CN104636998A - Subway construction rapid risk assessment method based on neural network - Google Patents
Subway construction rapid risk assessment method based on neural network Download PDFInfo
- Publication number
- CN104636998A CN104636998A CN201310557563.6A CN201310557563A CN104636998A CN 104636998 A CN104636998 A CN 104636998A CN 201310557563 A CN201310557563 A CN 201310557563A CN 104636998 A CN104636998 A CN 104636998A
- Authority
- CN
- China
- Prior art keywords
- data
- neural network
- subway
- risk assessment
- server
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 23
- 238000012502 risk assessment Methods 0.000 title claims abstract description 18
- 238000010276 construction Methods 0.000 title abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000001514 detection method Methods 0.000 claims abstract description 13
- 238000012544 monitoring process Methods 0.000 claims abstract description 4
- 238000011156 evaluation Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 8
- 238000007500 overflow downdraw method Methods 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 4
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 230000003014 reinforcing effect Effects 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 abstract description 2
- 230000008901 benefit Effects 0.000 abstract description 2
- 230000010354 integration Effects 0.000 abstract 2
- 238000003491 array Methods 0.000 abstract 1
- 238000004364 calculation method Methods 0.000 abstract 1
- 238000012805 post-processing Methods 0.000 abstract 1
- 230000004927 fusion Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 208000035126 Facies Diseases 0.000 description 1
- 241001074085 Scophthalmus aquosus Species 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 239000011449 brick Substances 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000034994 death Effects 0.000 description 1
- 231100000517 death Toxicity 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000003116 impacting effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 230000000116 mitigating effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 230000005641 tunneling Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a subway construction rapid risk assessment method based on a neural network. The method includes arranging multielement sensors in site, transmitting detection data to a subway site data acquisition server in a wire or wireless manner, allowing the subway site data acquisition server to filter the data returned by the multielement sensors and transmit the processed data to a risk assessment server, and allowing the risk assessment server to sort and integrate the detection data returned by the subway site data acquisition server and convert the detection data into data arrays adaptive to calculation by the neural network integration method; allowing the risk assessment server to perform risk assessment on the data by the neural network integration method and transmit the risk rapid assessment result to a detection and monitoring central computer; allowing a computer central processing unit to perform the post processing. The method has the advantages of convenience for usage, high processing speed and easiness for implementation.
Description
Technical field
The present invention relates to a kind of subway work risk fast evaluation method based on neural network.
Background technology
The time in early stage of building subway is longer, due to needs planning and government's examination & approval, even also needs test.From ferment that putting into practice breaks ground and need the time grown very much, short then several years, the long then more than ten years are also possible.Due to the structure of subway, and cause very easily because these factor generation tragedies.The construction of subway is divided into: 1, the simplest directly method of open cut backfill is bright cut and fill (open cut backfill).Hollow place is excavated in general Shi street to this method, then builds tunnel structure below, just road surface is spread again after there are enough supporting forces in tunnel.Except road is opened by pick, other underground structures such as electric wire, telephone wire, water pipe etc. all need to reconfigure.The material building this tunnel is generally concrete or steel, but older system also has and to use fragment of brick and iron.2, brill digs method: another kind of method first digs a vertical shaft in somewhere, ground, then at shaft bottom tunneling.Modal method is for using drilling and digging machine (shield machine, shield machine), and one side is excavated one side and preprepared assembly is arranged in tunnel wall.For the place that depth of building is intensive, bore the method for construction digging method or even unique feasible.The advantage Shi Dui street of this method or the impact of other underground installations very little, even can build at the bottom; The design in tunnel also has more writing space, such as station can than station and station between tunnel higher, help train leaving from station time accelerate and enter the station time slow down.But this method of digging neither be impeccable, one of them often needs to pay attention to underground water mitigation; In addition at some harder rock stratum excavation, explosive may be needed.Underground air supply problem even tunnel cave also likely causes workman's injures and deaths.In addition, for the place that building height is intensive, during excavation except will noticing and avoiding impacting the building structure of building site surrounding, the public utilities at place sometimes also to be planned as a whole, the water delivery at the bottom of ground, the migration of transmission of electricity pipeline, to make way to build passage of train.
So just can see the importance drawing preliminary preparation, and this most important thing is exactly site reconnaissance work, whether the data of exploration are accurate, very large on the impact of design and construction.Along with the development of electronic devices and components, the precision of sensor increases substantially, and existing exploration level has accomplished the degree that single parameter error is ignored.But, geology actual state, usually by composite factor shadow, carries out simulation modelling with regard to needs to different geological condition like this, and the data of collection are as the training data of model and analysis data, the accurate model of final acquisition, then change geologic parameter, checking arrangement and method for construction, this process need is analyzed one by one to contingent situation, checking is trained one by one by the parameter of model to change, do degree of accuracy so high, practical operation is effective, but the cycle is oversize.
Information fusion is that the Incomplete information of multiple support channels, multi-faceted collection is in addition comprehensive, eliminates the information of redundancy and the contradiction that may exist between multi-source information, and in addition complementary to it, reduces the process that its uncertain system environment facies describe complete consistance.Information fusion can improve the decision-making of intelligent system, planning, the rapidity of reaction and positive plan risk, and being a cross discipline relating to information science, computer science and robotization science, is the important directions that current information society must be studied.The generation of multisource information fusion technology improves the accuracy of intelligent system decision-making, reduces risk of policy making.The high scheme of construction risk is tentatively got rid of by information fusion, retain the arrangement and method for construction that feasibility is higher, and then by training checking one by one above by the parameter of model to feasible scheme, doing like this and guaranteeing that degree of accuracy is high, raise the efficiency simultaneously, reduce proving period in early stage.
Neural network has very strong fault-tolerance and self study, self-organization and adaptive ability, can the Nonlinear Mapping of Simulation of Complex.For subway work risk rapid evaluation provides technical support.
Summary of the invention
The present invention is directed to the proposition of above problem, and development is based on the subway work risk fast evaluation method of neural network.The technical solution used in the present invention is as follows:
Based on a subway work risk fast evaluation method for neural network, it is characterized in that comprising the steps:
1) detection data are transferred to subway on-site data gathering server by wired or wireless mode by on-the-spot multielement bar of laying, subway on-site data gathering server carries out filtration treatment to multielement bar returned data, then the data after process is sent to risk assessment server;
2) risk assessment server is classified to the detection data that the transmission of subway on-site data gathering server is returned and integrates, and is converted to the data array being suitable for Neural Network Fusion Method and calculating;
3) then risk assessment server adopts Neural Network Fusion Method to carry out risk assessment process to above-mentioned data, concrete processing procedure comprises: to detecting data determination method mainly in the weights distribution of network, simultaneously, the specific learning algorithm of neural network can be adopted to obtain knowledge, obtain uncertain inference mechanism;
4) risk rapid evaluation result is issued test and monitoring central computer by ultimate risk evaluating server, is for further processing by computer center's processing unit.
Also comprise in step 3):
Signal is carried out from processing power and automated reasoning to detection data.
Described scene is laid multielement bar and is comprised displacement meter, taseometer, ventage piezometer, reinforcing rib meter, pressure cell and flowmeter.
Based on the subway work risk fast evaluation method of neural network, to on-the-spot returned data fusion treatment, tentatively get rid of the scheme that construction risk is high, retain the arrangement and method for construction that feasibility is higher, and then by training checking one by one above by the parameter of model to feasible scheme, do like this and guarantee that degree of accuracy is high, raise the efficiency simultaneously, reduce proving period in early stage.The method also has in addition: easy to use, processing speed, technology realize the feature such as easy and be suitable for extensive popularization.
Accompanying drawing explanation
Fig. 1 is the structured flowchart of system of the present invention;
Fig. 2 is realization flow figure of the present invention.
Embodiment
As depicted in figs. 1 and 2 based on the subway work risk fast evaluation method of neural network, comprise the steps:
1) detection data are transferred to subway on-site data gathering server by wired or wireless mode by on-the-spot multielement bar of laying, subway on-site data gathering server carries out filtration treatment to multielement bar returned data, then the data after process is sent to risk assessment server;
2) risk assessment server is classified to the detection data that the transmission of subway on-site data gathering server is returned and integrates, and is converted to the data array being suitable for Neural Network Fusion Method and calculating;
3) then risk assessment server adopts Neural Network Fusion Method to carry out risk assessment process to above-mentioned data, concrete processing procedure comprises: to detecting data determination method mainly in the weights distribution of network, simultaneously, the specific learning algorithm of neural network can be adopted to obtain knowledge, obtain uncertain inference mechanism;
4) risk rapid evaluation result is issued test and monitoring central computer by ultimate risk evaluating server, is for further processing by computer center's processing unit.
Also comprise in step 3):
Signal is carried out from processing power and automated reasoning to detection data.
Described scene is laid multielement bar and is comprised displacement meter, taseometer, ventage piezometer, reinforcing rib meter, pressure cell and flowmeter.
The above; be only the present invention's preferably embodiment; but protection scope of the present invention is not limited thereto; anyly be familiar with those skilled in the art in the technical scope that the present invention discloses; be equal to according to technical scheme of the present invention and inventive concept thereof and replace or change, all should be encompassed within protection scope of the present invention.
Claims (3)
1., based on a subway work risk fast evaluation method for neural network, it is characterized in that comprising the steps:
1) detection data are transferred to subway on-site data gathering server by wired or wireless mode by on-the-spot multielement bar of laying, subway on-site data gathering server carries out filtration treatment to multielement bar returned data, then the data after process is sent to risk assessment server;
2) risk assessment server is classified to the detection data that the transmission of subway on-site data gathering server is returned and integrates, and is converted to the data array being suitable for Neural Network Fusion Method and calculating;
3) then risk assessment server adopts Neural Network Fusion Method to carry out risk assessment process to above-mentioned data, concrete processing procedure comprises: to detecting data determination method mainly in the weights distribution of network, simultaneously, the specific learning algorithm of neural network can be adopted to obtain knowledge, obtain uncertain inference mechanism;
4) risk rapid evaluation result is issued test and monitoring central computer by ultimate risk evaluating server, is for further processing by computer center's processing unit.
2. a kind of subway work risk fast evaluation method based on neural network according to claim 1, is characterized in that also comprising in step 3):
Signal is carried out from processing power and automated reasoning to detection data.
3. a kind of subway work risk fast evaluation method based on neural network according to claim 1, is characterized in that described scene is laid multielement bar and comprised displacement meter, taseometer, ventage piezometer, reinforcing rib meter, pressure cell and flowmeter.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310557563.6A CN104636998A (en) | 2013-11-07 | 2013-11-07 | Subway construction rapid risk assessment method based on neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310557563.6A CN104636998A (en) | 2013-11-07 | 2013-11-07 | Subway construction rapid risk assessment method based on neural network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104636998A true CN104636998A (en) | 2015-05-20 |
Family
ID=53215708
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310557563.6A Pending CN104636998A (en) | 2013-11-07 | 2013-11-07 | Subway construction rapid risk assessment method based on neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104636998A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113706838A (en) * | 2021-07-17 | 2021-11-26 | 北京工业大学 | Portable subway and underground pipe gallery construction risk automatic analyzer based on intelligent sensing |
-
2013
- 2013-11-07 CN CN201310557563.6A patent/CN104636998A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113706838A (en) * | 2021-07-17 | 2021-11-26 | 北京工业大学 | Portable subway and underground pipe gallery construction risk automatic analyzer based on intelligent sensing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110109895B (en) | Surrounding rock grading combined prediction method suitable for TBM tunneling tunnel and application | |
CN111058855B (en) | Deformation control method and evaluation system for shield underpassing structure | |
CN101914912B (en) | In-situ testing method for deep underground engineering during rockburst preparation and evolution process | |
CN104747184A (en) | Measurement-while-drilling method and device for three-dimensional wave velocity imaging of rock mass in front of tunnel face | |
CN105353427A (en) | Tunnel surrounding rock dynamic grading method and device thereof | |
CN107861157A (en) | A kind of underground water seal cave depot runs phase micro seismic monitoring method | |
CN109268072B (en) | Big data cloud platform for intelligent and real-time prediction and early warning of water inrush disaster of coal mine floor | |
CN110987347A (en) | Method for judging stability of surrounding rocks of pumped storage power station factory building under excavation disturbance effect | |
CN102880918B (en) | Based on the deep excavation risk evaluation method that data fusion is analyzed | |
CN104636576A (en) | Rapid subway construction risk evaluation method based on weighted average method | |
AU2021101678A4 (en) | Method for testing soft rock ground stress in exploration engineering | |
CN113137226A (en) | Portable rock-soil body mechanics parameter drilling test system and device | |
CN211123324U (en) | BIM + GIS-based advanced geological forecast information system for tunnel construction | |
CN104636511A (en) | Rapid subway construction risk evaluation method based on Dasarathy model | |
CN104636998A (en) | Subway construction rapid risk assessment method based on neural network | |
CN110210051A (en) | A kind of geotechnical engineering cloud micromessage technology | |
CN104636997A (en) | Rapid subway construction risk assessment method based on Kalman filtering method | |
CN104637020A (en) | Rapid subway construction risk assessment method based on bayesian estimation method | |
Khoo et al. | Geotechnical challenges and innovations in urban underground construction–The Klang Valley Mass Rapid Transit project | |
CN104636996A (en) | Subway construction rapid risk assessment method based on fuzzy logic | |
Niu et al. | An intelligent prediction method of the karst curtain grouting volume based on support vector machine | |
CN104637019A (en) | Subway construction rapid risk assessment method based on extension OODA model | |
CN104636994A (en) | Rapid subway construction risk assessment method based on evidence reasoning method | |
CN104636995A (en) | Rapid subway construction risk assessment method based on JDL (joint directors of laboratories) model | |
CN104636811A (en) | Rapid subway construction risk assessment method based on Boyd control loop |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150520 |
|
WD01 | Invention patent application deemed withdrawn after publication |