AU2021101951A4 - Method of real-time safety warning of tunnel approaching construction based on data fusion - Google Patents
Method of real-time safety warning of tunnel approaching construction based on data fusion Download PDFInfo
- Publication number
- AU2021101951A4 AU2021101951A4 AU2021101951A AU2021101951A AU2021101951A4 AU 2021101951 A4 AU2021101951 A4 AU 2021101951A4 AU 2021101951 A AU2021101951 A AU 2021101951A AU 2021101951 A AU2021101951 A AU 2021101951A AU 2021101951 A4 AU2021101951 A4 AU 2021101951A4
- Authority
- AU
- Australia
- Prior art keywords
- indicator
- level
- fusion
- security
- risk
- 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.)
- Ceased
Links
- 230000004927 fusion Effects 0.000 title claims abstract description 71
- 238000010276 construction Methods 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000005516 engineering process Methods 0.000 claims abstract description 18
- 238000010206 sensitivity analysis Methods 0.000 claims abstract description 15
- 238000004364 calculation method Methods 0.000 claims abstract description 10
- 238000012502 risk assessment Methods 0.000 claims abstract description 5
- 238000000342 Monte Carlo simulation Methods 0.000 claims description 16
- 238000012544 monitoring process Methods 0.000 claims description 14
- 238000011156 evaluation Methods 0.000 claims description 11
- 230000035945 sensitivity Effects 0.000 claims description 10
- 238000004088 simulation Methods 0.000 claims description 10
- 238000007499 fusion processing Methods 0.000 claims description 6
- 238000009412 basement excavation Methods 0.000 claims description 5
- 230000001186 cumulative effect Effects 0.000 claims description 4
- 230000009977 dual effect Effects 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract description 4
- 230000008447 perception Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 abstract description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000007500 overflow downdraw method Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000004836 empirical method Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000004927 clay Substances 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 230000005641 tunneling Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
- G05B19/0428—Safety, monitoring
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0275—Fault isolation and identification, e.g. classify fault; estimate cause or root of failure
- G05B23/0281—Quantitative, e.g. mathematical distance; Clustering; Neural networks; Statistical analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- 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
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/257—Belief theory, e.g. Dempster-Shafer
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04Q—SELECTING
- H04Q9/00—Arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station, in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Evolutionary Computation (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Automation & Control Theory (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Pure & Applied Mathematics (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Algebra (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The present invention belongs to the technical field of security risk perception of
deformation of an adjacent building induced by tunnel construction, and specifically
relates to a method for early warning security of a surrounding building in tunnel
construction based on a plurality of sensors, including the following steps: (1)
constructing a multi-level information fusion model; (2) constructing basic credibility
distribution of different risk levels of input variables via membership calculation in a
cloud model theory; (3) combining Dempster rule and a weighted average rule to
process conflicting multi-source evidence fusion and inference; (4) use Monte Carlo
technology to characterize fuzzy random uncertainty of an input factor in a
measurement process via normal probability distribution; and (5) proposing a risk
analysis credibility factor and a global sensitivity analysis indicator to obtain a final
security risk level. The method can effectively deal with uncertainties, conflicts, errors
and other problems existing in complex decision-making problems, obtain more
accurate security early warning results, and have strong accuracy and fault tolerance
capacity.
1/2
FIGURES OF THE SPECIFICATION
(Start
etermine influencing factors
C={ C, C ., Cs}
onstruct a cloud model
nstruct basic credibility
ssinment distribution
Set evidence set
E={Ei,E2,.. Eo}
Iculate the conflict coefficient
K in multi-source evidence
K' ?
es no
empster's eighted
a era e rule
Multi-evidence fusion
Are all the no
nce fuse
Yes
Security risk level
nervent n
lobal sensitivity analysis
GEnd I
FIG.1
Description
1/2
(Start etermine influencing factors C={ C, C ., Cs} onstruct a cloud model
nstruct basic credibility ssinment distribution
Set evidence set E={Ei,E2,.. Eo}
Iculate the conflict coefficient K in multi-source evidence
K' ? es no empster's eighted a era e rule
Multi-evidence fusion
Are all the no nce fuse Yes Security risk level nervent n
lobal sensitivity analysis
GEnd I
FIG.1
Method of real-time safety warning of tunnel approaching construction
based on data fusion
The present invention belongs to the technical field of security risk
perception of deformation of an adjacent building induced by tunnel construction,
and specifically relates to a method for early warning security of a surrounding
building in tunnel construction based on a plurality of sensors, which can monitor,
analyze and evaluate a security state of an existing building in an environment of
tunnel construction in a real-time and accurate manner.
In order to cope with urban complex diseases such as population growth,
space constraints, and environmental degradation, a scale of mechanized
construction of subways, highways, pipelines and public utility tunnels in major
cities in the world is rapidly increasing. Tunnel excavation in soft soil will
inevitably lead to ground surface settlement, which will cause deformation,
rotation, distortion and even irreversible damage to an adjacent building,
especially those with shallow foundations.
At present, methods for evaluating ground surface settlement and damage to
an adjacent building induced by a tunnel at home and abroad can be roughly
divided into three categories: an empirical method, an analytical method, and a
numerical simulation method. These methods have their own advantages in
predicting the damage to the adjacent building induced by the tunnel, but also have their own limitations in application. For example, Loganathan believed that application of the empirical method in different ground conditions and construction techniques was limited, and therefore could not draw high-precision conclusions (refer to An innovative method for assessing tunneling induced risks to adjacent structures, PB2009William Barclay Parsons Fellowship Monograph
, Parsons Brinckerhoff Inc., New York, USA, 2011, pp.1-129). Chou and Bobet
believed that the analytical method did not consider time and stratum creep loss
and tended to underestimate the maximum soil deformation or overestimate the
minimum settlement (refer to Predictions of ground deformations in shallow
tunnels in clay, Tunnelling and Underground Space Technology 17 (1) (2002) 3
19.). Lodygowski and Summerka believed that construction and verification of a
numerical simulation model took a lot of time, especially when analyzing adjacent
buildings, and accuracy and effectiveness of the numerical simulation method
were extremely sensitive to boundary conditions (refer to Limitations in
application of finite element method in acoustic numerical simulation, Journal of
theoretical and applied mechanics 44 (4) (2006) 849-865). In addition, because
of dynamic variability and complexity of tunnel engineering, there are a lot of
randomness and uncertainty in a construction process. The forgoing methods are
difficult to comprehensively consider such randomness and uncertainty and
various error, and easily cause significant deviations in security management
decision-making.
Therefore, in order to meet actual use security requirements of the existing
building, a security state of the existing building under the environment of the tunnel construction is monitored, analyzed, and evaluated in a real-time and accurate manner, which can effectively perceive and predict a security risk of the damage to the adjacent building induced by the tunnel construction, and then timely and effective take corresponding control measures.
In view of the forgoing technical problems, a complete, effective and
convenient security warning method have not yet seen. How to solve the forgoing
technical difficulties and design a method for early warning security of a
surrounding building in tunnel construction to achieve infinite proximity of damage
to the surrounding building and an actual ground surface settlement is the
problem to be solved by the present invention.
Summary
In view of the forgoing deficiencies or improvement requirements of the prior
art, the present invention provides a method for early warning security of a
surrounding building in tunnel construction based on a plurality of sensors. The
method is based on a multi-source information fusion method of deformation of
an adjacent building induced by the tunnel construction under uncertainty
conditions of a cloud model, a D-S evidence theory and Monte Carlo simulation
technology to perceive security risk state. The result obtained by this method is
infinitely close to a real situation and can meet accuracy requirements of security
risk estimation of the surrounding building before the tunnel construction.
In order to achieve the forgoing objective, according to one aspect of the
present invention, a method for early warning security of a surrounding building in
tunnel construction based on a plurality of sensors is provided and includes the following steps:
Si: constructing an evaluation indicator system: determining qualitative and
quantitative indicators that comprehensively evaluate a security risk level of the
surrounding building induced by tunnel construction, and constructing a multi
level information fusion model of security early warning of the surrounding
building in the tunnel construction according to the qualitative and quantitative
indicators;
S2: identifying a risk interval: according to standard specifications, dividing a
size of damage to the surrounding building induced by the tunnel construction
into a plurality of risk levels; and determining a reasonable interval division of the
qualitative and quantitative indicators, each of the qualitative and quantitative
indicators being divided into a plurality of intervals corresponding to the plurality
of risk levels;
S3: acquiring data: acquiring quantitative indicator data and qualitative
indicator data via a hard sensor and a soft sensor;
S4: constructing a basic probability distribution based on a cloud model
theory: calculating membership degrees of the qualitative and quantitative
indicators corresponding to each risk level based on the cloud model as the basic
probability distribution;
S5: realizing multi-level fusion based on an improved D-S evidence theory:
performing three-level fusion of monitoring point fusion, indicator fusion and
overall security risk state fusion based on the improved D-S evidence theory;
S6: determining sensitivity of the indicator based on Monte Carlo simulation technology: using Monte Carlo simulation technology for security risk assessment, calculating a final security level, and using a correlation coefficient of the final security level to measure global sensitivity analysis of each input indicator for an output indicator.
Further, preferably, in step S1, the quantitative indicator comprises
cumulative settlement (C1), daily settlement (C2) and a building inclination rate
(C3); and the qualitative indicator comprises foundation leakage (C4), ground
crack conditions (C 5 ) and wall crack conditions (C6).
Preferably, in step S2, the size of the damage to the building induced by a
tunnel is divided into four risk levels: I: a security level; II: a low risk level; III: a
medium risk level; and IV: a high risk level; each of the qualitative and
quantitative indicators is divided into four intervals corresponding to four risk
levels.
Preferably, in step S3, the hard sensor is at least one electronic sensor for
monitoring and acquiring deformation feature data of the building caused by
tunnel excavation; and the soft sensor is used to acquire a qualitative indicator
judged by humans.
Preferably, step S4 further includes:
S4a: constructing a normal cloud model: constructing cloud models for
different levels of each indicator, that is, calculating three feature values of the
cloud model: Ex, En, He; and dividing each factor into different risk levels Cij
(i=1,2,...,M; j=1,2,..,N), wherein each interval has its own dual restriction interval
[Cij(L) , Cij(R)](i=1,2,...,M; j=1,2,...,N); formula (1) converts a level interval [Cij(L),
Cij(R)] into the normal cloud model (Exij, Enij, Heij), and all indicators
corresponding to the normal cloud model Rij=(Exij, Enij, Heij) of different risk levels
(i=1,2.....,M; j=1,2,...,N) are all acquired in this way, the formula (1) is as follows:
Where "Exi" is expectation of a normal cloud in a j-th level interval of an i-th
indicator; "Eni" is entropy of the normal cloud in the j-th level interval of the i-th
indicator; "Hei" is super-entropy of the normal cloud in the j-th level interval of the
i-th indicator; "s" is a constant from 0 to "Enij", and represents uncertainty in
indicator division; "xij(L)" and "xij(R)" are left and right boundary values of the j-th
level interval of the i-th indicator, respectively.
S4b: acquiring a membership degree of each indicator corresponding to
each level: according to the qualitative indicator data and the quantitative
indicator data, combining with calculation of a feature value of the cloud model to
obtain a membership degree of an observed value of the indicator for a specific
level; wherein a membership degree in the cloud model represents a correlation
degree of an observed value Xiof the indicator Ci relative to a certain risk level Aj
(i=1,2,...,M; j=1,2,...,N), therefore, calculation of the membership degree is
capable of being used for evaluating a basic probability distribution of an indicator
Aj (i=1,2,...,M; j=1,2,...,N), and a basic probability distribution of different risk
levels of a specific indicator is capable of being acquired by formula (2), where,
mi(A) represents the correlation degree of the observed value xiof Ci relative to a certain risk level Aj (i=1,2,...,M; j=1,2,...,N), mi (9) represents the probability distribution of the part of the final output result where the security risk level cannot be determined, and a credibility factor represents 1-mi ((),the formula (2) is as follows:
M, (4.,~..Afj12.N (2)
Preferably, step S5 further includes:
S5a: constructing a multi-level fusion model: fusing the qualitative indicator
data and the quantitative indicator data via a first-level fusion to obtain a security
risk state of each indicator; fusing a plurality of indicators via a second-level
fusion to obtain an overall security risk state; and fusing the qualitative indicator
data and the quantitative indicator data via a three-level fusion to obtain the
security risk state of the damage to the surrounding building induced by the entire
tunnel construction;
S5b: selecting a fusion rule: selecting a threshold based on a rule that is 1
0.05=0.95, wherein when K is greater than , an evidence is considered to be
highly conflicted, and the weighted average rule, namely formula (3), is used for
evidence fusion; otherwise, the Dempster rule, namely formula (4), is used for
fusion; the formulas (3) and (4) are as follows:
JmA) [IK ~ IA~n(A,)rn(Ak)VA 0-A -_
K= V ,(A 2 A )J~(AA)< I
Where K is defined as a conflict coefficient, indicating the degree of conflict
between evidences; 1/(1-K) is a normalization coefficient to avoid allocating a
non-zero element in an empty set 0; 0 is numbering of an evidence body in the
fusion process, i , j and k represent the i-th, j-th, and k-th hypotheses,
respectively.
Where Wi is weight of an i-th evidence body; di is a sum of Euclidean
distances between the i-th evidence body and other evidences.
S5c: fusing a plurality of levels: obtaining a final security risk level of the
damage to the surrounding building via the three-level fusion of the monitoring
point fusion, the indicator fusion and the overall security risk state fusion.
Preferably, in step S6, setting the qualitative indicator data and quantitative
indicator data to obey a normal distribution, wherein the expectation value of
sampling distribution is an observed value of the indicator, a variance is 5% of
the observed value, the number Q of iterations is set to 1000, a multi-level
information fusion process is repeated 1000 times, and expected values of a
plurality of fusion results are calculated to obtain the final security level, that is,
the overall security risk state, and the correlation coefficient of the level is used to
measure the global sensitivity analysis of each input indicator for the output
indicator T.
Preferably, Monte Carlo simulation technology is used to obtain a statistical feature of an output variable based on probability distribution, simulation is used to obtain a series of input data sets :1 x (i=1,2,...M)of the i-th input indicator based on probability distribution of an input variable. Correspondingly, a series of output data sets {T1,T2,...,TQ} can be obtained after repeated iterations, where Q represents the number of the iterations; based on an interaction between a plurality of input factors, the correlation coefficient (for example, formula (5)) of the level is used to measure a contribution degree of sensitivity of each input indicator to the final security risk level, the global sensitivity analysis
(GSA) of the i-th indicator Ci is expressed as GSA (Ci), and the calculation is as
formula (5):
GTSA(C)= = 5
Where, Q is the number of repetition based on Monte Carlo simulation
technology; q represents a q-th iteration; R(x ) is an order of (x9) of the i-th
indicator Ci in a simulation input data set; R(x9) is an average value of R(x9);
R(Tq) is a sorting of the security risk result Tq of the Q-th iteration; R(Tq) is the
average value of R(Tq).
Generally speaking, compared with the prior art, the forgoing technical
solutions conceived by the present invention have the following advantages and
beneficial effects:
The present invention proposes a multi-source information fusion method of
deformation of an adjacent building induced by tunnel construction under uncertainty conditions of a cloud model, a D-S evidence theory and Monte Carlo simulation technology. The method combines an electronic (hard) sensor with expert experience (a soft sensor) to obtain multi-source data, which overcomes a current situation of single evaluation data sources. In order to construct basic credibility assignment of indicators for levels under the uncertainty conditions, a membership function is calculated based on a normal cloud model to strengthen accuracy of fusion results of the D-S evidence theory. In order to deal with highly conflicting evidence, the method combines a Dempster fusion rule and a weighted average rule to select a fusion rule by setting a threshold. In order to strengthen effectiveness of supervisory control, the method considers a nonlinear cross-relationship between indicators to determine global sensitivity analysis of input indicators under the uncertainty conditions, uses the Monte Carlo simulation technology to analyze the global sensitivity analysis based on a correlation coefficient of levels, and determines an allowable deviation of an observed value of the indicator.
This method is based on construction of a security risk evaluation indicator
system, classification of levels and the normal cloud model to realize an
uncertainty conversion between a qualitative concept and a quantitative indicator,
and construct the basic credibility assignment (BPA) of the evaluation indicators;
Combining the Dempster fusion rule and the average weighting rule, a new
fusion rule is proposed, which improves the traditional D-S evidence theory to
deal with high conflict evidence; based on BPA, adopts the improved D-S
evidence theory to realize the fusion of monitoring points and indicators of adjacent building deformation induced by tunnel construction Integrate with the overall security risk state; based on Monte Carlo simulation technology to determine the sensitivity of input indicators and the allowable value of measurement error under uncertain conditions. The present invention provides a security risk perception method and an information fusion method that integrate risk identification, risk analysis, risk evaluation, risk control, and risk decision making for tunnel construction. The proposal of this method is conducive to strengthening the reliability and accuracy of the evaluation of damage to the adjacent building induced by the tunnel construction and is of great significance to improving security risk management and control level of the tunnel construction. This method also has the advantages of small amount of data processing, easy operation, high reliability and accuracy of results.
FIG. 1 is a flowchart of a method according to an embodiment of the present
invention.
FIG. 2 is a framework diagram of multi-layer information fusion for security
risk perception in a method according to an embodiment of the present invention.
FIG. 3 is a distribution diagram of global sensitivity analysis of input
indicators according to an embodiment of the present invention.
In order to make the objectives, technical solutions, and advantages of the
present invention clearer, the following describes the present invention in further
detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as the technical features do not conflict with each other.
FIG. 1 shows a flow chart of a method for early warning security of a
surrounding building in tunnel construction based on a plurality of sensors
proposed by the present invention. Taking four buildings 1#-4# temporarily built
in a tunnel area as an example, the method mainly includes the following steps:
S1: constructing an evaluation indicator system:
Determining qualitative and quantitative indicators that comprehensively
evaluate a security risk level of an adjacent building induced by tunnel
construction, and constructing an evaluation indicator system, wherein preferably,
the qualitative and quantitative indicators are determined based on standard
specifications (such as "Building Foundation Design Code (GB 50007-2011)" and
"Metro Engineering Construction Security Evaluation Standards (GB 50715
2011)"), monitoring system, literature data, and expert experience. Since the
quantitative indicator mainly focuses on a deformation feature induced by tunnel
excavation, preferably, the quantitative indicator includes cumulative settlement
(CI), daily settlement (C2) and a building inclination rate (C3). In addition, experts
and/or engineers regularly go to a construction site to collect pictures and video
data reflecting the health of the adjacent building. The qualitative indicator is
obtained from the pictures and the video data. Preferably, the qualitative indicator includes foundation leakage (C4), ground crack conditions (C 5 ), and wall crack conditions (C6).
S2: identifying a risk interval:
According to standard specifications, the size of the damage to the building
induced by a tunnel is divided into four risk levels: I: a security level; II: a low risk
level; III: a medium risk level; and IV: a high risk level. According to a monitoring
record, standard specifications, a technical manual and a research report and
other engineering practice and theoretical analysis, on the basis of full
consideration of engineering practice and expert experience, reasonable interval
division of the qualitative and quantitative indicators is determined. Each of the
qualitative and quantitative indicators is divided into four intervals corresponding
to four risk levels, as shown in Table 1.
Projects Variables Description Level division _ _ 1__ 11 111 IV C1 stcum acted [0,24) [24,30) [30,36) [36,50]
items items C2 Daily settlement C2mm/d) [0,2) [2,3) [3,4) [4,6]
(Hard sensor) Building C3 inclination rate [0,2.4) [2.4,3) [3,3.6) [3.6,5] (%o) Expert C4 Foundation [80,100) [60,80) [40,60) [0,40] evaluation penetration Ce Ground crack conditions [80,100) [60,80) [40,60) [0,40] (Sot enor (Softsensor) C6 Wall crack state [80,100) [60,80) [40,60) [0,40]
S3: acquiring data:
The quantitative and the qualitative indicator are respectively acquired via a
hard sensor and a soft sensor. The hard sensor is at least one electronic sensor for monitoring and acquiring deformation feature data of a building caused by tunnel excavation. In this embodiment, each building is provided with four electronic sensors to obtain four sets of quantitative indicator data. The soft sensor is used to obtain the qualitative indicator judged by humans. For example, experts and/or engineers regularly go to the construction site to collect pictures and video data reflecting the building's health state and acquires the qualitative indicator from the pictures and the video data. In this embodiment, each building obtains the qualitative indicators via a total of four experts and engineers, and a total of four sets of qualitative indicator data is obtained. In this embodiment, one electronic sensor and one expert/engineer are defined as one sensor. Therefore, each building obtains four sets of monitoring data via four sensors S1-S4, namely
S1-S4. Specific data describing the qualitative and quantitative indicators
collected are shown in Table 3.
Table 3: Sensor monitoring data of four existing buildings
Factor| 1# 2# 3# 4# s S1 S2 S3 S4 S1 S2 S3 S4 S1 S2 S3 S4 S1 S2 S3 S4 C1 28.5|29.3|27.8 29.8 27.4 28.2|28.6 25.3 25.6 24.3|22.3 23.7 18.7 17.6 16.6 17.4 C2 2.7 2.6 2.4 2.7 3.5 3.6 3.6 3.5 2.5 2.3 2.3 2.2 1.5 1.4 1.1 1.5 C 3 2.89|2.75|2.62 2.78 3.02 2.79|3.42 3.05 2.6 2.31 2.12 2.02 1.35 1.45 1.32 1.21 C4 76 73 72 58 62 63 78 52 75 80 79 78 72 83 77 82 C5 66|65 53 58 54 56 58 79 68 77|85 86 84 79 87 86 C6 58 55 52 58 86 84 80 83 80 78 78 76 67 76 78 79
S4: constructing a basic probability assignment based on a cloud model
theory:
A membership degree of each indicator corresponding to each level is
calculated based on a cloud model as the basic probability assignment
distribution, which provides a basis for the subsequent DS evidence theory fusion.
Specifically, taking the 1# building's indicator C1 as an example, construction of a
basic probability distribution of C1 mainly includes the following steps:
S4a: constructing a normal cloud model: constructing cloud models for
different levels of each indicator, that is, calculating three feature values of the
cloud model: Ex, En, He; and dividing each factor into different risk levels Cij
(i=1,2,...,M; j=1,2,..,N), wherein each interval has its own dual restriction interval
[Cij(L), Cij(R)](i=1,2,...,M; j=1,2,...,N); formula (1) converts a level interval [Cij(L),
Cij(R)] into the normal cloud model (Exij, Enij, Heij), and all indicators
corresponding to the normal cloud model Rij=(Exij, Enij, Heij) of different risk levels
(i=1,2.,...,M; j=1,2,...,N) are all acquired in this way, the formula (1) is as follows:
x (L)4X4(p)
He=S(=..Mj12..A)I.
Where "Exij" is expectation of a normal cloud in a j-th level interval of an i-th
indicator; "Eni" is entropy of the normal cloud in the j-th level interval of the i-th
indicator; "Hei" is super-entropy of the normal cloud in the j-th level interval of the
i-th indicator; "s" is a constant from 0 to "Enij", and represents uncertainty in
indicator division; "xij(L)" and "xij(R)" are left and right boundary values of the j-th
level interval of the i-th indicator, respectively.
S4b: acquiring a membership degree of each indicator corresponding to
each level: according to the qualitative indicator data and the quantitative
indicator data, combining with calculation of a feature value of the cloud model to
obtain a membership degree of an observed value of the indicator for a specific level; wherein a membership degree in the cloud model represents a correlation degree of an observed value Xiof the indicator Ci relative to a certain risk level Aj
(i=1,2,...,M; j=1,2,...,N), therefore, calculation of the membership degree is
capable of being used for evaluating a basic probability distribution of an indicator
Aj (i=1,2,...,M; j=1,2,...,N), and a basic probability distribution of different risk
levels of a specific indicator is capable of being acquired by formula (2), where,
mi(A) represents the correlation degree of the observed value xiof Ci relative to
a certain risk level A (i=1,2,...,M; j=1,2,...,N), mi (9) represents the probability
distribution of the part of the final output result where the security risk level
cannot be determined, and a credibility factor represents 1-mi (0), the formula (2)
is as follows:
The obtained basic probability assignment distribution of the four sensors
S1-S4 is shown in Table 4.
Table 4: 1# Basic probability assignment distribution of four sensors for 1#
building's indicator C1
Observed The basic probability assignment distribution of indicator C1 Sensors values m(A1) m(A2) m(A3) m(A4) m(9) (mm) S1 28.5 0.000 0.324 0.000 0.000 0.676 S2 29.3 0.000 0.073 0.001 0.000 0.926 S3 27.8 0.000 0.727 0.000 0.000 0.273 S4 29.8 0.000 0.020 0.006 0.000 0.974
S5: realizing multi-level fusion based on an improved D-S evidence theory:
Performing three-level fusion of monitoring point fusion, indicator fusion and
overall security risk state fusion based on the improved D-S evidence theory to
obtain the final security risk level of the damage to the surrounding building
induced by the tunnel construction, which mainly includes the following steps;
S5a: constructing a multi-level fusion model: fusing the qualitative indicator
data and the quantitative indicator data via a first-level fusion to obtain a security
risk state of each indicator; fusing a plurality of indicators via a second-level
fusion to obtain an overall security risk state; and fusing the qualitative indicator
data and the quantitative indicator data via a three-level fusion to obtain the
security risk state of the damage to the surrounding building induced by the entire
tunnel construction;
S5b: selecting a fusion rule: selecting a threshold based on a rule that ( is 1
0.05=0.95, wherein when K is greater than (, an evidence is considered to be
highly conflicted, and the weighted average rule, namely formula (3), is used for
evidence fusion; otherwise, the Dempster rule, namely formula (4), is used for
fusion; the formulas (3) and (4) are as follows:
MIA= ,()n().nA)1 10 A 0(3
Where K is defined as a conflict coefficient, indicating the degree of conflict
between evidences. 1/(1-K) is a normalization coefficient to avoid allocating a
non-zero element in an empty set 0. 0 is numbering of an evidence body in the fusion process. i, j and k represent the i-th, j-th, and k-th hypotheses, respectively.
mI?(A)= (w* (
) = 1/d,
~~A ) (4)
Where Wi is weight of an i-th evidence body; di is a sum of Euclidean
distances between the i-th evidence body and other evidences.
S5c: fusing a plurality of levels: obtaining a final security risk level of the
damage to the surrounding building via the three-level fusion of the monitoring
point fusion, the indicator fusion and the overall security risk state fusion.
Specific fusion results are shown in Tables 5 to 8.
Table 5: Fusion results of three-level indicator sensor of 1# Building
Indicators m(A1) m(A2) m(A3) m(A4) m( C1 0.000 0.831 0.001 0.000 0.168 C2 0.000 0.998 0.000 0.000 0.002 C3 0.000 0.992 0.000 0.000 0.008
Table 6: Fusion results of indicator data (Hard Data) of hard sensor (B1) of
four existing buildings
Buildings The basic probability assignment distribution of B1 indicator m(A1) m(A2) m(A3) m(A4) m( 1# 0.000 1.000 0.000 0.000 0.000 2# 0.000 0.000 1.000 0.000 0.000 3# 0.000 1.000 0.000 0.000 0.000 4# 1.000 0.000 0.000 0.000 0.000
Table 7: Fusion result of indicator data (Soft Data) of soft sensor (B2) of four
existing buildings
Buildings The basic probability assignment distribution of B2 indicators m(A1) m(A2) m(A3) m(A4) m(9) 1# 0.000 0.653 0.337 0.000 0.010 2# 0.107 0.019 0.813 0.000 0.061 3# 0.112 0.832 0.000 0.000 0.056 4# 0.214 0.759 0.000 0.000 0.027
Table 8: Fusion results of (T) indicator (overall) of building level I
.uilig The basic probability assignment distribution of T indicator Buildings m(A1) m(A2) m(A3) m(A4) m(9) 1 0.000 1.000 0.000 0.000 0.000 2# 0.000 0.000 1.000 0.000 0.000 3# 0.000 1.000 0.000 0.000 0.000 4* 1.000 0.000 0.000 0.000 0.000
S6: determining sensitivity of the indicator based on Monte Carlo simulation
technology:
In actual engineering, because of measurement errors and human factors,
data observed from different information sources often have unavoidable
deviations. In order to reduce potential uncertainty in the process of input variable
characterization and measurement, the Monte Carlo simulation technology is
used for security risk assessment. The indicators C1-C6 are set to obey the
normal distribution. An expectation value of sampling distribution is an observed
value of the indicator, and the variance is 5% of the observed value. Because
p50.05 is a generally accepted statistical deviation level, the deviation level is set
to 5%. The number Q of iterations is set to 1000 times. The multi-level
information fusion process is repeated 1000 times. The final security level is
calculated to obtain the final overall security risk state. The correlation coefficient
of the level is used to measure the global sensitivity analysis of each input indicator Ci (i=1,2,...,6) for the output indicator T.
Specifically, Monte Carlo simulation technology is used to obtain a statistical
feature of an output variable based on probability distribution. Simulation is used
to obtain a series of input data sets -' (i=1,2,...M)of the i-th input
indicator based on probability distribution of an input variable. Correspondingly,
a series of output data sets {T1,T2,...,TQ} can be obtained after repeated iterations,
where Q represents the number of the iterations. Based on an interaction
between a plurality of input factors, the correlation coefficient (for example,
formula (5)) of the level is used to measure a contribution degree of sensitivity of
each input indicator to the final security risk level, the global sensitivity analysis
(GSA) of the i-th indicator Ci is expressed as GSA (Ci), and the calculation is as
formula (5):
GS4()- qI - ~(5) Y(R(,l) - RCxY)) R(Tq)}}
Where, Q is the number of repetition based on Monte Carlo simulation
technology; q represents a q-th iteration; R(x ) is an order of (xq) of the i-th
indicator Ci in a simulation input data set; R(x9) is an average value of R(x9);
R(Tq) is a sorting of the security risk result Tq of the Q-th iteration; R(Tq) is the
average value of R(Tq).
FIG. 3 reflects the results of global sensitivity analysis distribution of six input
indicators. It can be seen that the indicators C1-C3 are positive sensitive factors,
while the indicators C4-C6 are negative sensitive factors, where C1 (cumulative settlement) is the maximum sensitivity among the positive sensitive factors. The sensitivity of C5 (ground crack conditions) and C6 (wall crack conditions) is greater in negative sensitivity factors.
The person skilled in the art can easily understand that the forgoing
descriptions are only preferred embodiments of the present invention and are not
intended to limit the present invention. Any modification, equivalent replacement,
and equivalent improvements, etc. within the spirit and principle of the present
invention should all be included in the protection scope of the present invention.
Claims (8)
1. A method for early warning security of a surrounding building in tunnel
construction based on a plurality of sensors, comprising the following steps:
Si: constructing an evaluation indicator system: determining qualitative and
quantitative indicators that comprehensively evaluate a security risk level of the
surrounding building induced by tunnel construction, and constructing a multi
level information fusion model of security early warning of the surrounding
building in the tunnel construction according to the qualitative and quantitative
indicators;
S2: identifying a risk interval: according to standard specifications, dividing a
size of damage to the surrounding building induced by the tunnel construction
into a plurality of risk levels; and determining a reasonable interval division of the
qualitative and quantitative indicators, each of the qualitative and quantitative
indicators being divided into a plurality of intervals corresponding to the plurality
of risk levels;
S3: acquiring data: acquiring quantitative indicator data and qualitative
indicator data via a hard sensor and a soft sensor;
S4: constructing a basic probability distribution based on a cloud model
theory: calculating membership degrees of the qualitative and quantitative
indicators corresponding to each risk level based on the cloud model as the basic
probability distribution;
S5: realizing multi-level fusion based on an improved D-S evidence theory:
performing three-level fusion of monitoring point fusion, indicator fusion and overall security risk state fusion based on the improved D-S evidence theory; and
S6: determining sensitivity of the indicator based on Monte Carlo simulation
technology: using Monte Carlo simulation technology for security risk assessment,
calculating a final security level, and using a correlation coefficient of the final
security level to measure global sensitivity analysis of each input indicator for an
output indicator;
2. The method for early warning the security of the surrounding building in
the tunnel construction based on the plurality of sensors according to claim 1,
wherein in step S1, the quantitative indicator comprises cumulative settlement
(C1), daily settlement (C2) and a building inclination rate (C3); and the qualitative
indicator comprises foundation leakage (C4), ground crack conditions (C5) and
wall crack conditions (C6);
3. The method for early warning the security of the surrounding building in
the tunnel construction based on the plurality of sensors according to claim 1,
wherein in step S2, the size of the damage to the building induced by a tunnel is
divided into four risk levels: 1: a security level; II: a low risk level; III: a medium
risk level; and IV: a high risk level; each of the qualitative and quantitative
indicators is divided into four intervals corresponding to four risk levels;
4. The method for early warning the security of the surrounding building in
the tunnel construction based on the plurality of sensors according to claim 1,
wherein in step S3, the hard sensor is at least one electronic sensor for
monitoring and acquiring deformation feature data of the building caused by
tunnel excavation; and the soft sensor is used to acquire a qualitative indicator judged by humans;
5. The method for early warning the security of the surrounding building in
the tunnel construction based on the plurality of sensors according to claim 1,
wherein step S4 further comprises:
S4a: constructing a normal cloud model: constructing cloud models for
different levels of each indicator, that is, calculating three feature values of the
cloud model: Ex, En, He; and dividing each factor into different risk levels Cij
(i=1,2,...,M; j=1,2,..,N), wherein each interval has its own dual restriction interval
[Cij(L) , Cij(R)](i=1,2,...,M; j=1,2,...,N); formula (1) converts a level interval [Cij(L),
Cij(R)] into the normal cloud model (Exij, Enij, Hei), and all indicators
corresponding to the normal cloud model Rij=(Exij, Enij, Hei) of different risk levels
(i=1,2.,...,M; j=1,2,...,N) are all acquired in this way, the formula (1) is as follows:
L (R)-x,(R
where "Exi" is expectation of a normal cloud in a j-th level interval of an i-th
indicator; "Eni" is entropy of the normal cloud in the j-th level interval of the i-th
indicator; "Hei" is super-entropy of the normal cloud in the j-th level interval of the
i-th indicator; "s" is a constant from 0 to "Enij", and represents uncertainty in
indicator division; "xij(L)" and "xij(R)" are left and right boundary values of the j-th
level interval of the i-th indicator, respectively;
S4b: acquiring a membership degree of each indicator corresponding to
each level: according to the qualitative indicator data and the quantitative indicator data, combining with calculation of a feature value of the cloud model to obtain a membership degree of an observed value of the indicator for a specific level; wherein a membership degree in the cloud model represents a correlation degree of an observed value Xiof the indicator Ci relative to a certain risk level Aj
(i=1,2,...,M; j=1,2,...,N), therefore, calculation of the membership degree is
capable of being used for evaluating a basic probability distribution of an indicator
Aj (i=1,2,...,M; j=1,2,...,N), a basic probability distribution of different risk levels of
a specific indicator is capable of being acquired by formula (2), where, mi (Aj)
represents the correlation degree of the observed value xi of Ci relative to a
certain risk level A (i=1,2,...,M; j=1,2,...,N), the formula (2) is as follows:
6. The method for early warning the security of the surrounding building in
the tunnel construction based on the plurality of sensors according to claim 1,
wherein step S5 further comprises:
S5a: constructing a multi-level fusion model: fusing the qualitative indicator
data and the quantitative indicator data via a first-level fusion to obtain a security
risk state of each indicator; fusing a plurality of indicators via a second-level
fusion to obtain an overall security risk state; and fusing the qualitative indicator
data and the quantitative indicator data via a three-level fusion to obtain the
security risk state of the damage to the surrounding building induced by the entire
tunnel construction;
S5b: selecting a fusion rule: selecting a threshold based on a rule that is 1
0.05=0.95, wherein when K is greater than , an evidence is considered to be
highly conflicted, and the weighted average rule, namely formula (3), is used for
evidence fusion; otherwise, the Dempster rule, namely formula (4), is used for
fusion; the formulas (3) and (4) are as follows:
A, 1 ~(A )..n,6(A, ).VA A m (A)(3) K= i (A) ,...rnA,,)<1I
where K is defined as a conflict coefficient, indicating the degree of conflict
between evidences; 1/(1-K) is a normalization coefficient to avoid allocating a
non-zero element in an empty set 0; 0 is numbering of an evidence body in the
fusion process, i , j and k represent the i-th, j-th, and k-th hypotheses,
respectively;
m (A)= (wv,* m,{ A)
'(1/d,)
Ld,= j, (A()-A (4)
where Wi is weight of an i-th evidence body; di is a sum of Euclidean
distances between the i-th evidence body and other evidences;
S5c: fusing a plurality of levels: obtaining a final security risk level of the
damage to the surrounding building via the three-level fusion of the monitoring
point fusion, the indicator fusion and the overall security risk state fusion;
7. The method for early warning the security of the surrounding building in
the tunnel construction based on the plurality of sensors according to claim 1,
wherein in step S6, setting the qualitative indicator data and quantitative indicator
data to obey a normal distribution, wherein an expectation value of sampling
distribution is an observed value of the indicator, a variance is 5% of the
observed value, the number Q of iterations is set to 1000, a multi-level
information fusion process is repeated 1000 times, and expected values of a
plurality of fusion results are calculated to obtain the final security level, that is,
the overall security risk state, and the correlation coefficient of the level is used to
measure the global sensitivity analysis of each input indicator for the output
indicator T;
8. The method for early warning the security of the surrounding building in
the tunnel construction based on the plurality of sensors according to claim 7,
wherein Monte Carlo simulation technology is used to obtain a statistical feature
of an output variable based on probability distribution, simulation is used to obtain
a series of input data sets ' 'I (i=1,2,...M)of the i-th input indicator
(i=1,2,...M) based on probability distribution of an input variable, correspondingly,
a series of output data sets {T1,T2,...,TQ} can be obtained after repeated iterations,
where Q represents the number of the iterations; based on an interaction
between a plurality of input factors, the correlation coefficient (for example,
formula (5)) of the level is used to measure a contribution degree of sensitivity of
each input indicator to the final security risk level, the global sensitivity analysis
(GSA) of the i-th indicator Ci is expressed as GSA (Ci), and the calculation is as formula (5);
${ R~xi)- (xi)(R( T))- K( T')) GSA(C)= (5) (R(xi)- R(x)X{ R(T - R(T*}( q=1 q=i
where, Q is the number of repetition based on Monte Carlo simulation
technology; q represents a q-th iteration; R(x,)is an order of (x9) of the i-th
indicator Ci in a simulation input data set; R(x,) is an average value of R(x9);
R(Tq) is a sorting of the security risk result Tq of the Q-th iteration; R(Tq) is the
average value of R(Tq).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| AU2021101951A AU2021101951A4 (en) | 2021-04-15 | 2021-04-15 | Method of real-time safety warning of tunnel approaching construction based on data fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| AU2021101951A AU2021101951A4 (en) | 2021-04-15 | 2021-04-15 | Method of real-time safety warning of tunnel approaching construction based on data fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| AU2021101951A4 true AU2021101951A4 (en) | 2021-06-03 |
Family
ID=76132899
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| AU2021101951A Ceased AU2021101951A4 (en) | 2021-04-15 | 2021-04-15 | Method of real-time safety warning of tunnel approaching construction based on data fusion |
Country Status (1)
| Country | Link |
|---|---|
| AU (1) | AU2021101951A4 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114839696A (en) * | 2022-07-04 | 2022-08-02 | 武九铁路客运专线湖北有限责任公司 | Multi-source data fusion sensing three-dimensional tunnel unfavorable geology detection method |
| CN115481880A (en) * | 2022-09-06 | 2022-12-16 | 中国路桥工程有限责任公司 | Highway construction major risk source identification method |
-
2021
- 2021-04-15 AU AU2021101951A patent/AU2021101951A4/en not_active Ceased
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114839696A (en) * | 2022-07-04 | 2022-08-02 | 武九铁路客运专线湖北有限责任公司 | Multi-source data fusion sensing three-dimensional tunnel unfavorable geology detection method |
| CN114839696B (en) * | 2022-07-04 | 2022-09-13 | 武九铁路客运专线湖北有限责任公司 | Multi-source data fusion sensing three-dimensional tunnel unfavorable geology detection method |
| CN115481880A (en) * | 2022-09-06 | 2022-12-16 | 中国路桥工程有限责任公司 | Highway construction major risk source identification method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pan et al. | Multi-classifier information fusion in risk analysis | |
| CN106779296A (en) | A kind of constructing tunnel Adjacent Buildings safe early warning method based on multisensor | |
| Han et al. | Intelligent decision model of road maintenance based on improved weight random forest algorithm | |
| AU2021101951A4 (en) | Method of real-time safety warning of tunnel approaching construction based on data fusion | |
| Chen et al. | Resilience assessment of regional areas against earthquakes using multi-source information fusion | |
| CN104766129A (en) | Subway shield construction surface deformation warning method based on temporal and spatial information fusion | |
| Van et al. | Research trends on machine learning in construction management: a scientometric analysis | |
| CN105678481A (en) | Pipeline health state assessment method based on random forest model | |
| Wu et al. | Dynamic risk analysis for adjacent buildings in tunneling environments: a Bayesian network based approach | |
| Chen et al. | Vulnerability modeling, assessment, and improvement in urban metro systems: A probabilistic system dynamics approach | |
| CN111401653A (en) | Tunnel water leakage risk spatial dependency prediction method and prediction system | |
| CN111126853A (en) | Fuzzy FMEA-based hydraulic engineering risk early warning analysis method and system | |
| CN117172556B (en) | Construction risk early warning method and system for bridge engineering | |
| CN114444180A (en) | Full life cycle parameter prediction and monitoring method and system for assembly type building structure | |
| Zhou et al. | Topological mapping and assessment of multiple settlement time series in deep excavation: a complex network perspective | |
| CN118313181B (en) | Historical building protection condition assessment method for historical cultural block | |
| Lu et al. | Risk assessment of complex footbridge based on Dempster–Shafer evidence theory using Fuzzy matter–element method | |
| Chen et al. | Spatio‐temporal data mining method for joint cracks in concrete dam based on association rules | |
| Mahpour | Building maintenance cost estimation and circular economy: the role of machine-learning | |
| CN109710720A (en) | A kind of crime risk such environmental effects analysis method for taking background effect into account | |
| CN118095834A (en) | Traffic accident risk studying and judging method based on interpretable random forest | |
| Liu et al. | A novel reliability analysis method for a dependent system by copula model: a case study in operation tunnels maintenance | |
| CN117522192A (en) | Method and system for supporting intelligent map of urban physical examination and forming report | |
| Yu et al. | An improved multi-objective genetic algorithm and data fusion in structural damage identification | |
| Ma et al. | Slab arching degree identification and evaluation based on track dynamic inspection data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FGI | Letters patent sealed or granted (innovation patent) | ||
| MK22 | Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry |