CN109883474A - Building health monitoring systems and monitoring method based on field monitoring - Google Patents
Building health monitoring systems and monitoring method based on field monitoring Download PDFInfo
- Publication number
- CN109883474A CN109883474A CN201910130959.XA CN201910130959A CN109883474A CN 109883474 A CN109883474 A CN 109883474A CN 201910130959 A CN201910130959 A CN 201910130959A CN 109883474 A CN109883474 A CN 109883474A
- Authority
- CN
- China
- Prior art keywords
- building
- pressure
- monitored
- health
- soil
- 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
Landscapes
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses the building health monitoring systems based on field monitoring, comprising: pore water pressure sensor is embedded in building soil, for measuring the intracorporal seepage water pressure of building soil;Strain pressure transducer is arranged in the pipeline being laid between floors, measures the pressure of fluids within pipes and the pressure of gas;Pressure cell is embedded in the building soil body, is measured to the internal stress of the soil body, can also be measured to the contact stress between fabric structure;Temperature sensor is used to monitor the environment temperature of building;Humidity sensor is used to monitor the ambient humidity of building.The present invention provides the building health monitoring systems based on field monitoring, can be monitored in real time to building, can find the problem in the structure of building in time.
Description
Technical field
The present invention relates to building analyte detection fields, more particularly to the building health monitoring systems based on field monitoring and
Monitoring method.
Background technique
Due to China human mortality, high-rise and super high-rise building is the main trend of building.For super high-rise building
The considerations of stability and safety, with greater need for the health monitoring and management of building.Urban architecture is more and more intensive, increasingly
Height is the trend of urban development.Due to uncontrollable disaster such as natural geology or during artificially building by laying, building is easy
There are the disasters such as fracture, displacement, inclination.The disaster be it is unpredictalbe, immeasurable lives and properties damage can be brought
It loses.It therefore is highly important thing to the monitoring of the health status of building.
As China constantly advances, there are more and more buildings to enter period that is aged and needing to safeguard, this
The safety of a little buildings is concerned.Meanwhile available land area is fewer and fewer, the requirement that people want building
Also higher and higher, so that the engineering structure of building is become increasingly complex, carrying out that effective monitoring structural health conditions extremely have to it must
It wants.
With the continuous development of science and technology, various intelligent buildings can be continuously increased.When various in people's requirement building
While intelligent facility has more increases, the requirement also to the convenience used is also higher and higher.
Summary of the invention
The present invention is to solve current technology shortcoming, provides the building health monitoring system based on field monitoring
System, can in real time be monitored building, can find the problem in the structure of building in time.
It is right it is a further object of the present invention to provide building health monitoring systems and monitoring method based on field monitoring
Issuable security risk is predicted, is safeguarded early to building.
Technical solution provided by the invention are as follows: the building health monitoring systems based on field monitoring, comprising:
Pore water pressure sensor is embedded in building soil, for measuring the intracorporal infiltration hydraulic pressure of building soil
Power;
Strain pressure transducer is arranged in the pipeline that is laid between floors, measure fluids within pipes pressure and
The pressure of gas;
Pressure cell is embedded in the building soil body, is measured to the internal stress of the soil body, also can be to fabric structure
Between contact stress measure;
Temperature sensor is used to monitor the environment temperature of building;
Humidity sensor is used to monitor the ambient humidity of building.
Preferably, further includes:
Analog-digital converter, with the pore water pressure sensor, the strain pressure transducer, the pressure cell,
The temperature sensor is connected with the humidity sensor, is converted electrical signals to digital signal and is sent;
Correction module connects the analog-digital converter, issues after the digital signal is corrected;
Server receives the signal of the correction module, and carries out processing analysis;
Alarm is connect with the server, issues alarm;
Display is connect, for showing risk status with the server.
Preferably,
The pore water pressure is calculated as vibrating wire piezometer or silicon pressure type uplift pressure meter;
The pressure cell is vibrating-wire pressure cell or oil pocket pressure cell.
Preferably,
The alarm is buzz alarm, phonetic alarm or color break-up alarm.
Building health monitor method based on field monitoring, comprising:
Step 1: acquiring the health data of building to be monitored, obtained according to the health data of the building to be monitored
The health evaluating coefficient gamma of building to be monitored, as γ >=γt, health evaluating is carried out to the building to be monitored;Wherein,
γtFor critical health evaluating coefficient;
Step 2: acquiring building to be monitored soil intracorporal seepage water pressure, the internal stress of the soil body, fluids within pipes
Pressure, the pressure of gas in pipelines, the contact stress between structure, according to the intracorporal infiltration water of the building soil to be monitored
Pressure, the internal stress of the soil body, the pressure of fluids within pipes, the pressure of gas in pipelines, the contact stress between structure are to health
Metewand is handled to obtain health evaluating index τ, as τ >=τtWhen, health status judgement is carried out to building to be monitored;
Wherein, τtFor critical health evaluating index;
Step 3: according to the soil intracorporal seepage water pressure, the internal stress of the soil body, the fluids within pipes
Pressure, the pressure of the gas in pipelines, the contact stress between the structure and the health evaluating index carry out to be monitored
Building carries out health status judgement, is monitored to building health status.
Preferably, in said step 1, the health evaluating coefficient gamma calculation method are as follows:
In formula, κ is correction coefficient, and H is depth of building to be monitored, and h is structure foundation depth to be monitored, and S is wait supervise
The actual age of building is surveyed, S ' is the Effective Age of building to be monitored,For the annual environment temperature of building to be monitored
Degree,For the annual ambient humidity of building to be monitored, T is the environment temperature of building to be monitored, and E is building to be monitored
The ambient humidity of object, δ1For the first correction coefficient, δ2For the second correction coefficient.
Preferably, κ value is 1.02~1.05, γtValue is 0.15.
Preferably, the health evaluating index τ
In formula, PoFor the intracorporal seepage water pressure of soil, NiFor the internal stress of the soil body, PlFor the pressure of fluids within pipes, Pg
For the pressure of gas in pipelines, NcContact stress between structure, e are the truth of a matter of natural logrithm.
Preferably, in the step 3, health is carried out to building to be monitored by establishing BP neural network model
State judgement, includes the following steps:
Step 1, according to the sampling period, acquire the intracorporal seepage water pressure P of soil of building to be monitoredo, building to be monitored
The pressure P for the fluids within pipes being laid in objectlWith the pressure P of gasg, building to be monitored the soil body internal stress NiAnd building
Contact stress N between object structurec, determine the health evaluating index τ of building to be monitored;
Step 2 successively standardizes above-mentioned parameter, determines the input layer vector x of three layers of BP neural network
={ x1,x2,x3,x4,x5,x6, wherein x1For the intracorporal seepage water pressure coefficient of soil, x2For the pressure coefficient of fluids within pipes,
x3For the pressure coefficient of gas in pipelines, x4For the internal stress coefficient of the soil body, x5Contact stress coefficient between structure, x6For
Health evaluating index coefficient;
Step 3, the input layer DUAL PROBLEMS OF VECTOR MAPPING to hidden layer, the hidden layer vector y={ y1,y2,…,ym, m is hidden layer section
Point number;
Step 4 obtains output layer neuron vector o={ o1,o2,o3};Wherein, o1For the first order health etc. of setting
Grade, o2For the second level Health Category of setting, o3For the third level Health Category of setting, the output layer neuron value isK is output layer neuron sequence number, and k={ 1,2,3 }, i are i-th of the health etc. of setting
Grade, i={ 1,2,3 } work as okWhen being 1, at this point, building to be monitored is in okCorresponding Health Category;
Step 5, server judge that display shows risk status according to the Health Category of output;Wherein, described first
Grade Health Category is safe condition, is not necessarily to make safeguard measure to building to be monitored, the second level Health Category is danger
State makes prosecution early warning to building to be monitored, takes safeguard measure, the third level Health Category is high-risk status, right
Building to be monitored makes urgent early warning and safeguard measure.
Preferably, in the step 1, the data that correction module acquires sensor are corrected the number exported
According to acquiring the intracorporal seepage water pressure of soil of building to be monitored for pore water pressure sensor, the first correction factor is full
Foot:
P′0For the intracorporal real-time seepage water pressure of soil of pore water pressure sensor acquisition,It is intracorporal flat for local soil
Equal seepage water pressure, a are the correction factor of pore water pressure sensor;
The pressure and gas of the fluids within pipes that are laid in building to be monitored are acquired by strain pressure transducer
Second correction factor of pressure meets:
P′lFor strain pressure transducer acquisition fluids within pipes real-time pressure,For in local architecture pipe
Fluid average pressure, b are the correction factor of strain pressure transducer;
The third school of the pressure for the gas in pipelines being laid in building to be monitored is acquired by strain pressure transducer
Positive divisor meets:
P′gFor strain pressure transducer acquisition gas in pipelines real-time pressure,For in local architecture pipe
Gas average pressure.
It is of the present invention the utility model has the advantages that provide the building health monitoring systems based on field monitoring, can be real-time
Building is monitored, can find the problem in the structure of building in time, it is ensured that the safety in use can be realized
The unified monitoring of various data, saves cost, can promote and apply.Building health monitoring based on field monitoring is provided
System and monitoring method are predicted issuable security risk, are safeguarded early to building, and property damage is reduced
It loses.
Specific embodiment
The present invention is described in further detail below, to enable those skilled in the art's refer to the instruction text can
Implement accordingly.
Building health monitoring systems based on field monitoring of the invention, comprising: pore water pressure sensor is embedded in
In building soil, for measuring the intracorporal seepage water pressure of building soil;Strain pressure transducer is arranged between floors
In the pipeline of laying, the pressure of fluids within pipes and the pressure of gas are measured;Pressure cell is embedded in the building soil body, to soil
The internal stress of body measures, and can also measure to the contact stress between fabric structure;Temperature sensor is for monitoring
The environment temperature of building;Humidity sensor is used to monitor the ambient humidity of building.
Analog-digital converter and the pore water pressure sensor, the strain pressure transducer, the pressure cell, institute
It states temperature sensor to connect with the humidity sensor, converts electrical signals to digital signal and send;Correction module connects
The analog-digital converter is connect, is issued after the digital signal is corrected;Server receives the signal of the correction module,
And carry out processing analysis;Alarm is connect with the server, issues alarm;Display is connect with the server, for showing
Show risk status.
The pore water pressure is calculated as vibrating wire piezometer or silicon pressure type uplift pressure meter;The pressure cell is steel chord type pressure
Power box or oil pocket pressure cell.The alarm is buzz alarm, phonetic alarm or color break-up alarm.
The present invention also provides the building health monitoring systems based on field monitoring, comprising the following steps:
Step 1: acquiring the health data of building to be monitored, obtained according to the health data of the building to be monitored
The health evaluating coefficient gamma of building to be monitored, as γ >=γt, health evaluating is carried out to the building to be monitored;Wherein,
γtFor critical health evaluating coefficient;
The health evaluating coefficient gamma calculation method are as follows:
In formula, κ is correction coefficient, and H is depth of building to be monitored, and h is structure foundation depth to be monitored, and S is wait supervise
The actual age of building is surveyed, S ' is the Effective Age of building to be monitored,For the annual environment temperature of building to be monitored
Degree,For the annual ambient humidity of building to be monitored, T is the environment temperature of building to be monitored, and E is building to be monitored
The ambient humidity of object, δ1For the first correction coefficient, δ2For the second correction coefficient.
κ value is 1.02~1.05, γtValue is 0.15.
Step 2: acquiring building to be monitored soil intracorporal seepage water pressure, the internal stress of the soil body, fluids within pipes
Pressure, the pressure of gas in pipelines, the contact stress between structure, according to the intracorporal infiltration water of the building soil to be monitored
Pressure, the internal stress of the soil body, the pressure of fluids within pipes, the pressure of gas in pipelines, the contact stress between structure are to health
Metewand is handled to obtain health evaluating index τ, as τ >=τtWhen, health status judgement is carried out to building to be monitored;
Wherein, τtFor critical health evaluating index;
The health evaluating index τ
In formula, PoFor the intracorporal seepage water pressure of soil, NiFor the internal stress of the soil body, PlFor the pressure of fluids within pipes, Pg
For the pressure of gas in pipelines, NcContact stress between structure, e are the truth of a matter of natural logrithm.
Step 3: according to the soil intracorporal seepage water pressure, the internal stress of the soil body, the fluids within pipes
Pressure, the pressure of the gas in pipelines, the contact stress between the structure and the health evaluating index carry out to be monitored
Building carries out health status judgement, is monitored to building health status.
In step 3, health status judgement is carried out to building to be monitored by establishing BP neural network model, including such as
Lower step:
Totally interconnected connection is formed on BP model between the neuron of each level, is not connected between the neuron in each level
It connects, the output of input layer is identical as input, i.e. oi=xi.The operating characteristic of the neuron of intermediate hidden layer and output layer
For
opj=fj(netpj)
Wherein p indicates current input sample, ωjiFor from neuron i to the connection weight of neuron j, opiFor neuron
The current input of j, opjIt is exported for it;fjFor it is non-linear can micro- non-decreasing function, be generally taken as S type function, i.e. fj(x)=1/
(1+e-x)。
For the BP network architecture that the present invention uses by up of three-layer, first layer is input layer, total n node, corresponding
Indicate that n detection signal of equipment working state, these signal parameters are provided by data preprocessing module;The second layer is hidden layer,
Total m node is determined in an adaptive way by the training process of network;Third layer is output layer, total p node, by system
Actual needs output in response to determining that.
The mathematical model of the network are as follows:
Input vector: x=(x1,x2,...,xn)T
Middle layer vector: y=(y1,y2,...,ym)T
Output vector: o=(o1,o2,...,op)T
In the present invention, input layer number is n=6, and output layer number of nodes is p=3, and hidden layer number of nodes m is estimated by following formula
It obtains:
6 parameters of input layer respectively indicate are as follows: x1For the intracorporal seepage water pressure coefficient of soil, x2For the pressure of fluids within pipes
Force coefficient, x3For the pressure coefficient of gas in pipelines, x4For the internal stress coefficient of the soil body, x5Contact stress system between structure
Number, x6For health evaluating index coefficient.
Since the data that sensor obtains belong to different physical quantitys, dimension is different.Therefore, it is inputted in data
Before artificial neural network, need to turn to data requirement into the number between 0-1.
Normalized formula isWherein, xjFor the parameter in input layer vector, XjRespectively
Measurement parameter Po、Pl、Pg、Vb、Ni、Nc, j=1,2,3,4,5,6;XjmaxAnd XjminMaximum value in respectively corresponding measurement parameter
And minimum value.
The data that correction module acquires sensor are corrected the data exported, and pore water pressure is sensed
Device acquires the intracorporal seepage water pressure of soil of building to be monitored, and the first correction factor meets:
P′0For the intracorporal real-time seepage water pressure of soil of pore water pressure sensor acquisition,It is intracorporal flat for local soil
Equal seepage water pressure, a are the correction factor of pore water pressure sensor;Then
Po=ξ1P′o
The pressure and gas of the fluids within pipes that are laid in building to be monitored are acquired by strain pressure transducer
Second correction factor of pressure meets:
P′lFor strain pressure transducer acquisition fluids within pipes real-time pressure,For in local architecture pipe
Fluid average pressure, b are the correction factor of strain pressure transducer;Then
Pl=ξ2P′l
The third school of the pressure for the gas in pipelines being laid in building to be monitored is acquired by strain pressure transducer
Positive divisor meets:
P′gFor strain pressure transducer acquisition gas in pipelines real-time pressure,For in local architecture pipe
Gas average pressure;Then
Pg=ξ3P′g。
Specifically, the intracorporal seepage water pressure P of soil after pore water pressure sensor is measured and correctedo, carry out
After normalization, the intracorporal seepage water pressure coefficient x of soil is obtained1:
Wherein, Po-maxAnd Po-minRespectively native intracorporal infiltration water maximum pressure and minimum pressure.
Likewise, for the pipe being laid in the building to be monitored after acquiring and correct by strain pressure transducer
The pressure P of fluid in roadl, after being standardized, obtain the pressure coefficient x of fluids within pipes2:
Wherein, Pl-maxAnd Pl-minThe respectively maximum pressure and minimum pressure of fluids within pipes.
Likewise, for the pipe being laid in the building to be monitored after acquiring and correct by strain pressure transducer
The pressure P of gas in roadg, after being standardized, obtain the pressure coefficient x of gas in pipelines3:
Wherein, Pg-maxAnd Pg-minThe respectively maximum pressure and minimum pressure of gas in pipelines.
Likewise, the internal stress N of the soil body for building to be monitoredi, after being standardized, obtain the interior of the soil body and answer
Force coefficient x4:
Wherein, Ni-maxAnd Ni-minThe maximum internal stress of the soil body of building respectively to be monitored and minimum internal stress.
Likewise, for the contact stress N between fabric structure to be monitoredc, after being standardized, obtain structure it
Between contact stress coefficient x5:
Wherein, Nc-maxAnd Nc-min0 is respectively the Max.contact stress and minimal-contact between fabric structure to be monitored
Stress.
Likewise, after being standardized, obtaining health evaluating index for the health evaluating index τ of building to be monitored
Coefficient x6:
Wherein, τmaxAnd τminThe maximum health evaluating index of building respectively to be monitored and minimum health evaluating index.
It exports 3 parameters and is respectively as follows: o1For the first order Health Category of setting, o2For the second level Health Category of setting,
o3For the third level Health Category of setting.The output layer neuron value isK is output
Layer neuron sequence number, k={ 1,2,3 }, i are i-th Health Category of setting, and i={ 1,2,3 } works as okWhen being 1, at this point,
Building to be monitored is in okCorresponding Health Category;
Step 2, the training for carrying out BP neural network.
After establishing BP neural network nodal analysis method, the training of BP neural network can be carried out.It is passed through according to the history of product
Test the sample of data acquisition training, and the connection weight between given input node i and hidden layer node j, hidden node j and
Export the connection weight between node layer k.
(1) training method
Each subnet is using individually trained method;When training, first have to provide one group of training sample, each of these
Sample, to forming, when all reality outputs of network and its consistent ideal output, is shown to instruct by input sample and ideal output
White silk terminates;Otherwise, by correcting weight, keep the ideal output of network consistent with reality output;Output sample when the training of each subnet
This is as shown in table 1.
The output sample of 1 network training of table
(2) training algorithm
BP network is trained using error back propagation (Backward Propagation) algorithm, and step can return
It receives as follows:
Step 1: a selected structurally reasonable network, is arranged the initial value of all Node B thresholds and connection weight.
Step 2: making following calculate to each input sample:
(a) forward calculation: to l layers of j unit
In formula,L layers of j unit information weighted sum, ω when being calculated for n-thji (l)(n) for l layer j unit and
Connection weight between the unit i of preceding layer (i.e. l-1 layers),For preceding layer (i.e. l-1 layers, number of nodes nl-1) list
The working signal that first i is sent;When i=0, enable For l layers of j unit
Threshold value.
If the activation primitive of unit j is sigmoid function,
And
If neuron j belongs to the first hidden layer (l=1), have
If neuron j belongs to output layer (l=L), have
And ej(n)=xj(n)-oj(n);
(b) retrospectively calculate error:
For output unit
To hidden unit
(c) weight is corrected:
η is learning rate.
Step 3: new sample or a new periodic samples are inputted, and until network convergence, the sample in each period in training
Input sequence it is again randomly ordered.
BP algorithm seeks nonlinear function extreme value using gradient descent method, exists and falls into local minimum and convergence rate is slow
The problems such as.A kind of more efficiently algorithm is Levenberg-Marquardt optimization algorithm, it makes the e-learning time more
It is short, network can be effectively inhibited and sink into local minimum.Its weighed value adjusting rate is selected as
Δ ω=(JTJ+μI)-1JTe
Wherein J is error to Jacobi (Jacobian) matrix of weight differential, and I is input vector, and e is error vector,
Variable μ is the scalar adaptively adjusted, for determining that study is completed according to Newton method or gradient method.
In system design, system model is one merely through the network being initialized, and weight needs basis using
The data sample obtained in journey carries out study adjustment, devises the self-learning function of system thus.Specify learning sample and
In the case where quantity, system can carry out self study, to constantly improve network performance.
Step 3, server judge that display shows risk status according to the Health Category of output;Wherein, described first
Grade Health Category is safe condition, is not necessarily to make safeguard measure to building to be monitored, the second level Health Category is danger
State makes prosecution early warning to building to be monitored, takes safeguard measure, the third level Health Category is high-risk status, right
Building to be monitored makes urgent early warning and safeguard measure.
Although the embodiments of the present invention have been disclosed as above, but its institute not only in the description and the implementation
Column use, it can be fully applied to various fields suitable for the present invention, for those skilled in the art, can hold
It changes places and realizes other modification, therefore without departing from the general concept defined in the claims and the equivalent scope, the present invention is simultaneously
It is not limited to specific details and embodiment shown and described herein.
Claims (10)
1. the building health monitoring systems based on field monitoring characterized by comprising
Pore water pressure sensor is embedded in building soil, for measuring the intracorporal seepage water pressure of building soil;
Strain pressure transducer is arranged in the pipeline being laid between floors, measures the pressure and gas of fluids within pipes
Pressure;
Pressure cell is embedded in the building soil body, is measured to the internal stress of the soil body, also can be between fabric structure
Contact stress measures;
Temperature sensor is used to monitor the environment temperature of building;
Humidity sensor is used to monitor the ambient humidity of building.
2. the building health monitoring systems according to claim 1 based on field monitoring, which is characterized in that further include:
Analog-digital converter, with the pore water pressure sensor, strain pressure transducer, the pressure cell, described
Temperature sensor is connected with the humidity sensor, is converted electrical signals to digital signal and is sent;
Correction module connects the analog-digital converter, issues after the digital signal is corrected;
Server receives the signal of the correction module, and carries out processing analysis;
Alarm is connect with the server, issues alarm;
Display is connect, for showing risk status with the server.
3. the building health monitoring systems according to claim 2 based on field monitoring, which is characterized in that
The pore water pressure is calculated as vibrating wire piezometer or silicon pressure type uplift pressure meter;
The pressure cell is vibrating-wire pressure cell or oil pocket pressure cell.
4. the building health monitoring systems according to claim 2 based on field monitoring, which is characterized in that
The alarm is buzz alarm, phonetic alarm or color break-up alarm.
5. the building health monitor method based on field monitoring characterized by comprising
Step 1: acquiring the health data of building to be monitored, obtained according to the health data of the building to be monitored wait supervise
The health evaluating coefficient gamma for surveying building, as γ >=γt, health evaluating is carried out to the building to be monitored;Wherein, γtTo face
Boundary's health evaluating coefficient;
Step 2: acquire the intracorporal seepage water pressure of building to be monitored soil, the internal stress of the soil body, the pressure of fluids within pipes,
Contact stress between the pressure of gas in pipelines, structure, according to the intracorporal seepage water pressure of the building soil to be monitored, soil
The internal stress of body, the pressure of fluids within pipes, the pressure of gas in pipelines, the contact stress between structure are to health evaluating coefficient
It is handled to obtain health evaluating index τ, as τ >=τtWhen, health status judgement is carried out to building to be monitored;Wherein, τtTo face
Boundary's health evaluating index;
Step 3: according to the intracorporal seepage water pressure of the soil, the internal stress of the soil body, the pressure of the fluids within pipes,
Contact stress and the health evaluating index between the pressure of the gas in pipelines, the structure carry out building to be monitored
Health status judgement is carried out, building health status is monitored.
6. the building health monitor method according to claim 5 based on field monitoring, which is characterized in that in the step
In rapid one, the health evaluating coefficient gamma calculation method are as follows:
In formula, κ is correction coefficient, and H is depth of building to be monitored, and h is structure foundation depth to be monitored, and S is to be monitored builds
The actual age of object is built, S ' is the Effective Age of building to be monitored,For the annual environment temperature of building to be monitored,
For the annual ambient humidity of building to be monitored, T is the environment temperature of building to be monitored, and E is the ring of building to be monitored
Border humidity, δ1For the first correction coefficient, δ2For the second correction coefficient.
7. the building health monitor method according to claim 6 based on field monitoring, which is characterized in that
κ value is 1.02~1.05, γtValue is 0.15.
8. the building health monitor method according to claim 7 based on field monitoring, which is characterized in that the health
Assessment index τ
In formula, PoFor the intracorporal seepage water pressure of soil, NiFor the internal stress of the soil body, PlFor the pressure of fluids within pipes, PgFor pipeline
The pressure of interior gas, NcContact stress between structure, e are the truth of a matter of natural logrithm.
9. the building health monitor method according to claim 8 based on field monitoring, which is characterized in that in the step
In rapid three, health status judgement is carried out to building to be monitored by establishing BP neural network model, is included the following steps:
Step 1, according to the sampling period, acquire the intracorporal seepage water pressure P of soil of building to be monitoredo, building middle berth to be monitored
If fluids within pipes pressure PlWith the pressure P of gasg, building to be monitored the soil body internal stress NiAnd fabric structure
Between contact stress Nc, determine the health evaluating index τ of building to be monitored;
Step 2 successively standardizes above-mentioned parameter, determines the input layer vector x={ x of three layers of BP neural network1,
x2,x3,x4,x5,x6, wherein x1For the intracorporal seepage water pressure coefficient of soil, x2For the pressure coefficient of fluids within pipes, x3For pipe
The pressure coefficient of gas, x in road4For the internal stress coefficient of the soil body, x5Contact stress coefficient between structure, x6It is commented for health
Estimate index coefficient;
Step 3, the input layer DUAL PROBLEMS OF VECTOR MAPPING to hidden layer, the hidden layer vector y={ y1,y2,…,ym, m is hidden node
Number;
Step 4 obtains output layer neuron vector o={ o1,o2,o3};Wherein, o1For the first order Health Category of setting, o2For
The second level Health Category of setting, o3For the third level Health Category of setting, the output layer neuron value isK is output layer neuron sequence number, and k={ 1,2,3 }, i are i-th of the health etc. of setting
Grade, i={ 1,2,3 } work as okWhen being 1, at this point, building to be monitored is in okCorresponding Health Category;
Step 5, server judge that display shows risk status according to the Health Category of output;Wherein, the first order health
Grade is safe condition, and to building to be monitored without making safeguard measure, the second level Health Category is precarious position, right
Building to be monitored makes prosecution early warning, takes safeguard measure, and the third level Health Category is high-risk status, builds to be monitored
It builds object and makes urgent early warning and safeguard measure.
10. the building health monitor method according to claim 9 based on field monitoring, which is characterized in that the step
In rapid one, the data that correction module acquires sensor are corrected the data exported, for pore water pressure sensor
The intracorporal seepage water pressure of soil of building to be monitored is acquired, the first correction factor meets:
P0' intracorporal real-time the seepage water pressure of soil acquired for pore water pressure sensor,For the local intracorporal average infiltration of soil
Water pressure, a are the correction factor of pore water pressure sensor;
The pressure for the fluids within pipes being laid in building to be monitored and the pressure of gas are acquired by strain pressure transducer
The second correction factor meet:
PlThe real-time pressure of ' the fluids within pipes acquired for strain pressure transducer,It is flat for fluid in local architecture pipe
Equal pressure, b are the correction factor of strain pressure transducer;
By strain pressure transducer acquire the pressure for the gas in pipelines being laid in building to be monitored third correction because
Overabundance of amniotic fluid foot:
P′gFor strain pressure transducer acquisition gas in pipelines real-time pressure,It is flat for gas in local architecture pipe
Equal pressure.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910130959.XA CN109883474B (en) | 2019-02-20 | 2019-02-20 | Building health monitoring method based on-site monitoring |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910130959.XA CN109883474B (en) | 2019-02-20 | 2019-02-20 | Building health monitoring method based on-site monitoring |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109883474A true CN109883474A (en) | 2019-06-14 |
CN109883474B CN109883474B (en) | 2021-06-15 |
Family
ID=66928878
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910130959.XA Active CN109883474B (en) | 2019-02-20 | 2019-02-20 | Building health monitoring method based on-site monitoring |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109883474B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112067043A (en) * | 2020-08-14 | 2020-12-11 | 常州机电职业技术学院 | Defective degree detecting system of timber structure ancient building |
CN115063040A (en) * | 2022-07-28 | 2022-09-16 | 湖南工商大学 | Method and system for collaborative evaluation and prediction of house building structure health |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1740770A (en) * | 2005-09-18 | 2006-03-01 | 中国海洋大学 | Non-destructive health detecting method for large structural matter |
CN102147597A (en) * | 2010-02-10 | 2011-08-10 | 广州大学 | Health monitoring system for structures of great building and bridge |
JP2012083172A (en) * | 2010-10-08 | 2012-04-26 | Kajima Corp | Damage evaluation method for building and damage evaluation device for building |
CN109186848A (en) * | 2018-11-22 | 2019-01-11 | 苏州科技大学 | A kind of building health monitoring intellectualizing system based on BIM |
-
2019
- 2019-02-20 CN CN201910130959.XA patent/CN109883474B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1740770A (en) * | 2005-09-18 | 2006-03-01 | 中国海洋大学 | Non-destructive health detecting method for large structural matter |
CN102147597A (en) * | 2010-02-10 | 2011-08-10 | 广州大学 | Health monitoring system for structures of great building and bridge |
JP2012083172A (en) * | 2010-10-08 | 2012-04-26 | Kajima Corp | Damage evaluation method for building and damage evaluation device for building |
CN109186848A (en) * | 2018-11-22 | 2019-01-11 | 苏州科技大学 | A kind of building health monitoring intellectualizing system based on BIM |
Non-Patent Citations (1)
Title |
---|
张泽宇: "基于监测的空间钢结构健康状态评价体系研究", 《中国博士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112067043A (en) * | 2020-08-14 | 2020-12-11 | 常州机电职业技术学院 | Defective degree detecting system of timber structure ancient building |
CN112067043B (en) * | 2020-08-14 | 2022-08-26 | 常州机电职业技术学院 | Defective degree detecting system of timber structure ancient building |
CN115063040A (en) * | 2022-07-28 | 2022-09-16 | 湖南工商大学 | Method and system for collaborative evaluation and prediction of house building structure health |
Also Published As
Publication number | Publication date |
---|---|
CN109883474B (en) | 2021-06-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108154651A (en) | A kind of device and method for landslide disaster Monitoring and forecasting system in real-time | |
Yang et al. | An optimized BP neural network model for teaching management evaluation | |
CN109883474A (en) | Building health monitoring systems and monitoring method based on field monitoring | |
CN109655114B (en) | Urban underground pipe gallery monitoring method | |
CN108596507A (en) | A kind of disaster-stricken damage alarm method of mariculture net cage | |
CN110110425A (en) | A kind of slope sliding force prediction method based on reliability rule-based reasoning | |
CN109857988A (en) | A kind of safety monitoring method of cold ground assembled Modern Wood Construction | |
CN106021880B (en) | Jacket platform structural response calculation method based on BP neural network | |
CN109918791A (en) | A kind of nuclear plant digital master control room operator human reliability analysis method | |
CN102735468A (en) | Identification method for damaged cables based on mixed monitoring of generalized displacement and temperature change of support | |
CN102706670A (en) | Damaged cable and support generalized displacement identification method based on cable force monitoring of temperature change | |
Zhou et al. | Stability prediction of tailing dam slope based on neural network pattern recognition | |
CN103852288A (en) | Method for progressively recognizing damaged cables and loads based on cable force monitoring | |
CN103630388A (en) | Spatial coordinate monitoring method for identifying generalized displacement of concentrated loads of damaged cables | |
CN102706625A (en) | Damaged cable and support angular displacement identification method on basis of strain monitoring during temperature variation | |
CN102706669A (en) | Damaged cable and support generalized displacement identification method based on strain monitoring of temperature change | |
CN109740935A (en) | Architectural heritage monitoring system and monitoring method | |
CN110145695B (en) | Heating pipeline leakage detection method based on deep confidence network information fusion | |
CN102706631A (en) | Damaged cable and support angular displacement identification method on basis of angle monitoring during temperature variation | |
CN102721556A (en) | Damaged cable and support angular displacement progressive identification method used in case of temperature variation on basis of strain monitoring | |
CN113283138A (en) | Deep sea culture platform dynamic response analysis method based on deep learning | |
CN109726936A (en) | A kind of monitoring method rectified a deviation for tilting ancient masonry pagoda | |
CN103852280A (en) | Method for recognizing damaged cables and loads based on cable force monitoring | |
CN102735476A (en) | Problematic cable and support angular displacement identifying method based on strain monitoring at time of temperature change | |
CN102706610A (en) | Problem cable and supporting seat generalized displacement identification method based on strain monitoring at moment of temperature variation |
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 |