item；Crack of the fracture length more than or equal to 5m is 32.The Prior Probability of different brackets Lining Crack length is as shown in table 3:
The Prior Probability of 3 different brackets Lining Crack of table
Crack quantity of the fracture width less than 0.2mm is 21；Fracture width is greater than crack quantity of the 0.2mm less than 0.5mm
290；It is 62 that fracture width, which is more than or equal to crack quantity of the 0.5mm less than 2.5mm,；It is small that fracture width is more than or equal to 2.5mm
In 5mm crack quantity be 2.The Prior Probability of different brackets Lining Crack width is as shown in table 4:
The Prior Probability of 4 different brackets Lining Crack width of table
The crack quantity in vault crack is 97；Haunch crack quantity is 50；The crack quantity of abutment wall is 205；Foundation
Crack quantity is 23.The Prior Probability of different brackets Lining Crack position is as shown in table 5:
The Prior Probability of 5 different brackets Lining Crack position of table
(2) lining cutting back cavity
Tunnel shares at back cavity 35；Empty number of the empty length less than 2m has 4；Empty length is more than or equal to 2m and is less than
The empty number of 8m has 22；Empty length is more than or equal to 8m and the empty number less than 14m has 5；Empty length is more than or equal to 14m
And the empty number less than 20m has 2；Empty length is more than or equal to 20m and the empty number less than 26m has 1；Empty length is greater than
Empty number equal to 26 m has 1.The Prior Probability of different brackets cavity length is as shown in table 6:
The Prior Probability of 6 different brackets cavity length of table
(3) lining thickness is insufficient
Tunnel statistics shows that lining thickness deficiency shares at 76, at keystone 18, at haunch position 33, and abutment wall position
At 18, at foundation position 7.The Prior Probability of different brackets thinning area is as shown in table 7:
The Prior Probability of 7 different brackets thinning area of table
(4) Tunnel Water Leakage
Tunnel Water Leakage quantity is more, has reached percolating water at 332, wherein micro- infiltration quantity is most, has reached at 287, has seeped number slowly
At amount only 45.The Prior Probability that different brackets leaks water flow is as shown in table 8:
The Prior Probability of 8 different brackets of table leakage water flow
It is written by the prior probability for calculating obtained father node and by the probability inference calculation method of father node to child node
Probability inference computational chart between the node that NETICA software provides, specifies the reasoning and calculation relationship between node probability.Its essence is by father
The weight that the Prior Probability and father node of node influence every level-one child node determines conditional probability, this weight is foundation
Expert analysis mode is detected to determine.The case study function of being provided using NETICA software, the condition that can be obtained between each node are general
Rate.
The final appraisal results in tunnel are obtained according to obtained Prior Probability and conditional probability, as shown in Figure 4: calculating
The results show that the probability of 1 grade of the tunnel lining structure duty status is 19.3%, 2 grades of probability is 32.2%, and 3 grades of probability is
34.9%, 4 grades of probability is 13.6%.Therefore, comprehensive assessment is as a result, the tunnel lining structure duty status grade is 3 grades.
Above in conjunction with attached drawing, the embodiment of the present invention is explained in detail, but the present invention is not limited to above-mentioned
Embodiment within the knowledge of a person skilled in the art can also be before not departing from present inventive concept
It puts and makes a variety of changes.
Claims (5)
1. a kind of tunnel lining structure duty status evaluation method based on Bayesian network, which is characterized in that including following step
It is rapid:
(1) node and type of Bayesian network are determined: determining that variable factors relevant to tunnel lining structure duty status are made
For node, and distinguish according to variable property the type of node, wherein tunnel-liner duty status is as destination node, and by its
Evaluation result is divided into level Four, respectively 1 grade, 2 grades, 3 grades and 4 grades, correspond to, preferably, it is generally and poor；Disease damage type is as son
Node, that is, evidence node, child node are divided into three-level by security implication degree, respectively seriously, generally and slightly, represent father's section
Influence degree of the point for child node；The disease damage feature that describes of feature is carried out as father node i.e. middle node to disease damage type
Point, and grade classification is carried out to it；
(2) it determines bayesian network structure: according to tunnel lining structure disease damage feature, extending simple shellfish in conjunction with expertise and tree
This network method for calculation of leaf establishes the bayesian network structure model of tunnel lining structure duty status evaluation；
(3) Bayesian network parameters learn: detection data and environmental information during being on active service according to tunnel lining structure determine
Conditional probability of the Prior Probability and father node of father node for child node；
(4) probability inference of Bayesian network: Prior Probability and conditional probability are obtained according in step (3), using step (2)
The bayesian network structure model reasoning of middle foundation carries out tunnel lining structure duty status overall merit.
2. the tunnel lining structure duty status evaluation method according to claim 1 based on Bayesian network, feature
It is, the disease damage type includes Lining Crack, lining displacement or deformation, lining cutting back cavity, lining thickness is insufficient, lining cutting is bad
Change, lining cutting is crushed or is peeled off and lining cutting percolating water；
The disease damage feature of the Lining Crack includes: fracture length, fracture width, the penetration of fracture and crack location；
The lining displacement or the disease damage feature of deformation include: that rate of deformation and headroom are insufficient；
The disease damage feature of the lining cutting back cavity includes: empty length and empty depth；
The insufficient disease damage feature of lining thickness includes: lining cutting thickness thinning ratio and thinning area；
The disease damage feature of the lining cutting deterioration includes strength of lining ratio；
The lining cutting conquassation or the disease damage feature peeled off include: that diameter and lining cutting peeling depth are peeled off in lining cutting；
The disease damage feature of the lining cutting percolating water includes: percolating water position and leakage water flow.
3. the tunnel lining structure duty status evaluation method according to claim 1 based on Bayesian network, feature
Be, the detailed process of the step (2) are as follows: according to expertise determine the Bayesian network in step (1) each node it
Between logical relation, establish the causality between each node.
4. the tunnel lining structure duty status evaluation method according to claim 1 based on Bayesian network, feature
It is, the Prior Probability is obtained using the parametric learning method or probabilistic method of expectation maximization, conditional probability
It is determined by the weight that the Prior Probability and father node of father node influence every level-one child node, this weight is according to detection
Expert analysis mode determines.
5. the tunnel lining structure duty status evaluation method according to claim 4 based on Bayesian network, feature
It is, is the number of the disease damage feature of corresponding grade when the Prior Probability of the disease damage feature is calculated by probabilistic method
The ratio of amount and the quantity of total disease damage feature.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810811112.3A CN109145951B (en) | 2018-07-23 | 2018-07-23 | Bayesian network-based tunnel lining structure service condition evaluation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810811112.3A CN109145951B (en) | 2018-07-23 | 2018-07-23 | Bayesian network-based tunnel lining structure service condition evaluation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109145951A true CN109145951A (en) | 2019-01-04 |
| CN109145951B CN109145951B (en) | 2022-04-12 |
Family
ID=64801390
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810811112.3A Active CN109145951B (en) | 2018-07-23 | 2018-07-23 | Bayesian network-based tunnel lining structure service condition evaluation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109145951B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112381283A (en) * | 2020-11-10 | 2021-02-19 | 中铁（天津）隧道工程勘察设计有限公司 | Tunnel disease treatment method |
| CN115392797A (en) * | 2022-10-27 | 2022-11-25 | 北京城建设计发展集团股份有限公司 | Operating tunnel structure disease rapid intelligent diagnosis method based on Bayesian network |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004354119A (en) * | 2003-05-28 | 2004-12-16 | Hitachi Ltd | Apparatus and method for evaluating damage probability of structure |
| CN103867186A (en) * | 2012-12-17 | 2014-06-18 | 艾默生电气公司 | Method and Apparatus for Analyzing Image Data Generated During Underground Boring or Inspection Activities |
| CN104527495A (en) * | 2014-12-19 | 2015-04-22 | 云南省公路开发投资有限责任公司 | Integrated detection truck for road tunnel defects |
| CN105241490A (en) * | 2015-08-31 | 2016-01-13 | 招商局重庆交通科研设计院有限公司 | Method of testing influence of leakage water on in-service tunnel operation safety and system thereof |
| CN106627317A (en) * | 2017-01-03 | 2017-05-10 | 上海同岩土木工程科技股份有限公司 | Highway tunnel apparent disease collecting van |
| CN106910024A (en) * | 2017-03-03 | 2017-06-30 | 中国水产科学研究院黄海水产研究所 | A kind of method of utilization equation of structure Fuzzy comprehensive evaluation marine oil spill fishery infringement |
| CN106919784A (en) * | 2017-01-19 | 2017-07-04 | 上海隧道工程有限公司 | A kind of shield tunnel military service method of evaluating performance based on variable weight |
| CN107145997A (en) * | 2017-03-29 | 2017-09-08 | 中国铁道科学研究院铁道建筑研究所 | A kind of Railway Tunnel configuration state evaluation method |
-
2018
- 2018-07-23 CN CN201810811112.3A patent/CN109145951B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004354119A (en) * | 2003-05-28 | 2004-12-16 | Hitachi Ltd | Apparatus and method for evaluating damage probability of structure |
| CN103867186A (en) * | 2012-12-17 | 2014-06-18 | 艾默生电气公司 | Method and Apparatus for Analyzing Image Data Generated During Underground Boring or Inspection Activities |
| CN104527495A (en) * | 2014-12-19 | 2015-04-22 | 云南省公路开发投资有限责任公司 | Integrated detection truck for road tunnel defects |
| CN105241490A (en) * | 2015-08-31 | 2016-01-13 | 招商局重庆交通科研设计院有限公司 | Method of testing influence of leakage water on in-service tunnel operation safety and system thereof |
| CN106627317A (en) * | 2017-01-03 | 2017-05-10 | 上海同岩土木工程科技股份有限公司 | Highway tunnel apparent disease collecting van |
| CN106919784A (en) * | 2017-01-19 | 2017-07-04 | 上海隧道工程有限公司 | A kind of shield tunnel military service method of evaluating performance based on variable weight |
| CN106910024A (en) * | 2017-03-03 | 2017-06-30 | 中国水产科学研究院黄海水产研究所 | A kind of method of utilization equation of structure Fuzzy comprehensive evaluation marine oil spill fishery infringement |
| CN107145997A (en) * | 2017-03-29 | 2017-09-08 | 中国铁道科学研究院铁道建筑研究所 | A kind of Railway Tunnel configuration state evaluation method |
Non-Patent Citations (5)
| Title |
|---|
| FAN WANG 等: "Probabilistic risk assessment of tunneling-induced damage to existing properties", 《EXPERT SYSTEMS WITH APPLICATIONS》 * |
| 吴江滨 等: "铁路运营隧道病害现状及检测评估", 《中国安全科学学报》 * |
| 姜洲 等: "基于贝叶斯网络的运营隧道渗漏水病害风险评估", 《环境工程》 * |
| 胡鑫: "基于贝叶斯网络的高铁岩溶隧道风险分析", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
| 谢洪涛 等: "基于贝叶斯网络的隧道施工坍塌事故诊断方法", 《昆明理工大学学报( 自然科学版)》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112381283A (en) * | 2020-11-10 | 2021-02-19 | 中铁（天津）隧道工程勘察设计有限公司 | Tunnel disease treatment method |
| CN115392797A (en) * | 2022-10-27 | 2022-11-25 | 北京城建设计发展集团股份有限公司 | Operating tunnel structure disease rapid intelligent diagnosis method based on Bayesian network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109145951B (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109765559B (en) | A kind of mountain area disastrous rainstorm recognition methods based on Doppler radar and deep learning | |
| CN106022518B (en) | A kind of piping failure probability forecasting method based on BP neural network | |
| CN112258496A (en) | Underground drainage pipeline disease segmentation method based on full convolution neural network | |
| CN110197218A (en) | Thunderstorm gale grade forecast classification method based on multi-source convolutional neural networks | |
| CA3101276A1 (en) | System and method for real time prediction of water level and hazard level of a dam | |
| Tran et al. | Application of probabilistic neural networks in modelling structural deterioration of stormwater pipes | |
| CN114280696A (en) | Intelligent sea fog level forecasting method and system | |
| Mazaheri et al. | Assessing grounding frequency using ship traffic and waterway complexity | |
| CN109214308A (en) | A kind of traffic abnormity image identification method based on focal loss function | |
| CN109657880A (en) | A kind of Collision Accidents of Ships grade prediction technique and system based on Bayesian network | |
| Hutton et al. | Real-time burst detection in water distribution systems using a Bayesian demand forecasting methodology | |
| CN109145951A (en) | A kind of tunnel lining structure duty status evaluation method based on Bayesian network | |
| Ruiz et al. | Storms prediction: Logistic regression vs random forest for unbalanced data | |
| CN108454653A (en) | A kind of train control system communicated based on satellite communication and public cellular | |
| Chen et al. | Drinking water distribution systems asset management: statistical modelling of pipe breaks | |
| CN115980826A (en) | Rock burst intensity prediction method based on weighted meta-heuristic combined model | |
| Wang et al. | Application of BP neural network in early-warning analysis of investment financial risk in coastal areas | |
| CN109839617A (en) | A kind of non-precipitation echo removing method and system of radar network composite product | |
| CN109656904A (en) | A kind of case risk checking method and system | |
| CN109214937A (en) | The anti-fraud determination method of settlement of insurance claim intelligence and system | |
| CN107977727B (en) | Method for predicting blocking probability of optical cable network based on social development and climate factors | |
| CN105930430A (en) | Non-cumulative attribute based real-time fraud detection method and apparatus | |
| CN113689053B (en) | Strong convection weather overhead line power failure prediction method based on random forest | |
| CN115345245A (en) | Tropical cyclone rapid reinforcement forecasting method based on random forest and transfer learning | |
| Khadr et al. | Integration of data-driven modeling and stochastic modeling for multi-purpose reservoir simulation |
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 |