CN108647753A - A kind of construction site method for prewarning risk based on BIM and RFID technique - Google Patents
A kind of construction site method for prewarning risk based on BIM and RFID technique Download PDFInfo
- Publication number
- CN108647753A CN108647753A CN201810419786.9A CN201810419786A CN108647753A CN 108647753 A CN108647753 A CN 108647753A CN 201810419786 A CN201810419786 A CN 201810419786A CN 108647753 A CN108647753 A CN 108647753A
- Authority
- CN
- China
- Prior art keywords
- risk
- bim
- data
- particle
- construction site
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000005457 optimization Methods 0.000 claims abstract description 32
- 238000001514 detection method Methods 0.000 claims abstract description 10
- 241001269238 Data Species 0.000 claims abstract description 9
- 239000002245 particle Substances 0.000 claims description 53
- 230000006870 function Effects 0.000 claims description 45
- 239000013598 vector Substances 0.000 claims description 21
- 239000000463 material Substances 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 7
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 230000001788 irregular Effects 0.000 claims description 3
- 238000012804 iterative process Methods 0.000 claims description 3
- 238000012417 linear regression Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000013500 data storage Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 claims 1
- 238000012545 processing Methods 0.000 abstract description 3
- 230000005540 biological transmission Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 3
- 101100001676 Emericella variicolor andK gene Proteins 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 231100000749 chronicity Toxicity 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 238000009430 construction management Methods 0.000 description 1
- 239000004035 construction material Substances 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000002716 delivery method Methods 0.000 description 1
- 238000013278 delphi method Methods 0.000 description 1
- 230000006386 memory function Effects 0.000 description 1
- 210000003739 neck Anatomy 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
- G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of construction site method for prewarning risk based on BIM and RFID technique, characterized in that include the following steps:1)RFID risk datas acquire;2)Risk data processing;3)BIM database sharings are stored with risk data;4)BIM model foundations are transferred with BIM database datas;5)Collision detection;6)Generate risk report;7)Send out Risk-warning alarm;8)Export BIM data historian data;9)The risk profile of PSO algorithm optimization LS SVM;10)Generate prediction result:To step 9)PSO algorithm optimization LS SVM generate risk profile result.This method high efficient and reliable, the accurate acquisition for ensuring construction site risk data, timely transmission, the effective storage of risk data of risk information, the dynamic early-warning control and ex ante forecasting for realizing work progress risk are evaded.
Description
Technical field
The present invention relates to engineering construction fields, and in particular to a kind of construction site risk based on BIM and RFID technique is pre-
Alarm method.
Background technology
Engineering construction has complexity and chronicity, along with the risk factors of construction site also have it is uncertain and with
Machine, the uncertainty and randomness of risk factors cause larger potential threat to the smooth implementation of project, seriously affect and apply
The social image of the life security of worker person, the construction speed of project and enterprise.
Information is transmitted not in time in construction management at present, and working method is uncoordinated between each work post of each department, does over again and delays work
Phenomenon is serious, and Building Information Model (Building Information Modeling, abbreviation BIM) is new as one kind of industry
Technology has many advantages, such as visualization, collaboration, simulation, information sharing, and the research boom of industry has just been started from introducing China,
Risk information can effectively be stored by carrying out construction site Risk-warning based on BIM technology, simulated risk accidents, visualized
Work progress dynamic monitor, realize construction site participant collaborative work, avoid the generation of risk accidents.
Mainly by Delphi method, questionnaire method, Risk-warning relies primarily on for the acquisition of construction site risk factor
Get sth into one's head by rule of thumb in construction personnel, therefore, risk data, which obtains, lacks reliability, and construction period is longer, with when
Between passage, risk factors also occur it is corresponding change, rely on initial judgement merely, lack data acquisition promptness and
Dynamic.Radio frequency identification (Radio Frequency Identification, abbreviation RFID) technology is convenient, flexible with its,
The features such as memory function is strong, penetrability is good, highly effective and safe is widely used in the necks such as vehicle toll collection, supply chain tracking, access control
Domain.Label is attached in material, machinery, equipment and other items in construction, identifier can track its position, the time, temperature, into
Degree penetrates coating, wall plastering, ice and snow into row label reading, and with uniqueness, construction material, equipment have any label in addition
Quality problems can be positioned quickly, effectively trace to the source, return producer, and the entirety due to quality less than position influence engineering is avoided to use
Service life.
Therefore effective pre-alarm and prevention is carried out to construction site risk factors before risk accidents occur, it is accurate to obtain construction
Risk is reduced in range as small as possible or controllable by risk factors in the process, is ensureing project schedule plan on schedule
Carry out, promote project delivery method level, reduces cost of investment variation etc. and have important practical significance.
Invention content
The purpose of the present invention is in view of the deficiencies of the prior art, and it is existing to provide a kind of construction based on BIM and RFID technique
Method for prewarning risk, this method high efficient and reliable, the accurate acquisition that can ensure that construction site risk data, risk information and
When transmit, effective storage of risk data, can realize that the dynamic early-warning control of work progress risk and ex ante forecasting are evaded.
Realizing the technical solution of the object of the invention is:
A kind of construction site method for prewarning risk based on BIM and RFID technique, unlike the prior art, including such as
Lower step:
1) RFID risk datas acquire:Using the RFID with electronic tag model acquire the temperature of construction site, wind speed,
Pressure that material is born, the position that material is placed, the electric current of mechanical equipment, voltage, the position of mechanical equipment, safety cap position
(judging the location of personnel with this) data information, the article surface that work progress is related to adhere to RFID tag, pass through
RFID emits radiofrequency signal, and the material, mechanical equipment, safety cap information for being attached with RFID tag enter the field regions of RFID work
In domain, RFID makes RFID generate induced current to obtain energy, RFID will by the radio wave being coupled to receive into magnetic field
Pressure that the temperature of construction site, wind speed, material are born, material placement location, the electric current of mechanical equipment, voltage, mechanical equipment
Position, safety cap position data be sent to RFID, RFID is read out and decodes;
2) risk data is handled:Using data warehouse technology (Extract-Transform-Load, abbreviation ETL) to step
1) position of collected temperature, wind speed, material are born in pressure, material placement, electric current, voltage, the machinery of mechanical equipment
The position of equipment, the position data of safety cap check the consistency of data using computer system automatically, handle invalid value
And missing values, it is grouped according to computer code, effective risk data is converted into IFC reference formats, and be loaded onto BIM
Database side;
3) BIM database sharings are stored with risk data:This engineering project is covered using existing BIM database models structure
The new BIM databases of all risk informations in life cycle management store the risk data of IFC reference formats in step 2) to new
In BIM databases;
4) BIM model foundations are transferred with BIM database datas:According to this construction project design drawing, modeled using BIM
Software Revit establishes the BIM models of this engineering project, and BIM models transfer the new BIM established in step 3) by interface in real time
The construction site risk data of databases storage;
5) collision detection:The step of is established by BIM models and is transferred for step 4) using collision detection tool Navisworks
3) risk data carry out automatic collision, pop up the associated components clashed and error message;
6) risk report is generated:Result according to step 5) collision detection automatically generates risk report;
7) Risk-warning alarm is sent out:Risk-warning alarm is sent out while generating risk report according to step 6), is carried out
Risk-warning;
8) BIM data historian data are exported:Deriving step 3) risk data that stores in the BIM databases established;
9) risk profile of PSO algorithm optimizations LS-SVM:The construction site stored in BIM databases is exported according to step 8)
The historical data of risk information, using least square method supporting vector machine (Least Squares Support Vector
Machine, abbreviation LS-SVM) construction site risk data is predicted, for decision LS-SVM learning abilities and extensive energy
The regularization parameter and kernel functional parameter of power pass through population (Particle Swarm Optimization, abbreviation PSO) algorithm
It optimizes;
10) prediction result is generated:Risk profile result is generated to step 9) PSO algorithm optimizations LS-SVM.
Step 9) includes:
Give one group of training sample set:S={ (xi, yi), i=1,2 ..., l, wherein xi∈RdNumber is inputted for LS-SVM
According to yi∈ R are output data, and l is training sample number, and the linear regression function in lower dimensional space is:
Y=ω x+b (1)
ω is weight vector in formula, and b is departure, and the regression function in high-dimensional feature space is:
In formulaIt is Nonlinear Mapping of the input space to high-dimensional feature space, the original according to structural risk minimization
Then, LS-SVM double optimizations object function is:
In formula, eiFor error variance, e ∈ Rl×1For error vector;C is regularization parameter, controls the punishment journey to error
Degree, in order to which solving-optimizing problem converts constrained optimization problem to unconstrained optimization problem by introducing Lagrange multipliers:
λ is Lagrange multipliers, λ ∈ R in formulal×1, obtaining optimal value according to KKT optimal conditions is:
Above formula eliminates ω and e, converts double optimization problem to solution system of linear equations, solution obtains:
In formula:Q=[1,1 ..., 1]T, I is unit matrix, y=[y1, y2..., yl]T, Ω
∈Rl×l, andK is the kernel function for meeting Mercer conditions, the main core with former space
Dot-product operation in function substitution high-dimensional feature space, the regression function expression formula for obtaining LS-SVM are:
Radial basis function has good because its form is simple, radial symmetric, slickness are good in terms of handling nonlinear data
Performance, the kernel function being selected as in regression model, expression formula is:
In formula:X is m dimensional input vectors, xiIt is the center of i-th of radial basis function, with x dimensions having the same;σ is core
Function parameter, determining function surround the width of central point;||x-xi| | it is vector x-xiNorm, indicate x and xiBetween away from
From, for improve LS-SVM learning ability and generalization ability, need to optimize two parameters of c and σ, particle cluster algorithm has
The simple in rule, superiority such as precision is high, convergence is fast, preferably solve the problems such as non-linear, multi-modal, are suitable for LS-SVM parameters
Optimization problem,
PSO algorithms are the evolution algorithms based on iteration optimization of rising in recent years, are initialized as the random particle of a group, are led to
Cross iterative search optimal solution, each time in iterative process, particle by track two extreme values with realize itself speed and under
The location updating of an iteration, one of extreme value are the optimal solutions that particle itself searches, referred to as individual extreme value pibest, another
A extreme value is the optimal solution that population searches, referred to as global extremum gbest,
Assuming that in the search space of d dimensions, a particle populations are formed by m particle, wherein i-th of particle is in d
Position in dimension search space is expressed as xi, speed be expressed as vi, the optimal location that searches be expressed as pi, definition vector xi
=(xi1, xi2..., xid)、vi=(vi1, vi2... vid)、pi={ pi1, pi2..., pid), i=1,2 ..., m, entire kind of group hunting
The optimal location arrived is pg=(pg1, pg2..., pgd), then the speed with location update formula of PSO algorithms particle are:
In formula:c1、c2For aceleration pulse, adjust to pibestAnd gbestThe maximum step-length of direction flight;ω is inertia weight system
Number, value size influence the optimizing ability of population, can balance ability of searching optimum, and particle is made to have the ability for exploring new region;
r1、r2It is the random function in [0,1];K indicates optimization algebraically at this time;Indicate the search speed that particle i is tieed up in d when k;Indicate that particle i is in the spatial position that d tie up when k, the VC that SVM is built upon statistical learning is tieed up and grown up in theoretical foundation
A kind of machine learning method, the principle based on structural risk minimization can effectively solve the problem that small sample, non-linear, high-dimensional etc.
Problem.
LS-SVM is the extension of standard SVM, and parameter to be selected is relatively fewer, and the inequality in SVM is replaced with equality constraint
Constraint introduces least square linear and converts quadratic programming problem to Solving Linear, reduces the complicated journey that model calculates
Degree, improves convergent speed.
Generation risk profile described in step 10) includes:
(1) training sample the S={ (x of construction site risk data are inputtedi, yi), i=1,2 ..., l;
(2) optimal regularization parameter c and kernel functional parameter σ are obtained by particle group hunting;
(3) kernel function K (x, x appropriate are selectedi);
(4) optimization problem is solved, optimal solution is obtained
(5) decision function is constructed
(6) model prediction is carried out with decision function.
Step (2) includes:
A. construction site risk data is pre-processed, irregular data is mainly converted to the number of rule by interpolation
According to processing, in order to the operation of computer;
B. the search range of setting population population m, c and σ, maximum iteration Tmax, the dimension n of particle individual, inertia
Weight coefficient ω, aceleration pulse c1And c2, average grain is away from threshold values α, fitness variance threshold β parameters;
C. PSO algorithm flows are run, population is initialized;
D. the adaptive value of each particle is calculated according to particle current locationAnd make comparisons, setting individual
Extreme value pibest, global extremum gbest;
E. according to particle rapidity and location update formula (10), (11), new population is generated;
F. the fitness f of each particle of new population is calculated again;
G. it respectively compared with population history optimal location and optimal velocity, is replaced if more excellent, it is otherwise constant;
H. it finally checks whether and meets the maximum times T that optimizing termination condition reaches iterationmax, t=is enabled if being unsatisfactory for
T+1 repeats step d, continues iteration optimizing;
I. optimal solution is obtained if meeting, the most optimized parameter is assigned to least square method supporting vector machine, terminates search.
This method high efficient and reliable, the accurate acquisition for ensuring construction site risk data, risk information it is timely transmit,
Effective storage of risk data, the dynamic early-warning control and ex ante forecasting for realizing work progress risk are evaded.
Description of the drawings
Fig. 1 is embodiment method flow schematic diagram;
Fig. 2 is the flow diagram that the optimization of PSO methods obtains SVM parameters c and σ in embodiment;
Fig. 3 is LS-SVM Risk Forecast Method flow diagrams in embodiment;
Specific implementation mode
The content of present invention is further elaborated with reference to the accompanying drawings and examples, but is not limitation of the invention.
Embodiment:
Referring to Fig.1, a kind of construction site method for prewarning risk based on BIM and RFID technique, includes the following steps:
1) RFID risk datas acquire:Using the RFID with electronic tag model acquire the temperature of construction site, wind speed,
Pressure that material is born, the position that material is placed, the electric current of mechanical equipment, voltage, the position of mechanical equipment, safety cap position
(judging the location of personnel with this) data information, the article surface that work progress is related to adhere to RFID tag, pass through
RFID emits radiofrequency signal, and the material, mechanical equipment, safety cap information for being attached with RFID tag enter the field regions of RFID work
In domain, RFID makes RFID generate induced current to obtain energy, RFID will by the radio wave being coupled to receive into magnetic field
Pressure that the temperature of construction site, wind speed, material are born, material placement location, the electric current of mechanical equipment, voltage, mechanical equipment
Position, safety cap position data be sent to RFID, RFID is read out and decodes;
2) risk data is handled:Using collected temperature, wind speed, material are born in data warehouse technology pressure, material
Expect that the position data utilization of the position placed, the electric current of mechanical equipment, voltage, the position of mechanical equipment, safety cap calculates
The consistency of machine automatic checking data handles invalid value and missing values, is grouped according to computer code, will be effective
Risk data is converted to IFC reference formats, and is loaded onto BIM database sides;
3) BIM database sharings are stored with risk data:This engineering project is covered using existing BIM database models structure
The new BIM databases of all risk informations in life cycle management store the risk data of IFC reference formats in step 2) to new
In BIM databases;
4) BIM model foundations are transferred with BIM database datas:According to this construction project design drawing, modeled using BIM
Software Revit establishes the BIM models of this engineering project, and BIM models transfer the new BIM established in step 3) by interface in real time
The construction site risk data of databases storage;
5) collision detection:The step of is established by BIM models and is transferred for step 4) using collision detection tool Navisworks
3) risk data carry out automatic collision, pop up the associated components clashed and error message;
6) risk report is generated:Result according to step 5) collision detection automatically generates risk report;
7) Risk-warning alarm is sent out:Risk-warning alarm is sent out while generating risk report according to step 6), is carried out
Risk-warning;
8) BIM data historian data are exported:Deriving step 3) risk data that stores in the BIM databases established;
9) risk profile of PSO algorithm optimizations LS-SVM:The construction site stored in BIM databases is exported according to step 8)
The historical data of risk information is predicted construction site risk data using least square method supporting vector machine, for decision
The regularization parameter and kernel functional parameter of LS-SVM learning abilities and generalization ability are optimized by particle cluster algorithm;
10) prediction result is generated:Risk profile result is generated to step 9) PSO algorithm optimizations LS-SVM.
Step 9) includes:
Give one group of training sample set:S={ (xi, yi), i=1,2 ..., l, wherein xi∈RdNumber is inputted for LS-SVM
According to yi∈ R are output data, and l is training sample number, and the linear regression function in lower dimensional space is:
Y=ω x+b (1)
ω is weight vector in formula, and b is departure, and the regression function in high-dimensional feature space is:
In formulaIt is Nonlinear Mapping of the input space to high-dimensional feature space, the original according to structural risk minimization
Then, LS-SVM double optimizations object function is:
In formula, eiFor error variance, e ∈ Rl×1For error vector;C is regularization parameter, controls the punishment journey to error
Degree, in order to which solving-optimizing problem converts constrained optimization problem to unconstrained optimization problem by introducing Lagrange multipliers:
λ is Lagrange multipliers, λ ∈ R in formulat×1, obtaining optimal value according to KKT optimal conditions is:
Above formula eliminates ω and e, converts double optimization problem to solution system of linear equations, solution obtains:
In formula:Q=[1,1 ..., 1]T, I is unit matrix, y=[y1, y2..., yl]T, Ω
∈Rl×l, andK is the kernel function for meeting Mercer conditions, the main core with former space
Dot-product operation in function substitution high-dimensional feature space, the regression function expression formula for obtaining LS-SVM are:
Radial basis function has good because its form is simple, radial symmetric, slickness are good in terms of handling nonlinear data
Performance, the kernel function being selected as in regression model, expression formula is:
In formula:X is m dimensional input vectors, xiIt is the center of i-th of radial basis function, with x dimensions having the same;σ is core
Function parameter, determining function surround the width of central point;||x-xi| | it is vector x-xiNorm, indicate x and xiBetween away from
From, for improve LS-SVM learning ability and generalization ability, need to optimize two parameters of c and σ, particle cluster algorithm has
The simple in rule, superiority such as precision is high, convergence is fast, preferably solve the problems such as non-linear, multi-modal, are suitable for LS-SVM parameters
Optimization problem,
PSO algorithms are the evolution algorithms based on iteration optimization of rising in recent years, are initialized as the random particle of a group, are led to
Cross iterative search optimal solution, each time in iterative process, particle by track two extreme values with realize itself speed and under
The location updating of an iteration, one of extreme value are the optimal solutions that particle itself searches, referred to as individual extreme value pibest, another
A extreme value is the optimal solution that population searches, referred to as global extremum gbest,
Assuming that in the search space of d dimensions, a particle populations are formed by m particle, wherein i-th of particle is in d
Position in dimension search space is expressed as xi, speed be expressed as vi, the optimal location that searches be expressed as pi, definition vector xi
=(xi1, xi2..., xid)、vi=(vi1, vi2..., vid)、pi=(pi1, pi2..., pid), i=1,2 ..., m, entire population are searched
The optimal location that rope arrives is pg=(pg1, pg2..., pgd), then the speed with location update formula of PSO algorithms particle are:
In formula:c1、c2For aceleration pulse, adjust to pibestAnd gbestThe maximum step-length of direction flight;ω is inertia weight system
Number, value size influence the optimizing ability of population, can balance ability of searching optimum, and particle is made to have the ability for exploring new region;
r1、r2It is the random function in [0,1];K indicates optimization algebraically at this time;Indicate the search speed that particle i is tieed up in d when k;Indicate that particle i is in the spatial position that d tie up when k, the VC that SVM is built upon statistical learning is tieed up and grown up in theoretical foundation
A kind of machine learning method, the principle based on structural risk minimization can effectively solve the problem that small sample, non-linear, high-dimensional etc.
Problem.LS-SVM is the extension of standard SVM, and parameter to be selected is relatively fewer, and the inequality in SVM is replaced about with equality constraint
Beam introduces least square linear and converts quadratic programming problem to Solving Linear, reduces the complexity that model calculates,
Improve convergent speed.
As shown in figure 3, the generation risk profile described in step 10) includes:
(1) training sample the S={ (x of construction site risk data are inputtedi, yi), i=1,2 ..., l;
(2) optimal regularization parameter c and kernel functional parameter σ are obtained by particle group hunting;
(3) kernel function K (x, x appropriate are selectedi);
(4) optimization problem is solved, optimal solution is obtained
(5) decision function is constructed
(6) model prediction is carried out with decision function.
As shown in Fig. 2, step (2) includes:
A. construction site risk data is pre-processed, irregular data is mainly converted to the number of rule by interpolation
According to processing, in order to the operation of computer;
B. the search range of setting population population m, c and σ, maximum iteration Tmax, the dimension n of particle individual, inertia
Weight coefficient ω, aceleration pulse c1And c2, average grain is away from threshold values α, fitness variance threshold β parameters;
C. PSO algorithm flows are run, population is initialized;
D. the adaptive value of each particle is calculated according to particle current locationAnd make comparisons, setting individual
Extreme value pibest, global extremum gbest;
E. according to particle rapidity and location update formula (10), (11), new population is generated;
F. the fitness f of each particle of new population is calculated again;
G. it respectively compared with population history optimal location and optimal velocity, is replaced if more excellent, it is otherwise constant;
H. it finally checks whether and meets the maximum times T that optimizing termination condition reaches iterationmax, t=is enabled if being unsatisfactory for
T+1 repeats d, continues iteration optimizing;
I. optimal solution is obtained if meeting, the most optimized parameter is assigned to least square method supporting vector machine, terminates search.
Claims (4)
1. a kind of construction site method for prewarning risk based on BIM and RFID technique, characterized in that include the following steps:
1) RFID risk datas acquire:Using the temperature of the RFID acquisitions construction site with electronic tag model, wind speed, material
The pressure born, the position that material is placed, the electric current of mechanical equipment, voltage, the position of mechanical equipment, safety cap position data
Information;
2) risk data is handled:Using data warehouse technology to collected temperature, wind speed, material are born in step 1) pressure
The position data utilization of power, the position that material is placed, the electric current of mechanical equipment, voltage, the position of mechanical equipment, safety cap
Computer system checks the consistency of data automatically, handles invalid value and missing values, is grouped, will have according to computer code
The risk data of effect is converted to IFC reference formats, and is loaded onto BIM database sides;
3) BIM database sharings are stored with risk data:This engineering project full longevity is covered using existing BIM database models structure
The new BIM databases for ordering all risk informations in the period, by the risk data storage of IFC reference formats in step 2) to new BIM
In database;
4) BIM model foundations are transferred with BIM database datas:According to this construction project design drawing, using BIM modeling softwares
Revit establishes the BIM models of this engineering project, and BIM models transfer the new BIM data established in step 3) by interface in real time
The construction site risk data stored in library;
5) collision detection:Step 4) is established in BIM models and the step 3) transferred using collision detection tool Navisworks
Risk data carries out automatic collision, pops up the associated components clashed and error message;
6) risk report is generated:Result according to step 5) collision detection automatically generates risk report;
7) Risk-warning alarm is sent out:Risk-warning alarm is sent out while generating risk report according to step 6), carries out risk
Early warning;
8) BIM data historian data are exported:Deriving step 3) risk data that stores in the BIM databases established;
9) risk profile of PSO algorithm optimizations LS-SVM:The construction site risk stored in BIM databases is exported according to step 8)
The historical data of information predicts construction site risk data using least square method supporting vector machine, for decision LS-
The regularization parameter and kernel functional parameter of SVM learning abilities and generalization ability are optimized by particle cluster algorithm;
10) prediction result is generated:Risk profile result is generated to step 9) PSO algorithm optimizations LS-SVM.
2. the construction site method for prewarning risk according to claim 1 based on BIM and RFID technique, characterized in that step
It is rapid 9) to include:
Give one group of training sample set:S={ (xi, yi), i=1,2 ..., l, wherein xi∈RdFor LS-SVM input datas, yi∈
R is output data, and l is training sample number, and the linear regression function in lower dimensional space is:
Y=ω x+b (1)
ω is weight vector in formula, and b is departure, and the regression function in high-dimensional feature space is:
In formulaIt is Nonlinear Mapping of the input space to high-dimensional feature space, according to the principle of structural risk minimization, LS-
SVM double optimization object functions are:
In formula, eiFor error variance, e ∈ Rl×1For error vector;C is regularization parameter, controls the punishment degree to error, draws
Enter Lagrange multipliers, converts constrained optimization problem to unconstrained optimization problem:
λ is Lagrange multipliers, λ ∈ R in formulal×1, obtaining optimal value according to KKT optimal conditions is:
Above formula eliminates ω and e, converts double optimization problem to solution system of linear equations, solution obtains:
In formula:Q=[1,1 ..., 1]T, I is unit matrix, y=[y1, y2..., yl]T, Ω ∈ Rl×l,
AndK is the kernel function for meeting Mercer conditions, and the main kernel function with former space takes
For the dot-product operation in high-dimensional feature space, the regression function expression formula for obtaining LS-SVM is:
Radial basis function has good property because its form is simple, radial symmetric, slickness are good in terms of handling nonlinear data
Energy, the kernel function being selected as in regression model, expression formula are:
In formula:X is m dimensional input vectors, xiIt is the center of i-th of radial basis function, with x dimensions having the same;σ is kernel function
Parameter, determining function surround the width of central point;||x-xi| | it is vector x-xiNorm, indicate x and xiThe distance between, it needs
Two parameters of c and σ are optimized,
Population is initialized as the random particle of a group, and by iterative search optimal solution, each time in iterative process, particle passes through
Tracking two extreme values with realize itself speed and next iteration location updating, one of extreme value is that particle itself is searched
The optimal solution that rope arrives, referred to as individual extreme value pibest, another extreme value is the optimal solution that population searches, referred to as global extremum
gbest,
Assuming that in the search space of d dimensions, a particle populations are formed by m particle, wherein i-th of particle is searched in d dimensions
Position in rope space is expressed as xi, speed be expressed as vi, the optimal location that searches be expressed as pi, definition vector xi=
(xi1, xi2..., xid)、vi=(vi1, vi2..., vid)、pi=(pi1, pi2..., pid), i=1,2 ..., m, entire kind of group hunting
The optimal location arrived is pg=(pg1, pg2..., pgd), then the speed with location update formula of PSO algorithms particle are:
In formula:c1、c2For aceleration pulse, adjust to PibestAnd gbestThe maximum step-length of direction flight;ω is inertia weight coefficient,
Its value size influences the optimizing ability of population, can balance ability of searching optimum, and particle is made to have the ability for exploring new region;r1、r2
It is the random function in [0,1];K indicates optimization algebraically at this time;Indicate the search speed that particle i is tieed up in d when k;Table
Particle i is in the spatial position that d is tieed up when showing k.
3. the construction site method for prewarning risk according to claim 1 based on BIM and RFID technique, characterized in that step
It is rapid 10) described in generation risk profile include:
(1) training sample the S={ (x of construction site risk data are inputtedi, yi), i=1,2 ..., l;
(2) optimal regularization parameter c and kernel functional parameter σ are obtained by particle group hunting;
(3) kernel function K (x, x appropriate are selectedi);
(4) optimization problem is solved, optimal solution is obtained
(5) decision function is constructed
(6) model prediction is carried out with decision function.
4. the construction site method for prewarning risk according to claim 3 based on BIM and RFID technique, characterized in that step
Suddenly (2) include:
A. construction site risk data is pre-processed, at the data that irregular data is mainly converted to rule by interpolation
Reason, in order to the operation of computer;
B. the search range of setting population population m, c and σ, maximum iteration Tmax, the dimension n of particle individual, inertia weight
Coefficient ω, aceleration pulse c1And c2, average grain is away from threshold values α, fitness variance threshold β parameters;
C. PSO algorithm flows are run, population is initialized;
D. the adaptive value of each particle is calculated according to particle current locationAnd make comparisons, individual extreme value is set
pibest, global extremum gbest;
E. according to particle rapidity and location update formula (10), (11), new population is generated;
F. the fitness f of each particle of new population is calculated again;
G. it respectively compared with population history optimal location and optimal velocity, is replaced if more excellent, it is otherwise constant;
H. it finally checks whether and meets the maximum times T that optimizing termination condition reaches iterationmax, t=t+1 is enabled if being unsatisfactory for,
Step d is repeated, iteration optimizing is continued;
I. optimal solution is obtained if meeting, the most optimized parameter is assigned to least square method supporting vector machine, terminates search.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810419786.9A CN108647753B (en) | 2018-05-04 | 2018-05-04 | BIM and RFID technology-based construction site risk early warning method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810419786.9A CN108647753B (en) | 2018-05-04 | 2018-05-04 | BIM and RFID technology-based construction site risk early warning method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108647753A true CN108647753A (en) | 2018-10-12 |
CN108647753B CN108647753B (en) | 2021-03-23 |
Family
ID=63749385
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810419786.9A Expired - Fee Related CN108647753B (en) | 2018-05-04 | 2018-05-04 | BIM and RFID technology-based construction site risk early warning method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108647753B (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110057406A (en) * | 2019-05-22 | 2019-07-26 | 西安因联信息科技有限公司 | A kind of mechanical equipment trending early warning method of multi-scale self-adaptive |
CN110532664A (en) * | 2019-08-24 | 2019-12-03 | 中铁四局集团第三建设有限公司 | BIM-based subway construction risk source identification system |
CN111539060A (en) * | 2020-05-21 | 2020-08-14 | 广州市第四装修有限公司 | BIM-based building masonry construction method, device, equipment and medium |
CN112036528A (en) * | 2020-08-24 | 2020-12-04 | 浙江大华技术股份有限公司 | Helmet wearing detection system, method and device, card reader and storage medium |
CN113536071A (en) * | 2021-09-15 | 2021-10-22 | 国能大渡河大数据服务有限公司 | System for comprehensive management of hydropower engineering |
CN113705074A (en) * | 2021-05-25 | 2021-11-26 | 江苏省安全生产科学研究院 | Chemical accident risk prediction method and device |
WO2022084828A1 (en) * | 2020-10-19 | 2022-04-28 | OnsiteIQ Inc. | Risk assessment techniques based on images |
CN116664079A (en) * | 2023-07-24 | 2023-08-29 | 中天昊建设管理集团股份有限公司 | Building design dynamic flow supervision system and method based on Internet |
CN116703657A (en) * | 2023-08-08 | 2023-09-05 | 克拉玛依市鼎泰建设(集团)有限公司 | Building engineering construction management system based on BIM model |
CN116882038A (en) * | 2023-09-08 | 2023-10-13 | 南通汤姆瑞斯工业智能科技有限公司 | Electromechanical construction method and system based on BIM technology |
CN117350615A (en) * | 2023-09-18 | 2024-01-05 | 嘉兴环洋电商物流服务有限公司 | International logistics track tracking system and method |
CN117743955A (en) * | 2023-12-21 | 2024-03-22 | 广东人信工程咨询有限公司 | BIM (building information modeling) acquired data processing method, system, electronic equipment and storage medium |
CN117808310A (en) * | 2023-11-21 | 2024-04-02 | 中水珠江规划勘测设计有限公司 | Operation optimization method and system for reclaimed water engineering |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103455878A (en) * | 2013-08-28 | 2013-12-18 | 哈尔滨工业大学 | Method and device for construction progress network diagram real-time adjustment based on internet of things technology |
US20150057981A1 (en) * | 2013-08-26 | 2015-02-26 | Specialty Electrical, Llc | Method and apparatus for multi-mode tracking and display of personnel locations in a graphical model |
CN104766108A (en) * | 2015-03-06 | 2015-07-08 | 中国十七冶集团有限公司 | Optimizing processing method for FID electronic tag in BIM model |
CN104978696A (en) * | 2015-06-09 | 2015-10-14 | 广州市水电设备安装有限公司 | Electronic acceptance and handover method based on BIM technology |
CN205596351U (en) * | 2016-04-29 | 2016-09-21 | 浙江工业职业技术学院 | Underground works safe risk real -time prewarning device of being under construction based on thing networking |
CN107220786A (en) * | 2017-07-26 | 2017-09-29 | 西交利物浦大学 | A kind of construction site security risk is identificated and evaluated and prevention method |
CN107818524A (en) * | 2016-10-25 | 2018-03-20 | 福建省建筑设计研究院有限公司 | Building industrialization system based on BIM technology |
-
2018
- 2018-05-04 CN CN201810419786.9A patent/CN108647753B/en not_active Expired - Fee Related
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150057981A1 (en) * | 2013-08-26 | 2015-02-26 | Specialty Electrical, Llc | Method and apparatus for multi-mode tracking and display of personnel locations in a graphical model |
CN103455878A (en) * | 2013-08-28 | 2013-12-18 | 哈尔滨工业大学 | Method and device for construction progress network diagram real-time adjustment based on internet of things technology |
CN104766108A (en) * | 2015-03-06 | 2015-07-08 | 中国十七冶集团有限公司 | Optimizing processing method for FID electronic tag in BIM model |
CN104978696A (en) * | 2015-06-09 | 2015-10-14 | 广州市水电设备安装有限公司 | Electronic acceptance and handover method based on BIM technology |
CN205596351U (en) * | 2016-04-29 | 2016-09-21 | 浙江工业职业技术学院 | Underground works safe risk real -time prewarning device of being under construction based on thing networking |
CN107818524A (en) * | 2016-10-25 | 2018-03-20 | 福建省建筑设计研究院有限公司 | Building industrialization system based on BIM technology |
CN107220786A (en) * | 2017-07-26 | 2017-09-29 | 西交利物浦大学 | A kind of construction site security risk is identificated and evaluated and prevention method |
Non-Patent Citations (4)
Title |
---|
PING-SUN CHAN.ETC: "BIM-Enabled StreamlinedFault Localizationwith System Topology,RFID Technology andReal-Time Data AcquisitionInterfaces", 《IEEE INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING》 * |
仲青等: "基于RFID与BIM集成的施工现场安全监控***构建", 《建筑经济》 * |
郝宽胜等: "基于模糊最小二乘支持向量机的建设工程造价快速预测方法研究", 《铁路工程造价管理》 * |
齐贺等: "BIM 与RFID 技术用于装配式建筑项目的施工管理研究", 《施工技术》 * |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110057406A (en) * | 2019-05-22 | 2019-07-26 | 西安因联信息科技有限公司 | A kind of mechanical equipment trending early warning method of multi-scale self-adaptive |
CN110057406B (en) * | 2019-05-22 | 2022-05-17 | 西安因联信息科技有限公司 | Multi-scale self-adaptive mechanical equipment trend early warning method |
CN110532664A (en) * | 2019-08-24 | 2019-12-03 | 中铁四局集团第三建设有限公司 | BIM-based subway construction risk source identification system |
CN111539060A (en) * | 2020-05-21 | 2020-08-14 | 广州市第四装修有限公司 | BIM-based building masonry construction method, device, equipment and medium |
CN111539060B (en) * | 2020-05-21 | 2023-02-10 | 广州市第四装修有限公司 | BIM-based building masonry construction method, device, equipment and medium |
CN112036528B (en) * | 2020-08-24 | 2022-07-05 | 浙江大华技术股份有限公司 | Helmet wearing detection system, method and device, card reader and storage medium |
CN112036528A (en) * | 2020-08-24 | 2020-12-04 | 浙江大华技术股份有限公司 | Helmet wearing detection system, method and device, card reader and storage medium |
US11967155B2 (en) | 2020-10-19 | 2024-04-23 | OnsiteIQ Inc. | Systems and methods for improving accuracy of identifying observations based on images and risk assessment techniques using such determinations |
WO2022084828A1 (en) * | 2020-10-19 | 2022-04-28 | OnsiteIQ Inc. | Risk assessment techniques based on images |
CN113705074A (en) * | 2021-05-25 | 2021-11-26 | 江苏省安全生产科学研究院 | Chemical accident risk prediction method and device |
CN113705074B (en) * | 2021-05-25 | 2024-03-08 | 江苏省安全生产科学研究院 | Chemical accident risk prediction method and device |
CN113536071A (en) * | 2021-09-15 | 2021-10-22 | 国能大渡河大数据服务有限公司 | System for comprehensive management of hydropower engineering |
CN113536071B (en) * | 2021-09-15 | 2021-12-28 | 国能大渡河大数据服务有限公司 | System for comprehensive management of hydropower engineering |
CN116664079A (en) * | 2023-07-24 | 2023-08-29 | 中天昊建设管理集团股份有限公司 | Building design dynamic flow supervision system and method based on Internet |
CN116664079B (en) * | 2023-07-24 | 2024-05-17 | 中天昊建设管理集团股份有限公司 | Building design dynamic flow supervision system and method based on Internet |
CN116703657A (en) * | 2023-08-08 | 2023-09-05 | 克拉玛依市鼎泰建设(集团)有限公司 | Building engineering construction management system based on BIM model |
CN116703657B (en) * | 2023-08-08 | 2023-11-03 | 克拉玛依市鼎泰建设(集团)有限公司 | Building engineering construction management system based on BIM model |
CN116882038A (en) * | 2023-09-08 | 2023-10-13 | 南通汤姆瑞斯工业智能科技有限公司 | Electromechanical construction method and system based on BIM technology |
CN116882038B (en) * | 2023-09-08 | 2023-12-12 | 南通汤姆瑞斯工业智能科技有限公司 | Electromechanical construction method and system based on BIM technology |
CN117350615A (en) * | 2023-09-18 | 2024-01-05 | 嘉兴环洋电商物流服务有限公司 | International logistics track tracking system and method |
CN117350615B (en) * | 2023-09-18 | 2024-04-19 | 嘉兴环洋电商物流服务有限公司 | International logistics track tracking system and method |
CN117808310A (en) * | 2023-11-21 | 2024-04-02 | 中水珠江规划勘测设计有限公司 | Operation optimization method and system for reclaimed water engineering |
CN117743955A (en) * | 2023-12-21 | 2024-03-22 | 广东人信工程咨询有限公司 | BIM (building information modeling) acquired data processing method, system, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN108647753B (en) | 2021-03-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108647753A (en) | A kind of construction site method for prewarning risk based on BIM and RFID technique | |
Bean | Genetic algorithms and random keys for sequencing and optimization | |
Johnson et al. | Optimization by simulated annealing: an experimental evaluation; part II, graph coloring and number partitioning | |
CN104751367A (en) | System for sensing, controlling and tracking breeding quality of breeding pigs in pig farm in whole process | |
CN109598320A (en) | A kind of RFID indoor orientation method based on locust algorithm and extreme learning machine | |
Liu et al. | Artificial intelligence in smart logistics cyber-physical systems: State-of-the-arts and potential applications | |
Ye | An Algorithm for Construction Project Cost Forecast Based on Particle Swarm Optimization‐Guided BP Neural Network | |
CN116703303A (en) | Warehouse visual supervision system and method based on multi-layer perceptron and RBF | |
CN117234214A (en) | Automatic shuttle for stacking industrial goods | |
Cui | Intelligent coordination distribution of the whole supply chain based on the internet of things | |
CN115329683A (en) | Aviation luggage online loading planning method, device, equipment and medium | |
Sun | [Retracted] Path Planning of Mobile Robots in Warehouse Logistics Relying on Computer Multimedia 3D Reconstruction Technology | |
Raghib et al. | Hierarchical multiobjective approach for optimising RFID reader deployment | |
Liang | Production Logistics Management of Industrial Enterprises Based on Wavelet Neural Network. | |
KR102506255B1 (en) | SYSTEM AND METHOD FOR MANUFACTURING Customer-Customized MACHINE EQUIPMENT BASED ON BIG DATA | |
Wang et al. | Warehouse scheduling in airport freight station with multi-objective artificial bee colony algorithm | |
Li et al. | An Improved Firefly Algorithm used to Location Selection of Distribution Center for Logistics UA V | |
Yeng et al. | The saturation of population fitness as a stopping criterion in genetic algorithm. | |
Đaković et al. | Deep neural network configuration sensitivity analysis in wind power forecasting | |
Yi | Logistics scheduling optimisation and allocation of intercultural communication trade under internet of things and edge computing | |
Liang et al. | [Retracted] Construction of Mathematical Model of Logistics Delivering Based on Intelligent Mobilization | |
Liu et al. | Logistics Engineering Simulation Using Computer 3D Modeling Technology | |
Kan et al. | Multi-zone building control system for energy and comfort management | |
Dong et al. | Ultra-Short-Term Load Forecasting Based on Convolutional-LSTM Hybrid Networks | |
Yin et al. | Forecasting the intrinsic viscosity of polyester based on improved extreme learning machine |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210323 |